Big Data Analytics for Prediction of Mobile Users Movement using Neural Networks
No Thumbnail Available
Date
2019-06
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Addis Ababa University
Abstract
The rise of data warehouses and the rise of multi-media, social media and the Internet of Things
(IoT) generate an increasing Volume of structured, semi-structured and unstructured data. Towards
the investigation of these large Volumes of data, Big Data and data analytics have become
emerging research fields attracting the attention of academia, industry and governments. Researchers,
entrepreneurs, decision makers and problem solvers view ‘Big Data’ as an important
tool used to revolutionize various industries and sectors, such as business, health-care, retail,
research, education and public administration.
In this context, a general view on analysis of Big Data, especially in telecommunications industry
is proposed. In order to allocate scarce resources efficiently the location of mobile users
should be predicted. So, this work focuses on analysis of data for mobile users movement prediction
in telecommunications network. The objective of this work is to process and analyze
obtained samples of OpenCelliD data by means of Neural Network and provide as accurate mobile
users movement prediction as possible. More specifically, Modified Levenberg-Marquardt
(LM) algorithm is presented as an effective algorithm for movement prediction. Obtained result
from prediction is optimized by iteration method designed for finding the best possible combination
of Neural Network parameters. Efficiency of mobile users movement prediction is verified
by simulation in Matrix Laboratory (MATLAB). Simulation results show sufficient accuracy
for wide use of prediction for mobile networks optimization or services exploiting prediction
of mobile users movement. Measured results fully reflect real solution for telecommunications
industry and can help to plan activities connected with mobile users movement in a given area.
Description
Keywords
Big Data, Data Analytics, Location-Based Services (LBS), Telecommunications, Prediction, Neural Network, Non-Linear Autoregressive with External Input Neural Network (NARXNN), Dataset, Training, Optimization