A5009995227- Imbalanced Data Classification Techniques
- Science Education and Pedagogy
- Online Learning and Analytics
- AI in cancer detection
- Anomaly Detection Techniques and Applications
- Radiomics and Machine Learning in Medical Imaging
- Adversarial Robustness in Machine Learning
- Advanced Vision and Imaging
- Fault Detection and Control Systems
- SARS-CoV-2 and COVID-19 Research
- Machine Learning and ELM
- Machine Learning and Data Classification
- Educational Strategies and Epistemologies
- Vehicle License Plate Recognition
- Brain Tumor Detection and Classification
- Metaheuristic Optimization Algorithms Research
- Rough Sets and Fuzzy Logic
- COVID-19 diagnosis using AI
- Medical Image Segmentation Techniques
- Retinal Diseases and Treatments
- Artificial Intelligence in Healthcare and Education
- Educational Technology and Assessment
- Heavy metals in environment
- Air Quality and Health Impacts
- Wireless Communication Security Techniques
Shanghai Jiao Tong University
2004-2025
Dalian University of Technology
2021-2025
Shanghai Jinyuan Senior High School
2024
Zhejiang Industry Polytechnic College
2019-2023
Yunnan University
2022-2023
Ministry of Education of the People's Republic of China
2023
University of Macau
2010-2022
Hunan Institute of Engineering
2021
Chongqing Vocational and Technical University of Mechatronics
2019-2021
West Virginia University
2019-2020
Problem solving is a complex process valuable in everyday life and crucial for learning the STEM fields. To support development of problem-solving skills it important researchers curriculum developers to have practical tools that can measure difference between novice expert performance authentic classroom work. It also useful if such be employed by instructors guide their pedagogy. We describe design, development, testing simple rubric assess written solutions problems given undergraduate...
This paper investigates the role that nonlinear camera response functions (CRFs) have on image deblurring. We present a comprehensive study to analyze effects of CRFs motion In particular, we show how can cause spatially invariant blur behave as varying blur. prove such nonlinearity large errors around edges when directly applying deconvolution blurred without CRF correction. These are inevitable even with known point spread function (PSF) and state-of-the-art regularization-based...
Background: COVID-19 has become one of the most serious global epidemics in 21st Century. This study aims to explore distribution research capabilities countries, institutions, and researchers, hotspots frontiers coronavirus past two decades. In it, references for funding support urgent projects international cooperation among institutions are provided. Method: Web Science core collection database was used retrieve documents related published from 2003 2020. Citespace.5.6.R2,...
The use of machine learning and data mining techniques across many disciplines has exploded in recent years with the field educational growing significantly past 15 years. In this study, random forest logistic regression models were used to construct early warning student success introductory calculus-based mechanics (Physics 1) electricity magnetism 2) courses at a large eastern land-grant university. By combining in-class variables such as homework grades institutional cumulative GPA, we...
Module Analysis for Multiple-Choice Responses (MAMCR) was applied to a large sample of Force Concept Inventory (FCI) pretest and post-test responses ($N_{pre}=4509$ $N_{post}=4716$) replicate the results original MAMCR study understand origins gender differences reported in previous this data set. When could not be replicated, modification method introduced, Modified (MMA). MMA productive understanding structure incorrect answers FCI, identifying 9 groups on 11 post-test. These groups, most...
Background: On December 8, 2019, the first new coronavirus case was discovered in Wuhan, China, and an intensive outbreak incepted next month (about January 20). Virologicalists epidemiologists predict that it will reach a peak about 90 days fade away till end 4 months (Early April), entire epidemic terminate early May. The daily rise confirmed cases increase number of communities on map always hit nerves panic. 31, 2020, World Health Organization (WHO) declared China 's "public health...
This study is to identify the optimum prognosis index for brain metastases by machine learning. Seven hundred cancer patients with were enrolled and divided into 446 training 254 testing cohorts. features seven prediction methods selected evaluate performance of each patient. We used mutual information rough set particle swarm optimization (MIRSPSO) predict patient’s highest accuracy at area under curve (AUC) = 0.978 ± 0.06. The improvement MIRSPSO in terms AUC was 1.72%, 1.29%, 1.83% higher...
The Curriculum Sequencing (CS) problem is a challenging task to tackle in the field of online teaching and learning system development. current methods education management might still possess certain drawbacks that would cause ineffectiveness incompatibility whole system. A solution for achieving better user satisfaction be treat users individually offer educational materials customized way. Adaptive (ACS) plays an important role system, it helps finding optimal sequence curriculum among...
Imbalanced data have become an essential stumbling block in the field of machine learning. In this paper, a novel oversampling method based on local density estimation, namely LD-SMOTE, is presented to address constraints popular rebalance technique SMOTE. LD-SMOTE initiates with k-means clustering quantificationally measure classification contribution each feature. Subsequently, distance metric grounded Jaccard similarity defined, which accentuates features that are more intricately linked...
Many studies have examined the structure and properties of Force Concept Inventory (FCI); however, far less research has investigated Motion Conceptual Evaluation (FMCE). This study applied Multidimensional Item Response Theory (MIRT) to a sample N=4528 FMCE post-test responses. Exploratory factor analysis showed that 5, 9, 10-factor models optimized some fit statistics. The uses extensive blocking items into groups with common stem; these blocks factored together in most models. A...
Demographic variables such as gender, underrepresented minority status, first-generation college student and low socioeconomic status are not important predictor in models to identify students likely receive a D, F, or withdraw their introductory physics course.
Extending modified module analysis of the Force Concept Inventory to include correct responses identifies combinations where response is likely being selected for incorrect reason.
With the application of artificial intelligence in many social fields, research human behavior recognition and non-contact detection physiological parameters based on face other technologies has developed rapidly, culture, sports entertainment also begun to rise. How apply existing mature technology training system taking table tennis as an example is a hot issue worthy study. In this paper, comprehensive intelligent platform Convolutional Neural Network heart rate designed, which mainly...
In this paper, we propose a fast surrogate leverage weighted sampling strategy to generate refined random Fourier features for kernel approximation. Compared the current state-of-the-art method that uses scheme (Li et al. 2019), our new is simpler and more effective. It alignment guide process it can avoid matrix inversion operator when compute function. Given n observations s features, reduce time complexity from O(ns2+s3) O(ns2), while achieving comparable (or even slightly better)...
Abstract Imbalanced datasets exist commonly in the real world, which leads to poor performance of general machine learning models because skewed class distribution. To address data‐imbalance problem, a novel oversampling method based on classification contribution degree, called OS‐CCD is presented. First new concept, established micro and macro information extracted from raw datasets. With enables positive samples near boundary located an area with high density generate more synthetic than...