Indexing Multivariate Mobile Data through Spatio-Temporal Event Detection and Clustering
Mobile and wearable devices are capable of quantifying user behaviors based on their contextual sensor data. However, few indexing and annotation mechanisms are available, due to difficulties inherent in raw multivariate data types and the relative sparsity of sensor data. These issues have slowed t...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-01-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/19/3/448 |
id |
doaj-2ce3cf49f6944af7830186f803d01004 |
---|---|
record_format |
Article |
spelling |
doaj-2ce3cf49f6944af7830186f803d010042020-11-24T21:59:53ZengMDPI AGSensors1424-82202019-01-0119344810.3390/s19030448s19030448Indexing Multivariate Mobile Data through Spatio-Temporal Event Detection and ClusteringReza Rawassizadeh0Chelsea Dobbins1Mohammad Akbari2Michael Pazzani3Department of Computer Science, University of Rochester, NY 14620, USAFaculty of Engineering, Architecture and Information Technology, University of Queensland, Brisbane 4072, AustraliaDepartment of Computer Science, University College London, London WC1E 6BT, UKDepartment of Computer Science, University of California, Riverside, CA 92507, USAMobile and wearable devices are capable of quantifying user behaviors based on their contextual sensor data. However, few indexing and annotation mechanisms are available, due to difficulties inherent in raw multivariate data types and the relative sparsity of sensor data. These issues have slowed the development of higher level human-centric searching and querying mechanisms. Here, we propose a pipeline of three algorithms. First, we introduce a spatio-temporal event detection algorithm. Then, we introduce a clustering algorithm based on mobile contextual data. Our spatio-temporal clustering approach can be used as an annotation on raw sensor data. It improves information retrieval by reducing the search space and is based on searching only the related clusters. To further improve behavior quantification, the third algorithm identifies contrasting events <i>within</i>a cluster content. Two large real-world smartphone datasets have been used to evaluate our algorithms and demonstrate the utility and resource efficiency of our approach to <i>search</i>.https://www.mdpi.com/1424-8220/19/3/448spatio-temporalclusteringevent detectionmobile sensing: contrast behavior mininghuman behavior |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Reza Rawassizadeh Chelsea Dobbins Mohammad Akbari Michael Pazzani |
spellingShingle |
Reza Rawassizadeh Chelsea Dobbins Mohammad Akbari Michael Pazzani Indexing Multivariate Mobile Data through Spatio-Temporal Event Detection and Clustering Sensors spatio-temporal clustering event detection mobile sensing: contrast behavior mining human behavior |
author_facet |
Reza Rawassizadeh Chelsea Dobbins Mohammad Akbari Michael Pazzani |
author_sort |
Reza Rawassizadeh |
title |
Indexing Multivariate Mobile Data through Spatio-Temporal Event Detection and Clustering |
title_short |
Indexing Multivariate Mobile Data through Spatio-Temporal Event Detection and Clustering |
title_full |
Indexing Multivariate Mobile Data through Spatio-Temporal Event Detection and Clustering |
title_fullStr |
Indexing Multivariate Mobile Data through Spatio-Temporal Event Detection and Clustering |
title_full_unstemmed |
Indexing Multivariate Mobile Data through Spatio-Temporal Event Detection and Clustering |
title_sort |
indexing multivariate mobile data through spatio-temporal event detection and clustering |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2019-01-01 |
description |
Mobile and wearable devices are capable of quantifying user behaviors based on their contextual sensor data. However, few indexing and annotation mechanisms are available, due to difficulties inherent in raw multivariate data types and the relative sparsity of sensor data. These issues have slowed the development of higher level human-centric searching and querying mechanisms. Here, we propose a pipeline of three algorithms. First, we introduce a spatio-temporal event detection algorithm. Then, we introduce a clustering algorithm based on mobile contextual data. Our spatio-temporal clustering approach can be used as an annotation on raw sensor data. It improves information retrieval by reducing the search space and is based on searching only the related clusters. To further improve behavior quantification, the third algorithm identifies contrasting events <i>within</i>a cluster content. Two large real-world smartphone datasets have been used to evaluate our algorithms and demonstrate the utility and resource efficiency of our approach to <i>search</i>. |
topic |
spatio-temporal clustering event detection mobile sensing: contrast behavior mining human behavior |
url |
https://www.mdpi.com/1424-8220/19/3/448 |
work_keys_str_mv |
AT rezarawassizadeh indexingmultivariatemobiledatathroughspatiotemporaleventdetectionandclustering AT chelseadobbins indexingmultivariatemobiledatathroughspatiotemporaleventdetectionandclustering AT mohammadakbari indexingmultivariatemobiledatathroughspatiotemporaleventdetectionandclustering AT michaelpazzani indexingmultivariatemobiledatathroughspatiotemporaleventdetectionandclustering |
_version_ |
1725846695468597248 |