No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
A Novel Smart System for Contaminants Detection and Recognition in Water
... The authors stem from a pre-existent system based on a specific multi-sensing platform, SENSIPLUS, briefly described in Section II. Furthermore, they exploit past efforts on the creation of a water monitoring smart system [11]- [13] to propose a low-cost solution, working as a finite-statemachine able to reduce false positive, thus enhancing system specificity, while keeping good system sensitivity. In detail, both in clean and waste water, what really influences the detection capability is the system's promptness to distinguish between normal condition (i.e. ...
... During acquisition phase, the distinction between aforementioned conditions is not straightforward, because the system continuously acquires and updates its background condition adopted to recognize pollutant case. In [11], the authors adopted a static background update, based on such a simple rule: the system acquired a certain amount of samples, surely belonging to background, and updated it with a very slow average operation, thus avoiding to sudden spikes, due to contaminant, to deeply influence the background levels. ...
... In this section, a new approach for baseline tracking is presented and compared to that proposed in [11]. ...
Water monitoring systems continuously working
ensure real–time pollutant detection capabilities according to
their sensitivity and specificity. It is necessary to balance such
features because, although being able to sense several substances
is a desired feature, the reduction of false positives is a primary
goal a classification system should have. High false positive makes
the system unusable. The current solution enables a 24/7 service
with a sampling rate equal to 0.6 Hz. Our goal is to limit false
positives to 1 per day, thus achieving 99.99% accuracy at least. In
this paper, we add a false positive reduction module to our pre-
existent system, aiming to manage false positive boosters as sensor
drift and signal oscillations. Obtained results, using a Multi Layer
Perceptron classifier, confirm the false positive reduction while
keeping high true positive rates.
... The EIS technique has been adopted for measurements from sensors, and nine different machine learning solutions have been evaluated for the classification task. Preliminary studies and research activities based on the same MASP technology have been proposed in Ferdinandi et al. [16] and Betta et al. [5] . Further experimental activities adopting the same technology for different applications were proposed in Cerro et al. [10] , Bruschi et al. [8] , and Cerro et al. [9] . ...
... Further experimental activities adopting the same technology for different applications were proposed in Cerro et al. [10] , Bruschi et al. [8] , and Cerro et al. [9] . This work extends our previous works [5,16] in several directions: (i) we consider new substances (Sulphuric Acid, Phosphoric Acid, Acetic Acid, Formic Acid, Hydrogen Peroxide, Ammonia); (ii) we adopt new sensor combinations, from two sensors (Gold and Copper) to four sensors (Gold, Silver, Nickel, Platinum) integrated in a compact configuration; (iii) we adopt a different sensor setting in which the stimulus signal has been changed to 200 Hz and 78 kHz; and (iv) we evaluate nine different classifiers and analyze their trade-off with respect to performance, processing time and memory usage. The idea exploited with the partially selective sensors reported at point (ii), is that they can contribute to the discrimination capability of the array. ...
Water pollution caused by human activities poses a serious global threat to human health. Sensor technologies enabling water monitoring are an important tool that can help facing this problem. In this work, we propose an embedded IoT-ready system based on a proprietary sensor technology for the detection and recognition of six water contaminants. The system architecture is composed of two layers: (i) a sensing layer based on the SENSIPLUS chip, a proprietary Micro-Analytical Sensing Platform with six interdigitated electrodes metalized through different materials; and (ii) a data collection, communication, and classification layer with both hardware and software components. Being classification the most computationally and resource intensive operation, we evaluated nine machine learning solutions of different complexity and analyzed the trade-off between recognition accuracy, processing time, and memory usage to find a solution suitable to be implemented on an edge node. The highest average accuracy of 95.4% was achieved with K-nearest neighbor classification without constraints on processing time and memory usage, which confirms the potentiality of the system. When such constraints are taken into consideration, the best performance dropped to 86.4% offered by Multi Layer Perceptron.
... In particular, several kinds of technologies contribute to developing sensors that discriminate and classify undesired substances to ensure an adequate water quality level. Some of the authors developed systems able to monitor both water and air thanks to the SENSIPLUS platform [10,11,12,13]. The monitoring outputs can vary, ranging from a classification of the pollutants to a simple binary decision on the presence of contaminants in general. ...
