A New Adaptive Encoder-Decoder Model for IoT Sensor Data Compression and Reconstruction: AdaED-IoT
JOIV : International Journal on Informatics Visualization · 31.03.2026 · 10 (2) · 494
DOI: 10.62527/joiv.10.2.5241 ↗Kurz gefasst
Fachartikel in der Zeitschrift JOIV : International Journal on Informatics Visualization, online erschienen am 31.03.2026. Verfasst von Atheer Ahmed Kadhim und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).
Abstract (Originalsprache)
The expansion of the Internet of Things (IoT) has brought new challenges to communication bandwidth and energy consumption. This situation has led to the development of methods that reduce the amount of data without risking any data value. This not only poses challenges in compression but also in maintaining the accuracy of automated control and anomaly detection. Consider the variability and often irregularities in sensor behavior. Therefore, this paper proposes a new adaptive encoding-decoder model for the compression and reconstruction of IoT sensor data: AdaED-IoT. It adjusts the recent performance of multiple sensing modes based on their characteristics and noise characteristics. By fine-tuning compression strategies to fit the statistical structure of the data, AdaED-IoT effectively regionalizes changes in indoor signals. We evaluate the performance of AdaED-IoT using two datasets: the first contains humidity, light, and voltage sensor values monitored by Intel Labs. The second dataset combines particulate matter (PM10, PM2.5) concentrations with atmospheric pressure data from the air quality platform. In both cases, AdaED-IoT outperformed the baseline multivariate dimensional reduction (MDR) approach, successfully achieving an error reduction rate of 32 times the mean squared error, or more than 98%.
Zitieren
APA
Kadhim, A. A., Wahid, N., & Alduais, N. A. M. (2026). A New Adaptive Encoder-Decoder Model for IoT Sensor Data Compression and Reconstruction: AdaED-IoT. JOIV : International Journal on Informatics Visualization, 10(2), 494. https://doi.org/10.62527/joiv.10.2.5241
Vancouver
Kadhim AA, Wahid N, Alduais NAM. A New Adaptive Encoder-Decoder Model for IoT Sensor Data Compression and Reconstruction: AdaED-IoT. JOIV : International Journal on Informatics Visualization. 2026;10(2):494. doi:10.62527/joiv.10.2.5241
BibTeX
@article{Kadhim2026,
author = {Kadhim, Atheer Ahmed and Wahid, Norfaradilla and Alduais, Nayef Abdulwahab Mohammed},
title = {A New Adaptive Encoder-Decoder Model for IoT Sensor Data Compression and Reconstruction: AdaED-IoT},
journal = {JOIV : International Journal on Informatics Visualization},
year = {2026},
volume = {10},
number = {2},
pages = {494},
doi = {10.62527/joiv.10.2.5241}
}
EUVIMED