A5101744619- Face and Expression Recognition
- Remote-Sensing Image Classification
- Sparse and Compressive Sensing Techniques
- Fish Ecology and Management Studies
- Fish Biology and Ecology Studies
- Image Retrieval and Classification Techniques
- AI in cancer detection
- Radiomics and Machine Learning in Medical Imaging
- Cambodian History and Society
- Neural Networks and Applications
- Text and Document Classification Technologies
- Functional Brain Connectivity Studies
- Brain Tumor Detection and Classification
- Gene expression and cancer classification
- Machine Learning and ELM
- Blind Source Separation Techniques
- Anomaly Detection Techniques and Applications
- Advanced Neuroimaging Techniques and Applications
- Remote Sensing and Land Use
- Video Surveillance and Tracking Methods
- Advanced Image and Video Retrieval Techniques
- Face recognition and analysis
- Fish biology, ecology, and behavior
- Dementia and Cognitive Impairment Research
- Machine Learning in Bioinformatics
Baotou Central Hospital
2020-2025
Fisheries Administration
2008-2024
Shenzhen Institutes of Advanced Technology
2023
Shenzhen University
2018-2022
Southern University of Science and Technology
2022
Shenzhen Bao'an District People's Hospital
2021
Georgia Regents Medical Center
2015
Augusta University
2015
Shenzhen Sixth People's Hospital
2014
University Town of Shenzhen
2013
Microarray techniques have been used to delineate cancer groups or identify candidate genes for prognosis. As such problems can be viewed as classification ones, various methods applied analyze interpret gene expression data. In this paper, we propose a novel method based on robust principal component analysis (RPCA) classify tumor samples of Firstly, RPCA is utilized highlight the characteristic associated with special biological process. Then, and RPCA+LDA (robust linear discriminant...
Subspace learning and Support Vector Machine (SVM) are two critical techniques in pattern recognition, playing pivotal roles feature extraction classification. However, how to learn the optimal subspace such that SVM classifier can perform best is still a challenging problem due difficulty optimization, computation, algorithm convergence. To address these problems, this paper develops novel method named Optimal Discriminant (ODSVM), which integrates support vector classification with...
High-dimensional small sample size data, which may lead to singularity in computation, are becoming increasingly common the field of pattern recognition. Moreover, it is still an open problem how extract most suitable low-dimensional features for support vector machine (SVM) and simultaneously avoid so as enhance SVM's performance. To address these problems, this article designs a novel framework that integrates discriminative feature extraction sparse selection into make full use...
Cambodia faces the challenge of managing excess water during wet season and insufficient dry season. This harms human life endangers aquatic natural resources, agricultural practices, food security. Water governance is crucial to ensure well-being both people their However, Cambodia’s hindered by various obstacles, including sectoral centralized influences, top-down large-scale strategies, weak coordination among relevant agencies, limited involvement local communities. study examines across...
Support vector machine (SVM), as a supervised learning method, has different kinds of varieties with significant performance. In recent years, more research focused on nonparallel SVM, where twin SVM (TWSVM) is the typical one. order to reduce influence outliers, robust distance measurements are considered in these methods, but discriminability models neglected. this article, we propose manifold bounded (RMTBSVM), which considers both robustness and discriminability. Specifically, novel...
The brain network is an effective tool and has been widely used in the field of neurodegenerative disease analysis. Due to high cost accessing medical image data, efforts have devoted investigating data augmentation. However, containing topological characteristics non-European space different from traditional which makes it challenging synthesize structural connectivity limits application In this paper, a Hemisphere-separated Cross-connectome Aggregating Learning (HCAL) model proposed...
The Mekong River is one of the most biodiverse, productive rivers in world, supporting more than 1000 fish species and livelihoods tens millions people. spatial dynamics population status many species, especially megafishes, are poorly understood. Therefore, this information rarely incorporated into environmental risk assessments for large infrastructure projects, such as mainstream hydropower developments, which have been accelerating rapidly Basin. In study, we present initial findings...
Despite the government’s active promotion of rice production, a significant portion population still faces food insecurity. While existing literature often highlights success achieving surplus, few studies delve into connections between surplus and security, critically analyze why security is persistent. In addressing this issue, study investigates underlying causes insecurity amidst efforts to increase production. The entails comprehensive review an examination in three provinces Cambodian...
Conventional linear discriminant analysis and its extended versions have some potential drawbacks. First, they are sensitive to outliers, noise, variations in data, which degrades their performances dimensionality reduction. Second, most of the analysis-based methods only focus on global structures data but ignore local geometric structures, play important roles More importantly, total number projections obtained by (LDA) based limited class training set. To solve problems mentioned above,...
Ridge Regression (RR) is a classical method that widely used in multiple regression analysis. However, traditional RR does not take the local geometric structure of data into consideration for discriminative learning and it sensitive to outliers as based on <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$L_{2}$</tex-math></inline-formula> -norm. To address this problem, article proposes novel called Joint...
To solve the Small Sample Size (SSS) problem, recent linear discriminant analysis using 2D matrix-based data representation model has demonstrated its superiority over that conventional vector-based in face recognition [7]. But explicit reason why is better than vectorized not been given until now. In this paper, a framework of Generalized Fisher Discriminant Analysis (G2DFDA) proposed. Three contributions are included framework: 1) essence these ’2D’ methods analyzed and their relationships...