陳 培基

機械知能システム学専攻助教
Ⅱ類(融合系)助教

学位

  • 工学博士, 電気通信大学, 2024年09月

研究キーワード

  • 生体信号計測・解析
  • ロボットハンド、義手
  • ヒューマン・ロボット・インターフェース

研究分野

  • 情報通信, ロボティクス、知能機械システム
  • 情報通信, ヒューマンインタフェース、インタラクション

経歴

  • 2024年10月 - 現在
    電気通信大学 機械知能システム学専攻、Ⅱ類(融合系) 助教

学歴

  • 2021年10月 - 2024年09月
    電気通信大学, 大学院情報理工学研究科, 機械知能システム学専攻
  • 2018年09月 - 2021年03月
    天津理工大学, 大学院電気・電子工学研究科, 制御科学・工学専攻, 中華人民共和国
  • 2014年09月 - 2018年06月
    天津理工大学, 自動化学部, 自動化学科, 中華人民共和国

受賞

  • 受賞日 2025年06月
    IEEE UR 2025 Program Committee
    A Framework for 3D Ultrasound Reconstruction Using Robotic Ultrasound Diagnostic System
    Finalists for the Best Conference Paper Award of IEEE UR 2025, Jiayi Zhou;Norihiro Koizumi;Yu Nishiyama;Peiji Chen;Kazushi Numata
  • 受賞日 2025年06月
    IEEE UR 2025 Program Committee
    A Framework for 3D Ultrasound Reconstruction Using Robotic Ultrasound Diagnostic System
    Finalists for the Best Application Paper Award of IEEE UR 2025, Jiayi Zhou;Norihiro Koizumi;Yu Nishiyama;Peiji Chen;Kazushi Numata

