Unveiling the complexity of human mobility by querying and mining massive trajectory data

Abstract

The technologies of mobile communications\ud pervade our society and wireless networks sense the movement\ud of people, generating large volumes of mobility data,\ud such as mobile phone call records and Global Positioning\ud System (GPS) tracks. In this work, we illustrate the striking\ud analytical power of massive collections of trajectory data in\ud unveiling the complexity of human mobility. We present the\ud results of a large-scale experiment, based on the detailed trajectories\ud of tens of thousands private cars with on-board GPS\ud receivers, tracked during weeks of ordinary mobile activity.\ud We illustrate the knowledge discovery process that, based on\ud these data, addresses some fundamental questions of mobility\ud analysts: what are the frequent patterns of people’s travels?\ud How big attractors and extraordinary events influence mobility?\ud How to predict areas of dense traffic in the near future?\ud How to characterize traffic jams and congestions? We also\ud describe M-Atlas, the querying and mining language and system\ud that makes this analytical process possible, providing the\ud mechanisms to master the complexity of transforming raw\ud GPS tracks into mobility knowledge. M-Atlas is centered\ud onto the concept of a trajectory, and the mobility knowledge\ud discovery process can be specified by M-Atlas queries that\ud realize data transformations, data-driven estimation of the\ud parameters of the mining methods, the quality assessment\ud of the obtained results, the quantitative and visual exploration\ud of the discovered behavioral patterns and models, the composition of mined patterns, models and data with further\ud analyses and mining, and the incremental mining strategies\ud to address scalability

What is an Appropriate Temporal Sampling Rate to Record Floating Car Data with a GPS?

“…FCD are an important data-source in traffic research. FCD allow to calculate time-dependent travel times along urban corridors [1], reveal traffic congestions [2] and unveil the complexity of human mobility [3]. They help to identify flaws in urban traffic planning [4] and to infer traffic states [5].…”

On processing GPS tracking data of spatio-temporal car movements: a case study

“…For instance, Kharrat et al (2008) proposed an algorithm (NETSCAN) for mobile object clustering and applied it in an environment constrained by a network. Giannotti et al (2011) presented a query and data mining system named M-Atlas, but noted that it is difficult to transform GPS tracking data into mobility knowledge. Etienne et al (2012) provided a method for detecting outliers of spatiotemporal trajectories with primary applicability for travel behaviour analysis.…”

Caracterização de padrões do comportamento espacial de veículos (monitorados) em movimento - PCEVM

“…O estudo insere-se no contexto da mineração de dados espaço-temporais de mobilidade, e a finalidade é apresentar uma ferramenta de análise espacial para auxiliar o processo de tomada de decisão no monitoramento de veículos e na gestão do sistema de transporte urbano, de modo a abordar algumas questões fundamentais do estudo da mobilidade urbana (quais os padrões espaciais das viagens urbanas; dos diferentes tipos de veículos; como se associam aos diferentes ramos de atividades econômicas; etc. ), tais como as apresentadas em Giannotti et al (2011).…”

“…Alternativamente, o presente estudo prevê que grandes volumes de dados ("big data") de mobilidade, mesmo em estado bruto, podem ser usados para superar as restrições das pesquisas de campo, como os altos custos envolvidos, baixa periodicidade de realização (frequência), rápida obsolescência, não são completas nem exatas. Por outro lado, os dados de mobilidade coletados remotamente são verdades de campo, pois descrevem atividades móveis reais, e desta forma são considerados dados confiáveis e podem ser continuamente coletados em tempo real (Giannotti et al, 2011).…”