检索结果-内蒙古大学图书馆

Spatio-Temporal and Retrieval-Augmented Modelling for Chest X-Ray Report Generation

IEEE Transactions on Medical Imaging 2025年第5期44卷 2244-2255页

作者： Yang, Yan You, Xiaoxing Zhang, Ke Fu, Zhenqi Wang, Xianyun Ding, Jiajun Sun, Jiamei Yu, Zhou Huang, Qingming Han, Weidong Yu, Jun Hangzhou Dianzi University School of Computer Science and Technology Hangzhou310018 China Tsinghua University Department of Automation Beijing100084 China School of Intelligence Science and Engineering 518055 China University of Chinese Academy of Sciences School of Computer and Control Engineering Beijing101408 China Zhejiang Cancer Hospital Department of Colorectal Medical Oncology Hangzhou310022 China

Chest X-ray report generation has attracted increasing research attention. However, most existing methods neglect the temporal information and typically generate reports conditioned on a fixed number of images. In this paper, we propose STREAM: Spatio-Temporal and REtrieval-Augmented Modelling for automatic chest X-ray report generation. It mimics clinical diagnosis by integrating current and historical studies to interpret the present condition (temporal), with each study containing images from multi-views (spatial). Concretely, our STREAM is built upon an encoder-decoder architecture, utilizing a large language model (LLM) as the decoder. Overall, spatio-temporal visual dynamics are packed as visual prompts and regional semantic entities are retrieved as textual prompts. First, a token packer is proposed to capture condensed spatio-temporal visual dynamics, enabling the flexible fusion of images from current and historical studies. Second, to augment the generation with existing knowledge and regional details, a progressive semantic retriever is proposed to retrieve semantic entities from a preconstructed knowledge bank as heuristic text prompts. The knowledge bank is constructed to encapsulate anatomical chest X-ray knowledge into structured entities, each linked to a specific chest region. Extensive experiments on public datasets have shown the state-of-the-art performance of our method. Related codes and the knowledge bank are available at https://***/yangyan22/STREAM. © 1982-2012 IEEE.

关键词： X ray production

来源：评论

学校读者我要写书评

暂无评论

Adaptive Particle Swarm Optimization of U-net Parameters for Marine Aquaculture Image Segmentation 13

Adaptive Particle Swarm Optimization of U-net Parameters for...

引用

13th International Conference on Intelligent control and Information Processing, ICICIP 2025

作者： Zhao, Jin Wang, Jun Han, Min Fan, Jianchao School of Computer Science and Engineering Chongqing Three Gorges University Chongqing China Department of Computer Science Department of Data Science City University of HongKong Hong Kong School of Control Science and Engineering Dalian University of Technology Dalian China

ISBN: (纸本)9798331516147

Marine aquaculture image segmentation plays a crucial role in managing aquatic resources and environmental protection. Traditional deep learning models rely on manual parameter tuning for image segmentation, which limits their efficiency and accuracy. This paper proposes an adaptive Particle Swarm Optimization (PSO) algorithm to optimize the parameters of the U-net model automatically. The algorithm dynamically adjusts the PSO parameters based on the population’s entropy and clustering metrics and employs a hill-climbing algorithm to address the issue of the PSO easily falling into local optima, enhancing the algorithm’s adaptability. The proposed algorithm updates and iterates particles to automatically find suitable model parameters. The remote sensing data used in this experiment were from the Yellow Sea aquaculture area near Dalian, China, with a segmentation accuracy of 91.8%. This method improves segmentation accuracy, reduces the burden of manual parameter tuning, and provides an effective solution for optimizing deep learning models. © 2025 IEEE.

关键词： Aquaculture

来源：评论

学校读者我要写书评

暂无评论

MedFILIP: Medical Fine-grained Language-Image Pre-training

引用

IEEE Journal of Biomedical and Health Informatics 2025年第5期29卷 3587-3597页

作者： Liang, Xinjie Li, Xiangyu Li, Fanding Jiang, Jie Dong, Qing Wang, Wei Wang, Kuanquan Dong, Suyu Luo, Gongning Li, Shuo The School of Computer Science and Technology Harbin Institute of Technology Harbin China The Department of Thoracic Surgery at No. 4 Affiliated Hospital Harbin Medical University Harbin China The School of Computer Science and Technology Harbin Institute of Technology Shenzhen China The College of computer and control engineering Northeast Forestry University Harbin China The Computer Electrical and Mathematical Sciences & Engineering Division King Abdullah University of Science and Technology Thuwal Saudi Arabia The Department of Biomedical Engineering Department of Computer Data Science Case Western Reserve University ClevelandOH United States

