A Comparative Analysis of Windowing Approaches in Dense Sensing Environments

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Windowing is a technique employed within dense sensing environments to extract relevant features from sensor data streams. Among the established approaches of Explicit, Time-based and Sensor-Event based windowing, Dynamic windowing approaches are beginning to emerge. These dynamic approaches claim to address the inherent shortcomings of the aforementioned established approaches by determining the appropriate window length for live sensor data streams, in realtime thereby offering the potential to optimize and increase the recognition of these sensor represented activities. Beyond these potential benefits, dynamic approaches could also support anomaly detection by actively uncovering new unknown window patterns within a trained model. This paper presents findings from a systematic study, which utilizes data from a single source dataset, towards benchmarking and comparing more traditional windowing approaches against a dynamic windowing approach.
Original languageEnglish
Title of host publicationProceedings of The International Conference on Ubiquitous Computing and Ambient ‪Intelligence‬‬)
PublisherMDPI AG
Number of pages6
Volume2
Edition19
DOIs
Publication statusPublished - 17 Oct 2018
Event12th International Conference on Ubiquitous Computing & Ambient Intelligence - Punta Cana, Dominican Republic
Duration: 4 Dec 20187 Dec 2018
http://mamilab.esi.uclm.es/ucami2018/

Publication series

NameProceedings of The International Conference on Ubiquitous Computing and Ambient ‪Intelligence‬‬)
PublisherMDPI AG
ISSN (Electronic)2504-3900

Conference

Conference12th International Conference on Ubiquitous Computing & Ambient Intelligence
Abbreviated titleUCAmI 2018
CountryDominican Republic
CityPunta Cana
Period4/12/187/12/18
Internet address

Keywords

  • Windowing
  • Segmentation
  • Human Activity Recognition
  • smart home
  • dynamic
  • sensor event

Fingerprint Dive into the research topics of 'A Comparative Analysis of Windowing Approaches in Dense Sensing Environments'. Together they form a unique fingerprint.

  • Cite this

    Quigley, B., Donnelly, M., Moore, G., & Galway, L. (2018). A Comparative Analysis of Windowing Approaches in Dense Sensing Environments. In Proceedings of The International Conference on Ubiquitous Computing and Ambient ‪Intelligence‬‬) (19 ed., Vol. 2). (Proceedings of The International Conference on Ubiquitous Computing and Ambient ‪Intelligence‬‬)). MDPI AG. https://doi.org/10.3390/proceedings2191245