The Spatiotemporal Data Reduction (STDR): An Adaptive IoT-based Data Reduction Approach
Mahmoud, Dina F.; Sherin M. Moussa; Badr, Nagwa;
Abstract
Due to the high increasing number and diversity of data sources, as well as the associated continuous flow of data, the Internet of Things (IoT) reveal several challenges, including the heavy consumption of network energy, processing resources and data storage. This urges to effective IoT data reduction before processing. Most of the current approaches for IoT data reduction are domain-dependent that fail to consider the spatiotemporal feature of IoT data, affecting data significance after reduction. In this paper, we propose the domain-independent Spatiotemporal Data Reduction (STDR) approach for IoT-based systems. STDR can be adapted to any computing model, in which it manages (i) the spatial feature of IoT data as per a clustering technique, and (ii) the temporal feature by eliminating the highly correlated data on a specific time basis. The proposed approach is examined on multiple real-world datasets. The obtained results demonstrate that the proposed STDR approach efficiently reduces IoT data size by 54%, with an average accuracy of 95% while handling IoT data spatiality and temporality features.
Other data
Title | The Spatiotemporal Data Reduction (STDR): An Adaptive IoT-based Data Reduction Approach | Authors | Mahmoud, Dina F.; Sherin M. Moussa ; Badr, Nagwa | Keywords | Data Cleansing;Data Clustering;Data Reduction;Internet of Things;IoT | Issue Date | 1-Jan-2021 | Conference | Proceedings - 2021 IEEE 10th International Conference on Intelligent Computing and Information Systems, ICICIS 2021 | ISBN | 9781665440769 | DOI | 10.1109/ICICIS52592.2021.9694199 | Scopus ID | 2-s2.0-85123646006 |
Recommend this item
Similar Items from Core Recommender Database
Items in Ain Shams Scholar are protected by copyright, with all rights reserved, unless otherwise indicated.