A5051900701- Recommender Systems and Techniques
- Data Management and Algorithms
- Advanced Bandit Algorithms Research
- Intelligent Tutoring Systems and Adaptive Learning
- Human Mobility and Location-Based Analysis
- Video Analysis and Summarization
- Online Learning and Analytics
- Image Retrieval and Classification Techniques
- Context-Aware Activity Recognition Systems
- Advanced Battery Technologies Research
- Advanced Multi-Objective Optimization Algorithms
- Advanced Wireless Network Optimization
- Text and Document Classification Technologies
- Advancements in Battery Materials
- Multi-Criteria Decision Making
- Advanced Battery Materials and Technologies
- Personality Traits and Psychology
- Advanced Data Compression Techniques
- Topic Modeling
- Advanced Graph Neural Networks
- Advanced Text Analysis Techniques
- Data Mining Algorithms and Applications
- Reservoir Engineering and Simulation Methods
- Expert finding and Q&A systems
- Network Security and Intrusion Detection
Shandong University of Finance and Economics
2025
Illinois Institute of Technology
2016-2024
Chongqing University of Technology
2024
Sinopec (China)
2020-2023
University of Science and Technology Beijing
2015-2021
Wuhan University of Technology
2020
Limerick Institute of Technology
2019
Chongqing University
2012-2018
China West Normal University
2018
DePaul University
2011-2016
Recommender system has been demonstrated as one of the most useful tools to assist users' decision makings. Several recommendation algorithms have developed and implemented by both commercial open-source libraries. Context-aware recommender (CARS) emerged a novel research direction during past decade many contextual proposed. Unfortunately, no engines start embed those in their kits, due special characteristics data format processing methods domain CARS. This paper introduces an Java-based...
In this study, the degradation of a LiFePO<sub>4</sub>/graphite battery under an over-discharge process and its effect on further cycling stability are investigated.
The main reason for the degradation of slightly overcharged NCM/graphite full cells was found to be unstable crystal structure NCM material at a relatively high delithiation state.
ChatGPT, an implementation and application of large language models, has gained significant popularity since its initial release. Researchers have been exploring ways to harness the practical benefits ChatGPT in real-world scenarios. Educational researchers investigated potential various subjects, e.g., programming, mathematics, finance, clinical decision support, etc. However, there limited attention given data science education. This paper aims bridge that gap by utilizing a course,...
Context-aware recommender systems (CARS) take contextual conditions into account when providing item recommendations. In recent years, context-aware matrix factorization (CAMF) has emerged as an extension of the technique that also incorporates conditions. this paper, we introduce another approach for recommendations, SLIM (CSLIM) recommendation approach. It is derived from sparse linear method (SLIM) which was designed Top-N recommendations in traditional systems. Based on experimental...
User and item splitting are well-known approaches to context-aware recommendation. To perform splitting, multiple copies of an created based on the contexts in which it has been rated. performs a similar treatment with respect users. The combination user splitting: UI splits both users items data set boost recommendations. In this paper, we empirical comparison these three (CASA) sets, also compare them other popular collaborative filtering (CACF) algorithms. evaluate those algorithms,...
Context-aware recommender systems (CARS) are extensions of traditional recommenders that also take into account contextual condition a user to whom recommendation is made. The problem is, however, still focused on recommending set items target user. In this paper, we consider the appropriate contexts in which an item should be selected. We believe context can used as another tools assist users' decision making. formulate and discuss motivation behind possible applications concept. identify...
Recommender systems (RSs) have been successfully applied to alleviate the problem of information overload and assist users' decision makings. Multi-criteria recommender is one RSs which utilizes multiple ratings on different aspects items (i.e., multi-criteria ratings) predict user preferences. Traditional approaches usually each criterion individually aggregate them together estimate In this paper, we propose an approach named as "Criteria Chains", where combination criteria can be utilized...
Recommender systems have been demonstrated as a useful tool in assisting decision makings. Multi-criteria recommender take advantage user preferences multiple criteria to produce better recommendations. In this paper, we propose utility-based multi-criteria recommendation algorithm, which learn the expectations by different learning-to-rank methods. Our experimental results based on real-world data sets demonstrate effectiveness of proposed models.
Recommender systems have been served to assist decision making by recommending a list of items the end users. Multi-criteria recommender system (MCRS) is type which enhance recommendation performance taking user preferences on multiple criteria. Traditional algorithms for MCRS usually predict ratings these criteria, and finally estimate overall rating different aggregation functions. In this paper, we propose new multi-criteria framework in can take advantage Pareto ranking based estimated...
Traditional recommender systems suggest items by learning from user preferences, but ignore other stakeholders in the whole system. Actually, not only receiver of recommendations, also may come into play, such as producers or those system owners. Reciprocal dating job recommendations is one these examples. However, we have to simulate utilities for each type stakeholder due utility definitions. In this paper, perform exploratory analysis on a speed-dating data, where expectations are clearly...
Abstract The influence of personality traits on educational outcomes has been widely recognized and studied. Research explored its effects factors such as student satisfaction, academic anxiety, dishonesty, particularly during the COVID-19 pandemic. However, there a lack studies comparing learning behaviors performance students with different pre, during, post-COVID-19 lockdown periods. This study fills this gap by analyzing differences in metrics, class grades assignment submissions, among...