检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： Yanlin Chen Xiaoqing Zhang Tianao Wang Chen Tang Haili Ye Jiang Liu Department of Computer Science and Engineering Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China Shenzhen Institute of Advanced Technology Center for High Performance Computing and Shenzhen Key Laboratory of Intelligent Bioinformatics Chinese Academy of Sciences Shenzhen China School of Ophthalmology and Optometry Wenzhou Medical University Wenzhou China The Oujiang Laboratory The Affiliated Eye Hospital Wenzhou Medical University Wenzhou China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Pathology symptoms of Parkinson disease (PD) are different from those of retinal diseases in the retinal layers, which are subtle. However, segmenting pathology information of PD from retinal layers automatically based on optical coherence tomography (OCT) images has not been studied before. Although existing Transformer-based segmentation methods have achieved good segmentation results, they have limitations in capturing local context information. Convolutional neural networks (CNNs) can construct local context dependencies among pixels, which is complementary to Transformers. Particularly, edge information extraction is significant for accurate retinal layer segmentation, which is ignored by both Transformers and CNNs but can be captured by frequency domain learning methods. To fully leverage the advantages of Transformers, CNNs, and frequency domain learning methods, we propose a Wavelet Transformer (WaveFormer) for retinal layer segmentation based on OCT images. In the WaveFormer, we design a Wavelet Spatial Attention block to exploit the potential of frequency information. Based on these advantages, WaveFormer can be data-efficient in limited OCT images of PD. The experimental results on the OCT-PD segmentation dataset show that our WaveFormer outperforms existing Transformers and CNNs. For example, WaveFormer outperforms Swin-UNet by 3.41% of IoU.

关键词： Learning systems Image segmentation Pathology Wavelet domain Image edge detection Frequency-domain analysis Transformers

来源：评论

学校读者我要写书评

暂无评论

design of Underwater Vehicle for Ship Draft Observation

Design of Underwater Vehicle for Ship Draft Observation

引用

Mechatronics and Robotics Engineering (ICMRE), International Conference on

作者： Jingyuan Zhu Meng Han Hongliang Zhang Lan Qi Lianyu Zhao Chenglin Wang Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of Technology Tianjin China Deepinfar Ocean Technology Inc Tianjin China

Underwater Vehicles are very important underwater operation equipment, and a new underwater vehicle is designed in order to realize the measurement of the ship draft. The design is based on the ROV(Remote Operated Vehicle) structure, and the mobile power supply and the upper computer are mounted on the underwater vehicle body, aiming to accomplish the task of disconnecting the underwater vehicle from the cable under complex sea conditions. In this paper, the system communication and power supply scheme design, thruster arrangement, the center of gravity and floating center position design, and 3D model design are completed in turn to obtain a structural design scheme of the underwater vehicle based on the actual engineering background. Subsequently, the strength check of the overall frame was carried out based on ANSYS WORKBENCH, which proved that the material selection and structural design met the reliability requirements. Finally, the hydrodynamic characteristics of the robot were analyzed using ANSYS CFD.

关键词： Weight measurement Underwater cables Solid modeling Three-dimensional displays Power supplies Hydrodynamics Finite element analysis

来源：评论

学校读者我要写书评

暂无评论

WeakSurg: Weakly supervised surgical instrument segmentation using temporal equivariance and semantic continuity

arXiv

引用

arXiv 2024年

作者： Wang, Qiyuan Liu, Yanzhe Zhao, Shang Liu, Rong Zhou, S. Kevin Anhui Hefei230026 China Suzhou Institute for Advanced Research USTC Jiangsu Suzhou215123 China Key Laboratory of Precision and Intelligent Chemistry USTC Anhui Hefei230026 China Institute of Computing Technology CAS Beijing100190 China Faculty of Hepato-Biliary-Pancreatic Surgery The First Medical Center Chinese PLA General Hospital Beijing China

For robotic surgical videos, instrument presence annotations are typically recorded with video streams, which offering the potential to reduce the manually annotated costs for segmentation. However, weakly supervised surgical instrument segmentation with only instrument presence labels has been rarely explored in surgical domain due to the highly underconstrained challenges. Temporal properties can enhance representation learning by capturing sequential dependencies and patterns over time even in incomplete supervision situations. From this, we take the inherent temporal attributes of surgical video into account and extend a two-stage weakly supervised segmentation paradigm from different perspectives. Firstly, we make temporal equivariance constraint to enhance pixel-wise temporal consistency between adjacent features. Secondly, we constrain class-aware semantic continuity between global and local regions across temporal dimension. Finally, we generate temporal-enhanced pseudo masks from consecutive frames to suppress irrelevant regions. Extensive experiments are validated on two surgical video datasets, including one cholecystectomy surgery benchmark and one real robotic left lateral segment liver surgery dataset. We annotate instance-wise instrument labels with fixed time-steps which are double checked by a clinician with 3-years experience to evaluate segmentation results. Experimental results demonstrate the promising performances of our method, which consistently achieves comparable or favorable results with previous state-of-the-art approaches. Copyright © 2024, The Authors. All rights reserved.

