Driver’s Drowsiness Detection Based on Behavioural Changes using ResNet
A. Jeyasekar1, Vivek Ravi Iyengar2

1Dr. A. Jeyasekar, Associate Professor, Department of CSE, SRMIST, Chennai.
2Vivek Ravi Iyengar, P.G Student, Internet of Things(IoT), Department of CSE, SRMIST, Chennai.

Manuscript received on 05 August 2019. | Revised Manuscript received on 10 August 2019. | Manuscript published on 30 September 2019. | PP: 5708-5712 | Volume-8 Issue-3 September 2019 | Retrieval Number: B2494078219/2019©BEIESP | DOI: 10.35940/ijrte.B2494.098319
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: TRecently there has been growing interest in intelligent transportation system because the road accidents become biggest problems of mankind and the casualties of accident also increases rapidly every year. The casualties are very often witnessed in heavy and light motor vehicles. Moreover, the accidents occur mainly due to carelessness and drowsy feeling of the driver. Intelligent transportation systems use deep learning mechanism to detect drowsiness of the driver and alert the same to driver. It results in reduction of accidents. The driver’s behaviour during drowsiness is detected by three types of approaches. One approach deploys the sensors in steering wheel and accelerator of the vehicle and analyzes the signal sent by the sensors to detect the drowsiness. Second approach focuses on measuring the heart rate, pulse rate and brain signals etc to predict the drowsiness. Third approach uses the facial expression of the driver such as blinking rate of eye, eye closure and yawning etc. The cause for most of the road accidents is driver’s drowsiness. Therefore, in this paper, the behavioural changes of driver is accounted to detect the drowsiness of the driver. Eye movement and yawning are two behavioural changes of driver is considered in this paper. There are many CNN based deep learning architectures such AlexNet, VGGNet, ResNet. In this paper, we propose the drowsiness detection using ResNet because this method works on the principle of passing the output to the next la. The performance of proposed mechanism detects the drowsiness of the driver better than AlexNet and VGGNet.
Keywords— Drowsiness Detection, Convolutional Neural Networks, Activation Functions, Microsoft Resnet.

Scope of the Article:
Neural Information Processing