Citation

Doğan G, Ergen B. Iran J. Comput. Sci. 2022; ePub(ePub): ePub.

Copyright

(Copyright © 2022, Holtzbrinck Springer Nature Publishing Group)

DOI

10.1007/s42044-022-00125-6

PMID

unavailable

Abstract

The number of vehicles used in traffic life has reached enormous dimensions today. The increase in the number of vehicles day by day causes some traffic problems along with it; such as traffic congestion, accidents, pollution, and safety. To overcome all these problems, convolutional neural networks (CNN) methods are one of the trend methods used in recent years due to their success. In this study, a new approach is proposed to use this power of CNN in low-power devices. First of all, MobileNetv1, MobileNetv2, and NASNetMobile models were optimized to increase accuracy performance. Then, an approach is proposed in which these optimized mobile CNN approaches are used only as feature extractors, and methods such as combining, selecting, and classifying the obtained features are used together. As a result of the classification made with this approach, the classification accuracy has increased by approximately 5%.

Language: en

Keywords

Classification; Deep learning; Feature selection; Vehicle types