Smart Monitoring of Drunk Driver Using IOT and Machine Learning Based Anomaly Detection

You are here: Homepage > Search

Smart Monitoring of Drunk Driver Using IOT and Machine Learning Based Anomaly Detection

Karimisetty, Sujatha / Arjuna Rao, A. / Dinesh Kumar, Y. / Kumudini Devi, P.

Now-a-days, many road accidents are occurring due to the alcohol consumption of the person who is driving the vehicle. Though drunken driving is a threatening issue, detection of drunk driver has become a cumbersome issue. Hence, a stable system is required with continuous monitoring of drunk driver. The Smart Monitoring of Drunk Driver using IOT and Machine Learning helpful to the owner of the vehicle if he handovers the vehicle to the driver. The owner of the vehicle can continuously monitor the vehicle movements by using the features such as GPS and can track the driver mannerism by using the IOT sensors that sense both alcohol and abnormal movements of the vehicle. This requires a two-step procedure, first using Internet of Things Drunk Driver Detection (IOTDDD) and next adapting Support Vector Machine Learning Based Anomaly Detection (SVMAD). This system helps police in easily identifying the drunk drivers in heavy traffic.

Access

Check access

Check availability in my library

Order at Subito €

Export, share and cite

Document information

Title :

Smart Monitoring of Drunk Driver Using IOT and Machine Learning Based Anomaly Detection

Additional title:

Lect. Notes in Networks, Syst.

Contributors:

Mahapatra, Rajendra Prasad (editor) / Peddoju, Sateesh Kumar (editor) / Roy, Sudip (editor) / Parwekar, Pritee (editor) / Goel, Lavika (editor) / Karimisetty, Sujatha (author) / Arjuna Rao, A. (author) / Dinesh Kumar, Y. (author) / Kumudini Devi, P. (author)

Published in:

Proceedings of International Conference on Recent Trends in Computing ; Chapter : 13 ; 139-145

Lecture Notes in Networks and Systems ; 341

Publication date :

2022-01-15

Size :

7 pages

ISBN :

978-981-16-7118-0 , 978-981-16-7117-3

ISSN :

2367-3389 , 2367-3370

DOI :