Litcius/Paper detail

DeepTread: Exploring Transfer Learning in Tyre Quality Classification

Sheshang Degadwala, Rocky Upadhyay, Shivam Upadhyay, Mukesh Soni, Dhara Jayendrakumar Parikh, Dhairya Vyas

202327 citationsDOI

Abstract

In recent years, the automotive industry has witnessed a significant shift towards leveraging advanced technologies for quality control and assessment, with a particular focus on tire quality. This research study presents “DeepTread,” an innovative approach that explores the untapped potential of transfer learning in the domain of tire quality classification. Transfer learning, a powerful paradigm within deep learning, allows the adaptation of pre-trained neural networks for the purpose of tire quality evaluation. By leveraging the knowledge gained from various related domains, DeepTread aims to improve the accuracy and efficiency of tire quality classification, thereby contributing to safer and more reliable automotive solutions. The methodology's effectiveness is validated through extensive experiments, demonstrating promising results and encouraging future developments in the field of tire quality assessment.

Topics & Concepts

Automotive industryQuality (philosophy)SAFERComputer scienceTransfer of learningArtificial intelligenceMachine learningArtificial neural networkAdaptation (eye)Domain (mathematical analysis)Field (mathematics)EngineeringComputer securityPhilosophyAerospace engineeringPure mathematicsMathematical analysisPhysicsOpticsEpistemologyMathematicsIndustrial Vision Systems and Defect DetectionTransport Systems and TechnologyQuality Function Deployment in Product Design
DeepTread: Exploring Transfer Learning in Tyre Quality Classification | Litcius