Kyushu University Academic Staff Educational and Research Activities Database
Search by Keyword How ro search
Keyword
Search Criteria
 
Detailed Search

Researcher information (To researchers) Need Help? How to update
Yugo Nakamura Last modified date：2024.04.27

Assistant Professor / HumanoPhilic Systems Lab
Department of Advanced Information Technology
Faculty of Information Science and Electrical Engineering


Graduate School
Department of Advanced information Technology
Graduate School of Information Science and Electrical Engineering


E-Mail　*Since the e-mail address is not displayed in Internet Explorer, please use another web browser:Google Chrome, safari.
Homepage
https://kyushu-u.elsevierpure.com/en/persons/yugo-nakamura
　Reseacher Profiling Tool　Kyushu University Pure
Phone
092-802-3792
Academic Degree
Doctor of Engineering, Ph.D
Country of degree conferring institution (Overseas)
No
Field of Specialization
IoT（Internet of Things）,behavior recognition, behavior change, nudging, distributed systems, information networks
ORCID(Open Researcher and Contributor ID)
0000-0002-8834-5323
Total Priod of education and research career in the foreign country
01years03months
Research
Research Interests
  • Research on realtime detection and attention control of digital distraction
    keyword : Digital Distraction, Personality, Multimodal Sensing, Tailored Intervention, Digital Wellbeing
    2024.04～2027.03.
  • Empowerment ICT Platform for Health Behavior Security
    keyword : Behavior recognition, behavior transformation, nudge, health behavior security, empowerment ICT
    2021.10～2024.03.
Academic Activities
Reports
 Show All Reports >>
Papers
 Show All Papers >>
1. Muhammad Ayat Hidayat, Yugo Nakamura, Yutaka Arakawa, Privacy-Preserving Federated Learning With Resource Adaptive Compression for Edge Devices, IEEE Internet of Things Journal, 10.1109/JIOT.2023.3347552, 2024.03, Federated learning (FL) has gained widespread attention as a distributed machine learning (ML) technique that offers data protection when training on local devices. Unlike conventional centralized training in traditional ML, FL incorporates privacy and security measures as it does not share raw data between the client and server, thereby safeguarding potentially sensitive information. However, there are still vulnerabilities in the FL field, and commonly used approaches, such as encryption and blockchain technologies, often result in significant computational and communication costs, making them impractical for devices with restricted resources. To tackle this challenge, we present a privacy-preserving FL system specifically designed for resource-constrained devices, leveraging compressive sensing and differential privacy (DP) techniques. We implemented the weight-pruning-based compressive sensing method with an adaptive compression ratio based on resource availability. In addition, we employ DP to introduce noise to the gradient before sending it to a central server for aggregation, thereby protecting the gradient’s privacy. Evaluation results demonstrate that our proposed method achieves slightly better accuracy when compared to state-of-the-art methods like DP-federated averaging, DP-FedOpt, and adaptive Gaussian clipping-DP (AGC-DP) for the MNIST, Fashion-MNIST, and Human Activity Recognition data sets. Furthermore, our approach achieves this higher accuracy with a lower total communication cost and training time than the current state-of-the-art methods. Moreover, we comprehensively evaluate our method’s resilience against poisoning attacks, revealing its better resistance than existing state-of-the-art approaches..


Unauthorized reprint of the contents of this database is prohibited.

Copyright © 2006, Kyushu University. All rights reserved.