| Title | A smart Iot-based waste management system using vehicle shortest path routing and trashcan visiting decision making based on deep convolutional neural network |
|---|---|
| ID_Doc | 79197 |
| Authors | Kona, VVS; Subramoniam, M |
| Title | A smart Iot-based waste management system using vehicle shortest path routing and trashcan visiting decision making based on deep convolutional neural network |
| Year | 2024 |
| Published | Peer-To-Peer Networking And Applications, 17, 3 |
| Abstract | Recently, IoT technologies have emerged and also it has been widely applicable in the smart city. Smart cities consist of smart governance, smart environment, smart loving, and mobility. Hence, the consideration of waste management becomes a crucial issue in the local and global levels. Moreover, it faces difficulties for handling waste management in smart cities. However, these issues are arising due to the improper collection and disposal approach. Thus, a new model is adapted for the smart IoT based waste management system. In the first phase, the images are obtained through different IoT-based devices. Then, the gathered waste images are processed in the Ensemble Convolutional Neural Network (En-CNN) variants such as Resnet, VGG19, and Inception approach to get the features from the pooling layers. Further, optimal features are chosen using the Hybrid Eurasian Oystercatcher and Sandpiper Optimization Algorithm (HEO-SOA). Then, the fully connected layers of the En-CNN variants are used to perform the waste classification by analyzing the optimal waste features. In the second phase, the trashcan visiting decision is performed. Then, the deep learning technique named Deep Convolutional Neural Network (DCNN) assists in detecting the visit period of the trashcan by collecting their historical data and the wastes are collected based on the deep learning decision. In the third phase, the IoT-based optimal routing path protocol considering a multi-objective function is implemented for waste management. This multi-objective function comprises distance, delay, energy, and weights of the waste, which estimates the shortest path of the waste-collecting vehicles toward the appropriate waste centers. The findings of the offered model show 98% in accuracy and sensitivity. The performance of the routing algorithm is then improved by tuning particular constraints by the offered HEO-SOA. |
Similar Articles
| ID | Score | Article |
|---|---|---|
38862
|
Al Duhayyim, M; Eisa, TAE; Al-Wesabi, FN; Abdelmaboud, A; Hamza, MA; Zamani, A; Rizwanullah, M; Marzouk, R Deep Reinforcement Learning Enabled Smart City Recycling Waste Object Classification(2022)Cmc-Computers Materials & Continua, 71, 3 | |
| 40950
|
Vijayalakshmi, J; Mohanarathinam, A; Nandini, V; Priya, G Internet of things enabled smart solid waste management system(2023)Global Nest Journal, 25, 5 | |
| 41580
|
Hamza, MA; Mengash, HA; Negm, N; Marzouk, R; Motwakel, A; Zamani, A Deep Consensus Network for Recycling Waste Detection in Smart Cities(2023)Cmc-Computers Materials & Continua, 75, 2 | |
| 43656
|
Oguz, A; Ertugrul, OF Determining the fullness of garbage containers by deep learning(2023) | |
| 44275
|
Khan, HA; Naqvi, SS; Alharbi, AAK; Alotaibi, S; Alkhathami, M Enhancing trash classification in smart cities using federated deep learning(2024)Scientific Reports, 14, 1 | |
| 40504
|
Malik, M; Prabha, C; Soni, P; Arya, V; Alhalabi, WA; Gupta, BB; Albeshri, AA; Almomani, A Machine Learning-Based Automatic Litter Detection and Classification Using Neural Networks in Smart Cities(2023)International Journal On Semantic Web And Information Systems, 19, 1 | |
| 37293
|
Yuvaraj, N; Praghash, K; Raja, RA; Karthikeyan, T An Investigation of Garbage Disposal Electric Vehicles (GDEVs) Integrated with Deep Neural Networking (DNN) and Intelligent Transportation System (ITS) in Smart City Management System (SCMS)(2022)Wireless Personal Communications, 123.0, 2 | |
| 43260
|
Khan, S; Ali, B; Alharbi, AAK; Alotaibi, S; Alkhathami, M Efficient IoT-Assisted Waste Collection for Urban Smart Cities(2024)Sensors, 24, 10 |