Significant Location Detection & Prediction in Cellular Networks using Artificial Neural Networks

Abstract

Location services and applications, based on network data or global positioning systems, are greatly influencing and changing the way people use mobile phone networks by improving not only user-applications but also the network management part. These applications and services can be further developed by introducing location prediction. We design a system that logs cell id and timestamp data from the users' mobile device, detects the significance of the location to the user, such as home and workplace, and predicts future locations over a chosen time period using artificial neural networks. A novel method is designed for location detection that automatically determines the significance of the location to the user, by spatial and temporal analysis. In our approach, the neural network is automatically adapted, with the help of the location detection algorithm, to the period of the week for which a prediction is desired, achieving accurate weekday and weekend location prediction.

A Case Study of Innovation in the Implementation of a DSS System for Intelligent Insurance Hub Services

“…This work proves that innovative tools, such as AI [4], [5] and Data Mining (DM) algorithms in combination with KPIs can certainly bring benefits in the insurance service sector, facilitating the improvement of processes. AI can play a crucial role in automation and improvement of the daily insurer operations in the insurance sector involving data processing.…”

Recent advances in location prediction methods for cellular communication networks

“…This means that further improvements of prediction accuracy should be based on the gathering and analysis of information from other sources. These sources can be: analysis of calls between users [14], social analysis of daily schedules that people share [7], [16], determination of social point of interests [17], social network analysis [18], combining cell tower location info with 802.11 access point location and GPS [19], user activity inferring and modelling [20].…”

“…Human mobility has been studied on different scales [5], [6], with results pointing to an upper limit of human mobility predictability of 93%, across data collected from 50000 anonymous mobile users [5]. These results are based on the fact that most users have daily routines inside significant locations such as home or workplace and also tend to follow the same path between these locations [7].…”

“…Their method consists of aiding location prediction with social relationship analysis, for users that choose to share their location with the cloud service. Location prediction is resumed to significant locations represented symbolical in a similar manner to [7].…”

Performance Analysis of Cellular Radio System Using Artificial Neural Networks

“…Several researchers have used ANNs and other soft computing techniques for studying channel assignment problems in cellular networks [16,17,18,19]. Some researchers have also used ANN for location detection and prediction in cellular networks [21,22].…”