DSpace Repository

AutoMind: Tyre Health Monitoring and Recommendation System

Show simple item record

dc.contributor.author 03-134211-016 KHALID HAMEED, 03-134202-089 WAJEEHA QURBAN
dc.date.accessioned 2026-04-22T09:11:14Z
dc.date.available 2026-04-22T09:11:14Z
dc.date.issued 2025-01-01
dc.identifier.uri http://hdl.handle.net/123456789/21080
dc.description DAWOOD AKRAM en_US
dc.description.abstract Road safety and operational efficiency depends on vehicle tire health. Accidents, increased maintenance cost and poor fuel efficiency are some of the effects of poor tire condition. However, the traditional tire inspection methods are usually time consuming and need expert knowledge. In response to this need, this project develops a Tire Health Monitoring System powered by deep learning techniques. To classify tire health based on images provided by users, the system uses MobileNetV2, a lightweight model famous for its computational efficiency. The system comprises a mobile application for users to upload tire images and enter tire serial numbers. The trained deep learning model analyzes these images to detect the tire condition in one of the four categories, excellent, good, poor, and cracked. A backend system supporting this functionality manages tire data, tracks health trends and issues notifications to users when maintenance or tire replacement is required. The dataset of tire images was trained using a model, fine tuned and early stopped to limit overfitting and generalize the model for different size tires. The evaluation of the model used in this thesis is presented: evaluation metrics of accuracy, precision, recall, F1 score, and confusion matrix present accuracy of 94%. The results show that the system can supply accurate and reliable tire health assessments. The Tire Health Monitoring System described in this report provides a proactive approach to tire maintenance, thereby reducing the risk of tire related accidents, minimizing downtime and optimizing vehicle performance. Additionally, the system prolongs tire life and enhances fuel efficiency, demonstrating considerable environmental and cost saving benefits. This project is an example of integrating machine learning with mobile technology which has the potential to change the way of vehicle safety and maintenance in the future, and offers a path for the future development of more advanced solutions in the automotive industry. en_US
dc.language.iso en_US en_US
dc.relation.ispartofseries ;BULC1360
dc.title AutoMind: Tyre Health Monitoring and Recommendation System en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account