A5038641394- Online Learning and Analytics
- Online and Blended Learning
- Innovative Teaching and Learning Methods
- Topic Modeling
- Advanced Technologies in Various Fields
- Educational Technology and Assessment
- Remote-Sensing Image Classification
- Text and Document Classification Technologies
- Innovative Educational Techniques
- Communication in Education and Healthcare
- Higher Education and Employability
- Educational Technology and Pedagogy
- Advanced Image and Video Retrieval Techniques
- Video Surveillance and Tracking Methods
- Big Data and Business Intelligence
- Educational Strategies and Epistemologies
- Intelligent Tutoring Systems and Adaptive Learning
- Network Security and Intrusion Detection
- Handwritten Text Recognition Techniques
- IoT and Edge/Fog Computing
- Cardiovascular Health and Risk Factors
- Technology-Enhanced Education Studies
- Advanced Graph Neural Networks
- Advanced Malware Detection Techniques
- Water Quality Monitoring and Analysis
Dalian University of Technology
2025
Yunnan Arts University
2021
Beijing University of Posts and Telecommunications
2020
Syracuse University
2019-2020
Beijing Normal University
2020
Xi'an Railway Survey and Design Institute
2020
Self-regulated learning (SRL) is a sustainable development skill that involves learners actively monitoring and adjusting their processes, which essential for lifelong learning. Learning feedback plays crucial role in SRL by aiding self-observation self-judgment. In this context, large language models (LLMs), with ability to use human continuously interact learners, not only provide personalized but also offer data-driven approach education. By leveraging real-time data, LLMs have the...
In recent years, the rapid rise of massive open online courses (MOOCs) has aroused great attention. Dropout prediction or identifying students at risk dropping out a course is an problem for MOOC researchers and providers. This paper formulates dropout as predicting how much content in whole syllabus can be completed by student. A rate model based on recurrent neural network (RNN), URL embedding layer proposed to solve this problem. The results show that accuracy significantly higher than...
Discussion has been widely used in courses, both online and otherwise, as it provides opportunities for students to construct knowledge through interaction with peers instructors. Grouping is a prominent strategy the use of discussion. However, simply dividing cannot guarantee active participation high learning performance. There therefore need pay attention structure and/or features grouping, especially group size composition. The study described this article focuses on combined effects...
The proliferation of massive open online courses (MOOCs) highlights the necessity developing accurate and diagnostic evaluation methods to assess courses' quality effectiveness. Hence, this study proposes a MOOC (DME) method that combines Analytic Hierarchy Process algorithm learner review mining integrate expert opinions, standardized rubrics, feedback into process. For purpose, 30 MOOCs from Coursera website were purposively selected evaluated using DME results compared with rating scores....
Malicious code detection is one of the important missions malicious analysis. Current researches on mostly focused single classifier, whereas classifier not suitable for based features different types. We utilized multi-classifiers ensemble fuzzy integral to improve accuracy framework. A framework Choquet was proposed fuse analysis results base classifiers with features.And genetic algorithm used obtain measure.Finally, result compared a threshold predefined determine maliciousness binary...
With the development of online learning, LMSs accumulated huge amounts students’ interaction data. Unfortunately, with support data, few researchers put a sight on research in MPOCs. Particularly, comparing activity patterns different achievement student groups and course processes MPOCs has been paid less attention. This paper generates hidden Markov models to identify frequently occurring sequence High/Low Learning/Exam under settings. The results demonstrate that High-achievement students...
The purpose of this paper is to study the quality evaluation model innovation and entrepreneurship talents education, combine innovative training system with Internet, improve current mode. Based on CIPP theory, uses analytic hierarchy process determine first level index second in system. background personnel X College, selects experience eight education experts teachers related fields as basis judging measuring influence degree indicators, reasonably arranges weight each indicator,...
In online learning, especially in MPOCs, interaction is considered an important factor that influences learning outcomes and learner achievement. However, few researchers have attempted to derive a valid reliable scale of MPOCs; thus measuring continues be challenging. this study, the MPOCsLI was constructed validated using Exploratory Factor Analysis. Three distinct dimensions MPOCs emerged: Learner-Instructor, Learner-Learner, Learner-Content. Evidence convergent discriminant validity reported.
Abstract In general, deep learning based text classification methods are considered to be effective but tend relatively slow especially for model training. this work, we present a powerful, so-called “scalable attention mechanism”, which performs better than conventional mechanism in terms of both effectiveness and the speed Based on scalable mechanism, propose neural network classification. The experimental results eight representative datasets show that our method can obtain similar...
If HIV-associated Neurocognitive Disorder (HAND) can be diagnosed and treated early, it may delay or reverse its pathological process improve the survival rate of patients. At present, there is little statistical information about HAND, which very disadvantageous to prevention treatment HAND. Therefore, this paper synthetically uses deep learning models such as bidirectional LSTMs, conditional random fields PCNN carry out entity recognition relationship extraction for text data, electronic...
With the popularization of education informatization, colleges and universities generally have information management systems, which can manage school information, teacher student performance are equipped with special databases or data clusters to store this information. How effectively use these extract mine valuable from data, so as provide schools teachers auxiliary decision-making, truly improve level quality running has become an issue worthy attention. The purpose paper is design...