← All research areas

Research area

International Programs

Projects by international students in the TEEP and IIPP programs.

Group photo of about fifty students outdoors under trees, holding flowers and banners, from an international exchange activity.

Each year the lab hosts international students through two Taiwan government programs: TEEP (Taiwan Experience Education Program, Ministry of Education; the lab’s Taiwan–India project since 2018) and IIPP (International Internship Pilot Program, National Science and Technology Council; since 2024). These students arrive with different backgrounds, and the lab gives them a concrete project in which to apply AI to a real problem.

Projects span signal processing, time-series prediction, robotics and computer vision, typically built with Python notebooks and low-cost embedded hardware such as Arduino and ESP boards. Several have grown into collaborations or papers, for example the two-step authentication work presented at ICETA 2024.

What interns do. Typical tasks are digital signal processing (short-time Fourier transform, discrete wavelet transform, digital filtering), machine learning with LSTM and general regression neural networks, simulation and analysis in MATLAB and Python, and implementing them on embedded hardware such as FPGA boards. Interns report weekly and meet the group every week; C or C++ programming is expected.

Topics offered. Recent calls offered smart grids and power quality, and wavelet neural networks for the industrial internet of things (IIoT), both covering feature extraction, system-response identification and system-status identification; embedded image recognition (feature extraction, contour identification, object recognition); and AI and edge computing for the campus battery energy storage system.

Representative projects include the Embedded Wavelet Neural Network for ECG Analysis, NCUE BEES energy consumption analysis and prediction and PatrolBot.

Related projects

Lets you in only when both your face and your voice match, with an ordinary webcam and microphone.

A two-step authentication design in which a VGG16 face classifier identifies an enrolled user and a ResCNN speaker encoder then verifies their voice, using only an ordinary webcam and microphone; published at ICETA 2024.

People Kuan-Wei Chen, Ting-Yi Lin

Jupyter Notebook 9 Updated Oct 4, 2026

PatrolBot

Archived

A small robot car that patrols on its own, holding a straight course and measuring distances with a laser sensor.

Design and construction of an autonomous patrol robot vehicle, using an MPU-6050 IMU with PID control to hold a straight course, VL53L-series distance sensing on ESP32, and Blynk-based monitoring.

C++ 0 Updated Feb 14, 2023

American Sign Language Translation with T5 and Linear Projection

Archived

Turns American Sign Language into English sentences.

Translates American Sign Language into English text by projecting sign features into a T5 language model through a linear layer.

Sign Language Translation

Archived

Recognizes signing from video and turns it into text or speech.

Related publications

  1. Two-step Authentication: Multi-biometric System Using Voice and Facial Recognition

    Kuan Wei Chen, Ting Yi Lin, Wen Ren Yang, Aryan Kesarwani, Riya Singh

    IET International Conference on Engineering Technologies and Applications (ICETA 2024), IET Conference Proceedings, vol. 2024, no. 22, pp. 11–12

    Combines face and voice recognition into a low-cost authentication system for a small group that needs only a camera and a microphone: a face model identifies the user, then a speaker model verifies the voice. Code and models are public.

In our interns’ words

TEEP and IIPP interns on their time in the lab, as they wrote it.

Interested? Visit the lab or write to us.