The detection of contaminants in several environments (e.g., air, water, sewage systems) is of paramount importance to protect people and predict possible dangerous circumstances. Most works do this using classical Machine Learning tools that act on the acquired measurement data. This paper introduces two main elements: a low-cost platform to acquire, pre-process, and transmit data to classify contaminants in wastewater; and a novel classification approach to classify contaminants in wastewater, based on deep learning and the transformation of raw sensor data into natural language metadata. The proposed solution presents clear advantages against state-of-the-art systems in terms of higher effectiveness and reasonable efficiency. The main disadvantage of the proposed approach is that it relies on knowing the injection time, i.e., the instant in time when the contaminant is injected into the wastewater. For this reason, the developed system also includes a finite state machine tool able to infer the exact time instant when the substance is injected. The entire system is presented and discussed in detail. Furthermore, several variants of the proposed processing technique are also presented to assess the sensitivity to the number of used samples and the corresponding promptness/computational burden of the system. The lowest accuracy obtained by our technique is 91.4%, which is significantly higher than the 81.0% accuracy reached by the best baseline method.
... At the same time, it has been demonstrated that the SENSIPLUS platform is suitable for identifying pollutants in water [27,28] or air [8,29] in an effective way. The open issue is that, in all these cases, the machine learning models have been deployed on external devices (PC, Workstation, or into the cloud). ...
The technological step towards sensors’ miniaturization, low-cost platforms, and evolved communication paradigms is rapidly moving the monitoring and computation tasks to the edge, causing the joint use of the Internet of Things (IoT) and machine learning (ML) to be massively employed. Edge devices are often composed of sensors and actuators, and their behavior depends on the relative rapid inference of specific conditions. Therefore, the computation and decision-making processes become obsolete and ineffective by communicating raw data and leaving them to a centralized system. This paper responds to this need by proposing an integrated architecture, able to host both the sensing part and the learning and classifying mechanisms, empowered by ML, directly on board and thus able to overcome some of the limitations presented by off-the-shelf solutions. The presented system is based on a proprietary platform named SENSIPLUS, a multi-sensor device especially devoted to performing electrical impedance spectroscopy (EIS) on a wide frequency interval. The measurement acquisition, data processing, and embedded classification techniques are supported by a system capable of generating and compiling code automatically, which uses a toolchain to run inference routines on the edge. As a case study, the system capabilities of such a platform in this work are exploited for water quality assessment. The joint system, composed of the measurement platform and the developed toolchain, is named SENSIPLUS-LM, standing for SENSIPLUS learning machine. The introduction of the toolchain empowers the SENSIPLUS platform moving the inference phase of the machine learning algorithm to the edge, thus limiting the needs of external computing platforms. The software part, i.e., the developed toolchain, is available for free download from GitLab, as reported in this paper.
... Water, which covers more than 70% of the Earth's surface and is involved in almost all life activities, is a primary factor influencing life on the Earth. Consequently, water quality monitoring is a crucial task, and ways to address it are widely spreading in the scientific literature (Ighalo et al., 2021;Budiarti et al., 2019;Saravanan et al., 2018;Akhter et al., 2022;Ferdinandi et al., 2019). Particularly critical is the issue related to wastewater (Trubetskaya et al., 2021), i.e., water having suffered pollution due to domestic, industrial, or hospital processes. ...
The problem of detecting illegal pollutants in wastewater is of fundamental importance for public health and security. The availability of distributed, low–cost and low–power monitoring systems, particularly enforced by IoT communication mechanisms and low-complexity machine learning algorithms, would make it feasible and easy to manage in a widespread manner. Accordingly, an End-to-End IoT-ready node for the sensing, local processing, and transmission of the data collected on the pollutants in the wastewater is presented here. The proposed system, organized in sensing and data processing modules, can recognize and distinguish contaminants from unknown substances typically present in wastewater. This is particularly important in the classification stage since distinguishing between background (not of interest) and foreground (of interest) substances drastically improves the classification performance, especially in terms of false positive rates. The measurement system, i.e., the sensing part, is represented by the so-called Smart Cable Water based on the SENSIPLUS chip, which integrates an array of sensors detecting various water-soluble substances through impedance spectroscopy. The data processing is based on a commercial Micro Control Unit (MCU), including an anomaly detection module, a classification module, and a false positive reduction module, all based on machine learning algorithms that have a computational complexity suitable for low-cost hardware implementation.
An extensive experimental campaign on different contaminants has been carried out to train machine-learning algorithms suitable for low-cost and low-power MCU. The corresponding dataset has been made publicly available for download. The obtained results demonstrate an excellent classification ability, achieving an accuracy of more than 95% on average, and are a reliable ”proof of concept” of a pervasive IoT system for distributed monitoring.
