A5100673449- Access Control and Trust
- Radiomics and Machine Learning in Medical Imaging
- Lung Cancer Diagnosis and Treatment
- Image Retrieval and Classification Techniques
- Context-Aware Activity Recognition Systems
- Energy Efficient Wireless Sensor Networks
- Modular Robots and Swarm Intelligence
- Remote-Sensing Image Classification
- Privacy-Preserving Technologies in Data
- ECG Monitoring and Analysis
- Image and Signal Denoising Methods
- IoT and Edge/Fog Computing
- Muscle activation and electromyography studies
- Multi-Agent Systems and Negotiation
- Control Systems in Engineering
- Advanced Image Fusion Techniques
- Robot Manipulation and Learning
- Spam and Phishing Detection
- Brain Tumor Detection and Classification
- Service-Oriented Architecture and Web Services
- Smart Agriculture and AI
- Non-Invasive Vital Sign Monitoring
- Logic, Reasoning, and Knowledge
- Medical Imaging Techniques and Applications
- Digital Radiography and Breast Imaging
Yangzhou University
2007-2024
South China University of Technology
2012-2024
Nanjing University
2007-2008
Various fall-detection solutions have been previously proposed to create a reliable surveillance system for elderly people with high requirements on accuracy, sensitivity and specificity. In this paper, an enhanced fall detection is person monitoring that based smart sensors worn the body operating through consumer home networks. With treble thresholds, accidental falls can be detected in healthcare environment. By utilizing information gathered from accelerometer, cardiotachometer sensors,...
<title>Abstract</title> <bold>Objective</bold>: The aim of this study was to develop and evaluate binary classification models detect physical fatigue in badminton athletes using inertial measurement unit (IMU) data machine learning algorithms. <bold>Methods</bold>: Thirty-two collegiate participated study. Movement these participants were collected multi-sensor IMUs placed on key body regions a single forearm IMU sensor before after induction. Feature selection performed Lasso regression...
This article proposes a method for single-leader–dual-follower teleoperation, where one robot (direct-follower robot, DFR) is directly teleoperated and the other (assisting-follower AFR) can autonomously cooperate with DFR to hold move deformable object, contact force regulated desired value. Since AFR does not know its partner's movement, first, it achieves position alignment by using force. Second, we develop an adaptive movement estimation algorithm according Lyapunov theory, such that...
Classification of benign and malignant pulmonary nodules can provide useful indicators for estimating the risk lung cancer. In this study, an improved random forest (RF) algorithm is proposed classification in thoracic computed tomography images. First, walk to automatically segment nodules. Then, intensity, geometric texture features based on grey‐level co‐occurrence matrix, rotation invariant uniform local binary pattern Gabor filter methods are combined generate effective discriminative...
Segmentation of pulmonary nodule in thoracic computed tomography (CT) plays an important role the computer-aided diagnosis (CAD) and clinical practices. However, segmentation nodules still remains a challenging task due to presence intrinsic noise, low contrast, intensity-profile inhomogeneity, variable sizes shapes. Many variants extensions fuzzy C-mean (FCM) clustering algorithm have been developed preserve image details as well suppress noises. these overemphasize importance spatial...
This article investigates an adaptive neural network (NN) control technique with fixed-time tracking capabilities, employing composite learning, for manipulators under constrained position error. The first step involves integrating the learning method into NN to address dynamic uncertainties that inevitably arise in manipulators. A updating law of weights is formulated, requiring adherence solely relaxed interval excitation (IE) conditions. In addition, output error, instead knowing initial...
Binary pattern methods play a vital role in extracting texture feature. However, most of them are deficient to capture comprehensive and discriminative information. This paper aims propose novel multi-statistic binary extract rotation invariance statistic features for classification. First, this encodes the center pixel, mean, variance range local neighborhood by corresponding multi-scale threshold, proposes pattern, mean pattern. Then, based compact multi-pattern encoding strategy, four...
In open and dynamic systems, interaction between participants suffers the problem of determining one another's trustworthiness. Automated trust negotiation is a process establishing step by through bilateral exchange credentials policies. However, due to lack credentials, prone fail. This paper presents an ATN framework based on subjective model. Representation in access control policies processes different strategies model are discussed analyzed. Meanwhile, it FIRE . With matrix...
Picture archiving and communication systems (PACS) require high-speed networks to transmit large image files between components.Image-data transmission from one site another through public network is usually characterized in term of privacy, authenticity, integrity.However, network's security issues had always been the significant problems.Recent years, IPv6 brings improvements mechanisms for assuring a higher level confidentiality transmitted information.Thus, it still necessary take care...
The intensity of diaphragmatic EMG (EMGdi) can be used to assess respiratory function and lung capacity. However, the estimation EMGdi is subject electrocardiographic (ECG) interference. removal ECG contamination from recordings so far a challenge due computational complexity user dependency. An adaptive method for reducing was proposed based on linear prediction algorithm in previous work. In this paper, modified by taking motion artifact into consideration, therefore model Interference...
Recent development of the lung nodule computer-aided diagnosis (CAD) in helical computed tomography (CT) images has shown great potential and treatment cancer. One key technology CAD system is classification nodules non-nodules. In this paper, we try to solve problem using ensemble relevance vector machine (ERVM). The contribution our work includes: 1) (RVM) used as classifier system. It been proven that RVM comparable SVM generalization capability with a much sparser solution; 2) skill...
In open Multi-agent Systems, trust plays the central role in facilitating interactions. Most of models need to collect witness reports, and they may suffer due existence malicious witness. To detect this paper presents an approach, OSM (Opinion Similarity Measure). Evaluator calculates opinion similarity state (OSS) between evaluator according their evaluates credibility OSS them. Experiment analysis show that is more robust than existing approaches.
In the open agent systems, agents have to meet how, when and with who interact. Trust reputation play an important role in reduces uncertain. However, existing trust metric is not effective strategically behaviors, such as sudden behavior or alter 'name'. This paper presents a novel metric, which can penalize of suddenly falling change