检索结果-内蒙古大学图书馆

Task-Oriented Multi-user Semantic Communication based on Deep Over-the-Air Computation

IEEE Transactions on Vehicular Technology 2025年

作者： Wei, Shuangying Feng, Chunyan Guo, Caili Zhang, Biling Chen, Jiujiu Beijing University of Posts and Telecommunications Beijing Key Laboratory of Network System Architecture and Convergence School of Information and Communication Engineering Beijing100876 China Nanchang Hangkong University Key Laboratory of Processing and Pattern Recognition of Jiangxi Province School of Information Engineering Nanchang330063 China

The presence of large-scale heterogeneous IoT devices and AI-based applications has brought significant transmission and computation pressure on the wireless communication system. In this paper, we propose a novel multi-user semantic communication framework based on deep over-the-air computation called SC-DAC to tackle this challenge. By integrating communication and computation through a deep over-the-air computation (AirComp) encoder, SC-DAC is able to utilize the superposition of multiple access channels, facilitating multi-user information fusion during transmission and eliminating the need for multi-user detection at the receiver. Further, to achieve the optimal task results, the semantic encoders, decoders, and AirComp encoder are jointly optimized, where stochastic gradient descent (SGD) algorithm and deep double-Q network (DDQN) are employed to optimize the encoder/decoder parameters. The simulation results demonstrate that as the number of users increased, the performance of the system remains relatively stable and shows potential in resource utilization. What's more, when applied to the AI-based tasks such as multi-user multimodal action recognition and semantic segmentation, SC-DAC enhances the accuracy of action recognition by 26% compared with traditional methods and by about 30%-50% compared with other multi-user semantic communication methods under conditions of low signal-to-noise ratio (SNR), while it enhances the accuracy of semantic segmentation by 0.22 to 0.32 compared to other methods © 1967-2012 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Thermal-Torsion Coupling Loading Analysis and Optimization of 3D PoP Assembly Solder Joints at Different Temperatures

引用

IEEE Transactions on Components, Packaging and Manufacturing Technology 2025年

作者： Gao, Chao Huang, Chunyue Liang, Yin Dian, Chen Lan, Jingyi Wang, Gui Guilin University of Electronic Technology School of Electrical and Mechanical Engineering Guilin541004 China Chengdu University Key Laboratory of Pattern Recognition and Intelligent Information Processing Institutions of Higher Education of Sichuan Province Chengdu610106 China Chengdu Aeronautic Vocational and Technical College Chengdu610021 China

A simulation analysis was conducted to investigate the stress distribution of Package-on-Package (PoP) assembly array solder joints subjected to thermal-torsional coupling loads, with the validity of the simulation confirmed through coupled loading stress-strain measurement experiments. The volume-weighted average method was employed to calculate the average equivalent stress (Δσ) of the critical solder joint danger element layer within the PoP assembly array, using Δσ as the evaluation benchmark. The impact and sensitivity of structural parameters on the thermal-torsional coupling stress of solder joints were examined. A structural parameter sensitivity model was developed to facilitate the stability and optimization analysis of the structural parameter intervals. The results indicate that solder joints in the lower array of the PoP assembly experience higher thermal-torsional coupling stress, with the peak internal stress occurring at the interface between the solder joint and the copper pad. The variation in thermal-torsional coupling stress of the array solder joints is more pronounced in the low-temperature region compared to the high-temperature region, with maximum stress occurring at -55°C and minimum stress observed at 125°C. Within the structural parameter range, the Δσ value of the critical solder joint shows a negative correlation with solder joint height, solder joint diameter, and substrate thickness, and a positive correlation with PCB thickness. The sensitivity to structural parameters follows the order: solder joint diameter, solder joint height, PCB thickness, and substrate thickness. Finally, the optimal range of structural parameters was determined, and the stability of this range was assessed. © 2011-2012 IEEE.

关键词： Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

TNIE-SLAM: Neural Implicit Surface Reconstruction for Tracking-Oriented SLAM

引用

Journal of Intelligent & Robotic Systems 2025年第2期111卷 1-22页

作者： Gan, Baolin Zhang, Congxuan Chen, Shuaixin Chen, Zhen He, Chao Lu, Ke Lu, Feng School of Instrument Science and Optoelectronic Engineering Nanchang Hangkong University Nanchang China Jiangxi Provincial Key Laboratory of Image Processing and Pattern Recognition Nanchang Hangkong University Nanchang China School of Information Engineering Nanchang Hangkong University Nanchang China The College of Engineering Science University of Chinese Academy of Sciences Beijing China

