(1) Course Overview:
This course utilizes two sets of tools for experimentation: AI Biomedical Health Applications and Python-based AIoT Smart Networking. It involves the use of controllers such as D1 mini, ESP32, and various sensors, covering over 20 experiments related to biomedical and artificial intelligence. Biomedical-related experiments include: polygraph, breathalyzer, blood oxygen meter, simple ECG machine, recurrent neural network heart rate monitor, recurrent neural network pulse meter, real-time blood pressure meter, and deep learning real-time thermometer. AI-related experiments include: temperature monitoring station, step frequency recorder, wireless body-sensing keyboard, gesture detection, and sound sensor. The AI-related portion primarily uses Python and Keras to implement deep neural networks and convolutional neural networks. AI neural network implementation involves collecting learning data through hardware circuits, training with Keras on Google Colab, and then storing the trained model in the ESP32 to control IoT circuits. This type of experiment is currently trending in AIoT, allowing students to work on practical applications of AI models.
(2) Course Outcomes:
AIoT involves adding AI learning models to traditional IoT controllers for control functions, which is a very popular topic in the field of information technology. In this course, AIoT smart networking has been incorporated into the experiments, conducting two AIoT experiments: a pedometer and voice control. This should be very useful for students, as they can consider integrating AI models into IoT experiments in the future. The course provides AI Keras and IoT Python programming, allowing students to use the experiment content as a template for modifications or expansions. This experiment aims to be beneficial for students in their future studies or employment.
(1) Course Overview:
This course will introduce an interdisciplinary approach combining medical, information technology, and telecommunications to develop health care IoT systems.
Medical Field: The course begins with human physiology, then delves into pathology and clinical experience related to health care and elderly care needs. Students will learn about clinical requirements and design IoT systems that address these needs, focusing on human-centered planning and design.
Information Technology: The course will apply basic and advanced analytical tools to data generated by health care devices. This will provide critical insights and enhance decision-making capabilities. Students will learn to extract useful data from various devices and monitoring equipment, manage and analyze large datasets, which will help reduce costs, improve care quality, provide value-oriented care, and connect with consumers to better understand treatment outcomes.
Telecommunications Technology: Based on the needs identified in the medical and IT fields, the course will introduce the architecture and implementation of corresponding IoT front-end and back-end systems.
(2) Expected Outcomes:
- 1.Enhance students' professional knowledge and skills in gerontology, care science, and assistive technology applications.
- 2.Develop students' understanding and practical experience in applying intelligent computing and IoT technologies in the health care field.
(1) Course Overview:
This course primarily utilizes Agile development, design thinking, and example-based gaming methods to easily introduce programming challenges, solve design problems, or test design prototypes. With current deep learning tools, performing deep learning is quite simple; it essentially involves three steps: "collect data, train data, and use data." In essence, deep learning is just a collection of functions. The course focuses on neural networks and a collection of functions where you input a set of values and the network outputs another set of values to find the best result. The course begins with an introduction to deep learning tools and then uses examples such as AI OX games, handwritten digit recognition, image recognition, and medical image recognition to explain the programming concepts.
(2) Expected Outcomes:
- Learn Python programming language.
- Become proficient in using TensorFlow tools.