No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
A spatially based machine learning algorithm for potential mapping of the hearing senses in an urban environment
Abstract
Mapping individuals’ sense of hearing in the urban environment helps urban managers and planners accomplish goals such as creating a favorable urban environment for the citizens. The present study has been conducted to address the lack of modeling and compilation of a sense of hearing potential map in the urban environment and can help urban managers and planners make decisions in this regard. The present study aims for spatial modeling of people's hearing senses and developing potential maps for various hearing states in Tehran, Iran, using a random forest (RF) machine learning algorithm. The four various states, including pleasant sound, annoying sound, normal sound, and stressful sound, have been considered in the present study for the sounds that can be heard in the city. First, a spatial database made up of dependent, and independent data was built. Dependent data included people's four states of hearing in the urban environment, and the respective data was collected through a questionnaire from 657 people. Independent data were categorized into four groups. The first group was traffic related noises including the criteria of traffic volume and equivalent continuous sound level (Leq), the second group included land use related criteria of distance to cemetery, distance to sports areas, distance to commercial areas, distance to primary streets, distance to secondary streets, distance to park, and distance to industrial areas. Furthermore, the public facilities related group includes the distance to airports and distance to public transportation stations, and the population related group includes population density. 70% of the data were used for training, and 30% were set aside for validation. The spatial database was used to develop the potential map for the four states of the hearing sense in the urban environment using the RF algorithm. The potential hearing sense map was evaluated using the receiver operating characteristic (ROC) curve and the respective area under the curve (AUC). The AUC values were 0.930, 0.957, 0.950, and 0.903 for each of the pleasant, annoying, normal, and stressful states, respectively. There was a higher potential for pleasant sounds in the northern districts and some of the central ones, for annoying sounds mainly in the central districts, for normal sounds in central and southern districts, and stressful sounds in some parts of the central and mainly southern districts.
... Tehran, in particular, has emerged as one of the world's most polluted cities due to noise pollution, exacerbated by the absence of acoustic boundaries in its urban landscape. As a result, Tehran ranks highest in noise pollution within Iran (Farahani, Razavi-Termeh, and Sadeghi-Niaraki 2022). ...
... . Distance to street Widespread urbanization and increased road transportation significantly contribute to individuals' exposure to environmental noise (Paviotti and Vogiatzis 2012). Noise from vehicles, motorcycles, and pedestrians on streets is a negative factor in the urban soundscape (Farahani, Razavi-Termeh, and Sadeghi-Niaraki 2022). Motor vehicle traffic is a significant source of air pollutants (emissions) and noise (Oji and Adamu 2020). ...
... Elevation is a factor that affects air pollution. Higher elevations lead to increased solar radiation and can contribute to the formation of photochemical smog (Farahani, Razavi-Termeh, and Sadeghi-Niaraki 2022). The digital elevation model (DEM) of the Shuttle Radar Topography Mission (SRTM) image was used on the GEE platform to build an altitude map. ...
This study addresses the critical need for comprehensive multi-pollution modeling in urban environments by employing Geospatial Artificial Intelligence (GeoAI) techniques. Specifically, it aims to elucidate the variability of air and noise pollution levels in Tehran, Iran, and develop precise multi-pollution susceptibility maps. A spatial database was compiled, encompassing annual average data (2019–2022) of the Air Quality Index (AQI) and Equivalent Continuous Sound Level (Leq), along with 19 influential factors related to both pollutants. The study utilized the CatBoost machine learning algorithm, enhanced with Grey Wolf Optimizer (GWO) and Harris Hawks Optimization (HHO) algorithms, to model and predict pollution patterns. Key quantitative achievements include a remarkable 15% reduction in Root Mean Square Error (RMSE) for air pollution and a 12% reduction in noise pollution when using the CatBoost-HHO configuration compared to the standalone CatBoost algorithm. Validation of the multi-pollution maps utilizing the Area Under the Curve (AUC) analysis showed high accuracy, with the CatBoost-HHO achieving AUC values of 0.943 for air pollution and 0.936 for noise pollution, outperforming CatBoost-GWO and standalone CatBoost models. These results underscore the efficacy of our approach in accurately identifying and mapping multi-pollution hotspots, contributing valuable insights for urban environmental management and public health preservation.
... Spatial analysis can help people solve complex location-based problems. The spatial analysis involves comprehending various aspects, including the distinctive features of a place, the interconnections between different locations, and the incidence of events within specific geographical areas (Farahani et al., 2022). It is possible to perform spatial analysis and solve spatial problems using a geographic information system (GIS) (Lü et al., 2019). ...
... RMSE and MAE are indicators that calculate the error between the actual and predicted values (Farahani et al., 2022). The primary difference between MAE and RMSE indices is that MAE assigns equal weight to all errors. ...
... In this equation, the four data categories in the confusion matrix are TN (True Negative), TP (True Positive), FN (False Negative), and FP (False Positive) (Davis and Goadrich, 2006). AUC is between 0 and 1 (Farahani et al., 2022). ...
Air pollution poses significant risks to human health and the environment, necessitating effective air quality management strategies. This study presents a novel approach to air quality management by integrating an autoencoder (AE) with a convolutional neural network (CNN) algorithm in Tehran city of Iran. One of the primary and vital problems in deep learning is model complexity, and the complexity of a model is affected by data distribution, data complexity, and information volume. AE provide a helpful way to denoise input data and make building deep learning models much more efficient. The proposed methodology enables spatial modeling and risk mapping of six air pollutants, namely, particulate matter 2.5 (PM2.5), particulate matter 10 (PM10), sulfur dioxide (SO2), nitrogen dioxide (NO2), ozone (O3), and carbon monoxide (CO). For air pollution modelling, data from a spatial database containing the annual average of six pollutants from 2012 to 2022 was utilized. The model considered various parameters influencing air pollution: altitude, humidity, distance to industrial areas, NDVI (normalized difference vegetation index), population density, rainfall, distance to the street, temperature, traffic volume, wind direction, and wind speed. The risk map accuracy was assessed using the area under the receiver operating characteristic (ROC) curve for six pollutants. Among them, NO2, PM10, CO, PM2.5, O3, and SO2 exhibited the highest accuracy with values of 0.964, 0.95, 0.896, 0.878, 0.877, and 0.811, respectively, in the risk map generated by the CNN-AE model. The findings demonstrated the CNN-AE model’s impressive precision when generating the pollution risk map.
... Estimating groundwater levels, GPM, vulnerability, and quality has grown more dependent on machine-learning algorithms in recent years (Tran et al. 2021;Masroor et al. 2023;Tegegne et al. 2024). Machine learning algorithms offer several advantages, including better accuracy, faster processing speed, higher robustness, and lower computational costs than traditional methods (Dargan et al. 2020;Sarker et al. 2021;Farahani et al. 2022). Machine learning algorithms can also identify data trends or patterns without human intervention, improving prediction performance with available data (Zhong et al. 2021). ...
... Multicollinearity generally occurs when there is a significant correlation between the factors affecting a phenomenon (Kalnins 2018). In this regard, independent variables may exhibit significant correlations in addition to the relation between independent and dependent variables, significantly impacting the interpretation of the results (Farahani et al. 2022). Multicollinearity in multiple regression is quantified by using the VIF (Eq. ...
Groundwater resources are essential for ensuring a consistent water supply in many regions. Groundwater potential maps (GPMs) can be utilized in many ways to estimate the quantity, quality, and distribution of subsurface water, supporting the decision-making processes of numerous stakeholders. This study contributes to improving the accuracy of GPMs, focusing on implementing Geospatial Artificial Intelligence (GeoAI) models. For this purpose, the accuracy performance of the Extreme Gradient Boosting (XGBoost) algorithm is improved in this study. To do this, two such popular metaheuristic algorithms, i.e., invasive weed optimization (IWO) and biogeography-based optimization (BBO), are integrated into the XGBoost algorithm for modeling and spatial prediction of the areas prone to groundwater. Three models—XGBoost, XGBoost-IWO, and XGBoost-BBO—are implemented within the Python programming environments to execute spatial modeling and generate predictive maps. The evaluation of results unfolds in two stages: model validation and GPM validation. For the training data, the root mean square error (RMSE) and mean absolute error (MAE) indices were 0.165 and 0.121 for XGBoost, 0.13 and 0.087 for XGBoost-IWO, and 0.114 and 0.082 for XGBoost-BBO, respectively. The test data showed similar trends, with XGBoost yielding RMSE and MAE values of 0.424 and 0.295, XGBoost-IWO at 0.416 and 0.287, and XGBoost-BBO at 0.39 and 0.28. XGBoost-BBO, XGBoost-IWO, and XGBoost had a prediction accuracy higher than other models. The respective area under the curve (AUC) of GMPs using receiver operating characteristic (ROC) curves for XGBoost, XGBoost-IWO, and XGBoost-BBO were 81.8 %, 83.1 %, and 83.7 %. Using bio-inspired metaheuristic algorithms, the GPM accuracy rate has improved further. The study of groundwater resources demonstrated how geological feature extraction by GeoAI may help employ advanced techniques.
... Multicollinearity indicates that the qualities of at least two predicted parameters in multiple regression are substantially associated with linearity (Achour et al. 2018). Therefore, an appropriate selection of these factors is required to establish their independence from one another (Farahani et al. 2022). Multicollinearity findings were evaluated objectively using the VIF (variance inflation factor) metric. ...
... where t represents a threshold value, AUC values less than 0.5 denote poor model performance, whereas values near 1 denote great model accuracy (Farahani et al. 2022). ...
Landslides pose a significant threat to human life and infrastructure, underscoring the ongoing need for accurate landslide susceptibility mapping (LSM) to effectively assess risks. This study introduces an innovative approach that leverages multi-objective evolutionary fuzzy algorithms for landslide modeling in Khalkhal town, Iran. Two algorithms, namely the non-dominated sorting genetic algorithm II (NSGA-II) and the evolutionary non-dominated radial slots-based algorithm (ENORA), were employed to optimize Gaussian fuzzy rules. By utilizing 15 landslide conditioning factors (aspect, altitude, distance from the fault, soil, slope, lithology, rainfall, distance from the road, the normalized difference vegetation index (NDVI), land cover, plan curvature, profile curvature, topographic wetness index (TWI), stream power index (SPI), and distance from the river) and historical landslide events (153 landslide locations), we randomly partitioned the input data into training (70%) and validation (30%) sets. The training set determined the weight of conditioning factor classes using the frequency ratio (FR) approach. These weights were then used as inputs for the NSGA-II and ENORA algorithms to generate an LSM. The NSGA-II algorithm achieved a root-mean-square error (RMSE) of 0.25 during training and 0.43 during validation. Similarly, the ENORA algorithm demonstrated an RMSE of 0.28 in training and 0.48 in validation. The findings revealed that the LSM created by the NSGA-II algorithm exhibited superior predictive capabilities (area under the receiver operating characteristic curve (AUC) = 0.867) compared to the ENORA algorithm (AUC = 0.844). Additionally, a particle swarm optimization (PSO) algorithm was employed to determine the importance of conditioning factors, identifying lithology, land cover, and altitude as the most influential factors.
