A5101872508- Robotics and Sensor-Based Localization
- Advanced Image and Video Retrieval Techniques
- Advanced Neural Network Applications
- Optical Systems and Laser Technology
- Advanced Memory and Neural Computing
- Robotic Path Planning Algorithms
- Assembly Line Balancing Optimization
- Scheduling and Optimization Algorithms
- Semiconductor materials and devices
- Hepatocellular Carcinoma Treatment and Prognosis
- Calibration and Measurement Techniques
- Advanced Manufacturing and Logistics Optimization
- Spacecraft Design and Technology
- Photonic and Optical Devices
- Adaptive optics and wavefront sensing
- Video Surveillance and Tracking Methods
- Advanced Vision and Imaging
- CCD and CMOS Imaging Sensors
- Semiconductor Lasers and Optical Devices
- Ferroelectric and Negative Capacitance Devices
- Membrane Separation Technologies
- Cancer, Lipids, and Metabolism
- Infrared Target Detection Methodologies
- Advanced Multi-Objective Optimization Algorithms
- Remote Sensing and LiDAR Applications
Shandong University of Technology
2024-2025
Jimei University
2025
Nanjing Forestry University
2024
Affiliated Hospital of Southwest Medical University
2023-2024
Zhejiang University of Technology
2024
China National Offshore Oil Corporation (China)
2015-2023
Dalian Maritime University
2022-2023
Wuhan University
2020-2022
State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing
2020-2022
Zhengzhou University of Light Industry
2022
This article presents a transformer and convolutional neural network (CNN) hybrid deep for semantic segmentation of very high resolution (VHR) remote sensing imagery. The model follows an encoder–decoder structure. encoder module uses new universal backbone Swin to extract features achieve better long-range spatial dependencies modeling. decoder draws on some effective blocks successful strategies CNN-based models in image segmentation. In the middle framework, atrous pyramid pooling block...
Self-driving cars have experienced rapid development in the past few years, and Simultaneous Localization Mapping (SLAM) is considered to be their basic capabilities. In this article, we propose a direct vision LiDAR fusion SLAM framework that consists of three modules. Firstly, two-staged visual odometry module, which frame-to-frame tracking step, an improved sliding window based thinning proposed estimate accurate pose camera while maintaining efficiency. Secondly, every time keyframe...
Solar steam generation (SSG) is developed as a promising way for seawater desalination and wastewater purification, bringing new opportunities solving the shortages of freshwater.
The optimal local treatment for HCC with tumor diameter ≥ 5 cm is not well established. This research evaluated the effectiveness of external beam radiation therapy (EBRT) versus transcatheter arterial chemoembolization (TACE) cm.A total 1210 patients were enrolled in this study, including 302 and 908 that received EBRT TACE, respectively. Propensity score matching (PSM) was used to identify patient pairs similar baseline characteristics. Overall survival (OS) primary study endpoint.We...
Different from object detection in natural image, optical remote sensing is a challenging task, due to the diverse meteorological conditions, complex background, varied orientations, scale variations, etc. In this paper, address issue, we propose novel network (the global-local saliency constraint network, GLS-Net) that can make full use of global semantic information and achieve more accurate oriented bounding boxes. More precisely, improve quality region proposals boxes, first pyramid...
Purpose To ensure the safety of electric power supply, it is necessary to inspect substation equipment. With dramatic increase in number substations, especially indoor intelligent robot inspection has become an important development direction. This paper aims describe design a trackless with robotic arm, which capable navigating autonomously and inspecting equipment narrow complex substation. Design/methodology/approach A robust four-wheel platform powered by motors used carry robot. By...
The progression and metastasis of tumors are typically accompanied by angiogenesis. Crucially, vascular endothelial growth factor (VEGF) its receptors (VEGFRs) play a significant role in tumor-associated In this study, the aim was to investigate antitumor effect combining bevacizumab (Bev) with anlotinib (An) on colorectal cancer (CRC).
This article discusses the application of ChatGPT Model in a travel assistant application. Nowadays, as world has recovered from pandemic, demand for tourism worldwide, whether domestic or international. However, one significant dilemmas travelers before trip is how to outline formation and plan when it challenging know local area, while agencies might be another unnecessary expense. By this chance, we are developing agency powered by OpenAI that incorporates ChatGPTs functionality inside,...
Most SLAM (Simultaneous Localization and Mapping) algorithms are based on the assumption that scene is static. However, in practice, most real scenes usually contain moving objects. In this letter, we introduce DymSLAM, a dynamic stereo visual system being capable of reconstructing 4D (3D + time) with rigid Unlike previous attempts have considered objects as outliers ignored them, DymSLAM obtains 6DoF motion trajectory 3D models about We segment different by multi-motion segmentation...
Trimethoxyoctadecylsilane (OTMS) was successfully used to decorate mesoporous silica with a self-assembly method enhance the relative gas selectivity. A quartz crystal microbalance employed measure gas-sensing properties. The content of OTMS crucial factor that greatly affected adsorption capacity (q) silica, which could be converted selectivity (S) study sensing mechanism. With increasing content, q far higher for small-molecule gases compared volatile organic compounds (VOCs), explained by...
The integration of the camera and LiDAR has played an important role in field autonomous driving, for example visual–LiDAR SLAM 3D environment fusion perception, which rely on precise geometrical extrinsic calibration. In this paper, we proposed a fully automatic end-to-end method based 3D–2D corresponding mask (CoMask) to directly estimate parameters with high precision. Simple subtraction was applied extract candidate point cluster from complex background, then points located checkerboard...
Most scenes in practical applications are dynamic containing moving objects, so accurately segmenting objects is crucial for many computer vision applications. In order to efficiently segment all the scene, regardless of whether object has a predefined semantic label, we propose two-level nested octave U-structure network with multi-scale attention mechanism, called U2-ONet. U2-ONet takes two RGB frames, optical flow between these and instance segmentation frames as inputs. Each stage filled...
Background In this retrospective study, we aimed to identify key risk factors and establish an interpretable model for HCC with a diameter ≥ 5 cm using Lasso regression effective stratification clinical decision-making. Methods 843 patients advanced hepatocellular carcinoma (HCC) tumor were included. Using screen multiple characteristic variables, cox proportional hazard random survival forest models (RSF) established. By comparing the area under curve (AUC), optimal was selected. The...
The effects of interfacial fluorination on the metal/Al 2 O 3 /HfO /SiO /Si (MAHOS) memory structure have been investigated. By comparing MAHOS memories with and without fluorination, it was identified that deterioration performance reliability is mainly due to formation an layer generates excess oxygen vacancies at interface. Interfacial suppresses growth layer, which confirmed by X-ray photoelectron spectroscopy depth profile analysis, increases enhanced program/erase efficiency, improves...