No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Garbage Classifying Application Using Deep Learning Techniques
... It can be observed from the figure that 16 (38%) out of 42 papers did not specify the size of their datasets. Six (14.28%) articles utilized datasets of less than or equal to 1000 records [13,51,62,69,74,75], nine (21.42%) articles used datasets ranging from 1000 to 5000 records, [33,60,61,[76][77][78][79][80][81], and one article used a dataset size greater than 5,0000 data points. Figure 19 shows the range of the dataset sizes used in the 42 selected articles. ...
... It can be observed from the figure that 16 (38%) out of 42 papers did not specify the size of their datasets. Six (14.28%) articles utilized datasets of less than or equal to 1000 records [13,51,62,69,74,75], nine (21.42%) articles used datasets ranging from 1000 to 5000 records, [33,60,61,[76][77][78][79][80][81], and one article used a dataset size greater than 5,0000 data points. Figure 20 depicts the intervals at which waste data were collected or generated in our selected studies. ...
We present a survey of machine learning works that attempt to organize the process flow of waste management in smart cities. Unlike past reviews, we focused on the waste generation and disposal phases in which citizens, households, and municipalities try to eliminate their solid waste by applying intelligent computational models. To this end, we synthesized and reviewed 42 articles published between 2010 and 2021. We retrieved the selected studies from six major academic research databases. Next, we deployed a comprehensive data extraction strategy focusing on the objectives of studies, trends of ML adoption, waste datasets, dependent and independent variables, and AI-ML-DL predictive models of waste generation. Our analysis revealed that most studies estimated waste material classification, amount of generated waste per area, and waste filling levels per location. Demographic data and images of waste type and fill levels are used as features to train the predictive models. Although various studies have widely deployed artificial neural networks (ANN) and convolutional neural networks (CNN) to classify waste, other techniques, such as gradient boosting regression tree (GBRT), have also been utilized. Critical challenges hindering the prediction of solid waste generation and disposal include the scarcity of real-time time series waste datasets, the lack of performance benchmarking tests of the proposed models, the reliability of the analytics models, and the long-term forecasting of waste generation. Our survey concludes with the implications and limitations of the selected models to inspire further research efforts.
... Augmentation techniques for addressing data scarcity are explored by 25 , while metadata-based approaches 26 and robotics-driven classification 27 contribute to the research landscape. Moreover, studies utilizing CNN models 28,29 underline the ongoing efforts to improve trash classification methodologies and their practical implications in waste management practices. Table 1 provides a comparison of some of the existing trash classification studies. ...
Efficient Waste management plays a crucial role to ensure clean and green environment in the smart cities. This study investigates the critical role of efficient trash classification in achieving sustainable solid waste management within smart city environments. We conduct a comparative analysis of various trash classification methods utilizing deep learning models built on convolutional neural networks (CNNs). Leveraging the PyTorch open-source framework and the TrashBox dataset, we perform experiments involving ten unique deep neural network models. Our approach aims to maximize training accuracy. Through extensive experimentation, we observe the consistent superiority of the ResNext-101 model compared to others, achieving exceptional training, validation, and test accuracies. These findings illuminate the potential of CNN-based techniques in significantly advancing trash classification for optimized solid waste management within smart city initiatives. Lastly, this study presents a distributed framework based on federated learning that can be used to optimize the performance of a combination of CNN models for trash detection.
... AI could increase the need for data centers and related digital infrastructures leading to an increase in material footprint, land use, and e-waste, while at the same time, ML and DL systems could support an optimized production system, resource efficiency, and environmental awareness [207,208]. AI for land management could improve the monitoring of waste treatment facilities and the detection of illegal landfills [189,[209][210][211][212][213][214]. However, it might also lead to increased waste due to the required digital infrastructures and digital-induced overconsumption [48]. ...