... These MLAs are well-suited for spatial regression analysis due to their ability to manage complex relationships, large datasets, and noise. They enhance predictive accuracy, reveal key factors, and offer robust, generalizable insights into asthma prevalence [43,44,89]. ...
Asthma prevalence in large urban areas of developing countries is a significant public health concern, with increased rates driven by various socioeconomic and environmental factors. This study aims to predict asthma risk in Tehran, a major urban center in Iran. Data from 1473 asthma patients, alongside demographic, socioeconomic, air quality, environmental, weather, and healthcare access variables, were analyzed using geographic information systems (GIS) and remote sensing techniques. Three ensemble machine learning algorithms-Random Forest (RF), Gradient Boosting Machine (GBM), and Extreme Gradient Boosting (XGBoost)-were applied to model and predict asthma risk. A Negative Binomial Regression Model (NBRM) identified seven key predictors: population density, unemployment rate, particulate matter (PM2.5 and PM10), nitrogen dioxide (NO2), sulfur dioxide (SO2), neighborhood deprivation index, and road intersection density. Among the algorithms, GBM outperformed the others, with a training RMSE of 0.56 and a test RMSE of 1.07, demonstrating strong generalization. Additionally , GBM achieved the highest R-squared values (0.95 for training and 0.76 for testing) and lower MAE values (0.43 for training and 0.88 for testing). Effective pattern recognition was confirmed by EV values of 0.95 for training and 0.75 for testing, along with a Moran's I value of 0.17, indicating minimal spatial autocorrelation.
... Overfitting also remains a concern, as RF can focus excessively on patterns in training data, limiting its generalizability to new data. The sensitivity of the RF model to the inclusion or exclusion of specific predictors has also been demonstrated in several studies, highlighting the importance of careful feature selection and pre-processing to mitigate potential biases (Farahani et al. 2022;Liu et al. 2021;Ruškić et al. 2022;Zhang et al. 2023). A deeper understanding of how these models handle feature interaction and importance reveals that XGB, through its boosting technique, excels at identifying intricate relationships between predictors, which could be overlooked by RF's ensemble averaging approach. ...
This study represents a pioneering effort to integrate geographic information systems (GIS) and ensemble machine learning methods to predict noise levels on a university campus. Three ensemble models including random forest (RF), gradient boosting (GB), and extreme gradient boosting (XGB) were developed to predict traffic noise based on data collected over a 4-week period at the Universiti Teknologi Malaysia (UTM) campus. Noise measurements were obtained during peak morning hours (7:30 to 9:30 a.m.) on weekdays within the UTM campus in Johor. Additional predictor variables, including data from the digital elevation model (DEM) and land use, were incorporated to capture the complex nonlinear relationships influencing noise levels. The models were optimized through hyperparameter tuning, resulting in high precision, as evidenced by performance metrics such as the coefficient of determination (R²), mean absolute error (MAE), and mean squared error (MSE). The XGB model emerged as the most accurate, with R² = 0.96, MAE = 0.9, and MSE = 0.3. Noise maps generated using the inverse distance weighting (IDW) interpolation technique highlighted the spatial distribution of noise levels, classified into five classes considering WHO standards. The findings identified distance from roads, the number of light vehicles, and proximity to green areas as the most significant predictors. However, challenges remain in accurately predicting noise levels associated with other predictors. The outcomes of the study indicate the superior performance of the XGB model compared to the GB and RF models. The study recommends several measures to manage and control noise pollution on the UTM campus, including raising awareness, regulating and enforcing vehicle speed limits, reevaluating land use, installing sound insulation systems, and planting trees and vegetation buffer zones around and within educational buildings.
... Sebagai tambahan, tanah perkuburan juga dikaitkan dengan bunyi bagi sesuatu kawasan. Ini kerana trafik yang tinggi dari manusia, muzik yang sedih dan berduka ketika melakukan upacara pengebumian yang boleh menyebabkan tekanan kepada masyarakat (Farahani et al., 2022). ...
... The validity of a regression model is compromised when a strong connection exists between two or more predictor variables (Farahani et al., 2022). Multicollinearity is a term that helps identify collinearity relationships. ...
... In addition to the study of the stratification of the median sound levels registered in each road category, the sensitivity, non-specificity, and predictive performance of the sound values registered in each road category were analyzed, and the results are shown in Fig. 4b. According to previous studies, this analysis has provided more precise information on the classification of the registered sound values (Farahani et al., 2022;Zambon et al., 2016;Rey-Gozalo & Barrigón Morillas, 2016). ...
Road traffic is the primary source of environmental noise pollution in cities. This problem is also spreading due to inadequate urban expansion planning. Hence, integrating road traffic noise analysis into urban planning is necessary for reducing city noise in an effective, adaptable, and sustainable way. This study aims to develop a methodology that applies to any city for the stratification of urban roads by their functionality through only their urban features. It is intended to be a tool to cluster similar streets and, consequently, traffic noise to enable urban and transportation planners to support the reduction of people's noise exposure. Three multivariate ordered logistic regression statistical models (Model 1, 2, and 3) are presented that significantly stratify urban roads into five, four, and three categories, respectively. The developed models exhibit a McFadden pseudo-R2 between 0.5 and 0.6 (equivalent to R2 >0.8). The choice between Model 1 or 2 depends on the scale of the city. Model 1 is recommended for developed cities with an extensive road network, while Model 2 is most suitable in intermediate and growing cities. On the other hand, Model 3 could be applied at any city scale but focused on local management of transit routes and for designing acoustic sensor installations, urban soundwalks, and identification of quiet areas. Urban features related to road width and length, presence of transport infrastructure, and public transport routes are associated with increased traffic noise in all three models. These models prove useful for future action plans aimed at reducing noise through strategic urban planning.
... Multicollinearity is commonly evaluated using the variance inflation factor (VIF). Generally, when the VIF value exceeds 10, there is significant multicollinearity among variables (Farahani, Razavi-Termeh, and Sadeghi-Niaraki 2022). ...
This study focuses on determining the optimal distance metric in the K-Nearest Neighbors (KNN) algorithm for spatial modelling of floods. Four distance metrics of the KNN algorithm, namely KNN-Manhattan, KNN-Minkowski, KNN-Euclidean, and KNN-Chebyshev, were utilized for flood susceptibility mapping (FSM) in Estahban, Iran. A spatial database comprising 509 flood occurrence points extracted from satellite images and 12 factors influencing floods was created for analysis. The particle swarm optimization (PSO) algorithm was employed for hyperparameter optimization and feature selection, considering eight influential factors as modelling inputs. The modelling results revealed that the KNN-Manhattan algorithm exhibited superior accuracy (root mean squared error (RMSE) = 0.169, mean absolute error (MAE) = 0.051, coefficient of determination (R²) = 0.884, and area under the curve (AUC) = 0.94) compared with the other algorithms for identifying flood-prone areas. The KNN-Minkowski algorithm followed closely, with an RMSE of 0.175, MAE of 0.056, R² of 0.876, and AUC of 0.939. The KNN-Euclidean algorithm achieved an RMSE of 0.183, MAE of 0.061, R² of 0.842, and AUC of 0.929, whereas the KNN-Chebyshev algorithm achieved an RMSE of 0.198, MAE of 0.075, R2 of 0.842, and AUC of 0.924.
... The Gini index is a number describing the quality of the split of a node on a variable. The Gini index is calculated for the variable X m with probability P i (i 1, 2, ..n) at node k by Eq. 7 (Farahani et al., 2022): ...
This research aimed to predict soil’s physical and chemical properties with a state-of-the-art hybrid model based on deep learning algorithms and optical satellite images in a region in the north of Iran. As dependent data, 317 soil samples (0–30 cm) were collected in field surveying and analyzed by the soil and water research institute for their physical (clay, silt, and sand) and chemical [electrical conductivity (EC), organic carbon (OC), phosphorus (P), soil reaction (pH), and potassium (K)] properties. Based on independent data, 23 remote sensing (RS) parameters (extracted from Landsat 8 optical images), 17 topographical parameters [extracted from the digital elevation model (DEM)], and four climatic parameters (derived from the meteorological organization). Spatial prediction of physical and chemical properties was implemented using a convolutional neural network (CNN), recurrent neural network (RNN), and hybrid CNN-RNN models. The evaluation results indicated that the hybrid CNN-RNN model had higher accuracy in all soil properties, followed by the RNN and CNN models. In the hybrid CNN-RNN model, pH (0.0206), EC (0.0958 dS/m), silt (0.0996%), P (0.1078 ppm), K (0.1185 ppm), sand (0.1360%), OC (0.1361%), and clay (0.1419%) had higher prediction accuracy, as determined by the root mean-squared error (RMSE) index. The hybrid CNN-RNN model proved to be the most effective for soil property prediction in this region. This finding underscores the potential of deep learning techniques in harnessing RS data for precise soil property mapping, with implications for land management and agricultural practices.
... R 2 illustrates the goodness of fit between the data and the regression model. The value of R 2 ranges from 0 to 1, with values closer to 1 indicating better model performance [60,61]. ...
... R 2 illustrates the goodness of fit between the data and the regression model. The value of R 2 ranges from 0 to 1, with values closer to 1 indicating better model performance [60,61]. ...
This study aims to predict vital soil physical properties, including clay, sand, and silt, which are essential for agricultural management and environmental protection. Precision distribution of soil texture is crucial for effective land resource management and precision agriculture. To achieve this, we propose an innovative approach that combines Geospatial Artificial Intelligence (GeoAI) with the fusion of satellite imagery to predict soil physical properties. We collected 317 soil samples from Iran’s Golestan province for dependent data. The independent dataset encompasses 14 parameters from Landsat-8 satellite images, seven topographic parameters from the Shuttle Radar Topography Mission (SRTM) DEM, and two meteorological parameters. Using the Random Forest (RF) algorithm, we conducted feature importance analysis. We employed a Convolutional Neural Network (CNN), RF, and our hybrid CNN-RF model to predict soil properties, comparing their performance with various metrics. This hybrid CNN-RF network combines the strengths of CNN networks and the RF algorithm for improved soil texture prediction. The hybrid CNN-RF model demonstrated superior performance across metrics, excelling in predicting sand (MSE: 0.00003%, RMSE: 0.006%), silt (MSE: 0.00004%, RMSE: 0.006%), and clay (MSE: 0.00005%, RMSE: 0.007%). Moreover, the hybrid model exhibited improved precision in predicting clay (R2: 0.995), sand (R2: 0.992), and silt (R2: 0.987), as indicated by the R2 index. The RF algorithm identified MRVBF, LST, and B7 as the most influential parameters for clay, sand, and silt prediction, respectively, underscoring the significance of remote sensing, topography, and climate. Our integrated GeoAI-satellite imagery approach provides valuable tools for monitoring soil degradation, optimizing agricultural irrigation, and assessing soil quality. This methodology has significant potential to advance precision agriculture and land resource management practices.
