Details of the Researcher

PHOTO

Alemayoh Tsige Tadesse
Section
Tough Cyberphysical AI Research Center
Job title
Specially Appointed Assistant Professor(Research)
Degree

  • D.Eng (Ehime University)

Education 4

  • Ehime University　Graduate School of Science and Engineering　Mechanical Engineering (PhD)

    2021/04 - 2024/03

  • Ehime University　Graduate School of Science and Engineering　Mechanical Engineering (MSc)

    2019/04 - 2021/03

  • Ehime University　Faculty of Engineering (Research student)

    2018 - 2019

  • Mekelle University　Electrical and Electronics and Engineering (BSc)

    2011 - 2016

Professional Memberships 4

  • The Japanese Society for Artificial Intelligence

    2025/04 - Present

  • The Robotics Society of Japan

    2024/07 - Present

  • The Japan Society of Mechanical Engineers

    2021 - Present

  • IEEE

    2021 - Present

Research Interests 1

  • Behavior Informatics, Cyber-dog, Intelligent systems

Research Areas 1

  • Manufacturing technology (mechanical, electrical/electronic, chemical engineering) / Control and systems engineering / Robotics, Intelligent Systems, VLA

Awards 3

  1. 優秀講演賞

    2022/12　公益社団法人計測自動制御学会　ニューラルネットワークを用いた慣性データからのセンサ姿勢推定

  2. Best Application Paper

    2021/07　Korean Robotics Society　Feedforward operational stiffness modulation and external force estimation of planar robots equipped with variable stiffness actuators

  3. 2016 Graduating Class Valedictorian

    2016/07　Mekelle University

Papers 31

  1. Dogs display context-dependent behavioral responses to subtle owner-derived multimodal stimuli Peer-reviewed

    Rio Ikeda, Maaya Saito, Yuki Iwata, Takumi Ozono, Tsige Tadesse Alemayoh, Takatomi Kubo, Ei-Ichi Izawa, Koichi Fujiwara, Toshitaka Yamakawa, Kazunori Ohno, Takefumi Kikusui, Miho Nagasawa

    Frontiers in Veterinary Science　13　2026/08/20

    Publisher: Frontiers Media SA

    DOI： 10.3389/fvets.2026.1916007 　

    eISSN： 2297-1769

    More details Close

    Introduction Dogs ( Canis familiaris ) can discriminate explicit human emotions using various sensory modalities. However, their sensitivity to subtle human-derived emotional cues accompanied by physiological changes, but lacking clear behavioral cues, remains poorly understood. This study investigated whether dogs could perceive owner-derived emotional cues when suppressing explicit expressions. Methods Owners were assigned to either stress or relaxation conditions designed to induce stress or relaxation, respectively. Following the experimental manipulation, facial video, voice, and olfactory samples were collected during a standardized reading task and simultaneously presented to the dogs. The behavioral responses and heart rate variability (HRV) of the dogs during stimulus presentation were recorded. Results Owners exhibited elevated physiological arousal during both the control and stress induction periods, whereas negative mood increased only during stress induction. In response to these owner-derived stimuli, dogs under the stress condition displayed greater stimulus-directed attention toward control-derived stimuli than toward stress-derived stimuli. No clear effects of condition or stimulus type on dog HRV were observed; however, SDNN-based physiological synchrony between owners and dogs tended to increase with stress-derived stimuli. Discussion Our results suggest that dogs respond to complex owner-derived stimuli in a context-dependent manner. These findings suggest that dogs may respond to subtle combinations of owner-derived cues that reflect physiological arousal, subjective emotional state, and task-related influences.

  2. Unsupervised Hierarchical Representation Learning of Time-series Motion Data

    Tsige Tadesse ALEMAYOH, Kai FUKUZAWA, Kazunori OHNO

    2026/02

  3. イヌの行動誘導におけるモチベーション維持の可視化の検討

    大野和則, 福澤快, Tsige Tadesse Alemayoh, 千代窪美帆, 永澤美保, 菊水健史

    第38回 自律分散システム・シンポジウム　2026/02

  4. Adaptive Costmap-based Path Planning in Partially Known Environments with Movable Obstacles

    Liviu-Mihai Stan, Ranulfo Bezerra, Shotaro Kojima, Tsige Tadesse Alemayoh, Satoshi Tadokoro, Masashi Konyo, Kazunori Ohno