Digitalization is globally transforming the world with profound implications. It has enormous potential to foster progress toward sustainability. However, in its current form, digitalization also continues to enable and encourage practices with numerous unsustainable impacts affecting our environment, ingraining inequality, and degrading quality of life. There is an urgent need to identify such multifaceted impacts holistically. Impact assessment of digital interventions (DIs) leading to digitalization is essential specifically for Sustainable Development Goals (SDGs). Action is required to understand the pursuit of short-term gains toward achieving long-term value-driven sustainable development. We need to understand the impact of DIs on various actors and in diverse contexts. A holistic understanding of the impact will help us align the visions of sustainable development and identify potential measures to mitigate negative short and long-term impacts. The recently developed digitainability assessment framework (DAF) unveils the impact of DIs with an in-depth context-aware assessment and offers an evidence-based impact profile of SDGs at the indicator level. This paper demonstrates how DAF can be instrumental in guiding participatory action for the implementation of digitainability practices. This paper summarizes the insights developed during the Digitainable Spring School 2022 (DSS) on “Sustainability with Digitalization and Artificial Intelligence,” one of whose goals was to operationalize the DAF as a tool in the participatory action process with collaboration and active involvement of diverse professionals in the field of digitalization and sustainability. The DAF guides a holistic context-aware process formulation for a given DI. An evidence-based evaluation within the DAF protocol benchmarks a specific DI’s impact against the SDG indicators framework. The participating experts worked together to identify a DI and gather and analyze evidence by operationalizing the DAF. The four DIs identified in the process are as follows: smart home technology (SHT) for energy efficiency, the blockchain for food security, artificial intelligence (AI) for land use and cover change (LUCC), and Big Data for international law. Each of the four expert groups addresses different DIs for digitainability assessment using different techniques to gather and analyze data related to the criteria and indicators. The knowledge presented here could increase understanding of the challenges and opportunities related to digitainability and provide a structure for developing and implementing robust digitainability practices with data-driven insights.
... In [79], the authors focus on the classification of garbage using metadata and evaluated the strategy using multiple deep learning algorithms such as VGG16, ResNet50, and DenseNet169 to compare it with the recently developed model ThanosNet, which achieved an accuracy of 94%. A lot of more research focuses on trash image classification from different devices such as in [80] for robotics, and those purely works with CNN with low accuracy such as in [81] and [82] using different benchmark datasets. The summary of the trash classification-based research is in Table 3: ...
Waste or trash management is receiving increased attention for intelligent and sustainable development, particularly in developed and developing countries. The waste or trash management system comprises several related processes that carry out various complex functions. Recently, interest in deep learning (DL) has increased in providing alternative computational techniques for determining the solution to various waste or trash management problems. Researchers have concentrated on this domain, and as a result, significant research has been published, particularly in recent years. According to the literature, a few comprehensive surveys have been done on waste detection and classification. However, no study has investigated the application of DL to solve waste or trash management problems in various domains and highlight the available datasets for waste detection and classification in different domains. To this end, this survey contributes by reviewing various image classification and object detection models, and their applications in waste detection and classification problems, providing an analysis of waste detection and classification techniques with precise and organized representation and compiling over twenty benchmarked trash datasets. Also, we backed up the study with the challenges of existing methods and the future potential in this field. This will give researchers in this area a solid background and knowledge of the state-of-the-art deep learning models and insight into the research areas that can still be explored.
... The system developed and achieved 75% accuracy. Arpit Patil et.al developed a classification of garbage using an android application [8]. The purpose of the design was to classify trash into different categories like paper, glass, metal and other types Dung D et.al proposed a method for smart waste city management with a low cost [9]. ...
This paper evaluates the performance of modern AI-based object detection models that can be used for object classification and sorting applications. In this case, we focused on the classification of the medical waste for the current global situation which is the medical waste management during the post-pandemic of Covid-19 phase. A few classification models were used and compared between (1) CNN and ResNet50 and (2) YOLO v3 and YOLO v4. The results also were compared with the previous works that focused on waste classification. The difference between this work is the image dataset, which our work train and test the medical waste (facemask, glove, and syringe), while the previous works focused on general waste such as food, plastic, metal, paper, and others. From 2207 images of the medical waste, CNN and ResNet achieved 89.35 and 85.75% of accuracy, respectively, where it requires more images per class for the training improvement. YOLO v3 and YOLO v4 used 3073 images for training and achieved 84.86 and 89.21% of mean average precision (mAP). Our YOLO v3 mAP is in the average value among the previous works, while YOLO v4 has a higher mAP compared to the YOLO v4 training from other works. The YOLO v4 then was tested in real-time medical waste detection and successfully detected the masks, gloves, and syringe. However, there are still some wrong detections during the real-time detection using the camera, especially with other objects with similar shapes to the medical waste. Further, performance evaluations are required that can be used for medical waste objects and also for other different objects based on the applications.
