Analysing spatiotemporal sequences in Bluetooth tracking data (original) (raw)
Related papers
Sequence alignment as a method for human activity analysis in space and time
Annals of the Association of American …, 2007
This article introduces the method of sequence alignment as a tool for analyzing the sequential aspects within the temporal and spatial dimensions of human activities. Sequence alignment was first developed during the 1980s and employed by biochemists to analyze DNA sequences. Toward the end of the 1990s it was adapted for use in the social sciences. However, unlike other social sciences practitioners, geographers have not, until now, exploited this method. In contrast to traditional quantitative methods, sequence alignment, as its name suggests, is directly concerned with the order (sequence) of events, and is therefore well suited for the pursuit of timegeographic research. To demonstrate the merits of sequence alignment for geographic research, a database composed of forty space-time sequences of visitors who had visited the Old City of Akko (Israel) was used. The sequences were obtained by means of GPS devices, which were distributed among the visitors tracked and which they operated for the duration of their visit to the city. The sequences thereby obtained were aligned using ClustalG, a sequence alignment computer program. The result of this analysis was the identification of three temporal-spatial time geographies of the visitors that were sampled in this study.
… Journal of Health …, 2011
Background: Global positioning systems (GPS) are increasingly being used in health research to determine the location of study participants. Combining GPS data with data collected via travel/activity diaries allows researchers to assess where people travel in conjunction with data about trip purpose and accompaniment. However, linking GPS and diary data is problematic and to date the only method has been to match the two datasets manually, which is time consuming and unlikely to be practical for larger data sets. This paper assesses the feasibility of a new sequence alignment method of linking GPS and travel diary data in comparison with the manual matching method.
Sequence Alignment Analysis of Variability in Activity Travel Patterns through 8 Weeks of Diary Data
Transportation Research Record: Journal of the Transportation Research Board, 2014
Variability of activity travel patterns has long been an important issue in transportation research. Such variability has been typically explained in relation to covariance with a set of sociodemographic character istics of travelers. However, variability also stems from differences in knowledge about the environment, which changes over time. To improve understanding of the contribution of different sources to variability in observed activity travel patterns, this paper applies sequence alignment to investigate different sources of variability in longitudinal patterns. The data on activity travel patterns were collected in 2010 for 3 months from newcomers to the city of Eindhoven, Netherlands. GPS technol ogy was used to obtain traces that were processed with TraceAnnotator to impute activities and trips. A set of activity travel sequences for 8 weeks for 27 respondents was used in the analysis. The results show that (a) interpersonal variability is significantly higher than intra personal variability, although intrapersonal variability is yet substantial and should not be ignored; (b) intrapersonal variability reflecting different speeds of learning the new environment substantially changes over time; and (c) both interpersonal and intrapersonal variability are affected by socio demographic characteristics such as gender and country of origin. The paper also discusses the implications of these findings for future research.
Recognising online spatial activities using a bioinformatics inspired sequence alignment approach
Pattern Recognition, 2008
In this paper we address the problem of recognising embedded activities within continuous spatial sequences obtained from an online video tracking system. Traditionally, continuous data streams such as video tracking data are buffered with a sliding window applied to the buffered data stream for activity detection. We introduce an algorithm based on Smith--Waterman (SW) local alignment from the field of bioinformatics that can locate and accurately quantify embedded activities within a windowed sequence. The modified SW approach utilises dynamic programming with two dimensional spatial data to quantify sequence similarity and is capable of recognising sequences containing gaps and significant amounts of noise. A more efficient SW formulation for online recognition, called Online SW (OSW), is also developed. Through experimentation we show that the OSW algorithm can accurately and robustly recognise manually segmented activity sequences as well as embedded sequences from an online tracking system. To benchmark the classification performance of OSW we compare the approach to dynamic time warping (DTW) and the discrete hidden Markov model (HMM). Results demonstrate that OSW produces higher precision and recall than both DTW and the HMM in an online recognition context. With accurately segmented sequences the SW approach produces results comparable to DTW and superior to the HMM. Finally, we confirm the robust property of the SW approach by evaluating it with sequences containing artificially incorporated noise.
