A5002250629- Dementia and Cognitive Impairment Research
- Brain Tumor Detection and Classification
- Rough Sets and Fuzzy Logic
- Functional Brain Connectivity Studies
- Machine Learning in Bioinformatics
- Advanced Neuroimaging Techniques and Applications
- Machine Learning in Healthcare
- Neurological Disease Mechanisms and Treatments
- vaccines and immunoinformatics approaches
- AI in cancer detection
- Advanced Computational Techniques and Applications
- Medical Image Segmentation Techniques
- Bioinformatics and Genomic Networks
- Time Series Analysis and Forecasting
- Medical Imaging Techniques and Applications
- Smart Agriculture and AI
- Gene expression and cancer classification
- Technology and Security Systems
- Immunotherapy and Immune Responses
- Cloud Data Security Solutions
- Radiomics and Machine Learning in Medical Imaging
- Cardiovascular Health and Disease Prevention
- Remote Sensing and LiDAR Applications
- Data Mining Algorithms and Applications
- Artificial Intelligence in Healthcare
Guangdong University of Technology
2020-2025
Guangdong Polytechnic Normal University
2019-2025
Beijing University of Technology
2010-2022
WSP Sverige (Sweden)
2020
Guangzhou Electronic Technology (China)
2019
Guangzhou Building Materials Institute
2012
China Mobile (China)
2002-2007
Guangzhou University
2007
China Southern Power Grid (China)
2002-2006
South China University of Technology
2002
Early detection is critical for effective management of Alzheimer's disease (AD) and screening mild cognitive impairment (MCI) common practice. Among several deep-learning techniques that have been applied to assessing structural brain changes on magnetic resonance imaging (MRI), convolutional neural network (CNN) has gained popularity due its superb efficiency in automated feature learning with the use a variety multilayer perceptrons. Meanwhile, ensemble (EL) shown be beneficial robustness...
Abstract Deep learning (DL) on brain magnetic resonance imaging (MRI) data has shown excellent performance in differentiating individuals with Alzheimer's disease (AD). However, the value of DL detecting progressive structural MRI (sMRI) abnormalities linked to AD pathology yet be established. In this study, an interpretable algorithm named Ensemble 3‐dimensional convolutional neural network ( 3DCNN ) enhanced parsing techniques is proposed investigate longitudinal trajectories whole‐brain...
To enhance the efficacy of crack detection techniques and tackle challenges such as selecting initial clustering centers in extraction algorithms their sensitivity to varying image backgrounds, this research proposes an intelligent concrete recognition system utilizing deep learning methodologies. Among these, convolutional neural networks (CNNs) stand out for representation capabilities, allowing them classify input data according a hierarchical structure. In case study involving bridge...
Alzheimer's disease (AD) classification models usually segment the entire brain image into voxel blocks and assign them labels consistent with image, but not every block is closely related to disease. To this end, an AD auxiliary diagnosis framework based on weakly supervised multi-instance learning (MIL) multi-scale feature fusion proposed, designed from three aspects: within block, between blocks, high-confidence blocks. First, a three-dimensional convolutional neural network was used...
Pre-extracted aortic dissection (AD) centerline is very useful for quantitative diagnosis and treatment of AD disease. However, extraction challenging because (i) the lumen narrow irregular, yielding failure in feature interrupted topology; (ii) acute nature requires a quick algorithm, however, scans usually contain thousands slices, time-consuming. In this paper, fast which based on local conformal deep reinforced agent dynamic tracking framework, presented. The potential dependence...
In this paper, we've developed a novel approach to knowledge acquisition based on rough set theory and principal component analysis. A PCA-based quantitative index measures the relative importance of different condition attributes among state space constructed by all attributes. The strengthens attribute attribute-value reductions while maintaining decision table's discernibility relations. Our KA-RSPCA algorithm outperformed four other RS algorithms two test data sets.
An adaptive interpretable ensemble model based on a 3-D convolutional neural network (3DCNN) and genetic algorithm (GA), i.e., 3DCNN+EL+GA, was proposed to differentiate the subjects with Alzheimer's disease (AD) or mild cognitive impairment (MCI) also identify discriminative brain regions significantly contributing classifications in data-driven way. The testing results datasets from both AD Neuroimaging Initiative (ADNI) Open Access Series of Imaging Studies (OASIS) indicated that...
The integration of structural magnetic resonance imaging (sMRI) and deep learning techniques is one the important research directions for automatic diagnosis Alzheimer's disease (AD). Despite satisfactory performance achieved by existing voxel-based models based on convolutional neural networks (CNNs), such only handle AD-related brain atrophy at a single spatial scale lack localization abnormal regions model interpretability. To address above limitations, we propose traceable...
In this paper, the PCA-PSOBP neural network has been put forward to model ultrafiltration of printing and dyeing wastewater. Firstly, Principal Component Analysis (PCA) was applied reduce dimensions correlations input parameters. Secondly, PSOBP used optimize weights thresholds networks, in which BP were adjusted by particle swarm optimization (PSO) rather than traditional gradient descent method. Based on experimental data, simulations are performed with MATLAB. The results showed that a...
IPTV services continue to disrupt the traditional cable-based TV delivery and grow in popularity. However, they also face challenges related of stable problem free video streams end users while minimizing downtime due inherent complexity uncertainty associated with IP based networks. In this work, we share our experience on addressing service assurance for a commercial provider. The key focus here is root cause inference aspects aimed at providing QoE hints localization network technicians...