IR@KDU Repository

Early Warning System for Landslides Using Wireless Sensor Networks

Show simple item record Perera, DKP Munasinghe, MKK Rajakaruna, WMCM Priyanwada, BGE Karunanayake, PN 2020-02-13T11:49:32Z 2020-02-13T11:49:32Z 2018
dc.description.abstract Landslides occur in many areas in Sri Lanka, and they cause considerable damage to natural habitat, environment, economy and other resources. Monitoring, predicting and controlling are the three major challenges associated with landslides due to the randomness of the event. Yet, developing an accurate prediction mechanism with an effective early warning system has become a need of the hour since the damages and the losses caused by the landslides are intolerable. Although there are expensive and advanced mechanisms deployed in foreign countries to predict the possibility of occurring landslides, such as satellites and radar systems with artificial intelligence capabilities, Sri Lanka finds it difficult to afford them due to the high cost and the advanced technologies used. When compared with the existing high-end systems, a simple wireless sensor network which is capable of identifying the underground movements and soil conditions is a cost effective, practical solution. But, dealing with a large number of variables manually with no proper understanding about their contribution for the occurrence of a landslide is difficult. Machine learning, which is a method used to create complex models and algorithms that lend themselves to predict is a fruitful solution for that issue. This research work is carried out to develop a cost-effective early warning system for land slides using WSNs incorporating machine learning. en_US
dc.language.iso en en_US
dc.subject Wireless sensor network en_US
dc.subject Machine Learning en_US
dc.subject Landslide Prediction en_US
dc.subject Early Warning en_US
dc.title Early Warning System for Landslides Using Wireless Sensor Networks en_US
dc.type Article Abstract en_US
dc.identifier.journal KDU-IRC en_US
dc.identifier.pgnos 39-45 en_US

Files in this item

This item appears in the following Collection(s)

Show simple item record

Search IR@KDU


My Account