論文

  • UFNet: A unified filter neural network for biosignal analysis across time, frequency, and time-frequency domains
    Peiji Chen; Yiwei Wang; Norihiro Koizumi; Hiroshi Yokoi; Yinlai Jiang
    筆頭著者, Neurocomputing, Elsevier BV, 666巻, 掲載ページ 132265-132265, 出版日 2026年02月, 査読付
    研究論文(学術雑誌)
  • A Coupled Tendon-Driven Modular Robotic Hand for Dexterous Manipulation
    Peiji Chen; Yiwei Wang; Tianyu Ouyang; Norihiro Koizumi; Hiroshi Yokoi; Yinlai Jiang
    筆頭著者, IEEE Robotics and Automation Letters, Institute of Electrical and Electronics Engineers (IEEE), 11巻, 1号, 掲載ページ 338-345, 出版日 2026年01月, 査読付
    研究論文(学術雑誌)
  • A novel gravity compensation mechanism for orthogonal DoFs with coupled springs
    Yiwei Wang; Peiji Chen; Shunta Togo; Hiroshi Yokoi; Yinlai Jiang
    Mechanism and Machine Theory, Elsevier BV, 216巻, 掲載ページ 106220-106220, 出版日 2025年11月, 査読付
    研究論文(学術雑誌)
  • Development of a Compact Single-Channel Wristband EMG Sensor System for Hand Gesture Recognition
    Peiji Chen; Yifan Tang; Yiwei Wang; Norihiro Koizumi; Feng Duan; Hiroshi Yokoi; Yinlai Jiang
    筆頭著者, 2025 IEEE International Conference on Cyborg and Bionic Systems (CBS), IEEE, 掲載ページ 285-290, 出版日 2025年10月17日, 査読付
    研究論文(国際会議プロシーディングス)
  • FESNet: A Fine-Grained EMG Segmentation Network for Enhanced Finger Movement Analysis
    Dian Li; Peiji Chen; Shunta Togo; Hiroshi Yokoi; Yinlai Jiang
    2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC), IEEE, 掲載ページ 4597-4602, 出版日 2025年10月05日, 査読付
    研究論文(国際会議プロシーディングス)
  • TF2AngleNet: Continuous finger joint angle estimation based on multidimensional time–frequency features of sEMG signals
    Hai Jiang; Yusuke Yamanoi; Peiji Chen; Xin Wang; Shixiong Chen; Xu Yong; Guanglin Li; Hiroshi Yokoi; Xiaobei Jing
    Biomedical Signal Processing and Control, Elsevier BV, 107巻, 掲載ページ 107833-107833, 出版日 2025年09月, 査読付
    研究論文(学術雑誌)
  • A Data Augmentation Method for sEMG Signals Based on CWGAN-GP Utilizing Multi-scale Feature Fusion Attention Mechanism
    Chenxi Zhu; Peiji Chen; Yifan Tang; Chenbo Chen; Jiaqi Li; Tiejun Zhou; Yinlai Jiang
    2025 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM), IEEE, 掲載ページ 1-6, 出版日 2025年07月14日, 査読付
    研究論文(国際会議プロシーディングス)
  • Advanced Data Augmentation Techniques for Biosignal Processing in Online Systems
    Peiji Chen; Yifan Tang; Dian Li; Hai Jiang; Shunta Togo; Hiroshi Yokoi; Yinlai Jiang
    筆頭著者, 2025 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM), IEEE, 掲載ページ 1-5, 出版日 2025年07月14日, 査読付
    研究論文(国際会議プロシーディングス)
  • 3D Reconstruction of the Kidney and Lesions from 2D Ultrasound Images Using Robotic Ultrasound Diagnostic System
    Jiayi. Zhou; Norihiro. Koizumi; Yu. Nishiyama; Peiji. Chen; Kazushi Numata
    Proceedings of the 47th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 出版日 2025年07月14日, 査読付
  • A Framework for 3D Ultrasound Reconstruction Using Robotic Ultrasound Diagnostic System
    Jiayi Zhou; Norihiro Koizumi; Yu Nishiyama; Peiji Chen; Kazushi Numata
    2025 22nd International Conference on Ubiquitous Robots (UR), IEEE, 掲載ページ 542-549, 出版日 2025年06月30日, 査読付
    研究論文(国際会議プロシーディングス)
  • Deep learning-based image registration method for RFA treatment efficacy evaluation without magnetic sensors
    R. Kasagi; N. Koizumi; P. Chen; N. Umetsu; K. Numata
    Proc. of 39th International Congress and Exhibition on computer assisted radiology and surgery (CARS 2025), International Journal of Computer Assisted Radiology and Surgery (IJCARS), 出版日 2025年06月20日, 査読付
  • Inferior Vena Cava Diameter Measurement System Using Ultrasound and Deep Learning
    N. Umetsu; H. Noro; P. Chen; Y. Nishiyama; R. Kasagi; H. Tsukihara; N. Koizumi
    Proc. of 39th International Congress and Exhibition on computer assisted radiology and surgery (CARS 2025), International Journal of Computer Assisted Radiology and Surgery (IJCARS), 出版日 2025年06月19日, 査読付
  • Automated MRI-TRUS fusion imaging using the prostate edge
    A. Endo; N. Koizumi; Y. Nisiyama; P. Chen; G. Karakida; M. Annju; S. Shoji
    Proc. pf 39th International Congress and Exhibition on computer assisted radiology and surgery (CARS 2025), International Journal of Computer Assisted Radiology and Surgery (IJCARS), 出版日 2025年06月19日, 査読付
  • Binary Classification of Liver Sides Roughness in Ultrasound Images Using Transformer and CNN Models with StyleGAN3 Data Augmentation
    I. Fujii; N. Koizumi; N. Matsumoto; Y. Nishiyama; R. Kasagi; P. Chen; M. Ogawa
    出版日 2025年06月18日, 査読付
  • 超音波診断ロボットによる下大静脈径の自動計測システム
    梅津菜央; 小泉憲裕; 笠置 陸; 西山 悠; 陳 培基; 月原弘之
