Details of the Researcher

PHOTO

Hidefumi Kamozawa
Section
Graduate School of Engineering
Job title
Assistant Professor
Degree

  • Doctor of Engineering (Akita University)

e-Rad No.
01043728

Education 2

  • Akita University

    2023/04 - 2026/03

  • Akita University　Graduate School of Engineering Science

    2021/04 - 2023/03

Professional Memberships 3

  • 米国電気電子工学会(IEEE)

  • 電気学会

  • 日本音響学会

Research Interests 5

  • Acoustic Signal Processing

  • Medical System Engineering

  • Musical Acoustics

  • Biomedical Signal Processing

  • Signal Processing

Research Areas 3

  • Informatics / Biological, health, and medical informatics /

  • Informatics / Perceptual information processing / Musical Signal Processing

  • Life sciences / Biomedical engineering /

Awards 6

  1. 令和7年度学生表彰 奨励賞（学術研究活動）

    2026/03　秋田大学

  2. 第6回とめ研究所若手研究者懸賞論文 優秀賞

    2025/11　株式会社とめ研究所　機械学習と誤り訂正を用いた長時間心電図からの心房細動検出

  3. 電気学会東北支部長賞（優秀論文賞）

    2025/04　一般社団法人 電気学会　A Detection Method of Atrial Fibrillation from 24-hour Holter-ECG Using CNN

  4. 若手研究者優秀論文賞

    2023/11　日本音響学会　楽器ごとの周波数特性を考慮した特徴抽出と再帰型NNによるドラム演奏楽音の認識の試み

  5. 理工学研究科長表彰

    2022/03　秋田大学

  6. The Best Paper Prize

    2021/12　IEEE Sendai Section　A Study on Detecting Atrial Fibrillation Using CNN from Long-Term Holter-ECG

Show all ︎Show 5

Papers 10

  1. Detection of Weld Root Crack in Metal Plates with Convolutional Neural Network Peer-reviewed

    Hidefumi Kamozawa, Makoto Fukuda, Motoshi Tanaka

    IEEJ Transactions on Electrical and Electronic Engineering (Early view)　22　(1)　2027/01

    DOI： 10.1002/tee.70398 　

  2. Pilot Study on Frailty Detection Using Non‐wearable Gait Sensing Peer-reviewed

    Hidefumi Kamozawa, Takayoshi Yamahira, Tomihiro Utsumi, Motoshi Tanaka, Yu Kume, Katsutoshi Saito

    IEEJ Transactions on Electrical and Electronic Engineering　21　(6)　937-939　2026/06

    DOI： 10.1002/tee.70205 　

    ISSN： 1931-4973 1931-4981

    More details Close

    <jats:p> To develop a system for early frailty detection, extracting frailty‐related parameters through gait sensing using non‐wearable sensors was investigated. Gait parameters, such as step length, were obtained using passive infrared sensors and footstep sounds were recorded using a floor‐mounted microphone. Fifty‐seven subjects were classified into robust, pre‐frail, and frail groups based on the Japan Cardiovascular Health Study (J‐CHS) criteria, and the parameters were compared across groups to assess their association with frailty. Frailty detection was attempted using the <jats:italic>k</jats:italic> ‐nearest‐neighbor algorithm with the extracted parameters, resulting in an F1‐score of up to 80.4%. These results suggest the feasibility of frailty detection using non‐wearable gait sensing. © 2025 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC. </jats:p>

  3. Error Correction in Atrial Fibrillation Detection Using Viterbi Algorithm Peer-reviewed

    Hidefumi Kamozawa, Motoshi Tanaka

    IEEJ Transactions on Electrical and Electronic Engineering　21　(6)　934-936　2026/06

    DOI： 10.1002/tee.70203 　

    ISSN： 1931-4973 1931-4981

    More details Close

    <jats:p>Error correction in the results of atrial fibrillation (AF) detected with a convolutional neural network (CNN) classifier was investigated using the Viterbi algorithm. State transition probabilities were calculated using annotations of Holter ECG recordings obtained from 60 subjects. Errors in the detection results were corrected based on the Viterbi algorithm using the pre‐calculated state transition probabilities and the emission probabilities output by the CNN classifier. As a result, the detection results were appropriately corrected, and the detection performance was improved, demonstrating the effectiveness of the proposed method. © 2025 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.</jats:p>

