EUVIMEDEUVIMED entdecken
Crossref

Multi-class Classification of Auscultatory Sounds Based on Spectrograms Using Edge Devices

Yuta KOYANAGI, Naoki UETA, Kaito YAMADA, Shunsuke KOMIZUNAI, Atsushi KONNO

Transactions of the Society of Instrument and Control Engineers · 2026 · 62 (7) · 263-268

DOI: 10.9746/sicetr.62.263 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Transactions of the Society of Instrument and Control Engineers, 2026. Verfasst von Yuta KOYANAGI und 4 weiteren Autor:innen. Die Arbeit nennt 9 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper proposes an edge-computing-based automated auscultation system for real-time lung sound classification to support nursing activities such as tracheal suctioning. While conventional AI-driven auscultation methods frequently depend on offline analysis, the proposed system performs the entire pipeline — from audio processing to neural network inference — locally on a Sony Spresense edge device. To capture temporal variations, spectrogram images are employed as input features. The system's performance was evaluated through binary, five-class, and seven-class classification tasks. Experimental results indicate that although the system achieves a high accuracy of approximately 95% in offline classification, the performance significantly decreases during real-time inference on the edge device. Furthermore, while the identification of various lung sounds including adventitious sounds was achieved, a substantial decline in accuracy occurred as the number of classification categories increased. These findings demonstrate the feasibility of real-time edge-AI auscultation while simultaneously highlighting the trade-offs between computational resource constraints and classification complexity. This autonomous system establishes a foundation for objective evaluation in home nursing, although further optimization remains necessary to maintain high precision in complex real-time environments.

Zitieren

APA

KOYANAGI, Y., UETA, N., YAMADA, K., KOMIZUNAI, S., & KONNO, A. (2026). Multi-class Classification of Auscultatory Sounds Based on Spectrograms Using Edge Devices. Transactions of the Society of Instrument and Control Engineers, 62(7), 263-268. https://doi.org/10.9746/sicetr.62.263

Vancouver

KOYANAGI Y, UETA N, YAMADA K, KOMIZUNAI S, KONNO A. Multi-class Classification of Auscultatory Sounds Based on Spectrograms Using Edge Devices. Transactions of the Society of Instrument and Control Engineers. 2026;62(7):263-268. doi:10.9746/sicetr.62.263

BibTeX
@article{KOYANAGI2026,
  author = {KOYANAGI, Yuta and UETA, Naoki and YAMADA, Kaito and KOMIZUNAI, Shunsuke and KONNO, Atsushi},
  title = {Multi-class Classification of Auscultatory Sounds Based on Spectrograms Using Edge Devices},
  journal = {Transactions of the Society of Instrument and Control Engineers},
  year = {2026},
  volume = {62},
  number = {7},
  pages = {263--268},
  doi = {10.9746/sicetr.62.263}
}
Kostenlos starten →