关键词： Robotic surgery

来源：评论

学校读者我要写书评

暂无评论

Experimental Study on Microstructure and Mechanical Properties of Dissimilar Cu/Al Welded by Hybrid Coaxial Blue-Ir Laser

SSRN

引用

SSRN 2024年

作者： Zhang, Mingjun Zhang, Yuxuan Zhang, Jian Wang, Hailong Li, Heqing Cheng, Bo Wu, Xiang Zhou, Dianwu Mao, Cong Hu, Yongle Li, Wen Hunan Provincial Key Laboratory of Intelligent Manufacturing Technology for High-performance Mechanical Equipment Changsha University of Science and Technology Changsha410114 China Institute of Metals College of Materials Science and Engineering Changsha University of Science & Technology Changsha410114 China State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Hunan University Changsha410082 China Hunan SANY Tower Lifting Machinery Co. Ltd. Changsha410600 China

A hybrid blue-infrared (IR) laser is adopted to weld 5052 Al with T2 Cu to investigate the impact of processing parameters on the quality of Cu/Al overlap joints in terms of microstructures, mechanical properties, and failure modes. The experiments show that combining an infrared laser and a blue laser has enlarged an opening channel of welds and stabilized the convention on edge of the weld pool. This eases the removals of bubbles and prevents the formations of pores. When a hybrid coaxial blue-IR laser with a power less than 500 W is used, the weld strengths of the specimens are increased significantly, and the plasticity is decreased slightly in comparison with the specimens welded by an infrared laser. When the power of the blue laser is increased to 800 W, the strength and plasticity of a lapped weld are decreased significantly. Moreover, the joints only welded by an infrared laser are fractured in a mixed fracture mode. When the blue laser power of the hybrid coaxial blue-IR laser is lower than 500 W, the weld is ruptured by a ductile fracture. However, a brittle fracture is observed as the blue laser power exceeding 800 W. © 2024, The Authors. All rights reserved.

关键词： Microstructure

来源：评论

学校读者我要写书评

暂无评论

Temporal Information Reconstruction and Non-Aligned Residual in Spiking Neural Networks for Speech Classification

arXiv

引用

arXiv 2024年

作者： Zhang, Qi Wang, Huamin Shen, Hangchi Duan, Shukai Wen, Shiping Huang, Tingwen College of Artificial Intelligence Southwest University Chongqing400715 China Chongqing Key Laboratory of Brain Inspired Computing and Intelligent Chips Chongqing400715 China College of Information Engineering University of Technology Sydney Australian Institute of Artificial Intelligence Sydney2007 Australia Faculty of Computer Science and Control Engineering Shenzhen University of Advanced Technology Shenzhen518055 China

Recently, it can be noticed that most models based on spiking neural networks (SNNs) only use a same level temporal resolution to deal with speech classification problems, which makes these models cannot learn the information of input data at different temporal scales. Additionally, owing to the different time lengths of the data before and after the sub-modules of many models, the effective residual connections cannot be applied to optimize the training processes of these models. To solve these problems, on the one hand, we reconstruct the temporal dimension of the audio spectrum to propose a novel method named as Temporal Reconstruction (TR) by referring the hierarchical processing process of the human brain for understanding speech. Then, the reconstructed SNN model with TR can learn the information of input data at different temporal scales and model more comprehensive semantic information from audio data because it enables the networks to learn the information of input data at different temporal resolutions. On the other hand, we propose the Non-Aligned Residual (NAR) method by analyzing the audio data, which allows the residual connection can be used in two audio data with different time lengths. We have conducted plentiful experiments on the Spiking Speech Commands (SSC), the Spiking Heidelberg Digits (SHD), and the Google Speech Commands v0.02 (GSC) datasets. According to the experiment results, we have achieved the state-of-the-art (SOTA) result 81.02% on SSC for the test classification accuracy of all SNN models, and we have obtained the SOTA result 96.04% on SHD for the classification accuracy of all models. Furthermore, on the non-spiking dataset GSC, we can achieve a test classification accuracy of 95.63%, which surpasses the original baseline SNN-Delays. Meanwhile, the method proposed in this paper can speed up the model’s processing speed and reduce its energy consumption. Copyright © 2024, The Authors. All rights reserved.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

