- Online Learning and Analytics
- Intelligent Tutoring Systems and Adaptive Learning
- Innovative Teaching and Learning Methods
- Online and Blended Learning
- E-Learning and Knowledge Management
- Topic Modeling
- Artificial Intelligence in Healthcare and Education
- Innovations in Medical Education
- Imbalanced Data Classification Techniques
- Data Mining Algorithms and Applications
- Rough Sets and Fuzzy Logic
- Natural Language Processing Techniques
- Wikis in Education and Collaboration
- Educational Technology and Assessment
- Text and Document Classification Technologies
- Innovative Teaching Methods
- Explainable Artificial Intelligence (XAI)
- Bluetooth and Wireless Communication Technologies
- Reflective Practices in Education
- AI in Service Interactions
- Empathy and Medical Education
- Machine Learning and Data Classification
- Teaching and Learning Programming
- Advanced Graph Neural Networks
- Software System Performance and Reliability
National Central University
2016-2025
Shanghai Jiao Tong University
2018-2019
University of Waikato
2008-2009
Human Media
2008
As information technology continues to evolve rapidly, programming skills become increasingly crucial. To be able construct superb skills, the training must begin before college or even senior high school. However, when developing comprehensive programmers, learning and teaching processes considered. In order improve students' outcome engagement in course, this study applied analytics into proposed massive online open courses (MOOCs) enabled collaborative course. Through activity,...
In order to enhance the experience of learning, many educators applied learning analytics in a classroom, major principle is targeting at-risk student and given timely intervention according results behavior analysis. However, when researchers machine train risk identifying model, reason which affected performance model was overlooked. This study collected seven datasets within three universities located Taiwan Japan listed metrics identification after fed data into eight classification...
Wikipedia has been applied as a background knowledge base to various text mining problems, but very few attempts have made utilize it for document clustering. In this paper we propose exploit the semantic in clustering, enabling automatic grouping of documents with similar themes. Although clustering is intrinsically unsupervised, recent research shown that incorporating supervision improves performance, even when limited provided. The approach presented applies using active learning. We...
With the rise of big data analytics, learning analytics has become a major trend for improving quality education. Learning is methodology helping students to succeed in classroom; principle predict student's academic performance at an early stage and thus provide them with timely assistance. Accordingly, this study used multiple linear regression (MLR), popular method predicting students' performance, establish prediction model. Moreover, we combined MLR principal component analysis (PCA)...
The flipped classroom pedagogy has been widely used recently. Despite many researches have paid attention with the learning outcome of classroom, there limited in regard to investigate relationship between behavior and outcomes a classroom. In this paper, we proposed influence online behaviors on short-term long-term This study Calculus grade point average (GPA) scores represent outcomes, respectively. Multiple linear regression indicated that students' does not significant effect but...
Background Medical Humanities (MH) curricula integrate humanities disciplines into medical education to nurture essential qualities in future physicians. However, the impact of MH on clinical competencies during formative training phases remains underexplored. This study aimed determine influence internship performance.
The advancements of ambient intelligence and ubiquitous computing are driving the unprecedented development smart spaces where enhanced services provided based on activity recognition. Meanwhile, user identification, which can enable personalization for specific users access control confidential information, becomes increasingly important. Traditional approaches to identification require either attached wearable sensors or active participation. This paper presents Au-Id, a non-intrusive...
In recent years, the field of learning analytics has gained significant attention as educators and researchers seek to understand optimize process in online systems. This paper presents a novel methodology for predicting performance systems by leveraging natural language processing (NLP) embedding techniques. The study focuses on two systems, namely BookRoll Viscode, aims analyze behaviors students using system logs extracted from databases. are converted into semester daily description...
Monitoring respiration and heartbeat contributes to disease prediction, sub-health diagnosis, exercise sleep quality analysis, fatigue warning, even emotion estimation. There is a compelling need for contactless, easy-to-deploy long-term monitoring. In this paper, we present CRH, an RFID-based contactless monitoring system. The key insight that the RFID signal fluctuation induced by chest motion synchronous with heartbeat. Therefore, CRH collects temporal phase information from tag array...
Regular exercise offers numerous health benefits and contributes to a healthy lifestyle. Doing at home is an attractive choice for many people due its convenience low cost. Motivated by this, we propose FitAssist in this paper, household virtual fitness assistant capable of performing fine-grained recognition quality assessment based on commercial WiFi devices. Unlike wearable devices systems, system more comfortable device-free. In addition, compared previous Wi-Fi monitoring whose...
In recent years, educational resources have gradually been digitized, and digital education platforms become popular. We use AI to accurately assist people in performing daily tasks through a machine learning process. education, we can many situations, such as predicting student's outcome discovering strategies. However, most solutions not yet utilized modern capabilities, natural language processing. This research aims help teachers machines automatically generate short answer questions...
The advancement in network technology has stimulated the proliferation of online learning. Online learning platforms, such as management systems (LMS) and e-book reading systems, are widely used higher education to enhance students' reflection planning process. Although many studies have explored relationships between patterns performances, few examined effects self-regulated learning, strategy, self-efficacy on performance students. Here, authors collected logs from an system BookRoll...
The earlier ideas for time interval sequential pattern mining discovering the between two product items help managers promote sale prediction of items. For example, if most customers purchased item A, and then they bought B C after r to s t u days respectively, can be provided make marketing decision while predicting purchasing A B, as well based on prediction. Nevertheless, research does not consider significance time-interval patterns. This work implements previous keeps patterns with high...
The purpose of time-interval sequential pattern mining is to help superstore business managers promote product sales. Sequential discovers the time interval patterns for items: example, if most customers purchase item <span class="bold"> A </span>, and then buy items B </span> C after r s t u days respectively, between can be provided facilitate informed marketing decisions. We treat these intervals as mined, predict purchasing well </span>. Nevertheless, little work...
Computer-supported Collaborative Learning (CSCL) is a pedagogical strategy associated with how learners construct knowledge group by computer-based learning system. In recent years, most of the systems record interaction log each learner when developing course assignments. However, recorded data facing challenge to expose behaviors during and design computer-supported collaborative activity. To address those challenges in this paper, novel programming tool called Software Project Development...
Improving learning outcomes is always one of the key objectives analytics (LA) and educational data mining (EDM). In recent years, many Massive Open Online Courses (MOOC) have been deployed making it easier to collect learners' for further analysis. Naturally, leveraging AI process such kind big becomes main research streams support education. this paper, we collected defined student patterns by online courses on Python programming then verified if their performance was influenced different...