プロフィール

京都大学 工学研究科の助教です。
研究では主にサロゲートモデリングに焦点を当てており、特に構造信頼性、構造ヘルスモニタリング、構造工学における機械学習の応用に興味があります。
最近は、構造物の地震応答を深層学習モデルで予測する研究に興味があります。
Go to English Page

興味・関心

  • 🤖 Surrogate Modeling
  • 🖥️ Machine Learning
  • 🌉 Structural Reliability

学歴

  • Ph.D. in Engineering, 2026

    University of Tsukuba, Tsukuba in Japan

  • Master of Engineering, 2023

    University of Tsukuba, Tsukuba in Japan

  • Bachelor of Engineering, 2021

    University of Tsukuba, Tsukuba in Japan

学術雑誌論文

すべての学術雑誌論文 »

ExSRNet: Explainable deep learning model for seismic response prediction with frequency attention mechanism

Engineering Structures, 2025
Taisei Saida, Mayuko Nishio
PDF DOI
ExSRNet: Explainable deep learning model for seismic response prediction with frequency attention mechanism

Optical Flow-Based Structural Anomaly Detection in Seismic Events From Video Data Combined With Computational Cost Reduction Through Deep Learning

Structural Control and Health Monitoring, 2025
Sifan Wang, Taisei Saida, Mayuko Nishio
PDF DOI
Optical Flow-Based Structural Anomaly Detection in Seismic Events From Video Data Combined With Computational Cost Reduction Through Deep Learning

System fragility analysis of highway bridge using multi-output Gaussian process regression surrogate model

Advances in Structural Engineering, 2024
Taisei Saida, Muhammad Rashid, Mayuko Nishio
DOI
System fragility analysis of highway bridge using multi-output Gaussian process regression surrogate model

Transfer learning Gaussian process regression surrogate model with explainability for structural reliability analysis under variation in uncertainties

Computers & Structures, 2023
Taisei Saida, Mayuko Nishio
DOI PDF (Accepted version)
Transfer learning Gaussian process regression surrogate model with explainability for structural reliability analysis under variation in uncertainties

TL-GPRSM: A python software for constructing transfer learning Gaussian process regression surrogate model with explainability

Software Impacts, 2023
Taisei Saida, Mayuko Nishio
PDF DOI
TL-GPRSM: A python software for constructing transfer learning Gaussian process regression surrogate model with explainability
発表文献一覧

会議論文

すべての会議論文 »

Large-Scale Structural Anomaly Detection During Seismic Events Using Optical Flow and Transfer Learning from Video Data

SHMII-13, 2025
Sifan Wang, Taisei Saida, Mayuko Nishio
DOI conference paper (PDF)

Seismic Fragility Assessment using Explainable Deep Kernel Learning Surrogate Model considering Structural and Seismic Uncertainties

IABSE, 2025
Taisei Saida, Mayuko Nishio
DOI conference paper (PDF)

Gaussian Process Regression Surrogate Model for Seismic Vulnerability Assessment of Highway Bridge Structure System

EVACES, 2023
Taisei Saida, Muhammad Rashid, Mayuko Nishio
DOI

Gaussian process regression surrogate model for dynamic analysis to account for uncertainties in seismic loading

SPIE, 2023
Taisei Saida, Mayuko Nishio
DOI

Digital twin framework for real-time dynamic analysis visualization with detecting dynamic changes in structures properties using PINN

SPIE, 2023
Toko Okuda, Taisei Saida, Gen Matono, Mayuko Nishio
DOI
発表文献一覧

連絡先