... On the other hand, the industry is moving towards systems that have the same goals, such as SPC5-STUDIO by ST Microelectronics [6] or the BME AI-Studio Software from Bosch Sensortec [7]. In particular, the multisensory device was exploited for the acquisition of characteristics suitable for the identification of pollutants in water [8]- [11] or air [12]- [14], creating a system that allows to automatically generate the complete firmware in all its parts. A firmware that starts from the acquisition of the features up to the preprocessing and classification phase, providing the output result according to an appropriate protocol. ...
... They are trying to propose new emerging sensors able to reliable detect pollutants saving money, size and energy consumption, new network technologies, new communication standards, and, finally, new methods for the data analysis. Many researchers are exploiting the advantages offered by Artificial Intelligence and Machine Learning (ML) [3,4,13,15]. ML techniques are often preprocessed using Principal Component Analysis (PCA). ...
The problem of detecting pollutants in water with non-invasive and low-cost sensors is an open question. In this paper, we propose a system for the detection and classification of pollutants based on the improvement of a previous proposal, focused on geometric cones. The solution is based on a classifier suitable to be implemented aboard the so-called Smart Cable Water (SCW) sensor, a multi-sensor based on SENSIPLUS® technology developed by Sensichips s.r.l. The SCW endowed with six interdigitated electrodes is a smart-sensor covered by specific sensing materials that allow differentiating between different water contaminants. Using the PCA or LDA decomposition, we obtain a data compression that makes data suitable for the “edge computing” paradigm with a reduction from a 10-dimensional space to a 3-dimensional space. We defined an ad-hoc classifier to distinguish contaminants represented by points in the 3-dimensional space. We used an evolutionary algorithm to learn the classifier’s parameters. Finally, we compared the performance of our system with that achieved by the old classification system based only on PCA, as well as those achieved by other machine learning algorithms. The proposed system achieved the best accuracy of 87%, outperforming the other state-of-the-art systems compared. The novelty of the system proposed lies in the usage of an evolutionary algorithm for the optimization of the parameters of a novel PCA-based classification algorithm for the detection of water pollutants.
... In such framework, a special mention is deserved by the monitoring of natural quantities, as temperature, humidity, water [4] and air quality [5], [6], specific gas presence in the atmosphere. Among them, a growing interest is given to the Radon Gas Monitoring [7]- [9], for two distinct aspects: human health and Earth's status. ...
... Nowadays, many research activities have been addressing the problem of pollution monitoring by using the emerging sensing technologies, as well as the new possibilities of data analysis offered by Artificial Intelligence and Machine Learning [3,4,15,17]. Among the others, in [7] the authors used Artificial Neural Network and Principal Component Regression techniques to estimate nitrate concentration in groundwater, whereas a pattern recognition solution based on partial least square discriminant analysis (PLS-DA) was presented in [15]. ...
Nowadays, the problem of pollution in water is a very serious issue to be faced and it is really important to be able to monitoring it with non-invasive and low-cost solutions, like those offered by smart sensor technologies. In this paper, we propose an improvement of an our innovative classification system, based on geometrical cones, to detect and classify pollutants, belonging to a given set of substances, spilled into waste water. The solution is based on an ad-hoc classifier that can be implemented aboard the Smart Cable Water (SCW) sensor, based on SENSIPLUS technology developed by Sensichips s.r.l. The SCW is a smart-sensor endowed with six interdigitated electrodes, covered by specific sensing materials that allow detecting between different water contaminants. In order to develop an algorithm suitable to apply the “edge computing” paradigm we first compress the input data from a 10-dimensional space to a 3-D space by using the PCA decomposition techniques. Then we use an ad-hoc classifier to classify between the different contaminants in the transformed space. To learn the classifier’s parameters we used the evolutionary algorithms. The obtained results have been compared with the old classification system and other, more classical, machine learning approaches.
... The Fig. 1. The adopted acquisition and processing system same MASP technology has been used in several studies for contaminants detection [12]- [15]. Due to time and cost issues of collecting measures for any substance that could be found in wastewater, the faced machine learning problem should be considered as an "open-set recognition" problem, i.e., a classification problem where the training data only gives a partial view of the application domain. ...
In smart city framework, the water monitoring through an efficient, low-cost, low-power and IoT-oriented sensor technology is a crucial aspect to allow, with limited resources, the analysis of contaminants eventually affecting wastewater. In this sense, common interfering substances, as detergents, cannot be classified as dangerous contaminants and should be neglected in the classification. By adopting classical machine learning approaches having a finite set of possible responses, each alteration of the sensor baseline is always classified as one out of the predetermined substances. Consequently, we developed an anomaly detection system based on one-class classifiers, able to discriminate between a recognized set of substances and an interfering source. In this way, the proposed detection system is able to provide detailed information about the water status and distinguish between harmless detergents and dangerous contaminants.
