I'm a graduate student in AIED. I've explored nearly six years in AIED, focusing on AI-driven assessment, academic performance prediction, and AI gamification. My education in Computer Science and Educational Technology enables me to tackle educational challenges as both an AIED engineer and a learning science researcher. I'm committed to professional growth and hope to aid educators and learners along the way. For more about me, please view my projects.
Jiamin Lou & Xiaoming Cao (2024). Investigating AI-driven formative assessment with note-tracking smart pens - An exploratory study in middle school
Status: Under review by Technology, Knowledge and Learning (EI & ESCI, IF=3.0)
Jiamin Lou, Zui Cheng, Shuning Li, & Yuanyuan Wang (2024). A systematic literature review on AI-driven gamification in K12: Insights, limitations, and future directions
Status: Under review by Interactive Learning Environments (SSCI Q1, IF=3.7)
Luming Zhao, Jingwen Xuan, Jiamin Lou, Yonghui Yu, Wenwu Yang (2025). Context-Aware Academic Emotion Dataset and Benchmark
Status: Under review by ICCV 2025
Master’s thesis: Research on the development and application of junior high school academic
performance prediction system based on accompanying classroom data
Keywords: Academic performance prediction, secondary education, artificial intelligence,
machine learning, precision teaching
This platform primarily helps deaf children and their teachers learn sign language through 3D sign language animation courses, AI-driven formative assessments via hand pose tracking, and a related question bank.
This course, designed for eighth-grade students, includes a series of problem scenarios related to math lessons. It helps students consolidate their math knowledge while learning to solve problems with programming.
This study highlights the potential of integrating precision teaching concepts into formative assessment, offering comprehensive and timely feedback by incorporating learning-achievement-related and engagement data into AI models.
This study creates a daily closed-loop teaching ecosystem powered by an intelligent predictive model and visualized learning analytics, with educators and learners at its core and guided by data-driven decisions.
This app features dialect-based humorous short videos and offers daily activities and professional editing tools. Alongside entertainment, it supports dialect preservation.
This project visualizes guest traffic changes, unique visitor trajectories, and communication logs to provide improvement suggestions for amusement park operations.
Skilled in in Python
(NumPy, Pandas, Scikit-learn, Keras, TensorFlow)
Proficient in front-end (HTML, CSS, JS), Database (MySQL), & back-end (Python-Flask)
Expertise in Python tools (Matplotlib, Seaborn) and D3.js
Skilled with SPSS statistical software