  4. Method to Detect Only Registered Pedestrian Using Out‐of‐Distribution Detection and CNN Classifier with Footsteps Peer-reviewed

    Hidefumi Kamozawa, Takayoshi Yamahira, Motoshi Tanaka

    IEEJ Transactions on Electrical and Electronic Engineering　20　(10)　1666-1668　2025/10/01

    DOI： 10.1002/tee.70036 　

    ISSN： 1931-4973 1931-4981

    More details Close

    <jats:p>A method for detecting registered pedestrians using footstep sounds is investigated. Pre‐trained persons were classified based on out‐of‐distribution detection and subsequently identified using a convolutional neural network classifier. As a training feature, the log mel‐spectrogram is calculated by a time–frequency analysis of the footstep sounds. The evaluation test results with newly prepared footsteps indicated the feasibility of the proposed method. © 2025 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.</jats:p>

  5. Atrial Fibrillation Detection from Holter ECG Using Hybrid CNN‒LSTM Model and P/f-wave Identification Peer-reviewed

    Hidefumi KAMOZAWA, Motoshi TANAKA

    Advanced Biomedical Engineering　14　46-53　2025/02

    DOI： 10.14326/abe.14.46 　

    ISSN： 2187-5219

  6. Estimation of magnetic field sources on printed circuit boards using object detection by machine learning of magnetic near-field information Peer-reviewed

    Yusuke Sato, Sho Muroga, Hidefumi Kamozawa, Motoshi Tanaka

    Transaction of the Magnetics Society of Japan Special issues　9　(1)　2025

    DOI： 10.20819/msjtmsj.25TR908 　

    ISSN： 2432-0471

  7. Detection of Atrial Fibrillation from Holter ECG using 1D Convolutional Neural Network after Arrhythmia Extraction Peer-reviewed

    Kamozawa, H., Tanaka, M.

    Advanced Biomedical Engineering　13　2024

    DOI： 10.14326/abe.13.19 　

    ISSN： 2187-5219

  8. An Estimation Method of Magnetic Coupling Coefficient Between Two Microstrip Lines Using Machine Learning of Near-Field Information Peer-reviewed

    Yusuke Sato, Sho Muroga, Hidefumi Kamozawa, Motoshi Tanaka

    IEEE Transactions on Magnetics　59　(11)　2023/11

    DOI： 10.1109/TMAG.2023.3302907 　

    ISSN： 1941-0069 0018-9464

  9. A Detection Method of Atrial Fibrillation from 24-hour Holter-ECG Using CNN Peer-reviewed

    Kamozawa, H., Muroga, S., Tanaka, M.

    IEEJ Transactions on Electrical and Electronic Engineering　18　(4)　577-582　2023/04

    Publisher: Wiley

    DOI： 10.1002/tee.23756 　

    ISSN： 1931-4981 1931-4973

  10. Size Parameters Classification of Loop Current Model of PCB Traces by CNN of Magnetic Near-Field Distribution

    Sho Muroga, Taichi Sasaki, Hidefumi Kamozawa, Yusuke Sato, Takahiro Mikami, Motoshi Tanaka

    2022 ASIA-PACIFIC MICROWAVE CONFERENCE (APMC)　904-906　2022

Show all ︎Show first 5

Misc. 1

  1. A Design Method for Electromagnetic Noise Suppression Sheets through the Combination of Electromagnetics-based Models and AI

    Sho Muroga, Takahiro Mikami, Hidefumi Kamozawa, Motoshi Tanaka

    109　(3)　175-180　2026/03

Presentations 36

  1. Investigation on Lung Disease Detection Using Machine Learning of Flow-Volume Curve

    Ryoma Shibata, Hidefumi Kamozawa, Motoshi Tanaka, Tsubasa Matsuo, Kazuhiro Imai

    The 13th IIAE International Conference on Intelligent Systems and Image Processing　2026/09/10

  2. Investigation on Registered Pedestrian Detection from Footsteps Using Convolutional Neural Network

    Taishu Tonooka, Hidefumi Kamozawa, Motoshi Tanaka

    The 13th IIAE International Conference on Intelligent Systems and Image Processing　2026/09/10

