EUVIMEDEUVIMED entdecken
Crossref

Multisensor Fusion Using Composite Tsetlin Machine With Adaptive Feature Bank Selection

Thrishank Hesaraghatta Shivakumar, Bethi Pardhasaradhi, Srinivas Boppu, Ole-Christoffer Granmo, Linga Reddy Cenkeramaddi

IEEE Sensors Journal · 01.06.2026 · 26 (11) · 17210-17223

DOI: 10.1109/jsen.2026.3680022 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Sensors Journal, erschienen am 01.06.2026. Verfasst von Thrishank Hesaraghatta Shivakumar und 4 weiteren Autor:innen. Die Arbeit nennt 45 Literaturangaben. Gefördert von: Research Council of Norway Project Entitled CaReLearner: Causal Reasoning With Logical Interpretable Learning, Logic-Based Artificial Intelligence Everywhere: Tsetlin Machines in Hardware.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A wide range of applications relies on multisensor setups to enhance their perception and decision-making capabilities. These sensors generate raw time-series data that can be transformed into the frequency domain using feature banks such as mel frequency cepstral coefficients (MFCC), Chroma-STFT (C-STFT), and spectral descriptors. Most deep learning (DL) and machine learning (ML) models utilize these frequency-domain representations, typically in the form of numeric data or spectrogram images, to enhance their decision-making capabilities. However, interpretability, resource constraints, and inference time remain challenging in DL and ML algorithms. The Tsetlin machine (TM) is an energy-efficient alternative based on propositional logic. TM applications to multisensor classification and fusion remain largely unexplored. In this work, a novel multisensor fusion framework using composite-TM (Co-TM) is proposed, where each sensor’s time-series signals are converted into frequency-domain representations using several feature banks. The framework adaptively selects the best frequency-domain representation during the feature bank selection phase and performs sensor-level fusion during training. The feature bank selection is guided by the TM’s learning and delearning behaviors, while sensor-level fusion is achieved through a Co-TM framework. To monitor TM learning dynamics and adaptively select the desired feature bank for each sensor, we propose a set of metrics, including average accuracy, top-m accuracy, stability coefficient, and the slope of the accuracy curve. The proposed framework is validated using an industrial machine fault detection dataset (multisensor heterogeneous data) and a rotating machinery fault dataset (multisensor homogeneous data). The experimental results demonstrate that the proposed method achieves state-ofthe- art accuracy compared with ML, convolutional neural network (CNN) models, and TM models.

Förderung

  • Research Council of Norway Project Entitled CaReLearner: Causal Reasoning With Logical Interpretable Learning
  • Logic-Based Artificial Intelligence Everywhere: Tsetlin Machines in Hardware

Zitieren

APA

Shivakumar, T. H., Pardhasaradhi, B., Boppu, S., Granmo, O., & Cenkeramaddi, L. R. (2026). Multisensor Fusion Using Composite Tsetlin Machine With Adaptive Feature Bank Selection. IEEE Sensors Journal, 26(11), 17210-17223. https://doi.org/10.1109/jsen.2026.3680022

Vancouver

Shivakumar TH, Pardhasaradhi B, Boppu S, Granmo O, Cenkeramaddi LR. Multisensor Fusion Using Composite Tsetlin Machine With Adaptive Feature Bank Selection. IEEE Sensors Journal. 2026;26(11):17210-17223. doi:10.1109/jsen.2026.3680022

BibTeX
@article{Shivakumar2026,
  author = {Shivakumar, Thrishank Hesaraghatta and Pardhasaradhi, Bethi and Boppu, Srinivas and Granmo, Ole-Christoffer and Cenkeramaddi, Linga Reddy},
  title = {Multisensor Fusion Using Composite Tsetlin Machine With Adaptive Feature Bank Selection},
  journal = {IEEE Sensors Journal},
  year = {2026},
  volume = {26},
  number = {11},
  pages = {17210--17223},
  doi = {10.1109/jsen.2026.3680022}
}
Kostenlos starten →