... A high degree of correlation in a data set is one potential cause of multicollinearity, which occurs when machine learning models assume that the variables they use are independent (Bui et al., 2016). The multicollinearity of the data when using any linear statistical method prevents the reliability and interpretation of the results (Farahani et al., 2022). The variance inflation factor (VIF) is a metric used to detect multicollinearity, which is a phenomenon that arises when there is a linear relationship between independent variables (Bui et al., 2016). ...
To mitigate the impact of dust on human health and the environment, it is crucial to create a model and map that identifies the areas susceptible to dust. The present study focused on identifying dust occurrences in the Bushehr province of Iran between 2002 and 2022 using moderate-resolution imaging spectroradiometer (MODIS) imagery. Subsequently, an ensemble machine learning model was improved to prepare a dust susceptibility map (DSM). The study employed differential evolution (DE), genetic algorithm (GA), and flower pollination algorithm (FPA) - three evolutionary algorithms - to enhance the random forest (RF) ensemble model. A spatial database was created for modeling, including 519 dust occurrence points (extracted from MODIS imagery) and 15 factors affecting dust (Slope, bulk density, aspect, clay, altitude, sand, rainfall, lithology, soil order, distance to river, soil texture, normalized difference vegetation index (NDVI), soil water content, land cover, and wind speed). By utilizing the differential evolution (DE) algorithm, we determined the significance of these factors in impacting dust occurrences. The results indicated that altitude, wind speed, and land cover were the most influential factors, while the distance to the river, bulk density, and soil texture had less impact on dust occurrence. Data were preprocessed using multicollinearity analysis and the frequency ratio (FR) approach. For this research, three RF-based meta-heuristic optimization algorithms, namely RF-FPA, RF-GA, and RF-DE, were created for DSM. The effectiveness prediction of the constructed models by indexes of root-mean-square-error (RMSE), the area under the receiver operating characteristic (AUC-ROC), and coefficient of determination (R2) from best to worst were RF-DE (RMSE = 0.131, AUC-ROC = 0.988, and R2 = 0.93), RF-GA (RMSE = 0.141, AUC-ROC = 0.986, and R2 = 0.919), RF-FPA (RMSE = 0.157, AUC-ROC = 0.981, and R2 = 0.9), and RF (RMSE = 0.173, AUC-ROC = 0.964, and R2 = 0.878). The results showed that combining evolutionary algorithms with an RF model improves the accuracy of dust susceptibility modeling.
... After selecting the influential factors and incorporating them into deep learning algorithms, it is important to examine the presence of multicollinearity among these factors. Multicollinearity refers to the correlation between two or more independent factors, which can lead to errors in the results [147,148]. One way to assess multicollinearity in the modeling process is by using the variance inflation factor (VIF) method [149,150]. ...
... After selecting the influential factors and incorporating them into deep learning algorithms, it is important to examine the presence of multicollinearity among these factors. Multicollinearity refers to the correlation between two or more independent factors, which can lead to errors in the results [147,148]. One way to assess multicollinearity in the modeling process is by using the variance inflation factor (VIF) method [149,150]. ...
Recurring wildfires pose a critical global issue as they undermine social and economic stability and jeopardize human lives. To effectively manage disasters and bolster community resilience, the development of wildfire susceptibility maps (WFSMs) has emerged as a crucial undertaking in recent years. In this research endeavor, two deep learning algorithms were leveraged to generate WFSMs using two distinct remote sensing datasets. Specifically, the Moderate-Resolution Imaging Spectroradiometer (MODIS) and Landsat-8 images were utilized to monitor wildfires that transpired during the year 2021. To develop an effective WFSM, two datasets were created by incorporating 599 wildfire locations with Landsat-8 images and 232 sites with MODIS images, as well as twelve factors influencing wildfires. Deep learning algorithms, namely the long short-term memory (LSTM) and recurrent neural network (RNN), were utilized to model wildfire susceptibility using the two datasets. Subsequently, four WFSMs were generated using the LSTM (MODIS), LSTM (Landsat-8), RNN (MODIS), and RNN (Landsat-8) algorithms. The evaluation of the WFSMs was performed using the area under the receiver operating characteristic (ROC) curve (AUC) index. The results revealed that the RNN (MODIS) (AUC = 0.971), RNN (Landsat-8) (AUC = 0.966), LSTM (MODIS) (AUC = 0.964), and LSTM (Landsat-8) (AUC = 0.941) algorithms demonstrated the highest modeling accuracy, respectively. Moreover, the Gini index was employed to assess the impact of the twelve factors on wildfires in the study area. The results of the random forest (RF) algorithm indicated that temperature, wind speed, slope, and topographic wetness index (TWI) parameters had a significant effect on wildfires in the study region. These findings are instrumental in facilitating efficient wildfire management and enhancing community resilience against the detrimental effects of wildfires.
... The sense of hearing allows distinguishing patterns in sounds or determining which sound predominates over another, how long it has lasted, and from what position it has been heard [28]. This ability is natural to humans and other animal species and is often overlooked. ...
Nowadays, the applications of hydraulic systems are present in a wide variety of devices in both industrial and everyday environments. The implementation and usage of hydraulic systems have been well documented; however, today, this still faces a challenge, the integration of tools that allow more accurate information about the functioning and operation of these systems for proactive decision-making. In industrial applications, many sensors and methods exist to measure and determine the status of process variables (e.g., flow, pressure, force). Nevertheless, little has been done to have systems that can provide users with device-health information related to hydraulic devices integrated into the machinery. Implementing artificial intelligence (AI) technologies and machine learning (ML) models in hydraulic system components has been identified as a solution to the challenge many industries currently face: optimizing processes and carrying them out more safely and efficiently. This paper presents a solution for the characterization and estimation of anomalies in one of the most versatile and used devices in hydraulic systems, cylinders. AI and ML models were implemented to determine the current operating status of these hydraulic components and whether they are working correctly or if a failure mode or abnormal condition is present.
... This index is calculated using Eq. 21 to find the difference between the actual and forecasted values (Farahani et al. 2022). ...
Potable water scarcity is a worldwide issue that can be addressed by looking for new regions with adequate groundwater. The study used a combination of three metaheuristic optimization algorithms (particle swarm optimization (PSO), grey wolf optimizer (GWO), and ant colony optimization (ACO)) and a group method of data handling (GMDH) algorithm to delineate groundwater potential zones in Boroujen, Iran. The spatial datasets were created using twelve conditioning factors and spring data (429 locations). The mentioned dataset was divided into two training (70%) and validation (30%) groups. The weights generated from the frequency ratio (FR) method were utilized as modeling inputs. The groundwater potential maps were created using the GMDH, GMDH-PSO, GMDH-GWO, and GMDH-ACO algorithms. With an area under the receiver operating characteristic curve (AUC-ROC) of 87.4%, the GMDH-PSO algorithm outperformed the GMDH-GWO, GMDH-ACO, and GMDH algorithms, which had AUC-ROC values of 85.1%, 83.3% and 80.3%, respectively. Furthermore, the regression relief (Rrelief) method revealed that rainfall, land use/cover, and altitude play a greater role in groundwater assessment. The findings of this research could help with groundwater resource management and groundwater investment planning for long-term sustainability.
... Each DT is trained with randomly selected samples and features . For the final prediction, all DTs contribute to the prediction, and each sample data is predicted by averaging or voting between DTs' predictions (Farahani et al., 2022). • Support vector classification: Support vector machine (SVM) is a popular ML algorithm used for classification (SVC) and regression problems. ...
Driver drowsiness leads to fatal road traffic accidents. The effects of drowsy driving on electroencephalogram (EEG) signal are well visible. Accordingly, classifying EEG signal with machine learning (ML) is known as a reliable and accurate drowsiness detection technique. The type of ML algorithm, data preprocessing, and tuning the hyperparameters influence classification results greatly. In this paper, the drowsy EEG signal of 20 participants was measured in simulator tests. Six ML algorithms of decision tree, extra trees, K-nearest neighbors, multi-layer perceptron, random forest, and support vector classification were trained and cross-validated with different approaches to understand how data preprocessing and tuning the ML hyperparameters can improve drowsy EEG signal modeling. Results indicated that the type of ML algorithm has a more notable effect on modeling accuracy and modeling error than the modeling approach. Data preprocessing generally improved modeling results. But tuning the hyperparameters with the random search method wasn't helpful. Comparison of algorithms showed that tree-based ensemble algorithms (extra trees and random forest) were the most accurate models. They are more practical for real-time applications of drowsy EEG signal modeling.
An accurate understanding of noise perception is important for urban planning, noise management and public health. However, the visual and acoustic urban landscapes are intrinsically linked: the intricate interplay between what we see and hear shapes noise perception in the urban environment. To measure this complex and mixed effect, we conducted a mobility-based survey in Hong Kong with 800 participants, recording their noise exposure, noise perception and GPS trajectories. In addition, we acquired Google Street View images associated with each GPS trajectory point and extracted the urban visual environment from them. This study used a multi-sensory framework combined with XGBoost and Shapley additive interpretation (SHAP) models to construct an interpretable classification model for noise perception. Compared to relying solely on sound pressure levels, our model exhibited significant improvements in predicting noise perception, achieving a six-classification accuracy of approximately 0.75. Our findings revealed that the most influential factors affecting noise perception are the sound pressure levels and the proportion of buildings, plants, sky, and light intensity. Further, we discovered non-linear relationships between visual factors and noise perception: an excessive number of buildings exacerbated noise annoyance and stress levels and diminished objective noise perception at the same time. On the other hand, the presence of green plants mitigated the effect of noise on stress levels, but beyond a certain threshold, it led to worsened objective noise perception and noise annoyance instead. Our study provides insight into the objective and subjective perception of noise pressure, which contributes to advancing our understanding of complex and dynamic urban environments.
Dust pollution poses significant risks to human health, air quality, and food safety, necessitating the identification of dust occurrence and the development of dust susceptibility maps (DSMs) to mitigate its effects. This research aims to detect dust occurrence using satellite images and prepare a DSM for Bushehr province, Iran, by enhancing the attentive interpretable tabular learning (TabNet) model through three swarm-based metaheuristic algorithms: particle swarm optimization (PSO), grey wolf optimizer (GWO), and hunger games search (HGS). A spatial database incorporating dust occurrence areas was created using Moderate Resolution Imaging Spectroradiometer (MODIS) images from 2002 to 2022, including 15 influential criteria related to climate, soil, topography, and land cover. Four models were employed for modeling and DSM generation: TabNet, TabNet-PSO, TabNet-GWO, and TabNet-HGS. Evaluation of the modeling results using performance metrics indicated that the TabNet-HGS model outperformed the other models in both training (mean absolute error (MAE) = 0.055, root-mean-square error (RMSE) = 0.1, coefficient of determination (R2) = 0.959), and testing (MAE = 0.063, RMSE = 0.114, R2 = 0.947) data. Following TabNet-HGS, the TabNet-PSO, TabNet-GWO, and TabNet models demonstrated progressively lower accuracy. The validation of the DSM was performed by assessing receiver operating characteristic (ROC) curves, revealing that the TabNet-HGS, TabNet-PSO, TabNet-GWO, and TabNet models exhibited the highest modeling accuracy, with corresponding area under the curve (AUC) values of 0.994, 0.986, 0.98, and 0.832, respectively. These results highlight the enhanced accuracy of dust susceptibility modeling achieved by integrating swarm-based metaheuristic algorithms with the TabNet model. The dust susceptibility map provides valuable insights into the sources, pathways, and impacts of dust particles on the environment and human health in the study area.
