Leak detection using random forest and pressure simulation

Aymon, Lucien (School of Engineering and Architecture (HEIA-FR), HES-SO // University of Applied Sciences Western Switzerland) ; Carrino, Francesco (School of Engineering and Architecture (HEIA-FR), HES-SO // University of Applied Sciences Western Switzerland) ; Baltensperger, Richard (School of Engineering and Architecture (HEIA-FR), HES-SO // University of Applied Sciences Western Switzerland)

This article presents a framework to facilitate and optimize the management of field operations for bike-sharing companies. The study focuses on two modules based on artificial intelligence: the prediction module forecasts bikes availability at station-level using machine-learning and the rebalancing module provides optimal rebalancing operations and routes using constraint programming. The evaluation on 9 months of data collected from a real bike-sharing network notably highlighted the superior forecasting accuracy of the Multilayer Perceptron algorithm.


Keywords:
Conference Type:
short paper
Faculty:
Ingénierie et Architecture
School:
HEIA-FR
Institute:
HumanTech - Technology for Human Wellbeing Institute
Publisher:
Bern, Switzerland, 14 June 2019
Date:
2019-06
Bern, Switzerland
14 June 2019
Pagination:
2 p.
Published in:
Proceedings of 6th Swiss Conference on Data Science – SDS|2019, 14 June 2019, Bern, Switzerland
Numeration (vol. no.):
pp. 109-110
ISBN:
978-1-7281-3105-4
External resources:
Appears in Collection:

Note: The status of this file is: restricted


 Record created 2020-01-14, last modified 2020-01-14

Fulltext:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)