Smart Vehicle Health Monitoring System Based On ARIMA and Ordinal Logistic Regression for Analysis of Vehicle Parameters

Existing Vehicle Monitoring Systems use an OBD-II device to retrieve problem codes and live data from the vehicle, which is then displayed to the user as raw data. A user-friendly system is required so that the user can grasp the vehicle's status on their own, preventing serious accidents. The purpose of this study is to produce a user-friendly and intelligible web application that allows the user to monitor the vehicle's health. The concept of the Internet of Vehicles (IoV) is discussed in this study, in which several vehicles form a network and communicate with one another. Machine learning models (Autoregressive Integrated Moving Average and Ordinal Logistic Regression) are used to estimate future vehicle conditions from available data and categorize the condition as “Good ”, “Moderate,” or “Bad”.