... pH, conductivity and turbidity. Moreover, the huge datasets generated require the adoption of Artificial Intelligence (AI) and Machine Learning (ML) techniques (Bernieri et al., 2006;Gunda et al., 2018;Betta et al., 2019;Bruschi et al., 2018;Cerro et al., 2017Cerro et al., , 2018Ferdinandi et al., 2019). ...
Water pollution causes an ever-increasing number of diseases and represents a worldwide concern, both for governments and researchers, as well as public opinion. This pollution also regards drinkable water, with two billion people plagued by this problem. Therefore, it is crucial to find reliable and low-cost technologies for a continuous and diffused monitoring of water. In this paper, we present a novel approach that allows the detection of water contaminants by using an ad-hoc classification system that can be implemented aboard low-cost sensors. To this aim, we first project the input data from the sensors into a 3-D space by using the PCA algorithm, then we use an ad-hoc devised classifier to distinguish the contaminants in the transformed space. We used an evolutionary algorithm to learn the parameters of the classifiers. The experiments were performed on a large dataset containing data from four contaminants, with the phosphoric and sulphuric acids, among the others. The results obtained confirm the effectiveness of the proposed approach.
... In this sense, the authors propose an integrated system, able to optimize both the sensing and processing, responding to desirable requirements such as low cost, integration, portability, light computational burden, good sensitivity and classification capability. In detail, stemming from the authors' experience in gas recognition [7], water analysis [8], [9], an indoor air monitoring system, VOLUME 4, 2016 based on a compact and low cost sensing technology and Artificial Intelligence (AI) techniques for the detection and classification of air contaminants, is proposed. The system development starts from the assumption, well known in scientific literature on this field, that a single sensor is seldom sensitive to more contaminants and therefore the best solution is the employment of a sensor array, as implemented in this work. ...
In the framework of indoor air monitoring, this paper proposes an Internet of Things ready solution to detect and classify contaminants. It is based on a compact and low–power integrated system including both sensing and processing capabilities. The sensing is composed of a sensor array on which electrical impedance measurements are performed through a microchip, named SENSIPLUS, while the processing phase is mainly based on Machine Learning techniques, embedded in a low power and low resources micro controller unit, for classification purposes. An extensive experimental campaign on different contaminants has been carried out and raw sensor data have been processed through a lightweight Multi Layer Perceptron for embedded implementation. More complex and computationally costly Deep Learning techniques, as Convolutional Neural Network and Long Short Term Memory, have been adopted as a reference for the validation of Multi Layer Perceptron performance. Results prove good classification capabilities, obtaining an accuracy greater than 75% in average. The obtained results, jointly with the reduced computational costs of the solution, highlight that this proposal is a proof of concept for a pervasive IoT air monitoring system.
... As reported in [20], three steps are needed to perform the measurement procedure in a correct way. Firstly, the baseline values, i.e. the impedance measurements when only water is Fig. 8. Set-up for water monitoring purposes. ...
Internet of Things (IoT) is involving more and more fields where monitoring actions and fast and reliable data communication are simultaneously needed. Inside the general class of monitoring applications, those related to pollutant detection and classification are currently faced by many researchers and companies. Several approaches are being proposed in the literature, but lots of open issues and challenges are still to be handled before deploying a commonly considered optimum system. This contribution proposes a novel low-cost and highly flexible platform which is intended to tackle such challenges adopting ad-hoc hardware and software techniques. The proposed solution is applied to air and water contaminant detection case studies. The paper provides the reader with an innovative system in the field of pollution monitoring and focuses the attention on limitations, challenges and possible improvements needed to obtain reliable contaminant detection and, consequently, improve life quality.
Water pollution is a growing concern that affects ecosystems, human health, and industrial processes. Traditional water quality monitoring systems are often expensive and require expert analysis. This paper proposes a low-cost sensing platform integrated with Natural Language Generation (NLG) techniques to automatically detect and describe wastewater pollution. The system employs low-cost IoT sensors to measure key water quality parameters, including pH, turbidity, dissolved oxygen, and chemical contaminants. The collected sensor data is processed using machine learning models to identify pollution levels, and an NLG module translates the findings into human-readable reports. The proposed system provides an affordable, scalable, and real-time wastewater pollution detection solution, bridging the gap between raw sensor data and actionable insights for policymakers, industries, and environmental agencies.