Digitalization is globally transforming the world with profound implications. It has enormous potential to foster progress toward sustainability. However, in its current form, digitalization also continues to enable and encourage practices with numerous unsustainable impacts affecting our environment, ingraining inequality, and degrading quality of life. There is an urgent need to identify such multifaceted impacts holistically. Impact assessment of digital interventions (DIs) leading to digitalization is important specifically for Sustainable Development Goals(SDGs). Action is required to understand the pursuit of short-term gains toward achieving long-term value-driven sustainable development. We need to understand the impact of DIs on various actors and in diverse contexts. A holistic understanding of the impact it creates will help us align it with visions of sustainable development and identify potential measures to mitigate negative short and long-term impacts. The recently developed Digitainability Assessment Framework (DAF) unveils the impact of DIs with an in-depth context-aware assessment and offers an evidence-based impact profile of SDGs at the indicator level. We performed the impact assessment of diverse technologies using DAF. This paper summarizes the insights from the Digitainable Spring School 2022 on "Sustainability with Digitalization and Artificial Intelligence," one of whose goals was to operationalize the DAF as a tool in the action learning process with diverse professionals in the field of digitalization and sustainability. The DAF guides a holistic context-aware process formulation for a given DI. An evidence-based evaluation within the DAF protocol benchmarks a specific DI’s impact against the SDG indicators framework. The operationalization of the DAF was carried out by looking at four different DIs: smart home technologies (SHT) for energy efficiency, blockchain for food security, artificial intelligence for land use cover and changes (LUCC), and big data for international law. Each of the four studies addresses different DIs for digitainability assessment using different techniques for a diverse group of indicators, demonstrating the potential of the DAF but also outlining the existing data gaps that limit a comprehensive analysis.
Among the many deep learning methods, the convolutional neural network (CNN) model has an excellent performance in image recognition. Research on identifying and classifying image datasets using CNN is ongoing. Animal species recognition and classification with CNN is expected to be helpful for various applications. However, sophisticated feature recognition is essential to classify quasi-species with similar features, such as the quasi-species of parrots that have a high color similarity. The purpose of this study is to develop a vision-based mobile application to classify endangered parrot species using an advanced CNN model based on transfer learning (some parrots have quite similar colors and shapes). We acquired the images in two ways: collecting them directly from the Seoul Grand Park Zoo and crawling them using the Google search. Subsequently, we have built advanced CNN models with transfer learning and trained them using the data. Next, we converted one of the fully trained models into a file for execution on mobile devices and created the Android package files. The accuracy was measured for each of the eight CNN models. The overall accuracy for the camera of the mobile device was 94.125%. For certain species, the accuracy of recognition was 100%, with the required time of only 455 ms. Our approach helps to recognize the species in real time using the camera of the mobile device. Applications will be helpful for the prevention of smuggling of endangered species in the customs clearance area.
Aim
The 5G LTE-Advanced (LTE-A) intended to provide increased peak data rates for the mobile users with the use of Carrier Aggregation (CA) technology. Due to need of un-interrupted bi-directional communication between the eNodeB and User Equipment (UE) in LTE-A, Joint Scheduling Algorithm is considered as central research topic.
Objective
A modified joint Uplink/ Downlink (UL/DL) Scheduling algorithm to meet on demands service request from the UEs is proposed in this paper.
Methods
CA is used for calculate the weight factors for the bandwidth allocation among the mobile users based on the QoS Class Identifier (QCI). However due the huge amount of data flow in the indoor coverage yield introduction of the small cell called femtocells. Femtocells are randomly deployed in macro cell area in order to improve indoor coverage as well capacity enhancement.
Result
Mixed types of traffic are considered ranging from real time to non real time flows and quality of service is evaluated in term of throughput, packet loss ratio, fairness index and spectral efficiency. The proposed modified joint user scheduling algorithm results better in delay among the end users due the reduction in the traffic load of the macro cell base station.
Conclusion
Simulation results shows that, the proposed methodology suits best for the small scale network architecture with increased spectral efficiency and throughput among the UEs.
Maintaining a clean and hygienic civic environment is an indispensable yet formidable task, especially in developing countries. With the aim of engaging citizens to track and report on their neighborhoods, this paper presents a novel smartphone app, called SpotGarbage, which detects and coarsely segments garbage regions in a user-clicked geo-tagged image. The app utilizes the proposed deep architecture of fully convolutional networks for detecting garbage in images. The model has been trained on a newly introduced Garbage In Images (GINI) dataset, achieving a mean accuracy of 87.69%. The paper also proposes optimizations in the network architecture resulting in a reduction of 87.9% in memory usage and 96.8% in prediction time with no loss in accuracy, facilitating its usage in resource constrained smartphones.
Convolutional Neural Network: An Overview
- Priyanka Gulhane
- Manisha Thakkar
Simulation Research on Integrated Hybrid PV - Wind Driven Generator Supplying AC/DC Micro-grid
- Arjun Kumar