Deep Learning Approaches for Classification of Road Types Using Wearable Sensors Embedded in Smart Glasses

Abstract

The Internet of Vehicles (IoV) is an architecture of the intelligent transportation system that combines automotive, transportation, and information exchange to increase road safety. The categorization of roadways not only improves the passenger's comfort and safety but also provides autonomous cars with safe navigation paths. In this paper, we present an identification method based on movement data from smart glasses (electroocu-lography, acceleration, and angular velocity) to categorize four kinds of roads often experienced: highway, city road, highway, undeveloped region, and housing estate. We developed a deep pyramidal residual network that automatically recovers spatial-temporal data and efficiently identifies road kinds. We performed experiments to evaluate deep learning models utilizing a publicly available benchmark dataset, including sensor data acquired from intelligent eyewear. Experimentally, we discovered that the suggested 1D-PyramidNet model obtained the most incredible interpretation with the most increased accuracy (92.23%) and outperformed all other deep learning models.