A5101740350- Intelligent Tutoring Systems and Adaptive Learning
- Online Learning and Analytics
- Advanced Multi-Objective Optimization Algorithms
- Machine Learning in Materials Science
- Machine Learning and Algorithms
- Manufacturing Process and Optimization
- Advanced Battery Technologies Research
- Topic Modeling
- Imbalanced Data Classification Techniques
- Machine Learning in Healthcare
- Advancements in Battery Materials
- IoT-based Smart Home Systems
- Advanced Measurement and Metrology Techniques
- Cognitive Science and Mapping
- Privacy-Preserving Technologies in Data
- Infrastructure Resilience and Vulnerability Analysis
- Image and Video Quality Assessment
- Financial Distress and Bankruptcy Prediction
- Auction Theory and Applications
- Advanced Graph Neural Networks
- Scheduling and Timetabling Solutions
- Supply Chain and Inventory Management
- Educational Technology and Assessment
- Computability, Logic, AI Algorithms
- Advanced Algorithms and Applications
East China Normal University
2023-2025
Nanjing University of Information Science and Technology
2013
Cognitive diagnosis aims to gauge students' mastery levels based on their response logs.Serving as a pivotal module in web-based online intelligent education systems (WOIESs), it plays an upstream and fundamental role downstream tasks like learning item recommendation computerized adaptive testing.WOIESs are open environment where numerous new students constantly register complete exercises.In WOIESs, efficient cognitive is crucial fast feedback accelerating student learning.However, the...
Cognitive diagnosis models (CDMs) are designed to learn students' mastery levels using their response logs. CDMs play a fundamental role in online education systems since they significantly influence downstream applications such as teachers' guidance and computerized adaptive testing. Despite the success achieved by existing CDMs, we find that suffer from thorny issue learned too similar. This issue, which refer oversmoothing, could diminish CDMs' effectiveness tasks. comprise two core...
Multi-objective Bayesian optimization (MOBO) has shown promising performance on various expensive multi-objective problems (EMOPs). However, effectively modeling complex distributions of the Pareto optimal solutions is difficult with limited function evaluations. Existing set learning algorithms may exhibit considerable instability in such scenarios, leading to significant deviations between obtained solution and (PS). In this paper, we propose a novel Composite Diffusion Model based Set...
Knowledge tracing (KT) is a crucial task in computer-aided education and intelligent tutoring systems, predicting students’ performance on new questions from their responses to prior ones. An accurate KT model can capture student’s mastery level of different knowledge topics, as reflected predicted questions. This helps improve the learning efficiency by suggesting appropriate that complement states. However, current models have significant drawbacks they neglect imbalanced discrimination...
Cognitive diagnosis is a vital upstream task in intelligent education systems. It models the student-exercise interaction, aiming to infer students' proficiency levels on each knowledge concept. This paper observes that most existing methods can hardly effectively capture homogeneous influence due its inherent complexity. That say, although students exhibit similar performance given exercises, their inferred by these vary significantly, resulting shortcomings interpretability and efficacy....
Due to computationally and/or financially costly evaluation, tackling expensive multi-objective optimization problems is quite challenging for evolutionary algorithms. One popular approach these building cheap surrogate models replace the real function evaluations. To this end, various kinds of surrogate-assisted algorithms (SAEAs) have been proposed, which predict fitness values, classifications, or relation candidate solutions. However, off-spring generation, despite its important role in...
Wireless communication is well used in home energy management systems (HEMS). ZigBee, as a typical example helps to achieve cheap and fast deployment, but also brings resource limits performance issues. An enhanced routing algorithm therefore present this paper improve congestion detection avoidance. Better has been achieved According the experiments conducted practical environment.
Multi-objective combinatorial optimization (MOCO) problems are prevalent in various real-world applications. Most existing neural methods for MOCO rely solely on decomposition and utilize precise hypervolume to enhance diversity. However, these often approximate only limited regions of the Pareto front spend excessive time diversity enhancement because ambiguous time-consuming calculation. To address limitations, we design a Geometry-Aware set Learning algorithm named GAPL, which provides...
The fraudulent insurance claim is critical for the industry. Insurance companies or agency platforms aim to confidently estimate fraud risk of claims by gathering data from various sources. Although more sources can improve estimation accuracy, they inevitably lead increased costs. Therefore, a great challenge verification lies in well balancing these two aspects. To this end, paper proposes framework named cost-efficient optimization with submodularity (CEROS) optimize process verification....
Customer segmentation plays a crucial role in credit risk assessment by dividing users into specific levels based on their scores. Previous methods fail to comprehensively consider the stability process, resulting frequent changes and inconsistencies users' over time. This increases potential risks company. To this end, paper at first introduces formalizes concept of regret process. However, evaluating is challenging due its black-box nature computational burden posed vast user data sets....
Knowledge tracing (KT) is a crucial task in intelligent education, focusing on predicting students' performance given questions to trace their evolving knowledge. The advancement of deep learning this field has led deep-learning knowledge (DLKT) models that prioritize high predictive accuracy. However, many existing DLKT methods overlook the fundamental goal tracking dynamical mastery. These do not explicitly model mastery processes or yield unreasonable results educators find difficulty...