Geleneksel Türk Evinin Biçim GrameriYöntemiyle Plan Türetimi: Konya Mengüç Caddesi Örneği
Flash floods are one of the worst natural disasters, causing massive economic losses and many deaths. Creating a flood susceptibility map (FSM) that pinpoints the areas most at risk of flooding is a crucial non-structural solution for managing floods. This study aimed to assess the efficacy of combinations of the random forest (RF) model with three biology-inspired metaheuristic algorithms, namely invasive weed optimization (IWO), slime mould algorithm (SMA), and satin bowerbird optimization (SBO), for flood susceptibility mapping in Estahban town, Iran. Initially, synthetic-aperture radar (SAR) (Sentinel-1) and optical (Landsat-8) satellite images were integrated to monitor the flooded areas during the July 2022 monsoon in the study area. A dataset of 509 flood occurrence points was created to identify flood-prone areas using remote sensing techniques, considering the monitored flood areas. The dataset also included twelve flood-related criteria: topography, land cover, and climate. The holdout method was employed for modeling, with a ratio of 70:30 used for the train/test split. Data pre-processing techniques were conducted to improve model performance, including determining criteria importance and addressing multicollinearity issues using certainty factor (CF), multicollinearity, and information gain ratio (IGR) methods. Then FSM was prepared using RF, RF-IWO, RF-SBO, and RF-SMA models. The findings of this research revealed that the RF-IWO model was the best predictive model of flood susceptibility modeling, with root-mean-square-error (RMSE) (0.211 and 0.0.27), mean-absolute-error (MAE) (0.103 and 0.15), and coefficient-of-determination (R2) (0.821 and 0.707) in the training and testing phases, respectively. Receiver operating characteristic (ROC) curve analysis of FSM revealed that the most accurate models were the RF-IWO (area under the curve (AUC) = 0.983), RF-SBO (AUC = 0.979), RF-SMA (AUC = 0.963), and RF (AUC = 0.959), respectively. Integrating biology-inspired computing algorithms with machine learning algorithms presents a novel approach to enhancing the accuracy of FSMs.
Rainfall monsoons and the resulting flooding have always been cataclysmic disasters that have heightened global concerns in light of climate change. Flood susceptibility modeling is an indirect method for reducing flood disaster losses. This study aimed to improve flood susceptibility modeling by developing a sequential ensemble (extreme gradient boosting (XGBoost)) model utilizing three swarm-based algorithms (bacterial foraging optimization (BFO), cuckoo search (CS), and artificial bee colony (ABC) algorithms). Initially, an integration of optical (Landsat-8) and radar (Sentinel-1) satellite images were used to monitor the flooded areas during the July 2022 monsoon in the Kazerun region, Iran. A total of 1358 flood occurrence points were considered from the monitored flood areas; 70% (952 points) and 30% (406 points) were used for modeling and evaluating the models, respectively. Based on flood points and thirteen spatial criteria influencing floods, four flood models ((XGBoost, XGBoost-ABC, XGBoost-BFO, and XGBoost-CS)) were used to generate a flood susceptibility map (FSM). According to the results, the XGBoost-CS (area under the curve (AUC) = 0.96), XGBoost-BFO (AUC = 0.953), XGBoost-ABC (AUC = 0.941), and XGBoost (AUC = 0.939) models have greater accuracy in flood susceptibility modeling, respectively. The results indicated that the models coupled with the three metaheuristic algorithms (XGBoost-ABC, XGBoost-BFO, and XGBoost-CS) exhibited higher flood susceptibility modeling accuracy than the standalone XGBoost model.
The visual qualities of the urban environment influence people’s perception and reaction to their surroundings; hence the visual quality of the urban environment affects people’s mental states and can have detrimental societal effects. Therefore, people’s perception and understanding of the urban environment are necessary. This study used a deep learning-based approach to address the relationship between effective spatial criteria and people’s visual perception, as well as spatial modeling and preparing a potential map of people’s visual perception in urban environments. Dependent data on people’s visual perception of Tehran, Iran, was gathered through a questionnaire that contained information about 663 people, 517 pleasant places, and 146 unpleasant places. The independent data consisted of distances to industrial areas, public transport stations, recreational attractions, primary streets, secondary streets, local passages, billboards, restaurants, shopping malls, dilapidated areas, cemeteries, religious places, traffic volume, population density, night light, air quality index (AQI), and normalized difference vegetation index (NDVI). The convolutional neural network (CNN) algorithm created the potential map. The potential visual perception map was evaluated using the receiver operating characteristic (ROC) curve and area under the curve (AUC), with the estimates of AUC of 0.877 and 0.823 for pleasant and unpleasant visuals, respectively. The maps obtained using the CNN algorithm showed that northern, northwest, central, eastern, and some southern areas of the city are potent in pleasant sight, and southeast, some central, and southern regions had unpleasant sight potential. The OneR method results demonstrated that distance to local passages, population density, and traffic volume is most important for pleasant and unpleasant sights.
CV - Updated on 05 July 2024
in English and in Turkish
Emine KOSEOGLU Professor, PhD Istanbul, Turkey
Research Areas: Architectural Design, Environmental Psychology, Urban Morphology
Due to a surge in the frequency and intensity of disruptive events, such as natural disasters, the Covid-19 pandemic, and intentional attacks, the concept of resilience has attracted increased attention in recent years. Many scholars have focused on transportation network resilience because of its importance in society's well-being and recovery efforts after disturbances. Existing studies have suggested various definitions, indicators, and methods for assessing the resilience of transportation networks. This variation is due to differences in the nature, scale, and impact of disturbances. This systematic literature review presents resilience assessment methods for transportation networks, indicators, and disturbance categories. A new representation is suggested for the relationships between performance, time, and resilience, emphasizing other network characteristics and their association with resilience. Resilience indicators are categorized, and disturbance categories are analyzed. Approaches are grouped based on their methodologies and presenting their strengths and limitations. This paper directs future studies toward investigating emerging threats, including climate change, pandemics, cybersecurity, failure propagation, and the impacts of new technologies and paradigms on urban transportation resilience. Additionally, it highlights the benefits of identifying a reference metric. Finally, this paper promotes resilience-based thinking to address challenges facing cities worldwide as a cornerstone for creating lasting sustainable development.
Drivers’ lack of alertness is one of the main reasons for fatal road traffic accidents (RTA) in Iran. Accident-risk mapping with machine learning algorithms in the geographic information system (GIS) platform is a suitable approach for investigating the occurrence risk of these accidents by analyzing the role of effective factors. This approach helps to identify the high-risk areas even in unnoticed and remote places and prioritizes accident-prone locations. This paper aimed to evaluate tuned machine learning algorithms of bagged decision trees (BDTs), extra trees (ETs), and random forest (RF) in accident-risk mapping caused by drivers’ lack of alertness (due to drowsiness, fatigue, and reduced attention) at a national scale of Iran roads. Accident points and eight effective criteria, namely distance to the city, distance to the gas station, land use/cover, road structure, road type, time of day, traffic direction, and slope, were applied in modeling, using GIS. The time factor was utilized to represent drivers’ varied alertness levels. The accident dataset included 4399 RTA records from March 2017 to March 2019. The performance of all models was cross-validated with five-folds and tree metrics of mean absolute error, mean squared error, and area under the curve of the receiver operating characteristic (ROC-AUC). The results of cross-validation showed that BDT and RF performance with an AUC of 0.846 were slightly more accurate than ET with an AUC of 0.827. The importance of modeling features was assessed by using the Gini index, and the results revealed that the road type, distance to the city, distance to the gas station, slope, and time of day were the most important, while land use/cover, traffic direction, and road structure were the least important. The proposed approach can be improved by applying the traffic volume in modeling and helps decision-makers take necessary actions by identifying important factors on road safety.
The reduction of population concentration in some urban land uses is one way to prevent and reduce the spread of COVID-19 disease. Therefore, the objective of this study is to prepare the risk mapping of COVID-19 in Tehran, Iran, using machine learning algorithms according to socio-economic criteria of land use. Initially, a spatial database was created using 2282 locations of patients with COVID-19 from 2 February 2020 to 21 March 2020 and eight socio-economic land uses affecting the disease—public transport stations, supermarkets, banks, automated teller machines (ATMs), bakeries, pharmacies, fuel stations, and hospitals. The modeling was performed using three machine learning algorithms that included random forest (RF), adaptive neuro-fuzzy inference system (ANFIS), and logistic regression (LR). Feature selection was performed using the OneR method, and the correlation between land uses was obtained using the Pearson coefficient. We deployed 70% and 30% of COVID-19 patient locations for modeling and validation, respectively. The results of the receiver operating characteristic (ROC) curve and the area under the curve (AUC) showed that the RF algorithm, which had a value of 0.803, had the highest modeling accuracy, which was followed by the ANFIS algorithm with a value of 0.758 and the LR algorithm with a value of 0.747. The results showed that the central and the eastern regions of Tehran are more at risk. Public transportation stations and pharmacies were the most correlated with the location of COVID-19 patients in Tehran, according to the results of the OneR technique, RF, and LR algorithms. The results of the Pearson correlation showed that pharmacies and banks are the most incompatible in distribution, and the density of these land uses in Tehran has caused the prevalence of COVID-19.
Spatial modeling is an integral component of most geographic information systems (GISs). However, conventional GIS modeling techniques can require substantial processing time and storage space and have limited statistical and machine learning functionality. To address these limitations, many have parallelized spatial models using multiple coding libraries and have applied those models in a multiprocessor environment. Few, however, have recognized the inefficiencies associated with the underlying spatial modeling framework used to implement such analyses. In this paper, we identify a common inefficiency in processing spatial models and demonstrate a novel approach to address it using lazy evaluation techniques. Furthermore, we introduce a new coding library that integrates Accord.NET and ALGLIB numeric libraries and uses lazy evaluation to facilitate a wide range of spatial, statistical, and machine learning procedures within a new GIS modeling framework called function modeling. Results from simulations show a 64.3% reduction in processing time and an 84.4% reduction in storage space attributable to function modeling. In an applied case study, this translated to a reduction in processing time from 2247 h to 488 h and a reduction is storage space from 152 terabytes to 913 gigabytes.
