An Effective Identification of Human Trajectory Data Using Parameter Tuning Optimization Technique
B. Suryakumar1, E. Ramadevi2
1B. Suryakumar, Ph.D, Research Scholar, Department of Computer Science, NGM College, Pollachi (Tamil Nadu), India.
2Dr .E. Ramadevi, Associate Professor, Department of Computer Science, NGM College, Pollachi (Tamil Nadu), India.
Manuscript received on 25 May 2019 | Revised Manuscript received on 03 June 2019 | Manuscript Published on 22 June 2019 | PP: 86-90 | Volume-8 Issue-3S, February 2019 | Retrieval Number: C10170283S19/19©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: As the tremendous growth of location enabled social networks sites such as Facebook, Foursquare etc., a number of ways have been provided for tracing human movements from one location to another location, containing user-created contents like geographically tagged records, mobile technology embedded services and applications. For the datamining purpose human trajectory data, various type of techniques was proposed over the past decades. However, the main issue in many applications was analysing process of data mining trajectory data owing to the composite features mirrored in human mobility which is directly connected by different contextual information. So that the Multi-Context Trajectory Embedding Model using Convolutional Neural Network (MCTEM-CNN) was proposed that reduces the computation time during the process of learning contextual features. However, it requires an optimization of algorithm to enhance the tuning of parameters which are needed to model the different contextual information. So in this article, an Improved Multi-Context Trajectory Embedding Model (IMC-TEM) is proposed based on the frog-leaping optimization algorithm. In this algorithm, the main priority is for the parameters tuning process. The parameters are tuned according to the frog characteristics. For attaining this in each iteration, the universally best fitness is chosen to adjust the location of worst fitness frogs. Thus, the proposed IMC-TEM tunes parameters in an efficient manner. In the last step, the experimental results are conducted based on three real-world datasets to observe the performance efficiency of the IMC-TEM than MC-TEM-CNN.
Keywords: Optimization Data Process Applications Network.
Scope of the Article: Discrete Optimization