This paper proposes a deep leaning technique for accurate detection and reliable classification of organic pollutants in water. The pollutants are detected by means of cyclic voltammetry characterizations made by using low-cost disposable screen-printed electrodes. The paper demonstrates the possibility of strongly improving the detection of such platforms by modifying them with nanomaterials. The classification is addressed by using a deep learning approach with convolutional neural networks. To this end, the results of the voltammetry analysis are transformed into equivalent RGB images by means of Gramian angular field transformations. The proposed technique is applied to the detection and classification of hydroquinone and benzoquinone, which are particularly challenging since these two pollutants have a similar electroactivity and thus the voltammetry curves exhibit overlapping peaks. The modification of electrodes by carbon nanotubes improves the sensitivity of a factor of about ×25, whereas the convolution neural network after Gramian transformation correctly classifies 100% of the experiments.
“Compact and lightweight” graphene-based mortars were produced and their piezo-resistive behavior was analyzed. Such property is exploitable in the production of functional building materials, which could work as stress–strain sensors. First, graphene-isopropyl alcohol dispersion was synthesized through Liquid Phase Exfoliation and the few layered structure was evidenced via Raman spectroscopy. Afterward, “compact and lightweight” mortars-graphene based composites were produced by using, respectively, cement and cement/diatomite as matrix, the previously mentioned graphene dispersion and a suitable amount of water. The morphological, structural, thermal and electro-mechanical properties of the obtained materials were analyzed. The mix-design here discussed can pave the way for a new kind of eco-friendly, multi-applicative, multi-responsive building material.
The air quality is a fundamental aspect for human health and its monitoring is a crucial task that needs to be performed. In this framework, an IoT ready proposal is here reported to perform both the sensing and the classification of possible air contaminants. In particular, the paper focuses on the analysis of the measurement data, by characterizing them from a metrological point of view. In detail, after having designed a suitable measurement procedure by adopting several sensors available on the platform, data are acquired during clean air exposition, air contaminant injection and steady state conditions, where contaminant has been fully injected and measurements have reached a stable state. Considerations arising from the analysis of acquired data are the basis for a classification stage, based on machine learning mechanisms. Definitively, this work represents an extension of previously presented results, and it shows how the sensor technology has been greatly improved, thus allowing to feed the detection systems with higher reliable results and therefore enhancing their performance.
The need to ensure future food security and issues of varying estuarine water quality is driving the expansion of aquaculture into near-shore coastal waters. It is prudent to fully evaluate new or proposed aquaculture sites, prior to any substantial financial investment in infrastructure and staffing. Measurements of water temperature, salinity and dissolved oxygen can be used to gain insight into the physical, chemical and biological water quality conditions within a farm site, towards identifying its suitability for farming, both for the stock species of interest and for assessing the potential risk from harmful or toxic algae. The latter can cause closure of shellfish harvesting. Unfortunately, commercial scientific monitoring systems can be cost prohibitive for small organisations and companies to purchase and operate. Here we describe the design, construction and deployment of a low cost (<£5,000) monitoring buoy suitable for use within a near-shore aquaculture farm or bathing waters. The mooring includes a suite of sensors designed for supporting and understanding variations in near-shore physical, chemical and biological water quality. The system has been designed so that it can be operated and maintained by non-scientific staff, whilst still providing good quality scientific data. Data collected from two deployments totalling 14 months, one in a coastal bay location, another in an estuary, have illustrated the robust design and provided insight into the suitability of these sites for aquaculture and the potential occurrence of a toxin causing algae (Dinophysis spp.). The instruments maintained good accuracy during the deployments when compared to independent in situ measurements (e.g. RMSE 0.13–0.16 °C, bias 0.03–0.08 °C) enabling stratification and biological features to be identified, along with confirming that the waters were suitable for mussel (Mytilus spp.) and lobster (Homarus gammarus) aquaculture, whilst sites showed conditions agreeable for Dinophysis spp.
The water quality index (WQI) has been used to identify threats to water quality and to support better water resource management. This study combines a machine learning algorithm, WQI, and remote sensing spectral indices (difference index, DI; ratio index, RI; and normalized difference index, NDI) through fractional derivatives methods and in turn establishes a model for estimating and assessing the WQI. The results show that the calculated WQI values range between 56.61 and 2,886.51. We also explore the relationship between reflectance data and the WQI. The number of bands with correlation coefficients passing a significance test at 0.01 first increases and then decreases with a peak appearing after 1.6 orders. WQI and DI as well as RI and NDI correlation coefficients between optimal band combinations of the peak also appear after 1.6 orders with R² values of 0.92, 0.58 and 0.92. Finally, 22 WQI estimation models were established by POS-SVR to compare the predictive effects of these models. The models based on a spectral index of 1.6 were found to perform much better than the others, with an R² of 0.92, an RMSE of 58.4, and an RPD of 2.81 and a slope of curve fitting of 0.97.
