A5039518808- Topic Modeling
- Advanced Neural Network Applications
- Autonomous Vehicle Technology and Safety
- Natural Language Processing Techniques
- Advanced Image and Video Retrieval Techniques
- Video Surveillance and Tracking Methods
- Robotics and Sensor-Based Localization
- Domain Adaptation and Few-Shot Learning
- Text and Document Classification Technologies
- Colorectal Cancer Screening and Detection
- Ferroptosis and cancer prognosis
- Cancer Immunotherapy and Biomarkers
- Medical Image Segmentation Techniques
- Advanced Vision and Imaging
- Multi-Criteria Decision Making
- Rough Sets and Fuzzy Logic
- Multimodal Machine Learning Applications
- Gaze Tracking and Assistive Technology
- Teleoperation and Haptic Systems
- Image Processing Techniques and Applications
- Surgical Simulation and Training
- Image and Object Detection Techniques
- Advanced Text Analysis Techniques
- RNA modifications and cancer
- Gastrointestinal Bleeding Diagnosis and Treatment
Chengdu University of Traditional Chinese Medicine
2023-2025
Southern University of Science and Technology
2024
Tongji University
2024
Xiamen University
2020
Beijing Jiaotong University
2012-2019
Zhejiang Gongshang University
2017
Shaanxi University of Science and Technology
2011-2015
Delft University of Technology
2015
North China Institute of Science and Technology
2015
University of Hong Kong
2014
Intraoperative tracking of laparoscopic instruments is often a prerequisite for computer and robotic-assisted interventions. While numerous methods detecting, segmenting medical based on endoscopic video images have been proposed in the literature, key limitations remain to be addressed: Firstly, robustness, that is, reliable performance state-of-the-art when run challenging (e.g. presence blood, smoke or motion artifacts). Secondly, generalization; algorithms trained specific intervention...
The combination of lifelong learning algorithms with autonomous intelligent systems (AIS) is gaining popularity due to its ability enhance AIS performance, but the existing summaries in related fields are insufficient. Therefore, it necessary systematically analyze research on systems, aiming gain a better understanding current progress this field. This paper presents thorough review and analysis relevant work integration systems. Specifically, we investigate diverse applications AIS’s...
This study introduces an innovative master-slave cardiac ablation catheter robot system that employs magnetorheological fluids. The incorporates fluid to enable collision detection through haptic feedback, thereby enhancing the operator's situational awareness. A modular clamping and propulsion mechanism has been engineered for catheter, facilitating omnidirectional operation force feedback within cavity. To evaluate proposed system, in vitro experiment was performed. Results from indicate...
Intraoperative tracking of laparoscopic instruments is often a prerequisite for computer and robotic-assisted interventions. While numerous methods detecting, segmenting medical based on endoscopic video images have been proposed in the literature, key limitations remain to be addressed: Firstly, robustness, that is, reliable performance state-of-the-art when run challenging (e.g. presence blood, smoke or motion artifacts). Secondly, generalization; algorithms trained specific intervention...
Colour and its spatial distribution are the main information currently used to detect salient objects in an image, but this cannot always guarantee satisfying performance. To deal with problem, a object detection algorithm has been presented based on meanshift filtering fusion of colour information. Superpixel segmentation is analyse images by sets pixels instead single pixel, which improves robustness noises, as well efficiency. Meanshift modes every superpixel domain range domain,...
In recent years, immune checkpoint inhibitors (ICIs) has emerged as a fundamental component of the standard treatment regimen for patients with head and neck squamous cell carcinoma (HNSCC). However, accurately predicting effectiveness ICIs at same TNM stage remains challenge. this study, we first combined multi-omics data (mRNA, lncRNA, miRNA, DNA methylation, somatic mutations) 10 clustering algorithms, successfully identifying two distinct cancer subtypes (CSs) (CS1 CS2). Subsequently,...
Abstract Underwater defects in piers pose potential hazards to the safety and durability of river‐crossing bridges. The concealment difficulty detecting underwater often result their oversight. Acoustic methods face challenges directly achieving accurate measurements defects, while optical are time‐consuming. This study proposes a two‐step rapid inspection method for concrete bridge by combining acoustics optics. first step combines macroscopic sonar scanning with an enhanced YOLOv7 detect...
This study focuses on the driver's steering behavior in case of overtaking a two-lane highway. Furthermore, paper we propose customized controller for an automated vehicle. When observing current models human controllers, it can be concluded that these more or less share same configuration which three elements are importance, namely: trajectory planning, prediction horizon and controller. In proposed model, assumption driver envisages before process is problematic real-time applications due...
<title>Abstract</title> <bold>Background: </bold>In recent years, immune checkpoint inhibitors (ICIs) has emerged as a fundamental component of the standard treatment regimen for patients with head and neck squamous cell carcinoma (HNSCC). However, accurately predicting effectiveness ICIs at same TNM stage remains challenge. <bold>Methods: this study, we first combined over ten types omics data clustering algorithms, successfully identifying two distinct cancer subtypes (CSs) (CS1 CS2)....
As a pivotal research method in the field of granular computing (GrC), fuzzy rough sets (FRSs) have garnered significant attention due to their successful overcoming limitations traditional handling continuous data. This paper is dedicated exploring application potential FRS models within framework multi-source complex information systems, which undoubtedly holds profound significance. Firstly, novel mixed system (MsMIS), encompassing five distinct data types, introduced, thereby enriching...
Alzheimer disease (AD) is the most commonly occurring neurodegenerative disease. However, current diagnostics for AD primarily rely on invasive tests, which limit application of diagnostic procedures in early screening. Speech, as a noninvasive biomarker, closely associated with but has not been fully leveraged tool. This study develops novel diagnosis method that uses primitive speech and explores its potential community Moreover, proposes an innovative multimodal feature fusion combines...
This paper presents a new method to determine camera velocity from image data. Velocity estimation has been underexplored, compared estimating rotation and translation. Existing methods suffer various drawbacks in terms of necessary conditions on the 3D structure scene, types velocities they can solve for, convergence estimates, or partial knowledge scene velocity. Our approach uses optical flow vectors delivers estimates angular linear velocities. Rigid body equations are used derive...
Automatic coal sorting technology based on machine vision has the function of analyzing whether there is material conveyor.Contour image will be found when conveyor.The average color calculated according to respective proportion blue component and red in contour.Comparing with setting threshold judges type material.The advantage high efficiency, good stability, reliable, etc.The system also sending signals equipment statistic number various materials.The reduces production costs companies,...