    2025 IEEE International Conference on Advanced Robotics (ICAR)　353-359　2025/12/02

    Publisher: IEEE

    DOI： 10.1109/icar65334.2025.11338633 　

  5. 敷き均し積層型コンクリート3Dプリンタのスクリュー搬送の検証-スクリュー搬送のモデル化とシリコン砂を利用した検証

    2025/10

  6. Transformer Model for Search and Rescue Canine Activity Recognition

    Tsige Tadesse ALEMAYOH, Kazunori OHNO, Satoshi TADOKORO

    RSJ 2024　2025/09

  7. Behavior prediction of large dump trucks using iTransformer with compressed maps and behavior data as input

    澤村理生, 小島匠太郎, Tsige Tadesse Alemayoh, Ranulfo Bezerra, 落合聡, 鈴木太郎, 小松智広, 宮本直人, 浅野公隆, 鈴木高宏, 田所諭, 大野和則

    ROBOMECH2025　2025/06

  8. Multimedia Source Integration Using Specialized LLMs for News Generation

    Ahmed Youssef, Ranulfo Bezerra, Tsige Tadesse Alemayoh, Shotaro Kojima, Kazunori Ohno

    ROBOMECH2025　2025/06

  9. Dynamic Parameter Estimation of Manipulators for a Universal Control Policy: A Data-Driven Approach Using Joint-Specific Attention and Cross-Attention Mechanisms

    Mohammed Elseiagy, Tsige Tadesse Alemayoh, Ranulfo Bezerra, Kazunori Ohno

    ROBOMECH2025　2025/06

  10. Development of a Small and Lightweight Collar-type Dog Feeder

    福澤 快, Tsige Tadesse Alemayoh, 大園 卓幹, 小島 匠太郎, Ranulfo Bezerra, 永澤 美保, 菊水 健史, 田所 諭, 大野 和則

    ROBOMECH2025　2025/06

  11. Development of a simultaneous-multiple-stimulus-presentation device for canines Peer-reviewed

    Takumi Ozono, Tsige Tadesse Alemayoh (Presenter), Shotaro Kojima, Ranulfo Bezerra, Kai Fukuzawa, Miho Nagasawa, Rio Ikeda, Maaya Saito, Takatomi Kubo, Kouichi Fujiwara, Toshitaka Yamakawa, Satoshi Tadokoro, Kazunori Ohno

    30th Robotics Symposia 2025　2025/03

  12. 電極位置を調整可能なメッシュ型イヌ用脳波測定キャップの試作

    大園 卓幹, Tsige Tadesse Alemayoh, 小島 匠太郎, Ranulfo Bezerra, 福澤 快, 永澤 美保, 菊水 健史, 小池 瞳, 斎藤 愛彩, 久保 孝富, 藤原 幸一, 山川 俊貴, 田所 諭, 大野 和則

    SICE-SI 2024　2024/12

  13. イヌの誘導を長時間化する給餌器搭載光誘導スーツの開発と検証

    福澤 快, Alemayoh Tsige Tadesse, 大園 卓幹, 小島 匠太郎, Bezerra Ranulfo, 菊水 健史, 永澤 美保, 田所 諭, 大野 和則

    SICE-SI 2024　2024/12

  14. Transformer を用いた自動運転大型ダンプトラックの行動・衝突予測

    澤村 理生, 小島 匠太郎, Bezerra Ranulfo, Alemayoh Tsige Tadesse, 落合 聡, 鈴木 太郎, 小松 智広, 宮本 直人, 浅野 公隆, 鈴木 高宏, 田所 諭, 大野 和則

