Weigh-in-motion Using Machine Learning and Telematics
Authors:
- 1 July 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 115-120
Abstract
Driving overloaded vehicle causes road infrastructural damages, accidents, air pollution by excessive fuel consumption, and unusual expenses. Measuring the gross weight of a vehicle on a particular road segment without interrupting the traffic flow is a problem worth researching, and its solutions have several economic benefits. This paper proposes an alternative way of finding an overloaded vehicle in motion, by introducing a novel approach in inferring the weight of a vehicle on a road segment using Telematics data and Machine Learning.Keywords
This publication has 30 references indexed in Scilit:
- Driving Behavior Analysis for Smartphone-based Insurance Telematics2015
- Insurance Telematics: Opportunities and Challenges with the Smartphone SolutionIEEE Intelligent Transportation Systems Magazine, 2014
- Impact of Traffic Overload on Road Pavement PerformanceJournal of Transportation Engineering, 2013
- On-Board Safety Monitoring Systems for Driving: Review, Knowledge Gaps, and FrameworkJournal of Safety Research, 2012
- Vehicle detection and classification by measuring and processing magnetic signalMeasurement, 2011
- Design Science Research in Information Systems2010
- Vehicle Signal Analysis Using Artificial Neural Networks for a Bridge Weigh-in-Motion SystemSensors, 2009
- Research on Vehicle Overloading Influenced to Roadbed2009
- An introduction to ROC analysisPattern Recognition Letters, 2006
- Evaluation of an Artificial Neural Network Technique Applied to Multiple-Sensor Weigh-in-Motion SystemsTransportation Research Record: Journal of the Transportation Research Board, 2003