校際選修

115-1 選課時程

進行中

  • 初選第一階段 6/15/2026
  • 初選第二階段 6/22/2026
  • 校際選修 8/24/2026
  • 初選第三階段 8/31/2026
  • 開學後加退選 9/7/2026
  • 逾期加退選 9/21/2026
選課資源

生醫資料、訊號及影像的人工智慧

Artificial Intelligence for Biomedical Data, Signal, and Image

學期
113-1
學分
2 學分
當期課號
131013
永久課號
MDBI30093
開課單位
生物醫學資訊研究所
授課教師
朱原嘉、巫坤品、蘇家玉、吳俊穎
校區
陽明
類別
選修
上課時間表
週二
5
13:20–14:10
生醫資料、訊號及影像的人工智慧
YR101
2 節連堂
6
14:20–15:10

* 根據陽明交大上課時間表所列

概述

The course is designed to provide students with a comprehensive understanding of machine learning and deep learning theories that are specifically tailored for practical applications. The course will delve into the realm of AI and its potential applications in healthcare and will feature case studies that demonstrate real-world applications such as infoepidemiology during and post-COVID era, the hearing smart medical system, which leverages AI algorithms to analyze patient data and provide personalized treatment plans based on their hearing loss. The course will also demonstrate how AI can be used to predict heart failure risk from hemodialysis data and how mass spectrometry-based proteomics can be used. By using medical data examples, the course will highlight the potential and limitations of these techniques and provide students with a deep understanding of how these techniques can be applied in real-world settings. The course will also explore real-world implementations that involve various data processing methods, model development, and optimization strategies, providing students with a hands-on approach to learning. Overall, the course is an excellent opportunity for students to gain a comprehensive understanding of AI and its potential healthcare applications and explore the latest developments in machine learning and deep learning theories tailored for practical applications.

先修科目

• Basic concept of Python programming

教學方式

This course has been designed to offer practical exposure to a range of cutting-edge machine-learning models and signal-processing techniques.

評分方式

期中報告: 30% 期末專題: 40% 出席: 10% 作業: 20% Midterm Report: 30% Final Project: 40% Attendance: 10% Homework: 20%

週次計畫
週次主題
第 1 週Traditional statistics vs. AI
第 2 週Preprocessing health big data for AI models
第 3 週Mid-Fall Festival
第 4 週Infoepidemiology: Insights from the internet Search Trends in the COVID-19 pandemic
第 5 週Infoepidemiology: Impacts of Mental Health and Long-COVID Symptoms in the Post-COVID era
第 6 週Transitioning from artificial neural networks (ANN) to convolutional neural networks (CNN)
第 7 週Developing hearing smart medical system: from prototyping to aging hearing signal and public health
第 8 週Mid-term report
第 9 週Introduction to Mass Spectrometry-Based Proteomics
第 10 週Traditional vs. customized CNN models
第 11 週Transfer learning and development of models
第 12 週Real-time Analysis of Massive Continuous Data from a Dialysis Machine Signal to Predict Heart Failure Risk with New AI Platform
第 13 週Techniques for model evaluation and addressing imbalanced data
第 14 週Radiomics feature analysis
第 15 週Ensemble learning: Integration of image and clinical data
第 16 週Final report presentation
教科書

Teaching materials and appointment articles

Office Hours
地點
守仁樓數位醫學中心
時間
Tuesday 12:00-13:00.
聯絡方式
Email聯繫: cywu4@nycu.edu.tw Prof. Chun-Ying Wu