ARTÍCULO
TITULO

Machine Learning to Classify Driving Events Using Mobile Phone Sensors Data

Yazan Alqudah    
Belal Sababha    
Esam Qaralleh    
Tarek Yousseff    

Resumen

With the ever-increasing vehicle population and introduction of autonomous and self-driving cars, innovative research is needed to ensure safety and reliability on the road. This work introduces an innovative solution that aims at understanding vehicle behavior based on sensors data. The behavior is classified according to driving events. Understanding driving events can play a significant role in road safety and estimating the expense and risks of driving and consuming a vehicle. Rather than relying on the distance and time driven, driving events can provide a more accurate measure of vehicle driving consumption.  This measure will become more valuable as more autonomous vehicles and more ride sharing applications are introduced to roads around the world. Estimating driving events can also help better design the road infrastructure to reduce energy consumption.  By sharing data from official vehicles and volunteers, crowd sensing can be used to better understand congestion and road safety. This work studies driving events and proposes using machine learning to classify these events into different categories. The acquired data is collected using embedded mobile device motion sensors and are used to train machine learning algorithms to classify the events.

 Artículos similares

       
 
Leonardo Emiro Contreras Bravo, Nayibe Nieves-Pimiento, Karolina Gonzalez-Guerrero     Pág. e19514
Revista: Ingeniería

 
Dmitry Namiot,Eugene Ilyushin     Pág. 60 - 69

 
Ivan Kosyanenko,Roman Bolbakov     Pág. 53 - 59
In today's team-based software development, good commit messages - comments on changes made in natural language - are essential. The metric for evaluating a commit message is its relevance. A good commit message should not only describe the changes made,... ver más

 
Eugene Ilyushin,Dmitry Namiot,Ivan Chizhov     Pág. 17 - 22
The paper deals with the problem of adversarial attacks on machine learning systems. Such attacks are understood as special actions on the elements of the machine learning pipeline (training data, the model itself, test data) in order to either achieve t... ver más

 
Dmitry Namiot,Eugene Ilyushin,Ivan Chizhov     Pág. 135 - 147
In this article, we consider the relationship between artificial intelligence systems and cybersecurity. In the modern interpretation, artificial intelligence systems are machine learning systems, sometimes it is even more narrowed down to artificial neu... ver más