  3. ECG Generation Using Diffusion Model Conditioned on R-wave Positions and Its Quality Evaluation by MMD Distance

    Hidefumi Kamozawa, Motoshi Tanaka

    The Annual Meeting of The Institute of Electrical Engineers of Japan　2026/03/13

  4. Estimation of Noise Sources on Printed Circuit Boards Using Machine Learning of Magnetic Near-field Information Invited

    Motoshi Tanaka, Hidefumi Kamozawa

    MWE 2025 (2025 Microwave Workshops and Exhibition)　2025/11/26

  5. A Study on Detecting Weld Root Crack in Metal Plates Using Machine Learning

    Hidefumi Kamozawa, Makoto Fukuda, Motoshi Tanaka

    The 3rd NDE 4.0 Symposium　2025/10/28

  6. Generation of Atrial Fibrillation Waveform for Data Augmentation by Using Denoising Diffusion Probabilistic Model

    H. Kamozawa, M. Tanaka

    The 10th International Conference on Materials Engineering for Resources (ICMR2025)　2025/10/25

  7. Study on Acquisition of Cardiopulmonary Sound and Anomaly Detection Using Small Microphone

    Motoshi Tanaka, Ryoga Sasaki, Hidefumi Kamozawa

    Technical Committee on ME and Bio Cybernetics (MBE)　2025/10/18

  8. A study on error correction of atrial fibrillation detection by Viterbi decoding

    Hidefumi Kamozawa, Motoshi Tanaka

    2025 The Institute of Electronics, Information and Communication Engineers General Conference　2025/03/25

  9. 近傍磁界情報の機械学習を用いたプリント配線板上の磁界源推定方法に関する検討

    佐藤雄亮, 室賀 翔, 鴨澤秀郁, 田中元志

    IEEE EMCS仙台チャプタ 学生研究発表会　2025/02/20

  10. 非ウェアラブルセンサを用いたフレイル検出に関する一検討

    山平崇喜, 鴨澤秀郁, 田中元志, 内海富博, 久米 裕, 齊藤勝俊

    第58回 日本生体医工学会東北支部大会　2024/12/14

  11. 小型マイクロフォンを用いた異常心音の検出に関する一検討

    佐々木涼冴, 鴨澤秀郁, 田中元志

    第58回 日本生体医工学会東北支部大会　2024/12/14

  12. ホルター心電図を対象とした不整脈分類器の追加学習による心室細動の検出に関する一検討

    鴨澤秀郁, 田中元志

    第58回 日本生体医工学会東北支部大会　2024/12/14

  13. 深層学習を用いた未知歩行者を含む足音からの個人識別に関する検討

    鴨澤秀郁, 山平崇喜, 仝 黄河, 田中元志

    光環境DX研究学会 第3回年次学術研究発表会　2024/12/05

  14. Drum Sound Recognition using Machine Learning of Features Based on Harmonic Structure

    Hidefumi Kamozawa, Motoshi Tanaka

    2024/10/05

  15. Atrial Fibrillation Detection from Holter-ECG by Using Hybrid CNN–LSTM Model and P/f-wave Identification

    H. Kamozawa, M. Tanaka

    Biomedical Engineering Symposium 2024　2024/09/13

  16. Estimation of magnetic field sources on printed circuit boards using object detection by machine learning of magnetic near-field information

    Yusuke Sato, Sho Muroga, Hidefumi Kamozawa, Motoshi Tanaka

    The 48th Annual Conference on MAGNETICS in Japan　2024/09

  17. A study on extracting position of magnetic field sources on printed circuit boards using loop current model and object detection method

    Yusuke Sato, Sho Muroga, Hidefumi Kamozawa, Motoshi Tanaka

    The 38th JIEP Annual Conference　2024

  18. A study on chord recognition of musical guitar sound using onset detection

    Shun Kondo, Hidefumi Kamozawa, Motoshi Tanaka

    2023/11/25

  19. A study on drum recognition from musical sound by using recursive neural network and feature extraction considering frequency characteristics of each instrument

    Hidefumi Kamozawa, Motoshi Tanaka

    2023/11/25

  20. A Study on Detecting Atrial Fibrillation with P/f-wave Identification by CNN

    Hidefumi Kamozawa, Sho Muroga, Motoshi Tanaka

    The Annual Meeting of The Institute of Electrical Engineers of Japan　2023/03/17

  21. An Estimation Method of Magnetic Coupling Coefficient Between Two Microstrip Lines Using Machine Leaning of Near Field Information

