A5020667410- Advanced Neural Network Applications
- Retinal Imaging and Analysis
- Retinal and Optic Conditions
- Digital Imaging for Blood Diseases
- Infrared Target Detection Methodologies
- Big Data and Business Intelligence
- Medical Imaging Techniques and Applications
- Radiomics and Machine Learning in Medical Imaging
- Video Surveillance and Tracking Methods
- Image and Video Stabilization
- Robotics and Sensor-Based Localization
- Robotics and Automated Systems
- Advanced Image Fusion Techniques
- Image Processing Techniques and Applications
- Anomaly Detection Techniques and Applications
- Autonomous Vehicle Technology and Safety
- Adversarial Robustness in Machine Learning
- Sentiment Analysis and Opinion Mining
- Image Enhancement Techniques
- Thermography and Photoacoustic Techniques
- Topic Modeling
- Text and Document Classification Technologies
- Reinforcement Learning in Robotics
- Industrial Vision Systems and Defect Detection
- Maritime Navigation and Safety
Anhui Polytechnic University
2023-2025
Fuzhou University
2025
Hangzhou Medical College
2023-2024
Polytechnic University
2023
Zhejiang Provincial People's Hospital
2023
Northeast Forestry University
2023
Purpose Innovation in AI technology has transformed the global economic landscape, thereby becoming a focal point for academic research. A review of extant literature reveals preponderant focus on application aspects technology, underscoring necessity more nuanced examination. However, innovation is led by managers who are likely influenced cognitive biases. Design/methodology/approach This study combines supervised machine learning models field and patent abstracts to accurately identify...
Neural network-based driving planners have shown great promises in improving task performance of autonomous driving. However, it is critical and yet very challenging to ensure the safety systems with neural components, especially dense highly interactive traffic environments. In this work, we propose a safety-driven planning framework for lane changing. To prevent over-conservative planning, identify behavior surrounding vehicles assess their aggressiveness, then adapt planned trajectory ego...
Three-dimensional reconstruction of head computed tomography (CT) images elucidates the intricate spatial relationships tissue structures, thereby assisting in accurate diagnosis. Nonetheless, securing an optimal CT scan without deviation is challenging clinical settings, owing to poor positioning by technicians, patient's physical constraints, or scanner tilt angle restrictions. Manual formatting and not only introduce subjectivity but also strain time labor resources. To address these...
Unmanned aerial vehicles (UAV) are essential for reconnaissance and monitoring. One of the greatest challenges facing UAVs is vision-based multi-target tracking. Multi-target tracking algorithms that depend on visual data utilized in a variety fields. In this study, we present comprehensive framework real-time ground robots forest grassland environments. This utilizes YOLOv5n detection algorithm monitoring robot activities video streams. We optimized both re-identification networks to...
Infrared and visible image fusion has been developed from vision perception oriented methods to strategies which both consider the high-level task. However, existing task-driven fail address domain gap between semantic geometric representation. To overcome these issues, we propose a infrared network via transformation, terms as HSFusion. Specifically, minimize representation, design two separate transformation branches by CycleGAN framework, each includes processes: forward segmentation...
In online video platforms, reading or writing comments on interesting videos has become an essential part of the watching experience. However, existing recommender systems mainly model users' interaction behaviors with videos, lacking consideration in user behavior modeling. this paper, we propose a novel recommendation approach called LSVCR by leveraging histories both and comments, so as to jointly conduct personalized comment recommendation. Specifically, our consists two key components,...
This pioneering research introduces a novel approach for decision-makers in the heavy machinery industry, focusing on production management. The study integrates machine learning techniques like Markov chain analysis and radar charts to optimize North American Crawler Cranes market processes. evaluates risk factors, aiding informed decision-making Radar simulate benchmark product designs, enabling datadriven decisions optimization. interdisciplinary equips with transformative insights,...
Three-dimensional (3D) reconstruction of head Computed Tomography (CT) images elucidates the intricate spatial relationships tissue structures, thereby assisting in accurate diagnosis. Nonetheless, securing an optimal CT scan without deviation is challenging clinical settings, owing to poor positioning by technicians, patient's physical constraints, or scanner tilt angle restrictions. Manual formatting and not only introduce subjectivity but also strain time labor resources. To address these...
<title>Abstract</title> Various problems afflict the complex network structures that are implemented in pedestrian detection and tracking applications, including a large number of parameters, lengthy training times, slow running speeds. This is especially true when current algorithms used on mobile devices. In this study, we proposed an improved model based YOLOv5s DeepSort video Mosaic algorithm scale-invariant feature transform (SIFT) to expand scope by addressing aforementioned problems....
Therefore, aiming at the problem of moving target detection in complex traffic scenes, a quadratic optimization algorithm is proposed based on Yolov5 model to improve clustering Anchor Boxes and introduce attention mechanism (SE module) algorithm, which can iteration speed emphasize learning features channel dimension. Finally, Retinex image enhancement algorithms are utilized or video frame quality accuracy recognition fog, haze, other bad weather. Experimental results demonstrate that...