    超音波医学, 出版日 2025年05月, 査読付
  • 深層学習を活用した肝静脈血管壁の不整の有無の分類
    旭 和哉; 小泉憲裕; 陳 培基; 西山 悠; 松本直樹; 増崎亮太; 藤井 樹; 小川眞広
    超音波医学, 出版日 2025年05月, 査読付
  • 肝腫瘍RFA 治療効果判定における深層学習を用いた新規画像位置合わせ手法
    笠置 陸; 小泉憲裕; Peiji Chen; 梅津菜央; 沼田和司
    超音波医学, 出版日 2025年05月, 査読付
  • Intra- and inter-channel deep convolutional neural network with dynamic label smoothing for multichannel biosignal analysis
    Peiji Chen; Wenyang Li; Yifan Tang; Shunta Togo; Hiroshi Yokoi; Yinlai Jiang
    筆頭著者, Neural Networks, Elsevier BV, 183巻, 掲載ページ 106960-106960, 出版日 2025年03月, 査読付
    研究論文(学術雑誌)
  • TMATH A Dataset for Evaluating Large Language Models in Generating Educational Hints for Math Word Problems
    Changyong Qi; Yuang Wei; Haoxin Xu; Longwei Zheng; Peiji Chen; Xiaoqing Gu
    出版日 2025年01月, 査読付
  • EduDCM: A Novel Framework for Automatic Educational Dialogue Classification Dataset Construction via Distant Supervision and Large Language Models
    Changyong Qi; Longwei Zheng; Yuang Wei; Haoxin Xu; Peiji Chen; Xiaoqing Gu
    Applied Sciences, MDPI AG, 15巻, 1号, 掲載ページ 154-154, 出版日 2024年12月27日, 査読付, Educational dialogue classification is a critical task for analyzing classroom interactions and fostering effective teaching strategies. However, the scarcity of annotated data and the high cost of manual labeling pose significant challenges, especially in low-resource educational contexts. This article presents the EduDCM framework for the first time, offering an original approach to addressing these challenges. EduDCM innovatively integrates distant supervision with the capabilities of Large Language Models (LLMs) to automate the construction of high-quality educational dialogue classification datasets. EduDCM reduces the noise typically associated with distant supervision by leveraging LLMs for context-aware label generation and incorporating heuristic alignment techniques. To validate the framework, we constructed the EduTalk dataset, encompassing diverse classroom dialogues labeled with pedagogical categories. Extensive experiments on EduTalk and publicly available datasets, combined with expert evaluations, confirm the superior quality of EduDCM-generated datasets. Models trained on EduDCM data achieved a performance comparable to that of manually annotated datasets. Expert evaluations using a 5-point Likert scale show that EduDCM outperforms Template-Based Generation and Few-Shot GPT in terms of annotation accuracy, category coverage, and consistency. These findings emphasize EduDCM’s novelty and its effectiveness in generating high-quality, scalable datasets for low-resource educational NLP tasks, thus reducing manual annotation efforts.
    研究論文(学術雑誌)
  • Postural Synergy Analysis of Continuous Hand Movements for Application to Prosthetic Hands
    Hai Jiang; Yusuke Yamanoi; Peiji Chen; Xu Yong; Guanglin Li; Hiroshi Yokoi; Xiaobei Jing
    2024 17th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI), IEEE, 掲載ページ 1-6, 出版日 2024年10月26日
    研究論文(国際会議プロシーディングス)
  • Analysis of Typical Features Using an Angle-to-sEMG Decoder Model
    Zehao Liu; Hai Jiang; Yusuke Yamanoi; Peiji Chen; Xiaobei Jing; Guanglin Li; Hiroshi Yokoi; Xu Yong
    2024 17th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI), IEEE, 掲載ページ 1-6, 出版日 2024年10月26日
    研究論文(国際会議プロシーディングス)
  • Dynamic Label Smoothing Strategy for Biosignal Classification
    Peiji Chen; Dian Li; Yifan Tang; Shunta Togo; Hiroshi Yokoi; Yinlai Jiang
    筆頭著者, ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, 掲載ページ 1556-1560, 出版日 2024年04月14日, 査読付
    研究論文(国際会議プロシーディングス)
  • An Exploratory Study on the Transmission of Language Memes: The Case of Chinese Language Memes
    Fei Wang; Pei-ji Chen; Wen-yang Li; Hiroshi Yokoi
    Journal of Creative Communications, SAGE Publications, 19巻, 3号, 掲載ページ 276-294, 出版日 2024年02月18日, 査読付, We did an exploratory investigation of the transmission of language memes using the meme concept. Using 62 Chinese language memes as an example, we mined the emotions of netizens’ posts containing these languages on Weibo, a Chinese social platform and successfully demonstrated language memes’ potential for eliciting both positive and negative emotions. By comparing the features of emotional changes with the features of the four different language meme transmission processes (bursty, continuous expansion, continuous decline and steady) classified in this study, the results of correlation analysis objectively illustrate the existed connection between emotion and language meme transmission. Specifically, we discovered that the positive emotion ‘good’ and the negative emotion ‘disgust’ are the most obvious emotions elicited by language memes. Additionally, 79% of language memes’ transmission processes were correlated with emotions (positive or negative). And most language memes’ transmission process belongs to the bursty type, especially the latency → burst mode.
