<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>Intelligent traffic congestion control is an integral aspect of making sustainable and efficient smart cities. With the increasing count of vehicles on the road and rapid urbanization, traffic congestion is a main concern nowadays that hinders the growth of the economy and affects the quality of life. In smart cities, an intelligent transportation solution (ITS) is enhance traffic flow by adjusting traffic signal timing and observing traffic patterns. Currently, one of the vital dilemmas in terms of transportation systems was traffic congestion which needs to be resolved for minimizing driver frustration, traffic jams, fuel waste, and accidents. Due to the high count of vehicles, most of the traffic interruptions in metropolitan cities arise. With the advancements in Artificial Intelligence (AI) and Machine Learning (ML), smart environments monitored in smart cities observe the influencing issues of the environment correctly, with the best control of traffic congestion, pollution, and other negative effects. Therefore, this study presents an intelligent traffic congestion control using Black Widow Optimization with Hybrid Deep Learning (ITC-BWOHDL) technique in Smart City Environment. The main aim of the ITC-BWOHDL technique is to utilize feature subset selection with parameter-tuning strategies for effective traffic congestion management. To obtain this, the ITC-BWOHDL technique primarily designs the emperor penguin optimizer-based feature selection (EPO-FS) approach for selecting a useful set of features. For the detection of traffic congestion, the ITCBWOHDL technique makes use of the HDL model which incorporates convolutional neural network (CNN) with gated recurrent unit (GRU) approach. To improve the classification results of the HDL model, the BWO-based hyperparameter tuning process gets executed. For exhibiting the improved classification outcome of the ITC-BWOHDL system, a comprehensive range of experiments was executed. The obtained outcome described the betterment of ITC-BWOHDL method over other existing techniques.</p>
</abstract>

Intelligent traffic congestion control is an integral aspect of making sustainable and efficient smart cities. With the increasing count of vehicles on the road and rapid urbanization, traffic congestion is a main concern nowadays that hinders the growth of the economy and affects the quality of life. In smart cities, an intelligent transportation solution (ITS) is enhance traffic flow by adjusting traffic signal timing and observing traffic patterns. Currently, one of the vital dilemmas in terms of transportation systems was traffic congestion which needs to be resolved for minimizing driver frustration, traffic jams, fuel waste, and accidents. Due to the high count of vehicles, most of the traffic interruptions in metropolitan cities arise. With the advancements in Artificial Intelligence (AI) and Machine Learning (ML), smart environments monitored in smart cities observe the influencing issues of the environment correctly, with the best control of traffic congestion, pollution, and other negative effects. Therefore, this study presents an intelligent traffic congestion control using Black Widow Optimization with Hybrid Deep Learning (ITC-BWOHDL) technique in Smart City Environment. The main aim of the ITC-BWOHDL technique is to utilize feature subset selection with parameter-tuning strategies for effective traffic congestion management. To obtain this, the ITC-BWOHDL technique primarily designs the emperor penguin optimizer-based feature selection (EPO-FS) approach for selecting a useful set of features. For the detection of traffic congestion, the ITCBWOHDL technique makes use of the HDL model which incorporates convolutional neural network (CNN) with gated recurrent unit (GRU) approach. To improve the classification results of the HDL model, the BWO-based hyperparameter tuning process gets executed. For exhibiting the improved classification outcome of the ITC-BWOHDL system, a comprehensive range of experiments was executed. The obtained outcome described the betterment of ITC-BWOHDL method over other existing techniques.

Intelligent Traffic Congestion Control Using Black Widow Optimization with Hybrid Deep Learning on Smart City Environment

Journal of Smart Internet of Things

This work is licensed under the Creative Commons Attribution 4.0 International License.

Intelligent traffic congestion control is an integral aspect of making sustainable and efficient smart cities. With the increasing count of vehicles on the...

Intelligent Traffic Congestion Control Using Black Widow Optimization with Hybrid Deep Learning on Smart City Environment

Data publikacji: 15 gru 2023

Zakres stron: 44 - 61

Otrzymano: 20 sie 2023

Przyjęty: 21 paź 2023

DOI: https://doi.org/10.2478/jsiot-2023-0010

Słowa kluczowe
Smart city, Intelligent transportation system, Hybrid deep learning, Black widow optimization, Feature selection

© 2023 Sarah Hadi Shaheed, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Intelligent Traffic Congestion Control Using Black Widow Optimization with Hybrid Deep Learning on Smart City Environment

Data publikacji: 15 gru 2023

Zakres stron: 44 - 61

Otrzymano: 20 sie 2023

Przyjęty: 21 paź 2023

DOI: https://doi.org/10.2478/jsiot-2023-0010

Słowa kluczoweSmart city, Intelligent transportation system, Hybrid deep learning, Black widow optimization, Feature selection

© 2023 Sarah Hadi Shaheed, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Słowa kluczowe
Smart city, Intelligent transportation system, Hybrid deep learning, Black widow optimization, Feature selection