In this paper, land subsidence susceptibility was assessed for Shahryar County in Iran using the adaptive neuro-fuzzy inference system (ANFIS) machine learning algorithm. Another aim of the present paper was to assess if ensembles of ANFIS with two meta-heuristic algorithms (imperialist competitive algorithm (ICA) and gray wolf optimization (GWO)) would yield a better prediction performance. A remote sensing synthetic aperture radar (SAR) dataset from 2019 to 2020 and the persistent-scatterer SAR interferometry (PS-InSAR) technique were used to obtain a land subsidence inventory of the study area and use it for training and testing models. Resulting PS points were divided into two parts of 70% and 30% for training and testing the models, respectively. For susceptibility analysis, eleven conditioning factors were taken into account: the altitude, slope, aspect, plan curvature, profile curvature, topographic wetness index (TWI), distance to stream, distance to road, stream density, groundwater drawdown, and land use/land cover (LULC). A frequency ratio (FR) was applied to assess the correlation of factors to subsidence occurrence. The prediction power of the models and their generated land subsidence susceptibility maps (LSSMs) were validated using the root mean square error (RMSE) value and area under curve of receiver operating characteristic (AUC-ROC) analysis. The ROC results showed that ANFIS-ICA had the best accuracy (0.932) among the models (ANFIS-GWO (0.926), ANFIS (0.908)). The results of this work showed that optimizing ANFIS with meta-heuristics considerably improves LSSM accuracy although ANFIS alone had an acceptable result.
Nowadays, owing to population growth, increasing environmental pollution, and lifestyle changes, the number of asthmatics has significantly increased. Therefore, the purpose of our study was to determine the asthma-prone areas in Tehran, Iran considering environmental, spatial factors. Initially, we built a spatial database using 872 locations of children with asthma and 13 environmental factors affecting the disease—distance to parks and streets, rainfall, temperature, humidity, pressure, wind speed, particulate matter (PM 10 and PM 2.5), ozone (O 3 ), sulfur dioxide (SO 2 ), carbon monoxide (CO), and nitrogen dioxide (NO 2 ). Subsequently, utilizing this spatial database, a random forest (RF) machine learning model, and a geographic information system, we prepared a map of asthma-prone areas. For modeling and validation, we deployed 70% and 30%, respectively, of the locations of children with asthma. The results of spatial autocorrelation and RF model showed that the criteria of distance to parks and streets as well as PM 2.5 and PM 10 had the greatest impact on asthma occurrence in the study area. Spatial autocorrelation analyses indicated that the distribution of asthma cases was not random. According to receiver operating characteristic results, the RF model had good accuracy (the area under the curve was 0.987 and 0.921, respectively, for training and testing data).
Background:
The outbreak of coronavirus disease 2019 (COVID-19) that occurred in Wuhan, China, has become a global public health threat. It is necessary to identify indicators that can be used as optimal predictors for clinical outcomes of COVID-19 patients.
Methods:
The clinical information from 126 patients diagnosed with COVID-19 were collected from Wuhan Fourth Hospital. Specific clinical characteristics, laboratory findings, treatments and clinical outcomes were analyzed from patients hospitalized for treatment from 1 February to 15 March 2020, and subsequently died or were discharged. A random forest (RF) algorithm was used to predict the prognoses of COVID-19 patients and identify the optimal diagnostic predictors for patients' clinical prognoses.
Results:
Seven of the 126 patients were excluded for losing endpoints, 103 of the remaining 119 patients were discharged (alive) and 16 died in the hospital. A synthetic minority over-sampling technique (SMOTE) was used to correct the imbalanced distribution of clinical patients. Recursive feature elimination (RFE) was used to select the optimal subset for analysis. Eleven clinical parameters, Myo, CD8, age, LDH, LMR, CD45, Th/Ts, dyspnea, NLR, D-Dimer and CK were chosen with AUC approximately 0.9905. The RF algorithm was built to predict the prognoses of COVID-19 patients based on the best subset, and the area under the ROC curve (AUC) of the test data was 100%. Moreover, two optimal clinical risk predictors, lactate dehydrogenase (LDH) and Myoglobin (Myo), were selected based on the Gini index. The univariable logistic analysis revealed a substantial increase in the risk for in-hospital mortality when Myo was higher than 80 ng/ml (OR = 7.54, 95% CI [3.42-16.63]) and LDH was higher than 500 U/L (OR = 4.90, 95% CI [2.13-11.25]).
Conclusion:
We applied an RF algorithm to predict the mortality of COVID-19 patients with high accuracy and identified LDH higher than 500 U/L and Myo higher than 80 ng/ml to be potential risk factors for the prognoses of COVID-19 patients in the early stage of the disease.
Multicollinearity occurs when the multiple linear regression analysis includes several variables that are significantly correlated not only with the dependent variable but also to each other. Multicollinearity makes some of the significant variables under study to be statistically insignificant. This paper discusses on the three primary techniques for detecting the multicollinearity using the questionnaire survey data on customer satisfaction. The first two techniques are the correlation coefficients and the variance inflation factor, while the third method is eigenvalue method. It is observed that the product attractiveness is more rational cause for the customer satisfaction than other predictors. Furthermore, advanced regression procedures such as principal components regression, weighted regression, and ridge regression method can be used to determine the presence of multicollinearity.
Keywords:
multicollinearity regression analysis variance inflation factor eigenvalue customer satisfaction
Accepted in Cities & Health Journal on 12 November 2019
Much research has focused on unwanted sound, or noise, and its links to poor health and wellbeing. In contrast, certain sounds-especially those drawn from nature-are linked to positive outcomes. There is increasing interest in identifying and protecting such sounds within cities to offer opportunities for psychological restoration or recovery. However, explanations of why certain sounds are perceived positively are limited. Theoretical development is needed in order to integrate available evidence into wider work on environment and wellbeing, and this should include attention to perceptual properties of sounds and their interpretations by listeners.
This paper reports on a study to assess the feasibility of creating an intuitive environmental sound monitoring system that can be used on-location and return meaningful measurements beyond the standard LAeq. An iOS app was created using Machine Learning (ML) and Augmented Reality (AR) in conjunction with the Sennheiser AMBEO Smart Headset in order to test this. The app returns readings indicating the human, natural and mechanical sound content of the local acoustic scene, and implements four virtual sound objects which the user can place in the scene to observe their effect on the readings. Testing at various types of urban locations indicates that the app returns meaningful ratings for natural and mechanical sound, though the pattern of variation in the ratings for human sound is less clear. Adding the virtual objects largely has no significant effect aside from the car object, which significantly increases mechanical ratings. Results indicate that using ML to provide meaningful on-location sound monitoring is feasible, though the performance of the app developed could be improved given additional calibration.
Automatic urban sound classification is a desirable capability for urban monitoring systems, allowing real-time monitoring of urban environments and recognition of events. Current embedded systems provide enough computational power to perform real-time urban audio recognition. Using such devices for the edge computation when acting as nodes of Wireless Sensor Networks (WSN) drastically alleviates the required bandwidth consumption. In this paper, we evaluate classical Machine Learning (ML) techniques for urban sound classification on embedded devices with respect to accuracy and execution time. This evaluation provides a real estimation of what can be expected when performing urban sound classification on such constrained devices. In addition, a cascade approach is also proposed to combine ML techniques by exploiting embedded characteristics such as pipeline or multi-thread execution present in current embedded devices. The accuracy of this approach is similar to the traditional solutions, but provides in addition more flexibility to prioritize accuracy or timing.
CITE:
Koseoglu, E., 2016, A SENSORY EXPERIENCE IN AN URBAN ENVIRONMENT: SOUND-WALKS AND SOUND- MAPS, ArchDesign'16 / III. International Architectural Design Conference, Ed. Berfu Ayhan, Dakam Publishing, ISBN: 978-605-9207-26-3, 17-18 June 2016, Istanbul.http://www.dakamconferences.org/#!archdesign/s5otu
Sensory studies are important to develop an understanding of the relationship between people and the environment and to see the need to relate buildings and the spaces between them. Stimuli from the sense organs are transformed into perception through processes that take place in mind and they are signified by mechanisms, interpreted, and thus perception occurs. The aim of this study is to introduce a way to obtain sensory information from the spatial environment, to understand and realize the methods to express the results of such an experience visually. A case study is conducted with first grade architectural students in Haskoy, Beyoglu in order to acquire auditory knowledge from the environment and to visualize them. The case study consists of three steps: understanding the issue of environmental sounds, acquiring environmental sounds with direct experience, and visualizing the data as forms of sense-maps using various techniques. Introduction Sound has a crucial role in the definition of space and place. For example, the identity of a space is not a static structure, and can vary from one social context to another (Relph, 1976). The identity of a city is not only defined by its visual, physical features and its appearance but also by its other sensory elements like soundscape. Space turns into a place conceptually when it is shaped by experiences. Wissmann (2014) suggests that sense of place seems an everyday term that is easier to experience than conceptualize. He adopts Tuan's (1975) approach of sense of place to sound. He argues that we do not listen to sounds, we take them for granted. Thus it becomes the part of sensing the place. Nevertheless if this process is needed to be analyzed, then sound-walks and sound-maps as the concrete products of the experience can be the methods for conscious sensory experiencing of space.
Noise on the highway cannot be avoided, given the increasing number of vehicles on the road. Such noise is known to be influenced by several factors, one of which is the distance from the noise source. A collection of exhaust sounds from vehicles in traffic is one such source of noise. This study aims to obtain the effect of traffic on the impact of noise generated on the open area without obstacles based on a predetermined distance of 0 meters, 17.5 meters, and 35 meters. From the result of the analysis, it is obtained that the traffic flow has a strong correlation level as a source of noise at the distance and noise levels show a decreasing level of correlation. At a distance of 0 meters (roadside) obtained correlation level is close to very strong (0.896). At a Distance of 17.5 meters, the correlation rate decreased to 0.823 and at a distance of 35 meters r-value to 0.814. The average noise change due to traffic activity is 0.29 dB per meter from roadside to 17.5 meters, and 0.15 dB per meter from 17.5 meters to 35 meters of the noise source. Thus, it can be concluded that the closer the distance to the traffic or noise source the greater the noise generated and the farther the distance from the traffic the less noise it generates.
Correlation in the broadest sense is a measure of an association between variables. In correlated data, the change in the magnitude of 1 variable is associated with a change in the magnitude of another variable, either in the same (positive correlation) or in the opposite (negative correlation) direction. Most often, the term correlation is used in the context of a linear relationship between 2 continuous variables and expressed as Pearson product-moment correlation. The Pearson correlation coefficient is typically used for jointly normally distributed data (data that follow a bivariate normal distribution). For nonnormally distributed continuous data, for ordinal data, or for data with relevant outliers, a Spearman rank correlation can be used as a measure of a monotonic association. Both correlation coefficients are scaled such that they range from -1 to +1, where 0 indicates that there is no linear or monotonic association, and the relationship gets stronger and ultimately approaches a straight line (Pearson correlation) or a constantly increasing or decreasing curve (Spearman correlation) as the coefficient approaches an absolute value of 1. Hypothesis tests and confidence intervals can be used to address the statistical significance of the results and to estimate the strength of the relationship in the population from which the data were sampled. The aim of this tutorial is to guide researchers and clinicians in the appropriate use and interpretation of correlation coefficients.This is an open-access article distributed under the terms of the Creative Commons Attribution-Non Commercial-No Derivatives License 4.0 (CCBY-NC-ND), where it is permissible to download and share the work provided it is properly cited. The work cannot be changed in any way or used commercially without permission from the journal.
