Crowd Mobility Analysis using WiFi Sniffers
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2016, Vol 7, Issue 12
Abstract
Wi-fi enabled devices such as today’s smart-phones are regularly in-search for connectivity. They continuously send management frames called Probe Requests searching for previ-ously accessed networks. These frames contain the sender’s MAC addresses in clear text, which can be used as an identifier for that sender. Being able to sniff that MAC address at several locations allows us to understand the mobility behavior of that device. In this paper, we present a solar-powered, beagle-bone based standalone system that continuously sniffs the air for probes and extract their MAC addresses. We deployed the system in the world’s largest gathering (The Hajj) and tested it at scale. Our objective was to build an infrastructure for non-invasive mass crowd analysis. Our deployment had a total of 8 sniffers covering a population of 185,000 people. We detected 37.5% of the population, analysed their arrival and departure behaviours, identified their smartphone manufacturers and extracted their transition patterns from one sub-location to another. By pre-senting valuable insights on the mobility of our target crowd, we validated the potential of our platform for crowd mobility analysis.
Authors and Affiliations
Anas Basalamah
Keywords
Related Articles
- EP ID EP397381
- DOI 10.14569/IJACSA.2016.071249
- Views 71
- Downloads 0
Effective Performance of Information Retrieval by using Domain Based Crawler
World Wide Web continuously introduces new capabilities and attracts many people[1]. It consists of more than 60 billion pages online. Due to this explosion in size, the information retrieval system or Search Engines are...
Collaborative System Model for Dynamic Planning of Supply Chain
The business need to be structured as an integrated supply chain pushes companies to make use of a greater level of co-operation and coordination. As a means of coordination, negotiation has been chosen in this work. The...
Integrating Semantic Features for Enhancing Arabic Named Entity Recognition
Named Entity Recognition (NER) is currently an essential research area that supports many tasks in NLP. Its goal is to find a solution to boost accurately the named entities identification. This paper presents an integra...
Multi-input Multi-output Beta Wavelet Network: Modeling of Acoustic Units for Speech Recognition
In this paper, we propose a novel architecture of wavelet network called Multi-input Multi-output Wavelet Network MIMOWN as a generalization of the old architecture of wavelet network. This newel prototype was applied to...
Blood Diseases Detection using Classical Machine Learning Algorithms
Blood analysis is an essential indicator for many diseases; it contains several parameters which are a sign for specific blood diseases. For predicting the disease according to the blood analysis, patterns that lead to i...