A Novel Microwave Humidity Sensor Based on a Complementary Interdigital Capacitor Resonator

SSRN

引用

SSRN 2024年

作者： Wang, Litian Chen, Jie Li, Dan Qian, Lirong Xiong, Yang Miao, Lin Zhang, Rong Li, Cuiping Tianjin Key Laboratory of Film Electronic and Communication Devices School of Integrated Circuit Science and Engineering Tianjin University of Technology Tianjin300384 China School of Integrated Circuit Science and Engineering Tianjin University of Technology Tianjin300384 China Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin300384 China National Demonstration Resonant for Experimental Mechanical and Electrical Engineering Education Tianjin University of Technology China

This study presents a novel microwave humidity sensor that utilizes a complementary interdigital capacitor resonator (CIDCR), an advanced design derived from the traditional complementary split ring resonator (CSRR) structure. The CIDCR design enhances the sensor's performance by concentrating the electric field in a more compact region, leading to improved sensitivity and miniaturization. The sensor is coated with a composite film of chitosan (CS) and polyacrylamide-glycerol (PAMG), combining the high moisture sensitivity of PAMG with the stability of CS. The CIDCR-based sensor demonstrates superior performance, including high sensitivity, a broad detection range, rapid response/recovery times, and excellent long-term stability. Density functional theory (DFT) calculations further elucidate the moisture-sensitive mechanisms at the molecular level, highlighting the role of hydrogen bonding in the composite film. Application tests confirm the sensor's potential for use in respiratory monitoring, non-contact sensing, and health monitoring, showcasing the advantages of the CIDCR structure in achieving enhanced humidity sensing capabilities. © 2024, The Authors. All rights reserved.

关键词： Humidity sensors

来源：评论

学校读者我要写书评

暂无评论

Non-Stoichiometric Protic Ionic Liquids for Efficient Carbon Dioxide Capture and Subsequent Conversion Under Mild Conditions

SSRN

引用

SSRN 2024年

作者： Wang, Litian Chen, Jie Wang, Shuai Zhou, Tongyao Li, Dan Li, Cuiping Qian, Lirong Xiong, Yang Miao, Lin Xie, Zhiyong Tianjin Key Laboratory of Film Electronic and Communication Devices School of Integrated Circuit Science and Engineering Tianjin University of Technology Tianjin300384 China School of Integrated Circuit Science and Engineering Tianjin University of Technology Tianjin300384 China Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin300384 China China Tianjin Bohua Yongli Chemical Industry CO. Ltd Tianjin30045 China

Protic ionic liquids (PILs) have emerged as innovative solvents with significant potential for CO2 capture and transformation, presenting a sustainable alternative to conventional methods which often involve energy-intensive processes or environmentally detrimental chemicals. Herein, a novel strategy for CO2 capture and conversion at mild conditions using non-stoichiometric protic ionic liquids (NPILs) was demonstrated for the first time. These NPILs, employed as sorbents, solvents, and catalysts, were composed of imidazole (Im) and 1,8-diazabicyclo [5.4.0] undec-7-ene (DBU) in various ratios. Correlations between the mole ratio of DBU/Im and physicochemical properties such as viscosity, conductivity, thermal stability, and the distribution of neutral and ionic species were systematically investigated. Effects of the absorption temperature and CO2 partial pressure on the absorption capacity were also studied. Different absorption mechanisms, including carbonate and carbamate pathways, were analyzed using FT-IR and NMR spectroscopy. Moreover, the fixed CO2 could be catalytically converted to quinazoline-2,4(1H,3H)-diones under exceptionally mild reaction conditions (1atm, 50 °C, metal-free process). A plausible reaction mechanism involving simultaneous CO2 activation and substrate activation for the transformation of CO2 into quinazoline-2,4(1H,3H)-diones was verified through NMR spectra. It is believed that the new insights into the CO2 mechanism will facilitate the rationaldesign of functional ionic liquids for CO2 capture, utilization, and storage in the future. © 2024, The Authors. All rights reserved.