    Y. Sato, S. Muroga, H. Kamozawa, M. Tanaka

    2023 IEEE International Magnetics Conference　2023

  22. フレイル検出のための歩行時音響信号解析による特徴抽出

    山平崇喜, 鴨澤秀郁, 室賀 翔, 田中元志, 齊藤勝俊, 内海富博, 久米 裕

    NPO法人 光環境DX研究学会　2023

  23. A Detection Method of Atrial Fibrillation from Holter ECG Using 1D CNN after Arrhythmia Extraction

    H. Kamozawa, M. Tanaka

    2023

  24. 近傍磁界測定と1次元CNNを用いた平行2線MSL間の磁気結合係数の推定に関する一検討

    佐藤雄亮, 室賀翔, 鴨澤秀郁, 田中元志

    IEEE EMCS仙台チャプタ 学生研究発表会　2023

  25. A Study on Onset Detection and Chord Recognition of Sound Played by Guitar

    Shun Kondo, Hidefumi Kamozawa, Sho Muroga, Motoshi Tanaka

    Technical Committee on Musical Acoustics　2022/12/17

  26. A Study on Chord Recognition by Extracting Tone with Its Harmonics

    Hidefumi Kamozawa, Sho Muroga, Motoshi Tanaka

    Technical Committee on;Musical Acoustics　2022/12/17

  27. An estimation of magnetic coupling coefficient between parallel two MSLs using machine leaning of near field information

    Yusuke Sato, Sho Muroga, Hidefumi Kamozawa, Motoshi Tanaka

    IEICE Technical Report　2022/10/13

  28. An investigation on size parameter detection of loop current model by machine learning of magnetic near-field map of MSL

    Taichi Sasaki, Sho Muroga, Hidefumi Kamozawa, Motoshi Tanaka

    Spring Annual Meeting of the Japan Institute of Electronics Packaging　2022/03/25

  29. Size Parameters Classification of Loop Current Model of PCB Traces by CNN of Magnetic Near-Field Distribution

    S. Muroga, T. Sasaki, H. Kamozawa, Y. Sato, T. Mikami, M. Tanaka

    2022 Asia-Pacific Microwave Conference (APMC 2022)　2022

  30. フレイル検出のための歩行時音響信号の解析

    山平祟喜, 鴨澤秀郁, 室賀翔, 田中元志, 齊藤勝俊, 内海富博, 久米裕

    NPO法人 光環境DX研究学会　2022

  31. 近傍磁界情報の機械学習による平行配線のループ電流モデル化に関する一検討

    佐々木太地, 室賀翔, 鴨澤秀郁, 田中元志

    2022年度 電気関係学会東北支部連合大会　2022

  32. 規則的な心拍間隔をもつ心房細動の検出に関する一検討

    鴨澤秀郁, 室賀翔, 田中元志

    2022年度 電気関係学会東北支部連合大会　2022

  33. A Study on Detecting Atrial Fibrillation by Identifying Its ECG Waveform Features with CNN

    H. Kamozawa, S. Muroga, M. Tanaka

    2022

  34. 心電図の深層学習を用いた心房細動の検出率向上に関する一検討

    鴨澤秀郁, 田中元志, 室賀翔

    第55回 日本生体医工学会東北支部大会　2021/12/11

  35. A Study on Detecting Atrial Fibrillation Using CNN from Long-Term Holter-ECG

    H. Kamozawa, M. Tanaka, S. Muroga

    2021/08/23

  36. A Study on Arrhythmia Extraction and Atrial Fibrillation Detection from Long-Term Holter-ECG

    H. Kamozawa, M. Tanaka, S. Muroga

    The 9th International Conference on Materials Engineering for Resources (ICMR2021Akita)　2021

Show all Show first 5

Industrial Property Rights 2

  1. 心電図からの心房細動識別方法、心房細動の識別装置

    田中元志, 鴨澤秀郁

    Property Type: Patent

  2. 心電図からの心房細動検出方法

    田中元志, 鴨澤秀郁

    Property Type: Patent

Research Projects 1

  1. 夜間睡眠時の近赤外映像を用いた非接触不整脈モニタリングシステムの開発

    鴨澤 秀郁

    Offer Organization: 日本学術振興会

    System: 科学研究費助成事業

    Category: 研究活動スタート支援

    Institution: 東北大学

    2026/07 - 2028/03