A5101553901- Retinal Imaging and Analysis
- Digital Imaging for Blood Diseases
- Retinal Diseases and Treatments
- Software Engineering Research
- Generative Adversarial Networks and Image Synthesis
- Advanced Image Processing Techniques
- Software System Performance and Reliability
- Aluminum Alloys Composites Properties
- Magnesium Alloys: Properties and Applications
- Mobile Ad Hoc Networks
- Coronary Interventions and Diagnostics
- Multimodal Machine Learning Applications
- Metal and Thin Film Mechanics
- Face recognition and analysis
- Industrial Vision Systems and Defect Detection
- Expert finding and Q&A systems
- Advanced Malware Detection Techniques
- Energy and Environmental Systems
- Network Security and Intrusion Detection
- Hydrogen Storage and Materials
- Artificial Intelligence in Healthcare
- IoT-based Smart Home Systems
- Software Reliability and Analysis Research
- Advancements in Photolithography Techniques
- Recommender Systems and Techniques
Northeastern University
2024
Chongqing Normal University
2024
Chongqing University
2016-2022
Automated medical image analysis is an emerging field of research that identifies the disease with help imaging technology. Diabetic retinopathy (DR) a retinal diagnosed in diabetic patients. Deep neural network (DNN) widely used to classify from fundus images collected suspected persons. The proposed DR classification system achieves symmetrically optimized solution through combination Gaussian mixture model (GMM), visual geometry group (VGGNet), singular value decomposition (SVD) and...
In the field of ophthalmology, diabetic retinopathy (DR) is a major cause blindness. DR based on retinal lesions including exudate. Exudates have been found to be one signs and serious anomalies, so proper detection these treatment should done immediately prevent loss vision. this paper, pretrained convolutional neural network- (CNN-) framework has proposed for Recently, deep CNNs were individually applied solve specific problems. But, CNN models with transfer learning can utilize previous...
In diabetic retinopathy (DR), the early signs that may lead eyesight towards complete vision loss are considered as microaneurysms (MAs). The shape of these MAs is almost circular, and they have a darkish color tiny in size, which means be missed by manual analysis ophthalmologists. this case, accurate detection helpful to cure DR before non-reversible blindness. proposed method, performed using hybrid feature embedding approach pre-trained CNN models, named VGG-19 Inception-v3. performance...
In Mobile Ad hoc Network (MANET) enabled Internet of Things (IoT) agricultural field monitoring, sensor devices are automatically connected and form an independent network that serves as a cloud for many services such securing, properly maintaining. Cloud-based in MANET models can prove to be extremely effective way smart functionalities device-to-device information exchange. Security is serious issue with Cloud-MANET-based IoT since nodes scattered, mobile, lacking centralized...
Internet of Things (IoT) is vulnerable to data-tampering (DT) attacks.Due resource limitations, many anomaly detection systems (ADSs) for IoT have high false positive rates when detecting DT attacks.This leads the misreporting normal data, which will impact operation IoT.To mitigate caused by rate ADS, this paper proposes an ADS management scheme clustered IoT.First, we model data transmission and in IoT.Then, strategy formulated as running probabilities all ADSs deployed on every device.In...
Existing image-to-image translation methods usually adopt an encoder-decoder structure to generate images. The encoder extracts the features of input images using a sequence convolution layers until bottleneck, and then, intermediate are decoded target image. However, existence bottleneck layer in such may lead blurry bad quality translated images, since different domain translations be related global or local region image even abstract level. To prevent these problems, we propose channel...
Static analysis tools (e.g., FindBugs) are widely used to detect potential defects in software development. A recent study suggests that there is a moderate correlation between the alerts reported by static and [1]. However, despite actionable tools, they may report too many meaningless unactionable alerts. Actionable alert refers which meaningful fixable. Unactionable (i.e., false positive alert) regarded as unimportant developers, inessential source code, or will not be fixed developers....