Indian Journal of Science and Technology

The PDF file you selected should load here if your Web browser has a PDF reader plug-in installed (for example, a recent version of Adobe Acrobat Reader).

If you would like more information about how to print, save, and work with PDFs, Highwire Press provides a helpful Frequently Asked Questions about PDFs.

Alternatively, you can download the PDF file directly to your computer, from where it can be opened using a PDF reader. To download the PDF, click the Download link above.

Fullscreen Fullscreen Off


Objective: To find the optimal time interval for predicting mobile user behavior in the location-based services. Methods: An innovative technique called Modified Particle Swarm Optimization based Optimal Time Interval Identification is introduced for predicting Mobile User Behavior (MPSO-OTI2-PMB)-in Location-Based Services. The MPSO algorithm intends to find the optimal time interval in the prediction of mobile user behavior for the location-based services. This MPSO algorithm aims to search the best time interval with less computation complexity. Contrast to the PSO algorithm, the MPSO algorithm decreases the search range during the optimization process. Results: MPSO-OTI2-PMB shows higher rate when compared to the existing Cluster-based Temporal Mobile Sequential Pattern Mine (CTMSP-Mine) method. In the MPSO algorithm, randomly generate the initial population with the search space and find the fitness value. Instead of fixed search range, the search range is decreased based on the fitness value during the optimization process. If the network size is 6, the precision rate in MPSO-OTI2-PMB is 0.92, the recall in MFAMGS is 0.9 and the F-Measure is 0.89. According to the comparison and the results from the experiment shows that the proposed method has high efficiency in terms of precision, recall and F-Measure. Conclusion: MPSO-OTI2-PMB is presented and this method has high efficiency for predicting mobile user behavior in the location-based services.

Keywords

Data Mining, Mobile Environments, Mining Methods and Algorithms, Particle Swarm Optimization.
User