Cloud based Vehicle Breakdown Prediction and Monitoring Driver behaviour |
Author(s): |
Kapil Sharma , Thakur College of Engineering and Technology; Chinmay Tompe, Thakur College of Engineering and Technology; Pavitra Vichare, Thakur College of Engineering and Technology; Aradhana Manekar, Thakur College of Engineering and Technology |
Keywords: |
ECU, Vehicle Breakdown, Cloud |
Abstract |
The usage of vehicles all over the worlds has drastically increased during the last decade. Over 60 million passenger cars have been manufactured in the year of 2012. This rapid increase of vehicles has led to many concerns for a range of people and organizations where most of these concerns are common to all parties. For example, all parties (i.e., drivers, insurance companies, fleet vehicle managements, low enforcements authorities, etc.) are concerned about reckless driving and driver anomalies whereas drivers as individuals and people who are willing to purchase and sell cars are concerned also about the condition of the vehicle. Given the potential benefits of vehicular data analysis and the availability of technologies such as OBD, several vehicle monitoring and intelligent transport systems have been proposed. But, in almost all the systems proposed, there has been either simple or no processing of the data gathered from the Engine Control Unit (ECU) prior to displaying and are restricted to monitoring. Also they, hardly include a backend; therefore, are limited by the computational power of the smart phone. Hence, it is hard to predict any undesired outcome, such as an accident or a failure of sensor since they require real time and long-term analysis of data regarding the driving habits and the vehicle condition. In the proposed system i.e. Cloud Based Driver Monitoring and Vehicle Breakdown Prediction using data analytics, the task starts with collection of data from the cloud bifurcation and categorization of data for ease of use. The categorized data is to be passed through a machine learning process. In Machine Learning we plan on using linear regression algorithm for training the model. Amazon Web Services will be used for fulfilling the requirements of database. Bifurcated and categorized data will be available to the user on an Android application which the user will have on his/her mobile phone. Using this application user will be well updated about various parameters of his vehicle whenever is car is being driven. The analyses are performed both in real time as well throughout a long period of time. While some of these analyses are performed within the app, more complex and resource consuming ones are performed in the back end. |
Other Details |
Paper ID: IJSRDV7I30014 Published in: Volume : 7, Issue : 3 Publication Date: 01/06/2019 Page(s): 67-69 |
Article Preview |
|
|