Big Data Analysis to Detect Cracks in Tires Using Predictive Analytics Method

Abstract

This study highlights the importance of early detection of tire cracks to improve driving safety. Conventional inspection methods remain manual, time-consuming, and prone to human error, thereby making them less effective. Therefore, this research aims to analyze the application of big data and predictive analytics for accurate and efficient tire crack detection. The data used in this study were obtained from image, pressure, and vibration sensors installed on vehicle tires. Large-scale data were processed through a pre-processing stage to reduce noise and enhance data quality. Machine learning algorithms, including Random Forest, Support Vector Machine (SVM), Convolutional Neural Network (CNN), and XGBoost, were employed to identify patterns indicating tire cracks. Model performance was evaluated using accuracy, precision, and recall metrics. The results show that the CNN model achieved the best performance on visual data, with a validation accuracy of 96.4% and a micro-crack detection accuracy of 94.7% for tire cracks. Meanwhile, the XGBoost model applied to sensor data achieved an accuracy of 94.8%, demonstrating strong predictive capability for detecting potential damage from sensor patterns. These findings indicate that a predictive analytics approach integrating image and sensor data is effective for enhancing early tire crack detection and supports the development of adaptive, accurate, big-data–driven vehicle maintenance systems. Furthermore, this approach has strong potential for integration with the Internet of Things (IoT) to enable future smart tire monitoring systems.