    SICE-SI 2024　2024/12

  15. A Deep Learning Approach for Biped Robot Locomotion Interface Using a Single Inertial Sensor Peer-reviewed

    Tsige Tadesse Alemayoh, Jae Hoon Lee, Shingo Okamoto

    Sensors　23　(24)　9841-9841　2023/12/15

    Publisher: MDPI AG

    DOI： 10.3390/s23249841 　

    eISSN： 1424-8220

    More details Close

    In this study, we introduce a novel framework that combines human motion parameterization from a single inertial sensor, motion synthesis from these parameters, and biped robot motion control using the synthesized motion. This framework applies advanced deep learning methods to data obtained from an IMU attached to a human subject’s pelvis. This minimalistic sensor setup simplifies the data collection process, overcoming price and complexity challenges related to multi-sensor systems. We employed a Bi-LSTM encoder to estimate key human motion parameters: walking velocity and gait phase from the IMU sensor. This step is followed by a feedforward motion generator-decoder network that accurately produces lower limb joint angles and displacement corresponding to these parameters. Additionally, our method also introduces a Fourier series-based approach to generate these key motion parameters solely from user commands, specifically walking speed and gait period. Hence, the decoder can receive inputs either from the encoder or directly from the Fourier series parameter generator. The output of the decoder network is then utilized as a reference motion for the walking control of a biped robot, employing a constraint-consistent inverse dynamics control algorithm. This framework facilitates biped robot motion planning based on data from either a single inertial sensor or two user commands. The proposed method was validated through robot simulations in the MuJoco physics engine environment. The motion controller achieved an error of ≤5° in tracking the joint angles demonstrating the effectiveness of the proposed framework. This was accomplished using minimal sensor data or few user commands, marking a promising foundation for robotic control and human–robot interaction.

  16. Leg Joint Angle Estimation From a Single Inertial Sensor During Variety of Walking Motions: A Deep Learning Approach Peer-reviewed

    Tsige Tadesse Alemayoh, Jae Hoon Lee, Shingo Okamoto

    IEEE Access　11　121978-121990　2023/10

    Publisher: Institute of Electrical and Electronics Engineers (IEEE)

    DOI： 10.1109/access.2023.3328798 　

    eISSN： 2169-3536

  17. A Neural Network-Based Lower Extremity Joint Angle Estimation from Insole Data Peer-reviewed

    Tsige Tadesse Alemayoh, Jae Hoon Lee, Shingo Okamoto

    2023 20th International Conference on Ubiquitous Robots (UR)　787-791　2023/06/25

    Publisher: IEEE

    DOI： 10.1109/ur57808.2023.10202438 　

  18. Leg-Joint Angle Estimation from a Single Inertial Sensor Attached to Various Lower-Body Links during Walking Motion Peer-reviewed

    Tsige Tadesse Alemayoh, Jae Hoon Lee, Shingo Okamoto

    Applied Sciences　13　(8)　2023/04/11

    DOI： 10.3390/app13084794 　

  19. Actuator Module Development for a 3D Printed Biped Robot Using Low-Cost BLDC Motor

    Kazuya Maegaki, Tsige Tadesse Alemayoh, Jae Hoon Lee, Shingo Okamoto

    28th International Symposium on Artificial Life and Robotics (AROB 2023)　2023/01

  20. Deep-Learning-Based Character Recognition from Handwriting Motion Data Captured Using IMU and Force Sensors Peer-reviewed

    Tsige Tadesse Alemayoh, Masaaki Shintani, Jae Hoon Lee, Shingo Okamoto

    Sensors　22　(20)　2022/10/15

    Publisher: MDPI AG

    DOI： 10.3390/s22207840 　

    eISSN： 1424-8220

    More details Close

    Digitizing handwriting is mostly performed using either image-based methods, such as optical character recognition, or utilizing two or more devices, such as a special stylus and a smart pad. The high-cost nature of this approach necessitates a cheaper and standalone smart pen. Therefore, in this paper, a deep-learning-based compact smart digital pen that recognizes 36 alphanumeric characters was developed. Unlike common methods, which employ only inertial data, handwriting recognition is achieved from hand motion data captured using an inertial force sensor. The developed prototype smart pen comprises an ordinary ballpoint ink chamber, three force sensors, a six-channel inertial sensor, a microcomputer, and a plastic barrel structure. Handwritten data of the characters were recorded from six volunteers. After the data was properly trimmed and restructured, it was used to train four neural networks using deep-learning methods. These included Vision transformer (ViT), DNN (deep neural network), CNN (convolutional neural network), and LSTM (long short-term memory). The ViT network outperformed the others to achieve a validation accuracy of 99.05%. The trained model was further validated in real-time where it showed promising performance. These results will be used as a foundation to extend this investigation to include more characters and subjects.

  21. LocoESIS: Deep-Learning-Based Leg-Joint Angle Estimation from a Single Pelvis Inertial Sensor Peer-reviewed

    Tsige Tadesse Alemayoh, Jae Hoon Lee, Shingo Okamoto

    2022 9th IEEE RAS/EMBS International Conference for Biomedical Robotics and Biomechatronics (BioRob)　1-7　2022/03/21

    Publisher: IEEE

    DOI： 10.1109/biorob52689.2022.9925420 　

  22. ニューラルネットワーク を 用いた 生慣性データ からの センサ姿勢推定

    アレマヨゥ ツィゲ タデッセ, 李在勲, 岡本伸吾

    令和４年度 SICE 四国支部学術 講演会　2022/03

  23. Feedforward operational stiffness modulation and external force estimation of planar robots equipped with variable stiffness actuators Peer-reviewed

