Towards a better understanding and behavior recognition of inhabitants in smart cities. A public transport case

TL;DR

This paper explores analyzing mobile network signals to understand inhabitants' behaviors in smart cities, aiming to develop context-aware systems for improved public transport management.

Contribution

It introduces a method for analyzing mobile phone data to identify behavioral patterns and proposes a multi-agent system with graph-based reasoning for urban behavior understanding.

Findings

Behavioral fingerprints can be extracted from mobile data.

Proposed scenarios demonstrate potential for public transport optimization.

Graph formalism enables reasoning about inhabitant behaviors.

Abstract

The idea of modern urban systems and smart cities requires monitoring and careful analysis of different signals. Such signals can originate from different sources and one of the most promising is the BTS, i.e. base transceiver station, an element of mobile carrier networks. This paper presents the fundamental problems of elicitation, classification and understanding of such signals so as to develop context-aware and pro-active systems in urban areas. These systems are characterized by the omnipresence of computing which is strongly focused on providing on-line support to users/inhabitants of smart cities. A method of analyzing selected elements of mobile phone datasets through understanding inhabitants' behavioral fingerprints to obtain smart scenarios for public transport is proposed. Some scenarios are outlined. A multi-agent system is proposed. A formalism based on graphs that allows reasoning about inhabitant behaviors is also proposed.