Several variants of the Long Short-Term Memory (LSTM) architecture for
recurrent neural networks have been proposed since its inception in 1995. In
recent years, these networks have become the state-of-the-art models for a
variety of machine learning problems. This has led to a renewed interest in
understanding the role and utility of various computational components of
typical LSTM variants. In this paper, we present the first large-scale analysis
of eight LSTM variants on three representative tasks: speech recognition,
handwriting recognition, and polyphonic music modeling. The hyperparameters of
all LSTM variants for each task were optimized separately using random search
and their importance was assessed using the powerful fANOVA framework. In
total, we summarize the results of 5400 experimental runs (about 15 years of
CPU time), which makes our study the largest of its kind on LSTM networks. Our
results show that none of the variants can improve upon the standard LSTM
architecture significantly, and demonstrate the forget gate and the output
activation function to be its most critical components. We further observe that
the studied hyperparameters are virtually independent and derive guidelines for
their efficient adjustment.
Emerging trends in Artificial Intelligence (AI) have provided a path to make better predictions in a variety of fields, including the detection of medical diseases, weather patterns, water, food quality patterns, remote sensing etc. Deep learning, a branch of AI that uses deep convolutional neural networks (CNN) modeled after the human brain, have been prominently used for accurate identification of facial features, text, and voice. This technique is used predominantly to classify a set of objects, that may not necessarily have a fixed set of features, making it very difficult to detect programmatically. As an example, researchers have started implementing deep learning techniques to identify non-uniform cancer cells from the high-resolution microscopic images of tissue samples. Similarly, most of the current screening/diagnostic devices are color-based indicators. By looking at the amount of color appearance on sensor zones of such devices, one can identify the level of certain contaminants, diseases or infections. Typically, look-up tables will be provided to classify the level of sensing parameters based on color intensity. This is a task that would be extremely time consuming and challenging to do physically, given that a complete database mapping color to concentration would have to be created and a minor difference may or may not indicate a significant concentration change. Deep learning will be very helpful for accurate identification of color and its intensity on such diagnostic devices. In the present work, we have developed an AI-based mobile application platform, that can capture the sensor image using an inbuilt smartphone camera, identify the presence of sensing parameter and classify the level of sensing parameter based on color intensity identified in the training sets on the captured image using deep CNN algorithm.
As a test case, we have implemented the developed AI-based mobile application platform for water quality monitoring for bacterial contamination. We used a low-cost rapid test kit i.e., Mobile Water Kit (MWK), developed by Gunda et al. [ Anal. Methods, 2014, 6, 6236-6246 and Analyst, 2016, 141, 2920-2929 ] for monitoring the quality of water for bacterial contamination. MWK detects indicator bacteria ( E. coli ) in water samples within an hour, based on the appearance of pinkish red color on the surface of the sensing area. The color intensity represents the level of bacteria in water samples. Using the AI-based mobile app, we capture the image of the MWK sensing area (after testing water samples) and classify them into E. coli present images (i.e. E. coli images) and E. coli absent images (non- E. coli images). Deep learning works very well when there is an abundance of training data and there are certain factors that will make it difficult to programmatically distinguish between types. Using traditional computer vision techniques, one would scan the colors of each concentration. However, determining the color intensity for each concentration level is very difficult (especially because these are different shades of pinkish red for MWK). Using deep learning, this is made easy as the system determines these color intensities through training sets that have been provided statistically.
In this present work, we have collected training data from MWK by testing the water samples with known concentrations of E. coli bacteria and then manually segregated the captured images based on whether the sample contains E. coli or not. Then we wrote a labeling script to label these images based on their type. We then used Google Tensorflow (a deep learning Artificial Intelligence open source tool) to distinguish between E. coli and non- E. coli images. Subsequently, we used the labeling script to classify whether an MWK tested image contains E. coli or not. As of now, we can classify the images with approximately 99% accuracy. We will also able to predict concentration levels using this method.
