Please use this identifier to cite or link to this item: http://hdl.handle.net/2080/3460
Title: AISS for Road Anomaly Detection using WSN-Based Distributed Strategy
Authors: Sahoo, Goutam Kumar
Gupta, Saurav
Singh, Poonam
Das, Santos Kumar
Keywords: Intelligent transport system (ITS)
Wireless sensor networks (WSNs)
Automatic information sharing system (AISS)
Hibernate-and-share strategy (HSS),
Alternating direction method of multipliers (ADMM)
Issue Date: Dec-2019
Publisher: IEEE
Citation: IEEE International Conference on Advanced Networks and Telecommunications Systems (IEEE ANTS), Goa, India, 16-19 December 2019
Abstract: With rapid climb in the number of vehicles, it is difficult to deal with traffic issues such as traffic congestion, road anomaly, and vehicle parking. Road anomaly, mainly caused due to accident, is one of the major risk factors in our day-to-day life. Although traditional ways to manage this traf-fic issue are quite prevalent, yet can be improved with the usage of intelligent and advanced technologies. This will give rise to a smart way of traffic management and can control the anomaly after detecting it in real-time. In this article, a wireless sensor network (WSN)-based automatic information sharing system (AISS) is developed to smartly tackle the above-mentioned issue in a distributed manner. This paper also discusses a hibernate-and-share strategy (HSS) which is employed in WSN to cooperatively find the parameters of interest. It utilizes alternating direction method of multipliers (ADMM) based least-mean-squares (LMS) algorithm to optimally solve the global objective function in a distributed fashion. Simulations are carried-out for the estimation of optimal weights correspond to road anomaly. The results obtained signify the efficient performance of the developed algorithm.
Description: Copyright belongs to proceeding publisher
URI: http://hdl.handle.net/2080/3460
Appears in Collections:Conference Papers

Files in This Item:
File Description SizeFormat 
2019_IEEE-ANTS_SKDas_AISS.pdf441.09 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.