Activity pattern similarity: a multidimensional sequence alignment method
Transportation Research Part B: Methodological, 2002
The classification of activity patterns is an important research topic in activity analysis. First, it constitutes the basis for analyzing activity patterns, for instance by correlating the derived classification with spatial and/or socio-economic variables. Secondly, the underlying mechanisms can be used to assess the degree of correspondence between observed activity patterns and activity patterns predicted by some activity-based model of transport demand. Traditionally, conventional Euclidean distance measures have been used for the comparison of activity patterns. Consequently, the sequence information embedded in activity patterns has not been explicitly considered when comparing activity patterns. More recently, sequence alignment methods have been proposed. Although these methods have some advantages, they are uni-dimensional and hence cannot incorporate the interdependencies between attributes. This paper therefore proposes a multidimensional sequence alignment method to measure differences in both sequential and interdependency information embedded in activity patterns. Ó
Analysing visitor flow using a Bluetooth positioning system
2019
Citation for published version (APA): van den Ham, P., Bredeweg, B., & Raijmakers, M. (2019). Analysing visitor flow using a Bluetooth positioning system. In K. Beuls, B. Bogaerts, G. Bontempi, P. Geurts, N. Harley, B. Lebichot, T. Lenaerts, G. Louppe, & P. Van Eecke (Eds.), BNAIC/BENELEARN 2019 : proceedings of the Reference AI & ML Conference for Belgium, Netherlands & Luxemburg: proceedings of the 31st Benelux Conference on Artificial Intelligence (BNAIC 2019) and the 28th Belgian Dutch Conference on Machine Learning (Benelearn 2019), Brussels, Belgium, November 6-8, 2019 [118] (CEUR Workshop Proceedings; Vol. 2491). CEUR-WS. http://ceurws.org/Vol-2491/abstract118.pdf
Geographical Analysis, 2010
Quantitative comparisons of space-time activity patterns are a critical element in several streams of research in regional science. Traditionally, Euclidean distance and the measures developed in botanical taxonomy have been widely used to measure the similarity between activity patterns that involve several attribute dimensions such as location, transport mode, accompanying persons, etc. Some other techniques, such as pattern recognition in signal processing theory, have also been introduced for this purpose. These measures however lack the ability to capture the information of the overall sequence of activity patterns of multiple attributes. Recently, the Sequence Alignment Methods (SAMs), developed in molecular biology that are concerned with the distances between DNA strings, have been introduced in time use research. The SAMs captures the similarity of activity patterns based on a single attribute only. Unfortunately, the extension of the unidimensional SAM to a multidimensional method induces the problem of combinatorial explosion. To solve this problem, this paper introduces effective heuristic methods for the comparison of multidimensional activity patterns. First, the combinatorial nature of the algorithm is discussed. The paper then develops alternative SAMs based on dynamic programming and genetic algorithms, respectively. These two SAMs are compared using empirical activity pattern data. The paper ends by discussing avenues of future research.
A Language of Life: Characterizing People Using Cell Phone Tracks
2009 International Conference on Computational Science and Engineering, 2009
Mobile devices can produce continuous streams of data which are often specific to the person carrying them. We show that cell phone tracks from the MIT Reality dataset can be used to reliably characterize individual people. This is done by treating each person's data as a separate language by building a standard n-gram language model for each "author." We then compute the perplexities of an unlabelled sample as based on each person's language model. The sample is assigned to the user yielding the lowest perplexity score. This technique achieves 85% accuracy and can also be used for clustering. We also show how language models can also be used for predicting movement and propose metrics to measure the accuracy of the predictions. Finally, we develop an alternative method for identifying individuals by counting the subsequences in a sample which are unique to their authors. This is done by building a generalized suffix tree of the training set and counting each subsequence from a sample which is unique for some person as evidence towards identifying that person as the author. We present the identification and prediction as a part of a HUMBLE human behavior modeling framework, outline general modeling goals, and show how our methods help. Our results suggest that people's medium-scale movement behavioral patterns, at the granularity of cell tower footprints, can be used to characterize individuals.
Behaviour Detection Using Bluetooth Proximity Data
Proceedings of Networking & Electronic …, 2009
The abundance of Bluetooth enabled devices used in daily life has created new ways to analyze and model the behaviour of individuals. Bluetooth integrated into mobile handsets can be used as an efficient short range sensor. In this paper we use Bluetooth proximity data to detect the repeated patterns and behaviour of an individual by using n-gram technique. The primary purpose of this study is to determine what kinds of repeated behaviours can be detected in Bluetooth data. These repeated behaviours can show the daily, monthly or yearly patterns in an individual's life that can help us in determining the complex and unusual routines of human behaviour.
1. Digital tracking technologies have considerably increased the amount and quality of animal trajectories, enabling the study of habitat use and habitat selection at a fine spatial and temporal scale. However, current approaches do not yet explicitly account for a key aspect of habitat use, namely the sequential variation in the use of different habitat features. 2. To overcome this limitation, we propose a tree-based approach that makes use of sequence analysis methods, derived from molecular biology, to explore and identify ecologically relevant sequential patterns in habitat use by animals. We applied this approach to ecological data consisting of simulated and real trajectories from a roe deer population (Capreolus capreolus), expressed as ordered sequences of habitat use. 3. We show that our approach effectively captured spatio-temporal patterns of sequential habitat use by roe deer. In our case study, individual sequences were clustered according to the sequential use of the elevation gradient (first order) and of open/closed habitats (second order). We provided evidence for several behavioural processes , such as migration and daily alternating habitat use. Some unexpected patterns, such as homogeneous sequences of use of open habitat, could also be identified. 4. Our findings advocate the importance of dealing with the sequential nature of movement data. Approaches based on sequence analysis methods are particularly useful and effective since they allow exploring temporal patterns of habitat use in a synthetic and visually captive manner. The proposed approach represents a useful and effective way to classify individual movement behaviour across populations and species. Ultimately, this method can be applied to explore the temporal scale of ecological processes based on movement.