A5084758250- Human Pose and Action Recognition
- Video Surveillance and Tracking Methods
- Advanced Image Processing Techniques
- Anomaly Detection Techniques and Applications
- Radiomics and Machine Learning in Medical Imaging
- Lung Cancer Diagnosis and Treatment
- Lung Cancer Treatments and Mutations
- Advanced Image and Video Retrieval Techniques
- COVID-19 diagnosis using AI
- Image Processing Techniques and Applications
- Automated Road and Building Extraction
- Advanced Neural Network Applications
- Gait Recognition and Analysis
- Cancer Immunotherapy and Biomarkers
- Advanced Image Fusion Techniques
- Advanced Vision and Imaging
- Handwritten Text Recognition Techniques
- Image Processing and 3D Reconstruction
- Value Engineering and Management
- Brain Metastases and Treatment
- Infrared Target Detection Methodologies
- Imbalanced Data Classification Techniques
- ECG Monitoring and Analysis
- Image and Signal Denoising Methods
- Hand Gesture Recognition Systems
First Affiliated Hospital of Xi'an Jiaotong University
2024
Hangzhou Dianzi University
2021-2024
State Grid Corporation of China (China)
2024
Sichuan University
2015-2023
Shandong First Medical University
2022
Ningbo Medical Center Lihuili Hospital
2021
Zhejiang Provincial Public Security Department
2020-2021
Shanghai Public Security Bureau
2019-2021
Xinjiang Institute of Engineering
2019-2021
Yangzhou University
2020
Grain number is crucial for analysis of yield components and assessment effects cultivation measures. The grain per spike thousand-grain weight can be measured by counting grains manually, but it time-consuming, tedious error-prone. Previous image processing algorithms cannot work well with different backgrounds sizes. This study used deep learning methods to resolve the limitations traditional algorithms. Wheat datasets were collected in scenarios three varieties, six background two...
Behavior recognition is a well-known computer version technology, it has been used in many applications such as video surveillance, robotics, human-computer interaction and sports video, etc. However, most of existing works ignored the depth information so that they resulted over-fitting inferior performance. Consequently, novel framework for behavior proposed which based on spatio-temporal convolution attention-based LSTM (ST-CNN & ATT-LSTM). In this framework, deep spatial merged into each...
Lung cancer is the most common solid tumor in worldwide. Targeted therapy and immunotherapy are important treatment options advanced non-small cell lung (NSCLC). The association of PTEN mutation less established for patients with NSCLC. We present case an Asian woman diagnosed stage IV adenocarcinoma harboring ERBB2 mutation. She received Nivolumab when her disease progresses after previous chemotherapy Afatinib treatment. However, patient did not response to Nivolumab. was detected by...
The extreme channels prior (ECP) relies on the bright and dark of an image, corresponding ECP-based methods perform well in blind image deblurring. However, we experimentally observe that pixel values some images are not concentratedly distributed 0 1 respectively. Based this observation, develop a model with joint which combines L <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">0</sub> -regularized intensity gradient for deblurring, previous...
Aiming at the problem that hand gesture recognition difficult issues in real scene, a method of combines skin color with SVM was proposed. The area separated by Otsu adaptive threshold algorithm YCbCr space, and segmente d criterion. Hu moment features finger number were extracted on contour as feature vector. Six common static gestures classified recognized classifier. Experimental result showed this had good stability real-time performance, average rate could reach 94%. On application,...
Targeted therapy is considered one of the most effective treatment strategies for advanced lung cancer, especially in patients with epidermal growth factor receptor (EGFR) mutations. However, current methods identifying EGFR mutations are both time-consuming and invasive. The integration CT imaging artificial intelligence techniques provides a non-invasive means predicting A notable challenge clinical practice limited availability EGFR-positive patients, which poses difficulties training...
Behavior recognition is a hot trending topic for smart cities in terms of the research and public security. This paper focuses on abnormal behavior that involves various people activities. In contrast to most existing works, which relies image data as raw input affected by environmental factors, this takes skeleton's depth location information into consideration proposes framework based skeleton spatio-temporal relationship incorporate in-depth spatial each segment. Our experiment undertakes...
Lung tissue segmentation is vital in computer-assisted diagnosis, and many studies have been devoted to this field. However, there are still challenges because of redundant information CT images the deformation organ tissue. In study, we constructed a fully convolution neural network-based model called LTS-Net segment lung from images. First, improve efficiency guarantee accuracy, network uses three downward max-pooling layers up-sampling layers. The number channels increases exponentially...