User's Future Location Research Articles

PreLoc: predicting pedestrian's location and learning unmapped pathways by long short‐term memory model

With increasing popularity of smartphone apps such as fitness assistants, location-based services, more and more pedestrians now travel in short distances with purposes of leisure, running exercise or social activities. As users move from place to place, the mobile apps capture the data showing the history of change in location in a definite time interval. Given the set of global positioning system (GPS) location points a user has travelled along, this study presents, PreLoc, a system that accurately predicts the user's future location. By preprocessing the raw data, the authors eliminate existing noises and extract valid trajectories from pedestrians or runners. Then the long short-term memory model is applied to predict the next GPS point that the user will pass through. Meanwhile, PreLoc is able to learn an unmapped pathway based on the trajectory data of mass users that have travelled over this pathway. Experimental results over real-world dataset show the distance error could achieve about 12 m in residential area, and achieve acceptable distance errors (about 30 m) for other larger and complicated sites. Moreover, they provide real scenarios for unmapped pathway learning.

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 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.

MAP BASED INTRA-CELL METHOD FOR LOCATION PREDICTION OVER UMTS NETWORK PLATFORM

Location based services (LBS) and their applications are regarded as the mostgrowing services applied on communication systems. According to the greatenhancement in the mobile network platform and its related database servers,we are not only able to develop LBS applications but also to enhance theperformance of mobile networks. Future location prediction of mobile userresults in great enhancement in LBS applications and mobile networkperformance. Many researches were introduced to predict location of mobileuser. In [7] User Mobility Pattern (UMP) algorithm based on sequentialmining prediction has been developed to deal with future location prediction inmobile networks. The main limitations of this pattern are: map based intra cellprediction cannot be extracted and the timestamps aren't associated with rules.In [8], another method has been introduced using All frequent MovementPattern (ALLMOP) algorithm for extracting all frequent movement patternswithin movement Rule based Location Prediction method (RLP). RLP methodworks on GPS network map based platform without manipulating cell to cellmovement. So, it can't be used to enhance mobile network's resource allocationand mobility management. In this paper we proposed a new method, Intra CellMovement Prediction (ICMP), for mobile user's future location prediction onUniversal Mobile Telecommunication System (UMTS) environments to benefitfrom both intra and inter cell based techniques for both network and servicesenhancement. The proposed method depends on map based intra-cellprediction and utilizes the network database and positioning techniques inextracting user trajectories and movement rules. As a result, the user positioncan be predicted for the next movement step. The performance of the proposedalgorithm is evaluated through computer simulation and compared with that of[7] and [8]. The simulation results indicate that the proposed method is highlyefficient for both network and services' improvements as it is used to enhancelocation based services with satisfactory accuracy, network's resourceutilization, reduce the latency in accessing resources and mobilitymanagement.

A mobility prediction architecture based on contextual knowledge and spatial conceptual maps

User Mobility prediction represents a key component in assisting handoff management, resource reservation, and service preconfiguration. However, most of the existing approaches presume that the user travels in an a priori known pattern with some regularity; an assumption that may not always hold. This paper presents a novel framework for user mobility prediction that can accurately predict the traveling trajectory and destination using knowledge of user's preferences, goals, and analyzed spatial information without imposing any assumptions about the availability of users' movements history. This framework thus incorporates the notion of combining user context and spatial conceptual maps in the prediction process. The main objective of this notion is to circumvent the difficulties that arise in predicting the user's future location when adequate knowledge about the history of user's traveling patterns is not available. Using concepts of evidential reasoning of Dempster-Shafer's theory, the user's navigation behavior is captured by gathering pieces of evidence concerning different groups of candidate future locations. These groups are then refined to predict the user's future location when evidence accumulates using the Dempster rule of combination. Simulation results are presented to demonstrate the performance of the proposed framework.