Urban noise pollution is one of the problems of the people who live in urban area and it is a cause of health and
social problem. The main purpose of this work is to identify the major cause of the pollution and to determine the noise
pollution levels in the city. A study was conducted on the main roads of Dire-Dawa city using digital Sound Level Meter
(SLM). A case study was illustrated by applying standardized methods to find noise pollution in the city. It was found that the
noise levels in overall city were very high and above the permissible limits. The result revealed that in the selected area of
hospitals, the noise pollution is 103.68 and 104.27 dB during morning and in afternoon respectively. In general, the average
values of the noise levels throughout the study area were between 45 and 95 dB in places of bargele and Medirbabur
respectively.
This study carried out aims to evaluate noise pollution in Oran province in Algeria (urban and industrial areas), and compares between noise pollution levels in both areas. Eventually, the noise is an integrated part in our environment; it makes actually a great challenge because of the dangerous health troubles it causes. Otherwise, a few studies were scientifically carried out on industrial noise in Algeria; but more and deeper researches are needed in order to determine its origins, sites measurements, noise mapping, and finally giving suggestions about the problem solving. Firstly, we‟ve divided this work into two parts; the first was about the urban area in Oran province where the population is exposed to all noise types especially road traffic noise. The second part concerning the industrial area where ahigher level of noise is observed, it skips the Algerian standard norms, and this noise pollution is mainly generated by machine engines. By a simple comparison between noise levels in both areas, we can observe that noise pollution is higher in the industrial areas than in the urban ones.
Urban noise pollution is one of the problems of the people who live in urban area and it is a cause of health and social problem. The main purpose of this work is to identify the major cause of the pollution and to determine the noise pollution levels in the city. A study was conducted on the main roads of Dire-Dawa city using digital Sound Level Meter (SLM). A case study was illustrated by applying standardized methods to find noise pollution in the city. It was found that the noise levels in overall city were very high and above the permissible limits. The result revealed that in the selected area of hospitals, the noise pollution is 103.68 and 104.27 dB during morning and in afternoon respectively. In general, the average values of the noise levels throughout the study area were between 45 and 95 dB in places of bargele and Medirbabur respectively.
Most humans now live in cities and their main experience of
nature is through urban greenery. An increasing number of
studies show the importance of urban green spaces for wellbeing,
although most of them are based on visual perception.
A questionnaire examining people’s evaluations of natural
sounds was answered by 1326 individuals living near one of
six urban green areas of varying naturalness in the city of
Gothenburg, Sweden. Women and the elderly reported greater
calmness when hearing bird song and rustling leaves (and
placed a higher importance on the richness of bird species) than
did men, younger and middle-aged individuals. Independent
of age and gender, urban woodlands (high naturalness) had
higher evaluations than parks (low naturalness). Our results
suggest that to increase positive experiences of urban green
areas, demographic variables of gender and age should be
taken into account, and settings that mimic nature should be
prioritized in planning.
In this paper a methodology for analyzing the behavior of the environmental noise pollution is proposed. It consists of a mobile application called ‘NoiseMonitor’, which senses the environmental noise with the microphone sensor available in the mobile device. The georeferenced noise data constitute Volunteered Geographic Information that compose a large geospatial database of urban information of the Mexico City. In addition, a Web-GIS is proposed in order to make spatio-temporal analysis based on a prediction model, applying Machine Learning techniques to generate acoustic noise mapping with contextual information.According to the obtained results, a comparison between support vector machines and artificial neural networks were performed in order to evaluate the model and the behavior of the sensed data.
The adverse impact of ignoring multicollinearity on findings and data interpretation in regression analysis is very well documented in the statistical literature. The failure to identify and report multicollinearity could result in misleading interpretations of the results. A review of epidemiological literature in PubMed from January 2004 to December 2013, illustrated the need for a greater attention to identifying and minimizing the effect of multicollinearity in analysis of data from epidemiologic studies. We used simulated datasets and real life data from the Cameron County Hispanic Cohort to demonstrate the adverse effects of multicollinearity in the regression analysis and encourage researchers to consider the diagnostic for multicollinearity as one of the steps in regression analysis.
Traffic related noise pollution accounts for nearly two-third of the total noise pollution in an urban area. Noise, a by product of urbanization, industrialization and motorization, is increasingly recognized as an environmental nuisance that effects human health and wellbeing. Traffic noise on existing urban roadways lowers the quality of life and property values for persons residing near these urban corridors Surat is now the tenth largest city of India having an estimated population of 40 lakhs plus at present. An inconceivable population growth rate of 76.02 % was observed in the last decade as a result of rapid industrialization. Surat is well known as diamond city and is also famous for silk and jari industry. Owing to its rapid industrialization and better job opportunities, observation is made for the migration from all over India and particularly from Orissa, U.P., M.P., Bihar and Rajasthan. Due to explosion of population and rapid industrialization the transportation in the city increased to un-imaginary heights, but due to the want of efficient Mass Transit System, individual vehicular growth also touched escalating heights. As on 31-12-2006, the vehicles registered at R.T.O. is 13 lakhs plus. This is equivalent to the highest growth rate of Delhi. Thus the explosion of population, rapid industrialization and highest growth rate in vehicle population made the traffic problems complicated. This research paper highlights the noise pollution study carried out on three of the busiest urban corridors of Surat city.
There is a lack of studies assessing the exposure-response relationship between transportation noise and annoyance in North America. Our aims were to investigate the prevalence of noise annoyance induced by road traffic, trains and airplanes in relation to distance to transportation noise sources, and to total environmental noise levels in Montreal, Canada; annoyance was assessed as noise-induced disturbance. A telephone-based survey among 4336 persons aged >18 years was conducted. Exposure to total environmental noise (A-weighted outdoor noise levels—LAeq24h and day-evening-night equivalent noise levels—Lden) for each study participant was determined using a statistical noise model (land use regression—LUR) that is based on actual outdoor noise measurements. The proportion of the population annoyed by road traffic, airplane and train noise was 20.1%, 13.0% and 6.1%, respectively. As the distance to major roads, railways and the Montreal International Airport increased, the percentage of people disturbed and highly disturbed due to the corresponding traffic noise significantly decreased. When applying the statistical noise model we found a relationship between noise levels and disturbance from road traffic and total environmental noise, with Prevalence Proportion Ratios (PPR) for highly disturbed people of 1.10 (95% CI: 1.07–1.13) and 1.04 (1.02–1.06) per 1 dB(A) Lden, respectively. Our study provides the first comprehensive information on the relationship between transportation noise levels and disturbance in a Canadian city. LUR models are still in development and further studies on transportation noise induced annoyance are consequently needed, especially for sources other than road traffic.
Groundwater is considered one of the most valuable fresh water resources. The main objective of this study was to produce groundwater spring potential maps in the Koohrang Watershed, Chaharmahal-e-Bakhtiari Province, Iran, using three machine learning models: boosted regression tree (BRT), classification and regression tree (CART), and random forest (RF). Thirteen hydrological-geological-physiographic (HGP) factors that influence locations of springs were considered in this research. These factors include slope degree, slope aspect, altitude, topographic wetness index (TWI), slope-length (LS), plan curvature, profile curvature, distance to rivers, distance to faults, lithology, landuse, drainage density, and fault density. Subsequently, groundwater spring potential was modeled and mapped using CART, RF and BRT algorithms. The predicted results from the three models were validated using the receiver operating characteristics curve (ROC). From 864 springs identified, 605 (≈70%) locations were used for the spring potential mapping, while the remaining 259 (≈30%) springs were used for the model validation. The area under the curve (AUC) for the BRT model was calculated as 0.8103 and for CART and RF the AUC were 0.7870 and 0.7119, respectively. Therefore, it was concluded that the BRT model produced the best prediction results while predicting locations of springs followed by CART and RF models, respectively. Geospatially integrated BRT, CART and RF methods proved to be useful in generating the Spring Potential Map (SPM) with reasonable accuracy.
Kolhapur city is a district place in the state of Maharashtra, India with population of 5, 49,283. It is one of the emerging industrial and commercial city of Western Maharashtra. Problems of pollution along with noise pollution are increasing with time especially due to increase in number of vehicles for transportation. In the present study, continuous monitoring of noise levels Leq dB (A) was carried out for three days in the month of December, 2011 at six different sites within the Kolhapur city. On the basis of location these sites were grouped into industrial, commercial, residential and silent zones respectively. The average noise level at industrial, commercial, residential and silence area are 74.28 dB (A), 65.52 dB (A), 58.88 dB (A) and 50.02 dB (A) respectively. The results showed that there is an enhanced pressure of noise at all sites due to increase in number of vehicles and facilities of transportation. All the sites under study showed higher sound level than the prescribed limits of Central Pollution Control Board (CPCB).
Urban air pollution is one of the most critical issues that affect the environment, community health, economy, and management of urban areas. From a public health perspective, PM2.5 is one of the primary air pollutants, especially in Tehran's metropolis. Owing to the different patterns of PM2.5 in different seasons, Spatio-temporal modeling and identification of high-risk areas to reduce its effects seems necessary. The purpose of this study was Spatio-temporal modeling and preparation of PM2.5 risk mapping using three machine learning algorithms (random forest (RF), AdaBoost, and stochastic gradient descent (SGD)) in the metropolis of Tehran, Iran. Therefore, in the first step, to prepare the dependent variable data, the PM2.5 average was used for the four seasons of spring, summer, autumn, and winter. Then, using remote sensing (RS) and a geographic information system (GIS), independent data such as temperature, maximum temperature, minimum temperature, wind speed, rainfall, humidity, normalized difference vegetation index (NDVI), population density, street density, and distance to industrial centers were prepared as a seasonal average. To Spatio-temporal modeling using machine learning algorithms, 70% of the data were used for training and 30% for validation. The frequency ratio (FR) model was used as input to machine learning algorithms to calculate the spatial relationship between PM2.5 and the effective parameters. Finally, Spatio-temporal modeling and PM2.5 risk mapping were performed using three machine learning algorithms. The receiver operating characteristic (ROC) area under the curve (AUC) results showed that the RF algorithm had the greatest modeling accuracy, with values of 0.926, 0.94, 0.949, and 0.949 for spring, summer, autumn, and winter, respectively. According to the RF model, the most important variable in spring and autumn was NDVI. Temperature and distance to industrial centers were the most important variables in the summer and winter, respectively. The results showed that autumn, winter, summer, and spring had the highest risk of PM2.5, respectively.