Medical vision-language pretraining (VLP) that leverages naturally-paired medical image-report data is crucial for medical image analysis. However, existing methods struggle to accurately characterize associations between images and diseases, leading to inaccurate or incomplete diagnostic results. In this work, we propose MedFILIP, a fine-grained VLP model, introduces medical image-specific knowledge through contrastive learning, specifically: 1) An information extractor based on a large language model is proposed to decouple comprehensive disease details from reports, which excels in extracting disease deals through flexible prompt engineering, thereby effectively reducing text complexity while retaining rich information at a tiny cost. 2) A knowledge injector is proposed to construct relationships between categories and visual attributes, which help the model to make judgments based on image features, and fosters knowledge extrapolation to unfamiliar disease categories. 3) A semantic similarity matrix based on fine-grained annotations is proposed, providing smoother, information-richer labels, thus allowing fine-grained image-text alignment. 4) We validate MedFILIP on numerous datasets, e.g., RSNA-Pneumonia, NIH ChestXray14, VinBigData, and COVID-19. For single-label, multi-label, and fine-grained classification, our model achieves state-of-the-art performance, the classification accuracy has increased by a maximum of 6.69%. © 2013 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Interference Suppression and Jitter Elimination Ability-Based Adaption Tracking Guidance for Robotic Fishes

引用

IEEE/CAA Journal of Automatica Sinica 2025年第1期12卷 126-137页

作者： Dongfang Li Jie Huang Rob Law Xin Xu Limin Zhu Edmond Q.Wu IEEE the School of Electrical Engineering and Automation Fuzhou University the Key Laboratory of System Control and Information Processing Ministry of Education the School of Electrical Engineering and Automation Fuzhou University 5G+Industrial Internet Institute Fuzhou University the University of Macau the College of Mechatronics and Automation National University of Defense Technology the School of Mechanical Engineering Shanghai Jiao Tong University the Department of Computer Science and Engineering Shanghai Jiao Tong University

This work presents an adaptive tracking guidance method for robotic fishes. The scheme enables robots to suppress external interference and eliminate motion jitter. An adaptive integral surge line-of-sight guidance rule is designed to eliminate dynamics interference and sideslip issues. Limited-time yaw and surge speed observers are reported to fit disturbance variables in the model. The approximation values can compensate for the system's control input and improve the robots' tracking ***, this work develops a terminal sliding mode controller and third-order differential processor to determine the rotational torque and reduce the robots' run jitter. Then, Lyapunov's theory proves the uniform ultimate boundedness of the proposed method. Simulation and physical experiments confirm that the technology improves the tracking error convergence speed and stability of robotic fishes.

关键词： Adaptive integral surge line-of-sight approximation robotic fish speed observer

来源：评论

学校读者我要写书评

暂无评论

Multi-scale network for single image deblurring based on ensemble learning module

引用

Multimedia Tools and Applications 2025年第11期84卷 9045-9064页

作者： Wu, WenBo Pan, Yun Su, Na Wang, JingTao Wu, ShaoChuan Xu, ZeKun Yu, YouJian Liu, YaPeng State Key Laboratory of Media Convergence and Communication Communication University of China Beijing100024 China School of Computer and Cyberspace Security Communication University of China Beijing100024 China School of Electronics and Information Engineering Harbin Institute of Technology Harbin150080 China College of Computer and Control Engineering Northeast Forestry University Harbin150040 China School of Computer and Information Engineering Tianjin Chengjian University Tianjin300384 China School of Computer Science and Technology Anhui University Hefei230601 China

In this paper, we have identified two primary issues with current multi-scale image deblurring methods. On the one hand, the blurring scale is ignored. On the other hand, the context information of images is not fully utilized, and the spatial detail information of images is lost. To better solve the above problems, on top of that, this paper proposes a multi-scale network for single image deblurring. The designed network contains two parts: 1) Ensemble Learning Model: The Weak Learning Model in this module connects multiple weak learners in series to increase network depth. Moreover, through multi-scale feature ensemble module, the output features and intermediate features of different weak learner are integrated, and finally strong learner is used to enhance the features with semantic information at different scales;2) Spatial Feature Enhancement Module: This module can preserve spatial detail information of images and compensate for the disadvantages of losing image spatial details due to continuous downsampling in the Ensemble Learning Model structure. Our proposed deblurring model has been extensively evaluated on several benchmark datasets, and the model achieves superior performance compared to the most advanced deblurring methods. In particular, the peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) values are 33.57 dB and 0.965 on the GoPro dataset, respectively, with PSNR and SSIM improving by 0.49 dB and 0.002 over NAFNet, and 0.65 dB and 0.004 over Restormer. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