Water Pollution: Causes, Effects And Control Is A Book Providing Comprehensive Information On The Fundamentals And Latest Developments In The Field Of Water Pollution.The Book Is Divided Into 28 Chapters Covering Almost All The Aspect Of Water Pollution Including Water Resources And General Properties Of Water; History Of Water Pollution And Legislation; Origin, Sources And Effects Of Pollutants; Bioaccumulation And Biomagnification; Toxicity Testing And Interaction Of Toxicities In Combination; Water Quality Standards; Biomonitoring Of Water Pollution; Bacteriological Examination And Purification Of Drinking Water; Monitoring And Control Of Pollution In Lakes, Rivers, Estuaries And Coastal Waters; Physical And Biological Structure Of Aquatic Systems; And Structure, Properties And Uses Of Water.Some Important Topics Like Eutrophication, Organic Pollution, Oil Pollution And Thermal Pollution Have Been Discussed In Detail. The Water Pollution Caused By Pesticides, Heavy Metals, Radio Nuclides And Toxic Organics And Inorganic Along With The Water Quality Problems Associated With Water-Borne Pathogens And Nuisance Algae Have Also Been Dealt With Extensively.The Book Covers In Detail The Flow Measurement And Characterization Of Waste Waters In Industries, And Control Of Water Pollution By Employing Various Techniques For Treatment Of Biological And Nonbiological Wastes. The Considerations For Recycling And Utilization Of Waste Waters Have Also Found A Place In The Book. Special Topic Has Also Been Given On Water Pollution Scenario And Water Related Policies And Programmes In India.The Book Shall Be Of Immediate Interest To The Students Of Environmental Science, Life Science And Social Sciences Both At Undergraduate And Postgraduate Levels. People From A Wide Variety Of Other Disciplines Like Civil, Chemical And Environmental Engineering; Pollution Control Authorities; Industries; And Practicing Engineers, Consultants And Researchers Will Also Find The Book Of Great Interest.
Monitoring the environment using stand-alone sensor nodes provides valuable information to researchers, practitioners and policy makers. One such problem in this area is bird activity monitoring using its sound patterns. There are several existing devices that can record bird sounds in a region. Then, the stored data is processed off-line. However, the time between the acquisition and processing stages while using such devices is generally of the order of weeks. This approach is not amenable to real-time monitoring. Therefore, there is a need for a system which is able to both monitor the environment and process data on the system itself. The most important attribute of such a system is its power consumption since it operates in the environment only by its battery. In this study, we propose such a stand-alone, energy efficient, low-level, custom-made, real-time bird call processing system concentrated on single-labeled bird calls. The system is composed of a microphone, Texas Instruments Tiva C microcontroller, and a storage unit. The proposed system enables data recording, preliminary on-board signal processing, feature extraction, classification, and data storage. In the proposed system, we simultaneously record and process data. Hence, the system not only stores the environmental sounds, it also classifies the detected birds on-site. The proposed system offers flexibility (both in hardware and software) for expansion.
Forest fire (wildfire) is one of the common hazards that is accrued in the forest. Fire monitoring has three phases: pre-fire (take appropriate action for fire control), during fire (detection of fire and planning to control fire), post-fire (damage assessment and mitigation planning). In older days, manually fire detection approach is used. In current days, satellite-based surveillance system is used to detect forest fire but this works when fire is spread in the large area. So these techniques are not efficient. According to a survey, approximately 80% losses are accrued in the forest due to the late detection of fire. So to overcome this problem, we use the Internet of things technology. In this paper, early fire detection model has been proposed with the help of the Raspberry Pi microcontroller and required sensors. Centralized server is used for storing the data and analyzing that data. Feed-forward fully connected neural network is used for prediction purpose. Then, an alert message is sent to the admin and to the people within the proximity.
Water is a vital resource for natural ecosystems and human life, and assuring a high quality of water and protecting it from chemical contamination is a major societal goal in the European Union. The Water Framework Directive (WFD) and its daughter directives are the major body of legislation for the protection and sustainable use of European freshwater resources. The practical implementation of the WFD with regard to chemical pollution has faced some challenges. In support of the upcoming WFD review in 2019 the research project SOLUTIONS and the European monitoring network NORMAN has analyzed these challenges, evaluated the state-of-the-art of the science and suggested possible solutions. We give 10 recommendations to improve monitoring and to strengthen comprehensive prioritization, to foster consistent assessment and to support solution-oriented management of surface waters. The integration of effect-based tools, the application of passive sampling for bioaccumulative chemicals and an integrated strategy for prioritization of contaminants, accounting for knowledge gaps, are seen as important approaches to advance monitoring. Including all relevant chemical contaminants in more holistic "chemical status" assessment, using effect-based trigger values to address priority mixtures of chemicals, to better consider historical burdens accumulated in sediments and to use models to fill data gaps are recommended for a consistent assessment of contamination. Solution-oriented management should apply a tiered approach in investigative monitoring, to identify toxicity drivers, strengthen consistent legislative frameworks and apply solutions-oriented approaches that explore risk reduction scenarios before and along with risk assessment.