Industrialization and increasing urbanization have led to increased air pollution, which has a devastating effect on public health and asthma. This study aimed to model the spatial-temporal of asthma in Tehran, Iran using a machine learning model. Initially, a spatial database was created consisting of 872 locations of asthma children and six air pollution parameters, including carbon monoxide (CO), particulate matter (PM10 and PM2.5), nitrogen dioxide (NO2), sulfur dioxide (SO2), and ozone (O3) in four-seasons (spring, summer, autumn, and winter). Spatial-temporal modeling and mapping of asthma-prone areas were performed using a random forest (RF) model. For Spatio-temporal modeling and assessment, 70 % and 30 % of the dataset were used, respectively. The Spearman correlation and RF model findings showed that during different seasons, the PM2.5 parameter had the most important effect on asthma occurrence in Tehran. The assessment of the Spatio-temporal modeling of asthma using the receiver operating characteristic (ROC)-area under the curve (AUC) showed an accuracy of 0.823, 0.821, 0.83, and 0.827, respectively for spring, summer, autumn, and winter. According to the results, asthma occurs more often in autumn than in other seasons.
Increasing municipal garbage poses a great threat to city sustainability especially in developing countries. It has become one of the main sources of environmental pollution in Chinese cities. Accordingly, Urban Garbage Classification is of great significance to city sustainability. Essentially, it’s a social behavior and entails public participation. Based on a random survey conducted in Chinese major cities, this paper investigates public participation in Urban Garbage Classification. Our findings show that (1) more willingness to garbage classifications do not mean a higher chance of behavior of garbage classification, which indicates a deviation exists between public’s willingness to garbage classification and the behavior of garbage classification. (2) Such a deviation depends mainly on contextual factors and the public’s attitudes and knowledge about urban garbage classification. (3) Those who pay more attention to urban environmental pollution, who know more about urban garbage classification, and who live in a community with more supporting facilities are more likely to participate in garbage classification. Our study provides a new perspective for understanding the importance of public participation in city sustainability. It can provide useful references for the government to reduce urban waste and the sustainable development of cities.
Driver drowsiness causes many road accidents, and preparing a risk map of these accidents with spatial criteria and data mining algorithms highlights accident points well. In this study, accidents risk caused by driver drowsiness in Qazvin province, Iran, was modeled using decision tree (DT), random forest (RF), and support vector regression (SVR) algorithms in GIS environment. Seven spatial criteria including road segment length, road width, slope angle, speed limit, land use/cover, distance to service area, and distance to speed camera were selected as effective criteria in modeling. The effect of criteria in modeling was applied using a fuzzy method, and three risk maps were prepared. Evaluation with ROC-AUC showed that the AUC for RF, SVR, and DT models were 0.904, 0.863, and 0.805, respectively, and the RF model overall had the best performance. Examining the importance of criteria showed that the speed limit was the most important criterion for modeling.
Traffic noise pollution has become a major environmental issue that plagues urban residents. The purpose of this study is to evaluate the traffic noise pollution based on noise maps. Twenty-four-hour noise maps of the Chancheng District in Foshan, China were developed for this study, and the results analyzed. The study area is divided into four types, based on the land use requirements for the acoustic environment, and the calculated noise value is compared to the noise limits of each class of the area. The average equivalent sound pressure level of the entire study area indicates the noise pollution is modest, but further analysis of the noise data in various types of areas shows a high magnitude of noise and long-lasting noise pollution near street-front buildings as well as the areas where quietness is required. It was also found that the noise level of the city is higher during off-peak hours than during rush hours, probably due to the faster speed and larger traffic volume during the off-peak hours. It is urgent to develop effective noise reduction measures to mitigate traffic noise pollution at night, based on the evaluation results.
Due to climate change and growth of urban communities, the need for new sources of freshwater, especially groundwater, is increasing in water-deficient countries like Iran. This study therefore aimed at groundwater potential mapping (GPM) of Nahavand plain, Iran, using optimized adaptive neuro fuzzy inference system (ANFIS) in geographic information system (GIS). ANFIS was optimized through three meta-heuristic algorithms, including differential evolution (DE), particle swarm optimization (PSO), and ant colony optimization (ACO). A spatial database was constructed using 273 spring locations and 14 groundwater conditioning factors, including: altitude, slope angle, slope aspect, slope length, stream power index (SPI), topographic wetness index (TWI), plan curvature, profile curvature, land use/land cover, lithology, distance from the river, distance from the fault, river density, and fault density. The optimization algorithms were evaluated using the receiver operating characteristic (ROC) technique. Results showed that ANFIS-DE, ANFIS-PSO, and ANFIS-ACO models had 0.816, 0.809, and 0.758 accuracy, respectively; and the high and very high potential for groundwater springs covered 26% of the Nahavand plain. Based on the RMSE results in train and validation data, the ANFIS-DE model had a lower value compared to the other two models. Results showed that ANFIS-PSO model has a higher convergence speed than the other two models. This study can play an important role in sustainable groundwater management in the Nahavand plain.
Floods are one of the most devastating types of disasters that cause loss of lives and property worldwide each year. This study aimed to evaluate and compare the prediction capability of the naïve Bayes tree (NBTree), alternating decision tree (ADTree), and random forest (RF) methods for the spatial prediction of flood occurrence in the Quannan area, China. A flood inventory map with 363 flood locations was produced and partitioned into training and validation datasets through random selection with a ratio of 70/30. The spatial flood database was constructed using thirteen flood explanatory factors. The probability certainty factor (PCF) method was used to analyze the correlation between the factors and flood occurrences. Consequently, three flood susceptibility maps were produced using the NBTree, ADTree, and RF methods. Finally, the area under the curve (AUC) and statistical measures were used to validate the flood susceptibility models. The results indicated that the RF method is an efficient and reliable model in flood susceptibility assessment, with the highest AUC values, positive predictive
rate, negative predictive rate, sensitivity, specificity, and accuracy for the training (0.951, 0.892, 0.941, 0.945, 0.886, and 0.915, respectively) and validation (0.925, 0.851, 0.938, 0.945, 0.835, and 0.890, respectively) datasets.
Earth fissures are the cracks on the surface of the earth mainly formed in the arid and the semi-arid basins. The excessive withdrawal of groundwater, as well as the other underground natural resources, has been introduced as the significant causing of land subsidence and potentially, the earth fissuring. Fissuring is rapidly turning into the nations’ major disasters which are responsible for significant economic, social, and environmental damages with devastating consequences. Modeling the earth fissure hazard is particularly important for identifying the vulnerable groundwater areas for the informed water management, and effectively enforce the groundwater
recharge policies toward the sustainable conservation plans to preserve existing groundwater resources. Modeling the formation of earth fissures and ultimately prediction of the hazardous areas has been greatly challenged due to the complexity, and the multidisciplinary involved to predict the earth fissures. This paper aims at proposing novel machine learning models for prediction of earth fissuring hazards. The Simulated annealing feature selection (SAFS) method was applied to identify key features, and the generalized linear model (GLM), multivariate adaptive regression splines (MARS), classification and regression tree (CART), random forest (RF), and support vector machine (SVM) have been used for the first time to build the prediction models. Results indicated that all the models had good accuracy (> 86%) and precision (> 81%) in the prediction of the earth fissure hazard. The GLM model (as a linear model) had the lowest performance, while the RF model was the best model in the modeling process. Sensitivity analysis indicated that the hazardous class in the study area was mainly related to low elevations with characteristics of high groundwater withdrawal, drop in groundwater level, high well density, high road density, low precipitation, and Quaternary sediments distribution.
In this study, models for predicting traffic-noise annoyance based on noise perception, noise exposure levels, and demographics were developed. By applying machine-learning techniques, in particular artificial neural networks (ANN), support vector machines (SVM) and multiple linear regressions (MLR), the traffic-noise annoyance models were obtained, and the error rates compared. A traffic noise map and the estimation of noise exposure for the case study area were developed. Although, it is quite evident that subjective noise perception and predicted noise exposure levels strongly influence traffic-noise annoyance , traditional statistical models fail to produce accurate predictions. Therefore, a machine-learning approach was applied, which showed a better performance in terms of error rates and the coefficient of determination (R2). The best results for predicting traffic-noise annoyance were obtained with the ANN model, obtaining 42% and 35% error reduction in training subsets compared to the MRL and SVM models, respectively. For testing subsets, the error reductions were 24% and 19% for the corresponding models. The coefficient of determination R2 increased 3.8 and 2.3 times using ANN compared to MRL and SVM models in training subsets respectively, and 1.7 times (in both MRL and SVM models) for testing subsets. In this way, the applied methodology can be used as a reliable and more accurate tool for determining the impact of transportation noise in urban context, promoting the well-being of the population and the creation of suitable public policy.
Recent research shows that street-level noise represents one of the main noise sources in urban spaces. The noise source includes various transportation modes, human activities and environmental sounds, such as the wind and rain. Continuous exposure to high-level noise may lead to health and psychological problems that directly threaten public health and well-being. This paper is an experimental study that aims to analyse street-level noise in three different urban settings in Tripoli, Lebanon, characterized by two categories: type of main activities and historical/new areas in the city of Tripoli. The data collection process is through sound and GPS data loggers aggregated into GIS maps. The results are compared to the spatial configuration analysis of the urban fabric, using space syntax theory and methods. The sound mapping could be the onset of wider research for obtaining a full soundscape of the city of Tripoli, with the potential of being applied in other cities.
Recent developments in the field of machine learning offer new ways of modelling complex socio-spatial processes, allowing us to make predictions about how and where they might manifest in the future. Drawing on earlier empirical and theoretical attempts to understand gentrification and urban change, this paper shows it is possible to analyse existing patterns and processes of neighbourhood change to identify areas likely to experience change in the future. This is evidenced through an analysis of socio-economic transition in London neighbourhoods (based on 2001 and 2011 Census variables) which is used to predict those areas most likely to demonstrate ‘uplift’ or ‘decline’ by 2021. The paper concludes with a discussion of the implications of such modelling for the understanding of gentrification processes, noting that if qualitative work on gentrification and neighbourhood change is to offer more than a rigorous post-mortem then intensive, qualitative case studies must be confronted with – and complemented by – predictions stemming from other, more extensive approaches. As a demonstration of the capabilities of machine learning, this paper underlines the continuing value of quantitative approaches in understanding complex urban processes such as gentrification.
