Deep learning and blockchain fusion for detecting driver's behavior in smart vehicles. Issue 6 (7th August 2019)

• Record Type: Journal Article
• Authors: Khan, Muhammad Z.; Khan, Muhammad U. G.; Irshad, Omer; Iqbal, Razi
• Is Part Of: Internet technology letters. Volume 3:Issue 6(2020)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2019-08-07
• Subjects: blockchain -- convolution neural network -- deep learning -- distracted behavior; Internet -- Periodicals; 004.67805
• DOI: 10.1002/itl2.119
• Languages: English
• ISSNs: 2476-1508

Abstract

Abstract : Studies have been actively conducted on analyzing the driver's behavior inside the vehicle premises. Moreover, the transmission of the tempered proof multimedia content is also a major point of interest for the research community. At present, most of the techniques for detecting the distracted behavior of the driver is based on the detection of different face attributes like eyes and head posture etc, by using the traditional hand crafted features. In this paper we propose the deep learning based algorithm using the Convolution Neural Network. The proposed algorithm is independent of feature extraction of the specific parts, instead, it automatically picks the best features specific to the problem. We have utilized the State Form Distracted Driver Detection dataset to train our proposed algorithm. Furthermore, this paper also proposes a secure and tempered proof multimedia transaction. Original video data may be edited and fabricated with the false information. Multimedia blockchain can be helpful in tackling this problem. We have used Secure Hashing Algorithm (SHA‐256) algorithm for extracting the hashes of multimedia content. By utilizing the blockchain, we safely transmit the tempered proof video data coming from inside the vehicle, automatically detecting abnormal activities with our deep learning based algorithm. So, this paper combines the deep learning algorithms with blockchain techniques which is novel in research. Comparison between the results of proposed algorithm with the current state of the art work shows that proposed algorithm outperforms by achieving 86.02% accuracy on the test data.