A5102785217- Advanced Neuroimaging Techniques and Applications
- Fetal and Pediatric Neurological Disorders
- Functional Brain Connectivity Studies
- Data Mining Algorithms and Applications
- Rough Sets and Fuzzy Logic
- Text and Document Classification Technologies
- Gene expression and cancer classification
- Neonatal and fetal brain pathology
- Face and Expression Recognition
- Hemispheric Asymmetry in Neuroscience
- Spam and Phishing Detection
- Machine Learning in Bioinformatics
- Imbalanced Data Classification Techniques
- Neural Networks and Applications
- Bioinformatics and Genomic Networks
- Morphological variations and asymmetry
- Network Security and Intrusion Detection
- Fuzzy Logic and Control Systems
- AI in cancer detection
- Machine Learning and ELM
- Neural dynamics and brain function
- Vestibular and auditory disorders
- Medical Image Segmentation Techniques
- Spinal Dysraphism and Malformations
- Web Data Mining and Analysis
Shandong University
2016-2025
Shanghai Center for Brain Science and Brain-Inspired Technology
2023-2025
Gannan Medical University
2023
Qilu Hospital of Shandong University
2022
University of Southern California
2017-2020
Shandong Provincial QianFoShan Hospital
2019
China Electronics Technology Group Corporation
2012-2013
Georgia State University
2005-2009
Medical University of South Carolina
2009
Shandong Provincial Hospital
1997
Extracting a subset of informative genes from microarray expression data is critical preparation step in cancer classification and other biological function analyses. Though many algorithms have been developed, the support vector machine-recursive feature elimination (SVM-RFE) algorithm one best gene selection algorithms. It assumes that smaller "filter-out" factor SVM-RFE, which results number features eliminated each recursion, should lead to extraction better subset. Because SVM-RFE...
Abstract The cerebellum plays a crucial role in functions, including sensory‐motor coordination, cognition, and emotional processing. Compared to the neocortex, human exhibits protracted developmental trajectory. This delayed timeline may lead increased sensitivity of external influences, potentially extending vulnerability period for neurological disorders. Abnormal cerebellar development individuals with autism has been confirmed, these atypical changes affect neocortex. However, due...
Abstract Numerous behavioral observations and brain function studies have demonstrated that neurological differences exist between East Asians Westerners. However, the extent to which these factors relate in structure is still not clear. As basis of functions, anatomical play a primary critical role origination functional behavior differences. To investigate underlying two cultural/ethnic groups, we conducted comparative study on education‐matched right‐handed young male adults (age = 22–29...
Mammography is one of the most popular tools for early detection breast cancer. Contour mass in mammography very important information to distinguish benign and malignant mass. smooth round or oval, while has irregular shape spiculated contour. Several studies have shown that 1D signature translated from 2D contour can describe features well.In this paper, we propose a new method translate into signature. The not only but also regularity Then segment whole different subsections. We extract...
Both neuropsychological and functional neuroimaging studies have identified that the posterior parietal lobe (PPL) is critical for attention function. However, unique role of distinct cortical subregions their underlying white matter (WM) remains in question. In this study, we collected both magnetic resonance imaging diffusion tensor (DTI) data normal participants, evaluated performance using network test (ANT), which could isolate three different components: alerting, orienting executive...
Extracting a subset of informative genes from microarray expression data is critical preparation step in cancer classification and other biological function analyses. Though many algorithms have been developed, the support vector machine-recursive feature elimination (SVM-RFE) algorithm one best gene selection algorithms. It assumes that smaller "filter-out" factor SVM-RFE, which results number features eliminated each recursion, should lead to extraction better subset. Because SVM-RFE...
Functional neuroimaging studies have indicated the involvement of separate brain areas in three distinct attention systems: alerting, orienting and executive control (EC). However, structural correlates underlying remains unexplored. Here, we utilized graph theory to examine neuroanatomical substrates systems measured by network test (ANT) 65 healthy subjects. White matter connectivity, assessed with DTI deterministic tractography was modeled as a comprising 90 nodes defined Automated...
The morphology and function of the cerebellum are associated with various developmental disorders healthy aging. Changes in cerebellar during aging process have been extensively investigated, most studies focusing on changes regional volume. volumetric method has used to quantitatively demonstrate decrease volume age, but it certain limitations visually presenting morphological atrophy from a three-dimensional perspective. Thus, we comprehensively described through measurements subregions...
Image spam poses a great threat to email communications due high volumes, bigger bandwidth requirements, and higher processing requirements for filtering. We present feature extraction classification framework that operates on features can be extracted from image files in very fast fashion. The considered are thoroughly analyzed regarding their information gain. performance results C4.5 decision tree support vector machine classifiers. Lastly, we compare the achieved using these more complex...
According to the latest Braak staging of Alzheimer's disease (AD), tau pathology occurs earliest in brain locus coeruleus (LC) brainstem, then propagates transentorhinal cortex (TEC), and later other neocortical regions. Recent animal vivo human imaging research also support trans-axonal propagation pathology. In addition, neurochemical studies link norepinephrine behavioral symptoms AD. It is thus critical examine integrity LC-TEC pathway studying early development disease, but there has...
Introduction: Major depressive disorder is a mental disease with complex pathogenesis and treatment mechanisms involving changes in both the gut microbiota neuroinflammation. Cuscutae Semen (CS), also known as Chinese Dodder seed, medicinal herb that exerts several pharmacological effects. These include neuroprotection, anti-neuroinflammation, repair of synaptic damage, alleviation oxidative stress. However, whether CuscutaeSemen an antidepressant effect remains unknown. Methods: In this...
We propose a new learning model called granular support vector machines for data classification problems. Granular systematically and formally combines the principles from statistical theory computing theory. It works by building sequence of information granules then machine in each granule. In this paper, we also give simple but efficient implementation method modeling just two top-down way (that is, halving whole feature space). The hyperplane used to halve space is selected extending...
Unwanted and malicious messages dominate email traffic pose a great threat to the utility of communications. Reputation systems have been getting momentum as solution. Such extract senders behavior data based on global sending distribution, analyze them assign value trust each IP address messages. We build two models for classification purpose. One is support vector machines (SVM) other random forests(RF). Experimental results show that either classifier effective. RF slightly more accurate,...
<para xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> A typical microarray gene expression dataset is usually both extremely sparse and imbalanced. To select multiple highly informative subsets for cancer classification diagnosis, a new <emphasis emphasistype="italic">Fuzzy Granular Support Vector Machine---Recursive Feature Elimination</emphasis> algorithm (FGSVM-RFE) designed in this paper. As hybrid of statistical learning, fuzzy clustering,...