Please cite published article in all cases; however, a pre-peer review copy is available in our IR: https://kclpure.kcl.ac.uk/portal/files/97604699/Author_s_final_version.pdf
Traffic noise pollution is a widespread public health problem in both developing and developed countries. Quickly and effectively evaluating the quality of an urban acoustic environment is an important challenge for urban planning and management. To solve this problem, this study first classified the urban function area of the study area according to the functional characteristics and environmental quality requirements of the region, and then, the traffic noise propagation model was applied to predict instantaneous sound levels (LA) based on noise attenuation. Finally, a traffic noise evaluation model was proposed to evaluate the quality of the urban acoustic environment. Taking Changchun city as our study area, eighty field samples of equivalent noise levels (Leq) were measured every ten minutes at four types of roads, classified as trunk roads, secondary roads, expressways and rural roads, in different urban function areas. An urban noise map was drawn to reflect the degree of traffic noise pollution. By comparing the measured and predicted values of noise levels, the results show that the traffic noise propagation model can be used to predict instantaneous sound levels. The traffic noise evaluation results show that the quality of the acoustic environment in our study area was at a medium level, which means that long-term exposure to it can affect the normal work and life of people. The traffic noise propagation model and proposed evaluation model are feasible methods for evaluating the quality of the acoustic environment and can provide a reference for the management of noise pollution control of urban traffic.
The preparation of a landslide susceptibility map is considered to be the first step for landslide hazard mitigation and risk assessment. However, these maps are accepted as end products that can be used for land use planning. The main goal of this study is to assess and compare four advanced machine learning techniques, namely the Bayes' net (BN), radical basis function (RBF) classifier, logistic model tree (LMT), and random
forest (RF) models, for landslide susceptibility modelling in Chongren County, China. A total of 222 landslide locations were identified in the study area using historical reports, interpretation of aerial photographs, and extensive field surveys. The landslide inventory data was randomly split into two groups with a ratio of 70/30 for training and validation purposes. Fifteen landslide conditioning factors were prepared for landslide susceptibility modelling. The spatial correlation between landslides and conditioning factors was analyzed using the information gain (IG) method. The BN, RBF classifier, LMT, and RF models were constructed using the training dataset. Finally, the receiver operating characteristic (ROC) and statistical measures, including sensitivity, specificity, and accuracy, were employed to validate and compare the predictive capabilities of the
models. Out of the tested models, the RF model had the highest sensitivity, specificity, and accuracy values of 0.787, 0.716, and 0.752, respectively, for the training dataset. Overall, the RF model produced an optimized balance for the training and validation datasets in terms of AUC values and statistical measures. The results of this study also demonstrate the benefit of selecting optimal machine learning techniques with proper conditioning
selection methods for landslide susceptibility modelling.
The mechanism of noise pollution propagation is considerably affected by 1) the type and configuration of its receiving environment and 2) the distance that sound waves pass to reach that environment. This study adopts a spatio-statistical approach to quantify and model associations between noise pollution levels and landscape metrics of land categories (built-up structures and urban green covers). Accordingly, noise levels were measured employing a sound pressure meter to quantify equivalent levels (Leq in dB A), in addition to their corresponding percentiles (L10 and L90). A collection of 30 sampling points were selected to measure noise data within the fall season and between 4 p.m. and 8 p.m. hours of the day. A hierarchical distance-sampling framework based on buffer areas with different radius (300m, 600 m and 1 km) around each sampling point was compiled to measure composition and configuration metrics of land categories within each buffer area. The results derived from Pearson correlation analysis and multiple-linear regression models indicated that there is a distance-dependent relationship between the metrics of green areas and noise levels. We didn’t find remarkable distance-dependency between built-up structures and noise levels. Based on our new spatio-statistical approach, we conclude that more connected and compacted pattern of green areas closer to pollution centers can significantly alleviate the effects of noise propagation mechanism and appropriate pattern of built-up areas follows a low density distribution with coming green areas in between. Findings of this study highlight the potential of landscape ecology approach as an effective planning paradigm for designing greener and calmer cities.
In recent years, the concept of smart sustainable cities has come to the fore. And it is rapidly gaining momentum and worldwide attention as a promising response to the challenge of urban sustainability. This pertains particularly to ecologically and technologically advanced nations. This paper provides a comprehensive overview of the field of smart (and) sustainable cities in terms of its underlying foundations and assumptions, state–of–the art research and development, research opportunities and horizons, emerging scientific and technological trends, and future planning practices. As to the design strategy, the paper reviews existing sustainable city models and smart city approaches. Their strengths and weaknesses are discussed with particular emphasis being placed on the extent to which the former contributes to the goals of sustainable development and whether the latter incorporates these goals. To identify the related challenges, those models and approaches are evaluated and compared against each other in line with the notion of sustainability. The gaps in the research within the field of smart sustainable cities are identified in accordance with and beyond the research being proposed. As a result, an integrated approach is proposed based on an applied theoretical perspective to align the existing problems and solutions identification for future practices in the area of smart sustainable urban planning and development. As to the findings, the paper shows that critical issues remain unsettled, less explored, largely ignored, and theoretically underdeveloped for applied purposes concerning existing models of sustainable urban form as to their contribution to sustainability, among other things. It also reveals that numerous research opportunities are available and can be realized in the realm of smart sustainable cities. Our perspective on the topic in this regard is to develop a theoretically and practically convincing model of smart sustainable city or a framework for strategic smart sustainable urban development. This model or framework aims to address the key limitations, uncertainties, paradoxes, and fallacies pertaining to existing models of sustainable urban form—with support of ICT of the new wave of computing and the underlying big data and context–aware computing technologies and their advanced applications. We conclude that the applied theoretical inquiry into smart sustainable cities of the future is deemed of high pertinence and importance—given that the research in the field is still in its early stages, and that the subject matter draws upon contemporary and influential theories with practical applications. The comprehensive overview of and critique on existing work on smart (and) sustainable cities provide a valuable and seminal reference for researchers and practitioners in related research communities and the necessary material to inform these communities of the latest developments in the area of smart sustainable urban planning and development. In addition, the proposed integrated approach is believed to be the first of its kind and has not been, to the best of one’s knowledge, produced elsewhere.
This chapter presents an overview of predictive modeling techniques commonly applied to drug sensitivity prediction based on genomic characterizations. We broadly categorize the approaches into groups of linear regression techniques, nonlinear regression methods, kernel approaches, ensemble methods, and dynamical models. Applications of these techniques to NCI-DREAM drug sensitivity challenge are also discussed.
Human activities are important to landscape design and urban planning; however, the effect of sound-related activities on human behaviours and acoustic comfort has not been considered. The objective of this study is to explore how human behaviours and acoustic comfort in urban open spaces can be changed by sound-related activities. On-site measurements were performed at a case study site in Harbin, China, and an acoustic comfort survey was simultaneously conducted. In terms of effect of sound activities on human behaviours, music-related activities caused 5.1–21.5% of persons who pass by the area to stand and watch the activity, while there was a little effect on the number of persons who performed excises during the activity. Human activities generally have little effect on the behaviour of pedestrians when only 1 to 3 persons are involved in the activities, while a deep effect on the behaviour of pedestrians is noted when > 6 persons are involved in the activities. In terms of effect of activities on acoustic comfort, music-related activities can increase the sound level from 10.8 to 16.4 dBA, while human activities such RS and PC can increase the sound level from 9.6 to 12.8 dBA; however, they lead to very different acoustic comfort. The acoustic comfort of persons can differ with activities, for example the acoustic comfort of persons who stand watch can increase by music-related activities, while the acoustic comfort of persons who sit and watch can decrease by human sound-related activities. Some sound-related activities can show opposite trend of acoustic comfort between visitors and citizens. Persons with higher income prefer music sound-related activities, while those with lower income prefer human sound-related activities.
This research studies urban soundscapes through the comparative analysis of twelve public open spaces in the city of Córdoba (Argentina), taken as case studies. The work aims to examine selection of indicators and assessment tools intended to characterize soundscape quality. The field study was carried out through surveys and acoustic and psychoacoustic indicators, that are used together to objectively describe the sound quality of urban spaces. The study shows that, while there is a relationship of these indicators with the sound quality of the spaces, this is not linear. Their relative importance or influence depends on the interrelations occurring between the parameters studied. A model analyzing and correlating the parameters with the sound quality, based on the postulates of fuzzy logic, was applied as a tool of analysis, and it was seen to achieve a very close approximation to the subjective or perceptual response of the inhabitants. This close match between the model results and the perceptual response of the users confirms the fuzzy model as an effective tool for the study, not only of soundscapes, but also for those situations in which objective parameters must be related to the perceptual response of users.
Environmental Noise Pollution: Noise Mapping, Public Health and Policy addresses the key debates surrounding environmental noise pollution with a particular focus on the European Union. Environmental noise pollution is an emerging public policy and environmental concern and is considered to be one of the most important environmental stressors affecting public health throughout the world. This book examines environmental noise pollution, its health implications, the role of strategic noise mapping for problem assessment, major sources of environmental noise pollution, noise mitigation approaches, and related procedural and policy implications. Drawing on the authors considerable research expertise in the area, the book is the first coherent work on this major environmental stressor, a new benchmark reference across disciplinary, policy and national boundaries. • Highlights recent developments in the policy arena with particular focus on developments in the EU within the context of the European Noise Directive • Explores the lessons emerging from nations within the EU and other jurisdictions attempting to legislate and mitigate against the harmful effects of noise pollution • Covers the core theoretical concepts and principles surrounding the mechanics of noise pollution as well as the evidence-base linking noise with public health concerns.
The purpose of this study was to perform computer-assisted noise mapping of an educational environment. The computer simulations were performed using SoundPLAN software. An analysis of the acoustic maps generated by the simulations indicates that contributions to the noise levels found on the campus originate mostly from three streets on campus, as well as from the roads surrounding the outer perimeter - the Green Line and the BR-277 highway. The computergenerated acoustic maps show that the noise levels within the campus exceed the limit of Leq = 50 dB(A) established for educational areas, according to the Brazilian standard for noise assessment in communities. Therefore, the noise maps indicate a critical situation of noise pollution on campus. However, despite this negative and concerning situation of noise pollution, the acoustic maps also reveal several "islands of acoustic tranquility" on campus. These "islands" can be observed adjacent to buildings where sound levels range from 45 to 48 dB(A) and from 48 to 51 dB(A), which are indicated in green tones on the acoustic maps.
In recent years, we have seen the emergence of sound mapping, through which users can share their recordings of sounds via online mapping platforms. These practices are enabled by an array of spatial and digital technologies that also facilitate the growth of the so-called volunteered geographic information (VGI) regarding contributions from users without training in conventional GIS or cartography. In the growing body of work on VGI, however, not much attention has been given to the emergence of such sound maps as part of the VGI constructions. Meanwhile, research in soundscape has not addressed the aspect of crowd-sourcing or user-generated contributions facilitated by new information and communication technologies. This article seeks to bridge this gap. It draws upon important insights from critical GIS research into investigating VGI as visual practices, while it is also informed by three areas of soundscape research including mapping soundscapes, tracing the production of soundscapes and exploring embodied experiences with soundscapes. Through an empirical case in China, this article suggests a two-level analytical framework: investigating in what ways crowd-sourced sound maps emerge and interpreting these sounds on their shared platforms. In so doing, this study calls for more engagement with the multi-modality aspect of visuality in mappings, which in turn may have implications for landscape design and planning. In this way, it seeks to enrich the discussion on critical visualization.