This paper proposes the realization and preliminary characterization of a smart sensor platform for the online monitoring of the residual life of activated carbon air based filters. The platform performs the measurement to give reliable information about the filter maintenance or early warning for the presence of dangerous gases both in industrial and military scenarios. A preliminary feasibility study has been carried out to evaluate the activated carbon filter electrical impedance sensitivity to chemicals adsorption. After a detailed presentation of the employed hardware and software solutions, a description of the experimental setup is given and a preliminary proof of the assumed relationship is provided.
Water is a vital resource for natural ecosystems and human life, and assuring a high quality of water and protecting it from chemical contamination is a major societal goal in the European Union. The Water Framework Directive (WFD) and its daughter directives are the major body of legislation for the protection and sustainable use of Euro- pean freshwater resources. The practical implementation of the WFD with regard to chemical pollution has faced some challenges. In support of the upcoming WFD review in 2019 the research project SOLUTIONS and the Europe- an monitoring network NORMAN has analyzed these challenges, evaluated the state-of-the-art of the science and suggested possible solutions. We give 10 recommendations to improve monitoring and to strengthen comprehen- sive prioritization, to foster consistent assessment and to support solution-oriented management of surface waters. The integration of effect-based tools, the application of passive sampling for bioaccumulative chemicals and an in- tegrated strategy for prioritization of contaminants, accounting for knowledge gaps, are seen as important ap- proaches to advance monitoring. Including all relevant chemical contaminants in more holistic “chemical status” assessment, using effect-based trigger values to address priority mixtures of chemicals, to better consider historical burdens accumulated in sediments and to use models to fill data gaps are recommended for a consistent assessment of contamination. Solution-oriented management should apply a tiered approach in investigative monitoring to identify toxicity drivers, strengthen consistent legislative frameworks and apply solutions-oriented approaches that explore risk reduction scenarios before and along with risk assessment.
This paper presents a developed methodology for the detection of bovine milk adulteration by applying electrical impedance measurements. This parameter allows characterizing samples of raw and ultrahigh temperature milk, adulterated with different proportions of drinking water, deionized water, hydrogen peroxide (H2O2), sodium hydroxide (NaOH), and formaldehyde (CH2O). The samples were electrically analyzed by applying the electrical impedance spectroscopy measurements and a dedicated microcontroller system, developed for this application. In both cases, the measures allowed classifying the milk quantitatively, enabling the development of real-time monitoring systems for fraud detection in milk composition. A classification of the results is proposed through a k-nearest neighbors algorithm that allows to quantitatively qualify the samples of pure and adulterated milk.
The water quality monitoring plays an important role in water contamination surveillance and guides the water resource protection for safe and clean water. A flexible automated real-time water quality monitoring and alarm system based on the wireless sensor network(WSN) is proposed. The WSN is built in accordance with Zigbee communication protocol, which consists of the sensor nodes, route nodes and coordinator node. The sensor nodes based on cheap and efficient sensors (pH electrode, dissolved oxygen electrode, temperature senor) and wireless transreceiver collect the environmental data and transmit to the coordinator node via the route nodes. The data are sent to the remote monitoring center with the help of GPRS. The time synchronous algorithm is adopted to wake up all the nodes in the network to improve the stability and reliability of the communication. The long-time measurement results verify the real time and accuracy in data acquisition and stability and reliability in communication. The system meets the requirements of water quality monitoring, and has great practical value.
Lstm: A search space odyssey
- K Greff
- R K Srivastava
- J Koutnk
- B R Steunebrink
- J Schmid-Huber
K. Greff, R. K. Srivastava, J. Koutnk, B. R. Steunebrink, J. Schmidhuber, Lstm: A search space odyssey, IEEE Transactions on Neural Networks and Learning Systems 28 (10) (2017) 2222-2232.
doi:10.1109/TNNLS.2016.2582924.
Forest Fire Detection System Using IoT and Artificial Neural Network, New Age International
- N C Vinay Dubey
- Prashant Kumar
N. C. Vinay Dubey, Prashant Kumar, Forest Fire Detection System
Using IoT and Artificial Neural Network, New Age International, 2006.
doi:doi.org/10.1007/978-981-13-2324-9.