Efficient classification based on multi-scale traffic data extraction patterns of cellular networks

Authors:
A. Kurien;G. Noel;A. Mellouk;B. Van Wyk;K. Djouani
Affiliations:
Tshwane University of Technology, Pretoria, South Africa;Tshwane University of Technology, Pretoria, South Africa;University Paris-Est (UPEC), IUT, Vitry sur Seine, France;Tshwane University of Technology, Pretoria, South Africa;Tshwane University of Technology, Pretoria, South Africa
Venue:
Proceedings of the 6th International Wireless Communications and Mobile Computing Conference
Year:
2010

Citing 6
Cited 0

Relevance feedback retrieval of time series data

Proceedings of the 22nd annual international ACM SIGIR conference on Research and development in information retrieval
Load Regulation in Mobile Network with Planned Pricing Model based on User Behaviour

ICAS-ICNS '05 Proceedings of the Joint International Conference on Autonomic and Autonomous Systems and International Conference on Networking and Services
A dimensionality reduction technique for efficient time series similarity analysis

Information Systems
Mining changing customer segments in dynamic markets

Expert Systems with Applications: An International Journal
An intelligent market segmentation system using k-means and particle swarm optimization

Expert Systems with Applications: An International Journal
A time series representation model for accurate and fast similarity detection

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

Africa has witnessed an incredible boom in the number of mobile subscribers in mobile networks across Africa. With the rise in demand for capacity in cellular networks, greater pressure is being placed on the network planner. Customer segmentation has been traditionally used in cellular network planning to better understand customer demands and needs. By developing more accurate profiling methods, operators are in a better position to market products and forecast future demand more accurately. This work looks at the extraction of frequency patterns from traffic signals originating from a typical mobile network using multi-scale analysis. By studying the features extracted, the classification of typical subscribers in the network can be conducted more efficiently and with greater granularity.