A5085214289- Anomaly Detection Techniques and Applications
- Data Mining Algorithms and Applications
- Data Management and Algorithms
- Brain Tumor Detection and Classification
- Face and Expression Recognition
- Text and Document Classification Technologies
- Rough Sets and Fuzzy Logic
- Network Security and Intrusion Detection
- Image Retrieval and Classification Techniques
- Advanced Computational Techniques and Applications
- Machine Learning and ELM
- Human Mobility and Location-Based Analysis
- Advanced Clustering Algorithms Research
- Artificial Immune Systems Applications
- Human Pose and Action Recognition
- Video Surveillance and Tracking Methods
- Advanced Algorithms and Applications
- Image and Video Quality Assessment
- Advanced Computing and Algorithms
- Privacy-Preserving Technologies in Data
- Geographic Information Systems Studies
- Advanced Image and Video Retrieval Techniques
- Data Visualization and Analytics
- Advanced Image Fusion Techniques
- Privacy, Security, and Data Protection
Nanjing Normal University
2016-2025
Air Force Medical University
2004-2020
Xijing Hospital
2009-2020
Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application
2018-2020
Jiangsu Key Laboratory of 3D Printing Equipment and Manufacturing
2015-2016
PRG S&Tech (South Korea)
2016
Fuzhou University
2015
Toyota Central Research and Development Laboratories (Japan)
2015
City College of New York
2015
New York Psychoanalytic Society and Institute
2015
Particle swarm optimization (PSO) is a heuristic global method, proposed originally by Kennedy and Eberhart in 1995. It now one of the most commonly used techniques. This survey presented comprehensive investigation PSO. On hand, we provided advances with PSO, including its modifications (including quantum-behaved bare-bones chaotic fuzzy PSO), population topology (as fully connected, von Neumann, ring, star, random, etc.), hybridization (with genetic algorithm, simulated annealing, Tabu...
(Purpose) Early diagnosis or detection of Alzheimer's disease (AD) from the normal elder control (NC) is very important. However, computer-aided (CAD) was not widely used, and classification performance did reach standard practical use. We proposed a novel CAD system for MR brain images based on eigenbrains machine learning with two goals: accurate both AD subjects AD-related regions. (Method) First, we used maximum inter-class variance to select key slices 3D volumetric data. Second,...
ABSTRACT Automated and accurate classification of MR brain images is crucially importance for medical analysis interpretation. We proposed a novel automatic system based on particle swarm optimization (PSO) artificial bee colony (ABC), with the aim distinguishing abnormal brains from normal in MRI scanning. The method used stationary wavelet transform (SWT) to extract features images. SWT translation‐invariant performed well even image suffered slight translation. Next, principal component...
Background: Developing an accurate computer-aided diagnosis (CAD) system of MR brain images is essential for medical interpretation and analysis. In this study, we propose a novel automatic CAD to distinguish abnormal brains from normal in MRI scanning. Methods: The proposed method simplifies the task binary classification problem. We used discrete wavelet packet transform (DWPT) extract coefficients images. Next, Shannon entropy (SE) Tsallis (TE) were harnessed obtain features DWPT...
Fruit classification is quite difficult because of the various categories and similar shapes features fruit. In this work, we proposed two novel machine-learning based methods. The developed system consists wavelet entropy (WE), principal component analysis (PCA), feedforward neural network (FNN) trained by fitness-scaled chaotic artificial bee colony (FSCABC) biogeography-based optimization (BBO), respectively. K-fold stratified cross validation (SCV) was utilized for statistical analysis....
Abstract Accurate fruit classification is difficult to accomplish because of the similarities among various categories. In this paper, we proposed a novel fruit‐classification system, with goal recognizing fruits in more efficient way. Our methodology included following steps. First, four‐step pre‐processing was employed. Second, features (colour, shape, and texture) were extracted. Third, utilized principal component analysis remove excessive features. Fourth, system based on...
Automated abnormal brain detection is extremely of importance for clinical diagnosis. Over last decades numerous methods had been presented. In this paper, we proposed a novel hybrid system to classify given MR image as either normal or abnormal. The method first employed digital wavelet transform extract features then used principal component analysis (PCA) reduce the feature space. Afterwards, constructed kernel support vector machine (KSVM) with RBF kernel, using particle swarm...
Background) We proposed a novel computer-aided diagnosis (CAD) system based on the hybridization of biogeography-based optimization (BBO) and particle swarm (PSO), with goal detecting pathological brains in MRI scanning.(Method) The method used wavelet entropy (WE) to extract features from MR brain images, followed by feed-forward neural network (FNN) training Hybridization BBO PSO (HBP), which combined exploration ability exploitation PSO.(Results) 10 repetition k-fold cross validation...
In Brief BACKGROUND: The treatment of postherpetic neuralgia (PHN) continues to be a challenge in clinical pain management. this randomized, controlled study, we assessed the effectiveness repetitive paravertebral injections with local anesthetics and steroids for prevention PHN patients acute herpes zoster. METHODS: One hundred thirty-two zoster diagnosed 1–7 days after onset rash were randomly assigned receive either standard therapy (oral antivirals analgesics) or additional mixture 10 mL...
In this paper, we proposed a hybrid system to predict corporate bankruptcy. The whole procedure consists of the following four stages: first, sequential forward selection was used extract most important features; second, rule-based model chosen fit given dataset since it can present physical meaning; third, genetic ant colony algorithm (GACA) introduced; fitness scaling strategy and chaotic operator were incorporated with GACA, forming new algorithm—fitness-scaling GACA (FSCGACA), which seek...
We propose the use of exponent wavelet transform (EWT) coefficients as a sparse representation which is combined with iterative shrinkage/threshold algorithm (ISTA) for reconstruction compressed sensing magnetic resonance imaging. In addition, random shifting (RS) employed to guarantee translation invariance property discrete transform. The proposed method termed exponential (EWISTARS), takes advantages EWT, simplicity ISTA, and RS. Simulation results on brain, vertebrae, knee MR images...
The multi-depot vehicle routing problem is a well-known non-deterministic polynomial-time hard combinatorial optimization problem, which crucial for transportation and logistics systems. We proposed novel fitness-scaling adaptive genetic algorithm with local search (FISAGALS). technique converts the raw fitness value to new that suitable selection. rates strategy changes crossover mutation probabilities depending on value. mechanism exploits space in more efficient way. experiments employed...
It is important to detect abnormal brains accurately and early. The wavelet-energy (WE) was a successful feature descriptor that achieved excellent performance in various applications; hence, we proposed WE based new approach for automated detection, reported its preliminary results this study. kernel support vector machine (KSVM) used as the classifier, quantum-behaved particle swarm optimization (QPSO) introduced optimize weights of SVM. on 5 × 5-fold cross validation showed + QPSO-KSVM...
It is well known that tumor microenvironment plays a vital role in drug resistance and cell adhesion-mediated (CAM-DR), form of de novo resistance. In our previous study, we reported MGr1-Ag/37LRP ligation-induced adhesion participated protecting gastric cancer cells from number apoptotic stimuli caused by chemotherapeutic drugs. Further study suggested MGr1-Ag could prompt CAM-DR through interaction with laminin. However, the MGr1-Ag-initiated intracellular signal transduction pathway still...