Double Helical Ensemble Multi-Dimensional 4-D Structured Neural Network to Analyze the Driving Pattern, Driver DNA and Generate License Score using Smartphone Sensor Data

Main Article Content

Dr. S. Karthikeyan, Dr. S. Gopikrishnan, Dhruv Batta, TathagatBanerjee

Abstract

In this paper, we delineate a way to assess the licensed score of a person. License score is a term coined here in
reference with a credit score which is used to identify the credibility of an individual on a financial basis. This research
leverages the accelerometer and gyroscope sensors present in the smartphones. These sensors help us realize our goal of
classifying driving events and detecting distracted driving due to the use of smartphones. We use sensors rich user micro
movements and irregularities that can be detected by sensors in the phone during driving. Our system distinguishes driving
events based on reference signals which are matched through our Pattern Matching Algorithm which uses dynamic time
warping. To validate our approach, we conducted extensive experiments with several users on various vehicles and
smartphones. A neural network model has been developed for the purpose of classifying signals in the future which leverages
our collected data. The model has a double helical stranded multidimensional 4-d neural network that uses layers of
Convolutional Neural Networks and Artificial Neural Networks. It uses long short-term memory (LSTM) layers to classify and
score the driving behaviours. The double-helical stranded neural network simulates a situation similar to the input and output
of different senses of the human brain. This helps us classifying driving events.

Downloads

Download data is not yet available.

Metrics

Metrics Loading ...

Article Details

How to Cite
Dr. S. Karthikeyan, Dr. S. Gopikrishnan, Dhruv Batta, TathagatBanerjee. (2021). Double Helical Ensemble Multi-Dimensional 4-D Structured Neural Network to Analyze the Driving Pattern, Driver DNA and Generate License Score using Smartphone Sensor Data. Turkish Journal of Computer and Mathematics Education (TURCOMAT), 12(13), 6447–6458. https://doi.org/10.17762/turcomat.v12i13.9983
Section
Research Articles