Abstract
The growth of urban areas in recent years has motivated a large amount of new sensor applications in smart cities. At the centre of many new applications stands the goal of gaining insights into human activity. Scalable monitoring of urban environments can facilitate better informed city planning, efficient security, regular transport and commerce. A large part of monitoring capabilities have already been deployed; however, most rely on expensive motion imagery and privacy invading video cameras. It is possible to use a low-cost sensor alternative, which enables deep understanding of population behaviour such as the Global Positioning System (GPS) data. However, the automated analysis of such low dimensional sensor data, requires new flexible and structured techniques that can describe the generative distribution and time dynamics of the observation data, while accounting for external contextual influences such as time of day or the difference between weekend/weekday trends. In this paper, we propose a novel time series analysis technique that allows for multiple different transition matrices depending on the data’s contextual realisations all following shared adaptive observational models that govern the global distribution of the data given a latent sequence. The proposed approach, which we name Adaptive Input Hidden Markov model (AI-HMM) is tested on two datasets from different sensor types: GPS trajectories of taxis and derived vehicle counts in populated areas. We demonstrate that our model can group different categories of behavioural trends and identify time specific anomalies.
Highlights
The rising population in modern cities introduces many challenges in urban city planning including problems associated with improving the inhabitants’ quality of life and security.The utilisation of sensors and communication technology gives rise to the concept of Smart Cities and enables the adequate study of specific focus problems in urban development
Building on the theory of the Vector Autoregressive Hidden Markov Model (VAR-HMM) [19] to allow for autoregressive self-dependence between observations, we introduce a new discrete and independent semi-Markov variable which acts as a parent to the state indicator variable in the graphical model to represent environmental factors that influence movement behaviour
We propose a novel Adaptive Input infinite Hidden Markov Model (AI-iHMM) where an additional Dirichlet Process (DP) layer is added to the models hierarchy allowing for the generation (v) of a different base measure G0 for each unique value of τ while still sharing the same upper level base distribution H for the sampling of the model parameters Θ k
Summary
The rising population in modern cities introduces many challenges in urban city planning including problems associated with improving the inhabitants’ quality of life and security. Despite the prior work on behaviour understanding from GPS [13,14,15], a lot of the GPS data analysis remains challenging due to noise, irregular sampling, heterogeneity and frequent interruption of data collection as environmental factors cause missing data [16] To address this Ellam et al [17], a recently proposed parameter estimation framework for spatial interaction models was demonstrated to simulate accurately the flow of customers. To account for this, Witayangkurn et al [18] proposed the use of a Hidden Markov Model (HMM) to detect anomalies from large scale GPS data This approach does not consider the time self-dependence of the observation sequence and requires that the model complexity be predefined which may bias the unsupervised approach to the analysis.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