    Tatsuya Ohe, Tsige Tadesse Alemayoh, Jae Hoon Lee, Shingo Okamoto

    Intelligent Service Robotics　15　(2)　179-192　2022/02/23

    Publisher: Springer Science and Business Media LLC

    DOI： 10.1007/s11370-022-00412-y 　

    ISSN： 1861-2776

    eISSN： 1861-2784

  24. Deep-Learning Method for Handwritten Numeral Recognition Utilizing Force and Inertial Sensors

    Tsige Tadesse Alemayoh, Masaaki Shintani, Jae Hoon Lee, Shingo Okamoto

    27th Proceedings of the Twenty-Seventh International Symposium on Artificial Life and Robotics 2022　2022/01

  25. New Sensor Data Structuring for Deeper Feature Extraction in Human Activity Recognition Peer-reviewed

    Tsige Tadesse Alemayoh, Jae Hoon Lee, Shingo Okamoto

    Sensors　21　(8)　2021/04/16

    Publisher: MDPI AG

    DOI： 10.3390/s21082814 　

    eISSN： 1424-8220

    More details Close

    For the effective application of thriving human-assistive technologies in healthcare services and human–robot collaborative tasks, computing devices must be aware of human movements. Developing a reliable real-time activity recognition method for the continuous and smooth operation of such smart devices is imperative. To achieve this, light and intelligent methods that use ubiquitous sensors are pivotal. In this study, with the correlation of time series data in mind, a new method of data structuring for deeper feature extraction is introduced herein. The activity data were collected using a smartphone with the help of an exclusively developed iOS application. Data from eight activities were shaped into single and double-channels to extract deep temporal and spatial features of the signals. In addition to the time domain, raw data were represented via the Fourier and wavelet domains. Among the several neural network models used to fit the deep-learning classification of the activities, a convolutional neural network with a double-channeled time-domain input performed well. This method was further evaluated using other public datasets, and better performance was obtained. The practicability of the trained model was finally tested on a computer and a smartphone in real-time, where it demonstrated promising results.

  26. A New Motion Data Structuring for Human Activity Recognition Using Convolutional Neural Network Peer-reviewed

    Tsige Tadesse Alemayoh, Jae Hoon Lee, Shingo Okamoto

    2020 8th IEEE RAS/EMBS International Conference for Biomedical Robotics and Biomechatronics (BioRob)　187-192　2020/10

    Publisher: IEEE

    DOI： 10.1109/biorob49111.2020.9224310 　

  27. レーザ・スキャナ 及びデプス・カメラ を 用いた 深層学習による ミンチ 肉の 重量推定

    河井 雄輝, Alemayoh Tsige Tadesse, 李 在勲, 岡本 伸吾

    日本機械学 会 中国四 国学生会 第 50 回学生 員卒業研究発表講演会　2020/03

  28. Detection of Irregular Human Motion Using a body-worn IMU Sensor and Deep Learning for Personal Safety

    Yohsuke Iguchi, Tsige Tadesse Alemayoh, Jae Hoon Lee, Shingo Okamoto

    25th International Symposium on Artificial Life and Robotics (AROB 2020)　2020/01

  29. Estimation of Minced Meat Weight Using Deep Learning on Laser Scan and Depth Image Data

    Yuki Kawai, Tsige Tadesse Alemayoh, Jae Hoon Lee, Shingo Okamoto

    25th International Symposium on Artificial Life and Robotics (AROB 2020)　2020/01

  30. Deep Learning Based Real-time Daily Human Activity Recognition and Its Implementation in a Smartphone Peer-reviewed

    Tsige Tadesse Alemayoh, Jae Hoon Lee, Shingo Okamoto

    2019 16th International Conference on Ubiquitous Robots (UR)　179-182　2019/06

    Publisher: IEEE

    DOI： 10.1109/urai.2019.8768791 　

  31. Implementation of convolutional neural network for classification of daily human activities

    Tsige Tadesse Alemayoh, Jae Hoon Lee, Shingo Okamoto

    24th International Symposium on Artificial Life and Robotics (AROB 2019)　2019/01

Show all ︎Show first 5

Presentations 1

  1. From Shepherding in Ethiopia to Researching in Japan: Challenges and Opportunities of Foreign Scholars Invited

    Tsige Tadesse ALEMAYOH

    2024 日本機械学会年次大会 International Students Symposium, Sep, 2024　2024/09/09