    研究論文(学術雑誌)
  • A Strain Gauge Based FMG Sensor for sEMG-FMG Dual Modal Measurement of Muscle Activity Associated with Hand Gestures
    Yifan Tang; Jiayi Wang; Peiji Chen; Wenyang Li; Haokang Xu; Shunta Togo; Hiroshi Yokoi; Yinlai Jiang
    Lecture Notes in Computer Science, Springer Nature Singapore, 掲載ページ 185-194, 出版日 2023年10月10日, 査読付
    論文集(書籍)内論文
  • A Layered sEMG–FMG Hybrid Sensor for Hand Motion Recognition From Forearm Muscle Activities
    Peiji Chen; Ziye Li; Shunta Togo; Hiroshi Yokoi; Yinlai Jiang
    筆頭著者, IEEE Transactions on Human-Machine Systems, Institute of Electrical and Electronics Engineers (IEEE), 53巻, 5号, 掲載ページ 935-944, 出版日 2023年10月, 査読付
    研究論文(学術雑誌)
  • Conditional Generative Adversarial Network-based Finger Position Estimation for Controlling Multi-Degrees-of-Freedom Myoelectric Prosthetic Hands
    Hai Jiang; Yusuke Yamanoi; Yuki Kuroda; Peiji Chen; Shunta Togo; Yinlai Jiang; Hiroshi Yokoi
    2022 IEEE International Conference on Cyborg and Bionic Systems (CBS), IEEE, 掲載ページ 444-449, 出版日 2023年03月24日, 査読付
    研究論文(国際会議プロシーディングス)
  • An improved multi-input deep convolutional neural network for automatic emotion recognition
    Peiji Chen; Bochao Zou; Abdelkader Nasreddine Belkacem; Xiangwen Lyu; Xixi Zhao; Weibo Yi; Zhaoyang Huang; Jun Liang; Chao Chen
    筆頭著者, Frontiers in Neuroscience, Frontiers Media SA, 16巻, 出版日 2022年10月04日, 査読付, Current decoding algorithms based on a one-dimensional (1D) convolutional neural network (CNN) have shown effectiveness in the automatic recognition of emotional tasks using physiological signals. However, these recognition models usually take a single modal of physiological signal as input, and the inter-correlates between different modalities of physiological signals are completely ignored, which could be an important source of information for emotion recognition. Therefore, a complete end-to-end multi-input deep convolutional neural network (MI-DCNN) structure was designed in this study. The newly designed 1D-CNN structure can take full advantage of multi-modal physiological signals and automatically complete the process from feature extraction to emotion classification simultaneously. To evaluate the effectiveness of the proposed model, we designed an emotion elicitation experiment and collected a total of 52 participants' physiological signals including electrocardiography (ECG), electrodermal activity (EDA), and respiratory activity (RSP) while watching emotion elicitation videos. Subsequently, traditional machine learning methods were applied as baseline comparisons; for arousal, the baseline accuracy and f1-score of our dataset were 62.9 ± 0.9% and 0.628 ± 0.01, respectively; for valence, the baseline accuracy and f1-score of our dataset were 60.3 ± 0.8% and 0.600 ± 0.01, respectively. Differences between the MI-DCNN and single-input DCNN were also compared, and the proposed method was verified on two public datasets (DEAP and DREAMER) as well as our dataset. The computing results in our dataset showed a significant improvement in both tasks compared to traditional machine learning methods (t-test, arousal: p = 9.7E-03 < 0.01, valence: 6.5E-03 < 0.01), which demonstrated the strength of introducing a multi-input convolutional neural network for emotion recognition based on multi-modal physiological signals.
    研究論文(学術雑誌)
  • Neural activities classification of left and right finger gestures during motor execution and motor imagery
    Chao Chen; Peiji Chen; Abdelkader Nasreddine Belkacem; Lin Lu; Rui Xu; Wenjun Tan; Penghai Li; Qiang Gao; Duk Shin; Changming Wang; Dong Ming
    Brain-Computer Interfaces, Informa UK Limited, 8巻, 4号, 掲載ページ 117-127, 出版日 2020年07月02日, 査読付
    研究論文(学術雑誌)

講演・口頭発表等

  • 回帰的推定モデルを用いた筋電義手のリアルタイム制御手法の開発
    Jiang Hai; 山野井 佑介; Chen Peiji; 井上 祐希; 辻本 立樹; 横井 浩史
    日本機械学会 2025年度年次大会
    発表日 2025年09月09日
  • 2自由度ワイヤ干渉駆動指モジュール を用いたロボットハンドの開発
    陳培基; 王 軼煒; 小泉憲裕; 横井浩史; 姜銀来
    第 43 回日本ロボット学会学術講演会, 査読付
    発表日 2025年09月
  • Dynamic Label Smoothingを用いた生体信号分類のための領域汎化,
    陳培基; 東郷俊太; 横井浩史; 姜銀来
    第41回日本ロボット学会学術講演会
    発表日 2023年09月
  • 半自動義手制御のためのオンチップ筋電解析システムの開発
    湯 一凡; 陳 培基; 東郷 俊太; 横井 浩史; 姜 銀来
    第45回バイオメカニズム学術講演会 2024年12月