A Novel Hybrid Deep Learning Algorithm for Smart City Traffic Congestion Predictions

Joseph, L. M. I. Leo; Goel, Pankaj; Rajyalakshmi, K.; Gulati, Kamal; Singh, Prithvipal

doi:10.1109/ispcc53510.2021.9609467

Cited by 10 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Regarding mobility, topological variations, propagation, and energy limitations, mobility and propagation models in RL are exceptional [22]. Therefore, the mobility and propagation models in RL, which are also a component of the research topics in this study, must be clarified in order for this discussion to be completed.…”

Section: • Propagation Modelsmentioning

confidence: 99%

Dynamic Obstacle Avoidance and Path Planning through Reinforcement Learning

2023

View full text Add to dashboard Cite

The use of reinforcement learning (RL) for dynamic obstacle avoidance (DOA) algorithms and path planning (PP) has become increasingly popular in recent years. Despite the importance of RL in this growing technological era, few studies have systematically reviewed this research concept. Therefore, this study provides a comprehensive review of the literature on dynamic reinforcement learning-based path planning and obstacle avoidance. Furthermore, this research reviews publications from the last 5 years (2018–2022) to include 34 studies to evaluate the latest trends in autonomous mobile robot development with RL. In the end, this review shed light on dynamic obstacle avoidance in reinforcement learning. Likewise, the propagation model and performance evaluation metrics and approaches that have been employed in previous research were synthesized by this study. Ultimately, this article’s major objective is to aid scholars in their understanding of the present and future applications of deep reinforcement learning for dynamic obstacle avoidance.

show abstract

Section: • Propagation Modelsmentioning

confidence: 99%

Dynamic Obstacle Avoidance and Path Planning through Reinforcement Learning

2023

View full text Add to dashboard Cite

show abstract

“…To deal with the traffic and the parade, the officials restrict a few traffic routes, which causes congestion. Hence, it is essential to pay more attention to integrating these elements in forecasts [36][37][38][39][40].…”

Section: Research Gapsmentioning

confidence: 99%

Optimizing Traffic Flow in Smart Cities: Soft GRU-Based Recurrent Neural Networks for Enhanced Congestion Prediction Using Deep Learning

Abdullah

Periyasamy²,

Kamaludeen

et al. 2023

Sustainability

View full text Add to dashboard Cite

Recently, different techniques have been applied to detect, predict, and reduce traffic congestion to improve the quality of transportation system services. Deep learning (DL) is becoming increasingly valuable for solving critiques. DL applications in transportation have been collected in several recently published surveys over the last few years. The existing research has discussed the cloud environment, which does not provide timely traffic forecasts, which is the cause of frequent traffic accidents. Thus, a solid understanding of the difficulties in predicting congestion is required because the transportation system varies widely between non-congested and congested states. This research develops a bi-directional recurrent neural network (BRNN) using Gated Recurrent Units (GRUs) to extract and classify traffic into congested and non-congested. This research uses a bidirectional recurrent neural network to simulate and forecast traffic congestion in smart cities (BRNN). Urban regions worldwide struggle with traffic congestion, and conventional traffic control techniques have failed miserably. This research suggests a data-driven approach employing BRNN for traffic management in smart cities, which uses real-time data from sensors and linked devices to control traffic more efficiently. The primary measures include predicting traffic metrics such as speed, weather, current, and accident probability. Congestion prediction performance has also been improved by extracting more features such as traffic, road, and weather conditions. The proposed model achieved better measures than the existing state-of-the-art methods. This research also explores an overview and analysis of several early initiatives that have shown promising results; moreover, it explores two potential future research approaches to increase the accuracy and efficiency of large-scale motion prediction.

show abstract

“…In [17], developed a hybrid method named boosted LSTM ensemble (BLSTME) in addition to CNNs for helping cars navigate nearby congested roads by presenting CNN great features allow for BLSTME that supports cars in dynamic atmospheres by predicting the probability of congestion. In [18], showed that noise pollution and traffic time-series data are utilized for training LSTM-RNNs that resulted in better traffic forecasting on the road.…”

Section: Related Workmentioning

confidence: 99%

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

Shaheed

2023

Journal of Smart Internet of Things

View full text Add to dashboard Cite

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.

show abstract

A Novel Hybrid Deep Learning Algorithm for Smart City Traffic Congestion Predictions

Cited by 10 publications

References 13 publications

Dynamic Obstacle Avoidance and Path Planning through Reinforcement Learning

Dynamic Obstacle Avoidance and Path Planning through Reinforcement Learning

Optimizing Traffic Flow in Smart Cities: Soft GRU-Based Recurrent Neural Networks for Enhanced Congestion Prediction Using Deep Learning

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

Contact Info

Product

Resources

About