Please use this identifier to cite or link to this item:
https://doi.org/10.21256/zhaw-29611
Publication type: | Conference paper |
Type of review: | Peer review (publication) |
Title: | AVOC : history-aware data fusion for reliable IoT analytics |
Authors: | Gkikopoulos, Panagiotis Kropf, Peter Schiavoni, Valerio Spillner, Josef |
et. al: | No |
DOI: | 10.1145/3564695.3564772 10.21256/zhaw-29611 |
Proceedings: | Proceedings of the 23rd International Middleware Conference Industrial Track |
Conference details: | 23rd ACM/IFIP International Middleware Conference (Middleware), Québec City, Canada, 7-11 November 2022 |
Issue Date: | 22-Nov-2022 |
Publisher / Ed. Institution: | ACM |
ISBN: | 9781450399173 |
Language: | English |
Subjects: | Voting algorithm; Data quality; Data fusion; IoT |
Subject (DDC): | 005: Computer programming, programs and data |
Abstract: | IoT systems rely on collected data to operate autonomously and generate insights. Such systems commonly produce redundant measurements, which can be insufficient to mitigate complex data disagreements. We believe a well-defined process to achieve internal ground truth through fusion is needed. Leveraging two case studies, we show how sensor data fusion with variants of history-aware voting can help to reconcile observations. We contribute a specification scheme with unified format to define the parameters and characteristics of a particular voting scenario, supporting reliable decision-making. Finally, we deploy and evaluate a novel method of bootstrapping historical records of sensor modules using a clustering algorithm. This method boosts the convergence of the measurements by 4x. |
URI: | https://digitalcollection.zhaw.ch/handle/11475/29611 |
Fulltext version: | Accepted version |
License (according to publishing contract): | Licence according to publishing contract |
Departement: | School of Engineering |
Organisational Unit: | Institute of Computer Science (InIT) |
Appears in collections: | Publikationen School of Engineering |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
2022_Gkikopoulos-etal_AVOC-history-aware-data-fusion-reliable-IoT-analytics.pdf | Accepted Version | 623.95 kB | Adobe PDF | View/Open |
Show full item record
Gkikopoulos, P., Kropf, P., Schiavoni, V., & Spillner, J. (2022, November 22). AVOC : history-aware data fusion for reliable IoT analytics. Proceedings of the 23rd International Middleware Conference Industrial Track. https://doi.org/10.1145/3564695.3564772
Gkikopoulos, P. et al. (2022) ‘AVOC : history-aware data fusion for reliable IoT analytics’, in Proceedings of the 23rd International Middleware Conference Industrial Track. ACM. Available at: https://doi.org/10.1145/3564695.3564772.
P. Gkikopoulos, P. Kropf, V. Schiavoni, and J. Spillner, “AVOC : history-aware data fusion for reliable IoT analytics,” in Proceedings of the 23rd International Middleware Conference Industrial Track, Nov. 2022. doi: 10.1145/3564695.3564772.
GKIKOPOULOS, Panagiotis, Peter KROPF, Valerio SCHIAVONI und Josef SPILLNER, 2022. AVOC : history-aware data fusion for reliable IoT analytics. In: Proceedings of the 23rd International Middleware Conference Industrial Track. Conference paper. ACM. 22 November 2022. ISBN 9781450399173
Gkikopoulos, Panagiotis, Peter Kropf, Valerio Schiavoni, and Josef Spillner. 2022. “AVOC : History-Aware Data Fusion for Reliable IoT Analytics.” Conference paper. In Proceedings of the 23rd International Middleware Conference Industrial Track. ACM. https://doi.org/10.1145/3564695.3564772.
Gkikopoulos, Panagiotis, et al. “AVOC : History-Aware Data Fusion for Reliable IoT Analytics.” Proceedings of the 23rd International Middleware Conference Industrial Track, ACM, 2022, https://doi.org/10.1145/3564695.3564772.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.