Please use this identifier to cite or link to this item:
https://doi.org/10.21256/zhaw-30872
Publication type: | Conference paper |
Type of review: | Peer review (abstract) |
Title: | Performance examination of symbolic aggregate approximation in IoT applications |
Authors: | Veljanovska, Suzana Doran, Hans Dermot |
et. al: | No |
DOI: | 10.21256/zhaw-30872 |
Proceedings: | Proceedings of the 2024 Embedded World Conference |
Page(s): | 468 |
Pages to: | 472 |
Conference details: | Embedded World Conference, Nuremberg, Germany, 9-11 April 2024 |
Issue Date: | May-2024 |
Publisher / Ed. Institution: | WEKA |
ISBN: | 978-3-645-50199-6 |
Language: | English |
Subjects: | Symbolic aggregate approximation; Low energy; IoT; Shape recognition; Anomaly detection |
Subject (DDC): | 006: Special computer methods |
Abstract: | Symbolic Aggregate approXimation (SAX) is a common dimensionality reduction approach for time-series data which has been employed in a variety of domains, including classification and anomaly detection in time-series data. Domains also include shape recognition where the shape outline is converted into time-series data forinstance epoch classification of archived arrowheads. In this paper we propose a dimensionality reduction and shape recognition approach based on the SAX algorithm, an application which requires responses on cost efficient, IoT-like, platforms. The challenge is largely dealing with the computational expense of the SAX algorithm in IoT-like applications, from simple time-series dimension reduction through shape recognition. The approach is based on lowering the dimensional space while capturing and preserving the most representative features of the shape. We present three scenarios of increasing computational complexity backing up our statements with measurement of performance characteristics. |
URI: | https://cloud.wekanet.de/s/6WxYxPEryHgDSdY?dir=undefined&openfile=1763799 https://digitalcollection.zhaw.ch/handle/11475/30872 |
Fulltext version: | Published version |
License (according to publishing contract): | Licence according to publishing contract |
Departement: | School of Engineering |
Organisational Unit: | Institute of Embedded Systems (InES) |
Published as part of the ZHAW project: | Reconfigurable Heterogeneous Highly Parallel Processing Platform for safe and secure AI (REBECCA) |
Appears in collections: | Publikationen School of Engineering |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
2024_Veljanovska-Doran_Performance-examination-symbolic-aggregate-approximation.pdf | 643.42 kB | Adobe PDF | View/Open |
Show full item record
Veljanovska, S., & Doran, H. D. (2024). Performance examination of symbolic aggregate approximation in IoT applications [Conference paper]. Proceedings of the 2024 Embedded World Conference, 468–472. https://doi.org/10.21256/zhaw-30872
Veljanovska, S. and Doran, H.D. (2024) ‘Performance examination of symbolic aggregate approximation in IoT applications’, in Proceedings of the 2024 Embedded World Conference. WEKA, pp. 468–472. Available at: https://doi.org/10.21256/zhaw-30872.
S. Veljanovska and H. D. Doran, “Performance examination of symbolic aggregate approximation in IoT applications,” in Proceedings of the 2024 Embedded World Conference, May 2024, pp. 468–472. doi: 10.21256/zhaw-30872.
VELJANOVSKA, Suzana und Hans Dermot DORAN, 2024. Performance examination of symbolic aggregate approximation in IoT applications. In: Proceedings of the 2024 Embedded World Conference [online]. Conference paper. WEKA. Mai 2024. S. 468–472. ISBN 978-3-645-50199-6. Verfügbar unter: https://cloud.wekanet.de/s/6WxYxPEryHgDSdY?dir=undefined&openfile=1763799
Veljanovska, Suzana, and Hans Dermot Doran. 2024. “Performance Examination of Symbolic Aggregate Approximation in IoT Applications.” Conference paper. In Proceedings of the 2024 Embedded World Conference, 468–72. WEKA. https://doi.org/10.21256/zhaw-30872.
Veljanovska, Suzana, and Hans Dermot Doran. “Performance Examination of Symbolic Aggregate Approximation in IoT Applications.” Proceedings of the 2024 Embedded World Conference, WEKA, 2024, pp. 468–72, https://doi.org/10.21256/zhaw-30872.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.