关键词： Carbon dioxide

来源：评论

学校读者我要写书评

暂无评论

ChartKG: A Knowledge-Graph-Based Representation for Chart Images

arXiv

引用

arXiv 2024年

作者： Zhou, Zhiguang Wang, Haoxuan Zhao, Zhengqing Zheng, Fengling Wang, Yongheng Chen, Wei Wang, Yong School of Media and Design Hangzhou Dianzi University CO Hangzhou310018 China School of Media and Design Hangzhou Dianzi University China Big Data Visualization and Human Computer Collaborative Intelligent Laboratory Hangzhou Dianzi University China Research Center of Big Data Intelligence Zhejiang Lab Hangzhou China State Key Lab of CAD&CG Zhejiang University China College of Computing and Data Science Nanyang Technological University Singapore

Chart images, such as bar charts, pie charts, and line charts, are explosively produced due to the wide usage of data visualizations. Accordingly, knowledge mining from chart images is becoming increasingly important, which can benefit downstream tasks like chart retrieval and knowledge graph completion. However, existing methods for chart knowledge mining mainly focus on converting chart images into raw data and often ignore their visual encodings and semantic meanings, which can result in information loss for many downstream tasks. In this paper, we propose ChartKG, a novel knowledge graph (KG) based representation for chart images, which can model the visual elements in a chart image and semantic relations among them including visual encodings and visual insights in a unified ***, we develop a general framework to convert chart images to the proposed KG-based representation. It integrates a series of image processing techniques to identify visual elements and relations, e.g., CNNs to classify charts, yolov5 and optical character recognition to parse charts, and rule-based methods to construct graphs. We present four cases to illustrate how our knowledge-graph-based representation can model the detailed visual elements and semantic relations in charts, and further demonstrate how our approach can benefit downstream applications such as semantic-aware chart retrieval and chart question answering. We also conduct quantitative evaluations to assess the two fundamental building blocks of our chart-to-KG framework, i.e., object recognition and optical character recognition. The results provide support for the usefulness and effectiveness of ChartKG. © 2024, CC BY.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Vibration Characteristics Analysis Of A Double-Suction Centrifugal Pump Identified By intelligent Algorithms 12

Vibration Characteristics Analysis Of A Double-Suction Centr...

引用

12th IEEE Global Reliability and Prognostics and Health Management, PHM-Nanjing 2021

作者： Gu, Zhenyue Zhang, Mian Li, Decai Kang, Tianbo Tang, Xiuyang Wang, Zhiyuan Pei, Zhenlong Wang, Yiqiao Tianjin Key Laboratory For Advanced Mechatronic System Design And Intelligent Control School Of Mechanical Engineering Tianjin University Of Technology Tianjin300384 China China Tianjin Todelon Scicnce &TECHOLOGY CO. Ltd Tianjin China State Key Lab Of Water Resources And Hydropower Engineering Science Wuhan University Wuhan China

ISBN: (纸本)9781665401302

Due to the merits of high flow rate and high lift, double-suction centrifugal pumps are widely used for agricultural irrigation along the Yellow River in northern China. The operational conditions of the pump are highly related to the silt concentration and flow rates. Therefore, it is crucial to identify the vibration characteristics corresponding to different silt concentrations and flow rates to provide a prior guideline for pump condition monitoring. To this end, this paper explores the identification capabilities of typical intelligent models, including convolutional neural network (CNN), deep neural network (DNN), and support vector machine (SVM), to intelligently establish the connection between vibration characteristics and different flow rates and silt concentrations. Experimental studies on a double-section pump covering a range of flow rates and different silt concentrations are conducted. The results show that CNN features higher identification accuracy than DNN and SVM. © 2021 IEEE.

关键词： Vibration analysis

来源：评论

学校读者我要写书评

暂无评论

Hand Pose Estimation Using Convolutional Neural Networks and Support Vector Regression 12th

Hand Pose Estimation Using Convolutional Neural Networks and...

引用

12th International Conference on e-Learning and Games, Edutainment 2018

作者： Dong, Yufeng Lu, Jian Zhang, Qiang Key Laboratory of Advanced Design and Intelligent Computing Dalian University Ministry of Education Dalian116622 China

ISBN: (纸本)9783030237110

In order to improve the accuracy of hand pose estimation from a depth image, a method based on convolutional neural network (CNN) is proposed in this paper. First of all, we modify the structure of traditional CNN to recognize the 3D joint locations from a depth image. By appending some shortcuts between layers, the proposed network increases the correlation between the front and back layers. This structure can avoid the information loss caused by the simple layer-by-layer transmission, and can improve the estimation accuracy effectively. Afterwards, the estimated joint locations continue to be inputted into a support vector regression (SVR) phase. The use of SVR can introduce the constraint of local joint information, which can get rid of those abnormal estimations further. Extensive experiments show that our method enables significant performance improvement over the-state-of-arts in the accuracy of hand pose estimation. © 2019, Springer Nature Switzerland AG.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：