Analysis and Implementation of Human Mobility Behavior Using Similarity Analysis Based on Co-Occurrence Matrix

Memon, Ambreen and Kilby, Jeff and Breñosa, Jose and Martínez Espinosa, Julio César and Ashraf, Imran UNSPECIFIED, UNSPECIFIED, josemanuel.brenosa@uneatlantico.es, ulio.martinez@unini.edu.mx, UNSPECIFIED (2022) Analysis and Implementation of Human Mobility Behavior Using Similarity Analysis Based on Co-Occurrence Matrix. Sensors, 22 (24). p. 9898. ISSN 1424-8220

[img]
Preview
Text
sensors-22-09898-with-cover.pdf
Available under License Creative Commons Attribution.

Download (672kB) | Preview

Abstract

The fast expansion of ICT (information and communications technology) has provided rich sources of data for the analysis, modeling, and interpretation of human mobility patterns. Many researchers have already introduced behavior-aware protocols for a better understanding of architecture and realistic modeling of behavioral characteristics, similarities, and aggregation of mobile users. We are introducing the similarity analytical framework for the mobile encountering analysis to allow for more direct integration between the physical world and cyber-based systems. In this research, we propose a method for finding the similarity behavior of users’ mobility patterns based on location and time. This research was conducted to develop a technique for producing co-occurrence matrices of users based on their similar behaviors to determine their encounters. Our approach, named SAA (similarity analysis approach), makes use of the device info i.e., IP (internet protocol) and MAC (media access control) address, providing an in-depth analysis of similarity behaviors on a daily basis. We analyzed the similarity distributions of users on different days of the week for different locations based on their real movements. The results show similar characteristics of users with common mobility behaviors based on location and time to showcase the efficacy. The results show that the proposed SAA approach is 33% more accurate in terms of recognizing the user’s similarity as compared to the existing similarity approach.

Item Type: Article
Uncontrolled Keywords: similarity analysis; mobility; co-occurrences matrix; device-to-device communications
Subjects: Subjects > Engineering
Divisions: Europe University of Atlantic > Research > Scientific Production
Fundación Universitaria Internacional de Colombia > Research > Scientific Production
Ibero-american International University > Research > Scientific Production
Ibero-american International University > Research > Scientific Production
Universidad Internacional do Cuanza > Research > Scientific Production
Depositing User: Sr Bibliotecario
Date Deposited: 09 Jan 2023 10:57
Last Modified: 11 Jul 2023 06:12
URI: http://repositorio.funiber.org/id/eprint/5332

Actions (login required)

View Item View Item