PSO-ANN in preventing traffic collisions: a comparative study

Ashikuzzaman, Md.; Akram, Wasim; Anik, Md. Mydul Islam; Hasan, Mahamudul; Ali, Md Sawkat; Jabid, Taskeed

doi:10.11591/ijeecs.v24.i3.pp1796-1803

Cited by 6 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One effective automated approach for hyperparameter selection is the utilization of metaheuristic algorithms such as particle swarm optimization (PSO). PSO and other metaheuristic algorithms draw inspiration from natural phenomena and have been successfully applied to optimize CNN models [10], [11]. By leveraging PSO, researchers can efficiently explore the parameter search space and adaptively adjust particle positions to achieve optimal solutions [12], [13].…”

Section: Introductionmentioning

confidence: 99%

Convolution neural network hyperparameter optimization using modified particle swarm optimization

Munsarif,

Sam'an,

Fahrezi

2024

Bulletin EEI

View full text Add to dashboard Cite

Based on the literature review, a convolutional neural network (CNN) is one of the deep learning techniques most often used for classification problems, especially image classification. Various approaches have been proposed to improve accuracy performance. In CNN architecture, parameter determination is very influential on accuracy performance. Particle swarm optimization (PSO) is a type of metaheuristic algorithm widely used for hyperparameter optimization. PSO convergence is faster than genetic algorithm (GA) and attracts many researchers for further studies such as genetic algorithms and ant colony. In PSO, determining the value of the weight parameter is very influential on accuracy. Therefore, this paper proposes CNN hyperparameter optimization using modified PSO with linearly decreasing randomized weight. The experiments use the modified National Institute of Standards and Technology (MNIST) dataset. The accuracy of the proposed method is superior, and the execution time is slower to random search. In epoch 1, epoch 3, and epoch 5, the proposed method is superior to baseline CNN, linearly decreasing weight PSO (LDWPSO), and RL-based optimization algorithm (ROA). Meanwhile, the accuracy performance of the proposed method is superior to previous studies, namely LeNet-1, LeNet-2, LeNet-3, PCANet-2, RANDNet-2, CAE1, CAE-2, and bee colony. Otherwise, lost to PSO-CNN, distributed PSO (DPSO), recurrent CNN, and CNN-PSO. However, the four methods have a complex architecture and wasteful execution time.

show abstract

Section: Introductionmentioning

confidence: 99%

Convolution neural network hyperparameter optimization using modified particle swarm optimization

Munsarif,

Sam'an,

Fahrezi

2024

Bulletin EEI

View full text Add to dashboard Cite

show abstract

“…A particle swarm optimization with artificial neural network (PSO-ANN) approach has been introduced to measure traffic collision in the paper [20]. In paper from [21], for preventing accidents, the relative locations of the vehicles have been determined with the help of GPS and transferred the information of the location using GPS in the targeted devices.…”

Section: Introductionmentioning

confidence: 99%

An intelligent road accident reduction system using device-to-device communication

Jabid

Rizvy

Mow

et al. 2023

IJEECS

View full text Add to dashboard Cite

<p>Every year thousands of people are dying due to road accidents and most of the accidents are occurring in urban areas and highways. As the number of vehicles is increasing day by day, the probability of the occurrence of the accident is also increasing. A system has been introduced in this paper that can reduce road accidents by sending an alert to drivers via smartphones. For this purpose, an android-based application has been developed. To reduce the accident, every driver of the car must have the application. Firstly, the location of the vehicle will be collected from the driver’s smartphone, then the data will be sent to the server through the application. An algorithm has been also developed using Haversine Formula which calculates the distance among the vehicles. A total of five cases have been implemented according to the dataset and compared for the performance evaluation. An extensive experimental study and comparison have been performed with the other methods where a complete performance is focused that can be claimed to reduce road accidents via the device-to-device communication process.</p>

show abstract

Enhancing road safety with machine learning: Current advances and future directions in accident prediction using non-visual data

Chai,

Lau,

Tee

et al. 2024

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

PSO-ANN in preventing traffic collisions: a comparative study

Cited by 6 publications

References 20 publications

Convolution neural network hyperparameter optimization using modified particle swarm optimization

Convolution neural network hyperparameter optimization using modified particle swarm optimization

An intelligent road accident reduction system using device-to-device communication

Enhancing road safety with machine learning: Current advances and future directions in accident prediction using non-visual data

Contact Info

Product

Resources

About