Recent studies on simultaneous localization and mapping (SLAM) have tended to employ implicit neural representation, which can improve the efficiency and robustness of SLAM system. However, these methodologies still face challenges, such as tracking failures and low-precision mapping. In this paper, we propose a dense reconstruction visual SLAM system enhanced with closed-loop threading and local map optimization, named TNIE-SLAM. First, we propose a tracking module that utilizes the similarity of ORB feature descriptors and the feature overlap rate of the current frame to model key frames, and then we define a complete and accurate initial map based on full bundle adjustment, which addresses the issue of tracking failure due to undermapped areas. Second, we add the 2D features of the initial map to the spatiotemporal encoding module to obtain the 3D features, enabling real-time prediction and tracking of unknown areas. Finally, considering the low-precision mapping issue arising from the complex geometric shapes of objects within the scene, we propose a local map optimization module that utilizes truncated signed distance fields to model 3D features and update the spatial occupancy of boundary and contour features of objects. We test our method on the synthetic Replica dataset and the real-world ScanNet and TUM RGB-D datasets to compare with some state-of-the-art RGB-D SLAM methods, and the experimental results indicate our method performs well in both tracking and mapping accuracy, surpassing the existing dense neural RGB-D SLAM methods.

关键词： Surface reconstruction

来源：评论

学校读者我要写书评

暂无评论

A Research Mode Based Evolutionary Algorithm for Many-Objective Optimization

引用

Chinese Journal of Electronics 2019年第4期28卷 764-772页

作者： CHEN Guoyu LI Junhua Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang Hangkong University

The development of algorithms to solve Many-objective optimization problems(MaOPs) has attracted significant research interest in recent *** various types of Pareto front(PF) is a daunting challenge for evolutionary algorithm. A Research mode based evolutionary algorithm(RMEA) is proposed for many-objective optimization. The archive in the RMEA is used to store non-dominated solutions that can reflect the shape of the PF to guide the reference vector *** concerning the population is collected, once the number of non-dominated solutions reaches its limit after many generations without exceeding a given threshold, RMEA introduces a research mode that generates more reference vectors to search through the solutions. The proposed algorithm showed competitive performance with four state-of-the-art evolutionary algorithms in a large number of experiments.

关键词： Many-objective optimization Reference vector Research mode Evolutionary algorithm

来源：评论

学校读者我要写书评

暂无评论

Deep Learning in Palmprint recognition-A Comprehensive Survey

arXiv

引用

arXiv 2025年

作者： Gao, Chengrui Yang, Ziyuan Jia, Wei Leng, Lu Zhang, Bob Teoh, Andrew Beng Jin College of Computer Science Sichuan University Chengdu610065 China Singapore School of Computer and Information Hefei University of Technology Hefei China Jiangxi Provincial Key Laboratory of Image Processing and Pattern Recognition Nanchang Hangkong University Nanchang China Pattern Analysis and Machine Intelligence Group Department of Computer and Information Science University of Macau Taipa China School of Electrical and Electronic Engineering College of Engineering Yonsei University Seoul Korea Republic of

Palmprint recognition has emerged as a prominent biometric technology, widely applied in diverse scenarios. Traditional handcrafted methods for palmprint recognition often fall short in representation capability, as they heavily depend on researchers' prior knowledge. Deep learning (DL) has been introduced to address this limitation, leveraging its remarkable successes across various domains. While existing surveys focus narrowly on specific tasks within palmprint recognition-often grounded in traditional methodologies-there remains a significant gap in comprehensive research exploring DL-based approaches across all facets of palmprint recognition. This paper bridges that gap by thoroughly reviewing recent advancements in DL-powered palmprint recognition. The paper systematically examines progress across key tasks, including region-of-interest segmentation, feature extraction, and security/privacy-oriented challenges. Beyond highlighting these advancements, the paper identifies current challenges and uncovers promising opportunities for future research. By consolidating state-of-the-art progress, this review serves as a valuable resource for researchers, enabling them to stay abreast of cutting-edge technologies and drive innovation in palmprint recognition. Copyright © 2025, The Authors. All rights reserved.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

Segmentation of the Ventricle Membranes in Short-Axis Sequences by Optical Flow Base on DLSRE Model

引用

Chinese Journal of Electronics 2021年第3期30卷 460-470页

作者： LI Lin WU Hengfei LI Junhua Department of Electronics and Information Engineering Bozhou University Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang Hangkong University

Recent studies have pointed out that the boundary of the extracted ventricle membranes is unsmooth, and the segmentation of the cardiac papillary muscle and trabecular muscle do inconformity the clinical requirements. To address these issues, this paper proposes an automatic segment algorithm for continuously extracting ventricle membranes boundary, which adopts optical flow field information and sequential images information. The images are cropped by frame difference method, which according to the continuity of adjacent slices of cardiac MRI images. The roughly boundary of epicardium is extracted by the Double level set region evolution(DLSRE) model, which combines image global information, local information and edge information. The ventricle endocardium and epicardial contours are tracked according to the optical flow field information between image sequences. The segmentation results are optimized by Delaunay triangulation algorithm. The experimental results demonstrate that the proposed method can improve the accuracy of segmenting the ventricle endocardium and epicardium contours, and segment the contour of the smooth ventricle membrane edge that meets the clinical definition.

