A5067457943- Rough Sets and Fuzzy Logic
- Advanced Computational Techniques and Applications
- Data Mining Algorithms and Applications
- Advanced Decision-Making Techniques
- Geoscience and Mining Technology
- EEG and Brain-Computer Interfaces
- Sleep and Work-Related Fatigue
- Heart Rate Variability and Autonomic Control
- Radiomics and Machine Learning in Medical Imaging
- Quantum Computing Algorithms and Architecture
- Semantic Web and Ontologies
- Color Science and Applications
- Advanced Algebra and Logic
- Advanced Sensor and Control Systems
- Data Management and Algorithms
- Quantum Information and Cryptography
- Fuzzy Logic and Control Systems
- Privacy-Preserving Technologies in Data
- Handwritten Text Recognition Techniques
- Image Enhancement Techniques
- Quantum Mechanics and Applications
- Currency Recognition and Detection
- Thyroid Cancer Diagnosis and Treatment
- Extenics and Innovation Methods
- AI in cancer detection
Nanchang University
2015-2025
China University of Petroleum, Beijing
2019
Nanchang Institute of Science & Technology
2017
Jiangxi College of Applied Technology
2010
Beijing Jiaotong University
2005-2010
East China Jiaotong University
2007
Nanjing University
2007
Abstract Water resources protection is related to the development of social economy, and monitoring prediction water environmental indicators have important practical significance. In view seasonality, periodicity, uncertainty, nonlinear characteristics quality data, traditional models poor performance. To address this issue, paper introduces a hybrid index model based on Ensemble Empirical Mode Decomposition (EEMD), combined with Convolutional Neural Network (CNN) Bidirectional Long...
The presence of gross extrathyroidal extension (ETE) in thyroid cancer will affect the prognosis patients, but imaging examination cannot provide a reliable diagnosis for it. This study was conducted to develop deep learning (DL) model localization and evaluation nodules ultrasound images before surgery ETE.From January 2016 December 2021 grayscale 806 (4451 images) from 4 medical centers were retrospectively analyzed, including 517 no ETE 289 nodules. 283 158 randomly selected internal...
Crowd monitoring in the context of smart libraries is great significance for resource optimization and service improvement. However, existing models struggle to achieve real-time performance accuracy high-density, enclosed environments.This study addresses these limitations following way: Firstly, pedestrian flow videos from side view angle were collected at different time periods on second floor library. The frame-extracted into images manually annotated, resulting a high-quality dataset...
In view of the nonlinear characteristics electroencephalography (EEG) signals collected in driving fatigue state recognition research and issue that accuracy method based on EEG is still unsatisfactory, this paper proposes a sample entropy (SE) kernel principal component analysis (KPCA), which combines advantage high advantages KPCA dimensionality reduction for components strong non-linear processing capability. By using support vector machine (SVM) classifier, proposed (called SE_KPCA)...
Our objective is to study how obtain features which can reflect the continuity and internal dynamic changes of electroencephalography (EEG) signals an effective method for fatigued driving state recognition based on obtained features.A EEG signalfeature extraction functional data analysis proposed. Combined with kernel principal component method, are applied driver fatigue state, a corresponding model constructed.The tested real collected by selecting suitable classifier. The test results...
Abstract At present, there are still many old-fashioned water meters in the society, and department needs to send staff read meter after arriving at scene with a handheld all-in-one machine. However, problems this manual reading method. First, large number of work leads low efficiency entire department, consuming lot time energy, high labor costs; second, natural scenes have such as serious dial contamination other environmental factors that interfere staff, results reader cannot be verified...
Abstract DBSCAN is a famous density-based clustering algorithm that can discover clusters with arbitrary shapes without the minimal requirements of domain knowledge to determine input parameters. However, not suitable for databases different local-density and also very time-consuming algorithm. In this paper, we present quantum mutual MinPts -nearest neighbor graph (MMNG)-based The proposed performs better on clusters. Furthermore, has dramatic increase in speed compared its classic counterpart.
hotspot in computer science nowadays. The main objective of this paper is to describe domain ontologies at different granularities and hierarchies based on granular computing. A space model for ontology learning was explored, some definitions such as concept granules, worlds the structure were described formally. Accordingly, composition decomposition granules operation properties introduced. proposed available research data mining levels granularity Index term-- Granular Computing, Concept...
Ontology learning technology has become a research hotspot in computer science nowadays. The main objective of this paper is to describe domain ontologies at different granularities and hierarchies based on granular computing. A space model for ontology was explored, some definitions such as concept granules, worlds the structure were described formally. Accordingly, composition decomposition granules operation properties introduced. proposed available data mining levels granularity