Deep LSTM with Dynamic Time Warping Processing Framework: A Novel Advanced Algorithm with Biosensor System for an Efficient Car-Driver Recognition

Francesco Rundo

doi:10.3390/electronics9040616

Abstract

The latest generation of cars are increasingly equipped with driver assistance systems called ADAS (advanced driver assistance systems) which are able to assist the car driver in different driving scenarios, and in the most advanced automation levels, able to take over driving the car if required due to dangerous situations. Therefore, it is essential to adapt the ADAS specifically to the car-driver’s identity in order to better customize the driving assistance. To this end, algorithms that allow correct recognition of the vehicle driver are fundamental and preparatory. In this context, an algorithm for car-driver identity recognition is proposed which allows, with an accuracy close to 99%, recognition of the driver by means of a properly designed pipeline based on the analysis of the car driver PhotoPlethysmoGraphic (PPG) signal. The proposed approach makes use of deep long short-term memory (LSTM) architecture for learning such PPG signal features needed to discriminate one car driver from another. The extended validation and testing of the proposed system confirm the reliability of the proposed pipeline.

Highlights

The automotive industry is constantly evolving to ensure reliability, durability, and safety for the car driver
Automotive design is turning to advanced driver assistance systems (ADAS), to address safety issues while driving
To manage the sampling and preprocessing part of the PPG signal by using devices of the SPCxx family of 32-bit automotive microcontrollers series produced by STMicroelectronics for the ADAS sector [24] and equipped with ADC

Summary

Introduction

The automotive industry is constantly evolving to ensure reliability, durability, and safety for the car driver. Automotive design is turning to advanced driver assistance systems (ADAS), to address safety issues while driving These ADAS inform the driver in case of danger related to reduced attention [1,2,3]. Each car driver has their own driving dynamics, level of perception, reflexes, readiness, and driving experience which, obviously, must be taken into consideration by the ADAS which are suitable to assist the driver. To this end, it is useful to continuously identify the user while driving in order to apply the most suitable ADAS assistance setup [4]. There are several approaches in the literature for car-driver identity recognition

Methods

Results

Conclusion