关键词： edge information image sequences automatic segment algorithm sequential images information clinical requirements medical image processing cardiology optical flow base extracted ventricle membranes roughly boundary local information ventricle endocardium trabecular muscle optical flow field information continuously extracting ventricle membranes boundary DLSRE model biomedical MRI smooth ventricle membrane edge image global information mesh generation muscle short-axis sequences cardiac MRI images image segmentation cardiac papillary muscle frame difference method region evolution model

来源：评论

学校读者我要写书评

暂无评论

Fast hybrid fitting energy-based active contour model for target detection

引用

Chinese Optics Letters 2011年第7期9卷 29-32页

作者：王登位张天序颜露新 State Key Laboratory for Multispectral Information Processing Technologies Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology

A novel hybrid fitting energy-based active contour model in the level set framework is proposed. The method fuses the region and boundary information of the target to achieve accurate and robust detection performance. A special extra term that penalizes the deviation of the level set function from a signed distance function is also included in our method. This term allows the time-consuming redistancing operation to be removed completely. Moreover, a fast unconditionally stable numerical scheme is introduced to solve the problem. Experimental results on real infrared images show that our method can improve target detection performance efficiently in terms of the number of iterations and the wasted central processing unit （CPU） time.

关键词： Infrared imaging Program processors

来源：评论

学校读者我要写书评

暂无评论

High performance reconfigurable hardware system for real-time image processing

引用

Journal of Systems Engineering and Electronics 2005年第3期16卷 502-509页

作者：赵广州张天序王岳环曹治国左峥嵘 State Key Laboratory for I mage Processing and Intelligent Control Inst .for Pattern Recognition and Artificial Intelligence Huazhong Univ .of Science and Technology

A novel reconfigurable hardware system which uses both muhi-DSP and FPGA to attain high performance and real-time image processing are presented. The system structure and working principle of mainly processing multi-BSP board, extended multi-DSP board are analysed. The outstanding advantage is that the communication among different board components of this system is supported by high speed link ports ＆ serial ports for increasing the system performance and computational power. Then the implementation of embedded real-time operating systems （RTOS） by us is discussed in detail. In this system, we adopt two kinds of parallel structures controlled by RTOS for parallel processing of algorithms. The experimental results show that exploitive period of the system is short, and maintenance convenient. Thus it is suitable for real-time image processing and can get satisfactory effect of image recognition.

关键词： multi-DSP fidd programmable gate arrays real-time image processing real time operating systems parallel structure.

来源：评论

学校读者我要写书评

暂无评论

Bioimage-based protein subcellular location prediction： a comprehensive review

引用

Frontiers of Computer Science 2018年第1期12卷 26-39页

作者： Ying-Ying XU Li-Xiu YAO Hong-Bin SHEN Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai 200240 China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai 200240 China

Subcellular localization of proteins can provide key hints to infer their functions and structures in cells. With the breakthrough of recent molecule imaging techniques, the usage of 2D bioimages has become increasingly popular in automatically analyzing the protein subcellular location pat- terns. Compared with the widely used protein 1D amino acid sequence data, the images of protein distribution are more intuitive and interpretable, making the images a better choice at many applications for revealing the dynamic char- acteristics of proteins, such as detecting protein translocation and quantification of proteins. In this paper, we systemati- cally reviewed the recent progresses in the field of automated image-based protein subcellular location prediction, and clas- sified them into four categories including growing of bioim- age databases, description of subcellular location distribution patterns, classification methods, and applications of the pre- diction systems. Besides, we also discussed some potential directions in this field.

关键词： bioimage informatics protein subcellular loca-tion prediction global and local features multi-location pro-tein recognition

来源：评论

学校读者我要写书评

暂无评论

Motion cue based pedestrian detection with two-frame-filtering

引用

High Technology Letters 2015年第3期21卷 328-332页

作者：吕敬钦 Zhang Miaohui Yang Jie Institute of Image Processing and Pattern Recognition Shanghai Jiaotong Universityand Key Laboratory of System Control and Information ProcessingMinistry of Education of China

This study proposes a motion cue based pedestrian detection method with two-trame-filtering （Tff） for video surveillance. The novel motion cue is exploited by the gray value variation between two frames. Then Tff processing filters the gradient magnitude image by the variation map. Summa- tions of the Tff gradient magnitudes in cells are applied to train a pre-deteetor to exclude most of the background regions. Histogram of Tff oriented gradient （HTffOG） feature is proposed for pedestrian detection. Experimental results show that this method is effective and suitable for real-time surveil- lance applications.

关键词： pedestrian detection two-frame-filtering （TFF） Tff magnitude vector （TffMV） Histogram of Tff oriented gradient （ HTffOG） SVM video surveillance

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：