A New Approach to Predict user Mobility Using Semantic Analysis and Machine Learning

Mobility prediction is a technique in which the future location of a user is identified in a given network. Mobility prediction provides solutions to many day-to-day life problems. It helps in seamless handovers in wireless networks to provide better location based services and to recalculate paths...

Full description

Saved in:
Bibliographic Details
Published in:Journal of medical systems 2017-12, Vol.41 (12), p.188-12, Article 188
Main Authors: Fernandes, Roshan, D’Souza G. L., Rio
Format: Article
Language:English
Subjects:
Bayesian analysis
Convergence of Deep Machine Learning and Nature Inspired Computing Paradigms for Medical Informatics
Emergency medical services
Health Informatics
Health Sciences
Learning algorithms
Location based services
Machine learning
Markov chains
Mathematical models
Medicine
Medicine & Public Health
Mobile & Wireless Health
Mobile ad hoc networks
Mobility
Performance measurement
Rescue vehicles
Security systems
Short message service
Social security
Statistics for Life Sciences
Wireless networks
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Mobility prediction is a technique in which the future location of a user is identified in a given network. Mobility prediction provides solutions to many day-to-day life problems. It helps in seamless handovers in wireless networks to provide better location based services and to recalculate paths in Mobile Ad hoc Networks (MANET). In the present study, a framework is presented which predicts user mobility in presence and absence of mobility history. Naïve Bayesian classification algorithm and Markov Model are used to predict user future location when user mobility history is available. An attempt is made to predict user future location by using Short Message Service (SMS) and instantaneous Geological coordinates in the absence of mobility patterns. The proposed technique compares the performance metrics with commonly used Markov Chain model. From the experimental results it is evident that the techniques used in this work gives better results when considering both spatial and temporal information. The proposed method predicts user’s future location in the absence of mobility history quite fairly. The proposed work is applied to predict the mobility of medical rescue vehicles and social security systems.
ISSN:0148-5598
1573-689X
DOI:10.1007/s10916-017-0837-x