State Estimation of a Spatial 2-D Linear Diffusion Process With Mobile Sensors

引用

IEEE Transactions on Automation science and engineering 2025年 22卷 12024-12032页

作者： Zhang, Xiao-Wei Chen, Kui Wu, Huai-Ning Wang, Jin-Liang Wang, Zi-Peng Beijing University of Technology School of Information Science and Technology Beijing100124 China Tiangong University School of Control Science and Engineering Tianjin300387 China Beihang University Science and Technology on Aircraft Control Laboratory School of Automation Science and Electrical Engineering Beijing100191 China Beihang University Hangzhou International Innovation Institute Hangzhou311115 China Tiangong University Tianjin Key Laboratory of Autonomous Intelligence Technology and Systems School of Computer Science and Technology Tianjin300387 China Beijing University of Technology School of Information Science and Technology Beijing Institute of Artificial Intelligence Beijing100124 China

This paper studies the state observer design of a spatial two-dimensional (2-D) linear diffusion process described by a linear parabolic partial differential equation (PDE) under mobile sensors. Firstly, we analyze the well-posedness of the PDE system and give the structure form of the state observer with mobile sensors. Subsequently, according to the number of mobile sensors, the 2-D space domain is divided into multiple sub-domains, and the mobile sensors are guided by the projection operator method, which can guarantee that the mobile sensors can only move in their respective 2-D sub-domains. Then, in the light of Lyapunov theory, Poincaré-Wirtinger inequality and Barbalat lemma, we propose an observation-plus-guidance design method to ensure the asymptotic stability of the state estimation error system. In the designed mobile strategy, the actual guidance of mobile sensors is essentially a physical synthesis of two direction guidance laws, where two dimensional guidance laws are designed separately. Moreover, the existence condition of the observer is given by linear matrix inequalities. At last, a numerical example is provided to demonstrate the efficacy of the proposed design scheme. © 2004-2012 IEEE.

关键词： Asymptotic stability

来源：评论

学校读者我要写书评

暂无评论

Compression Format and Systolic Array Structure Co-design for Accelerating Sparse Matrix Multiplication in DNNs 24th

Compression Format and Systolic Array Structure Co-design f...

引用

24th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2024

作者： Cao, Yongxiang Jiang, Jixiang Zhao, Guocheng Wang, Wei Jiang, Hongxu Song, Yanfei School of Computer Science and Engineering Beihang University Beijing China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

ISBN: (纸本)9789819615445

The systolic array (SA) architecture is widely used in accelerator/AI chip design due to its excellent matrix multiplication acceleration effect. However, the mismatch between the traditional sparse matrix compression format and the SA architecture results in poor SA performance in computing sparse matrices. To solve the problem, we propose a method for co-designing the sparse compression format and SA architecture. This work proposes the Vector Group Compressed Coordinate (VGCC) data stream compression format and designs a sparse SA architecture based on hardware encoding and decoding. VGCC can handle data streams of any size without increasing the index bit width. The VGCC compression size is significantly smaller than general sparse compression formats such as COO/CSR. In a sparse matrix with a sparsity of 90%, it saves 67.13% of storage space compared to the state-of-the-art ECOO data stream compression format and achieves an average acceleration of 1.54 times. We also propose a VGCC-friendly SA architecture. Our SA architecture engine reduces logic consumption by 51.6% compared to Sparse TPU while achieving a 3.23x speedup. To mitigate the issue of high no-load rates in systolic arrays, we introduce a Data Transmission Priority (DTP) data matching algorithm. With sparsity levels ranging from 50% to 90%, the algorithm’s calculation speed is enhanced by 1.124x to 1.991x. We implemented a sparse DNN accelerator on an FPGA Zynq UltraScale+MPSoC ZCU102, utilizing the VGCC compression format proposed in this study for compressing input data. When compared to the S2 Engine, the accelerator achieved a 3.37x speed improvement in matrix multiplication with 75% sparsity, significantly enhancing the speed of sparse matrix multiplication. The accelerator achieved an average throughput of 1079.33GOP/s when inferencing DNNs. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Systolic arrays

来源：评论

学校读者我要写书评

暂无评论

Aspect Sentiment Triple Extraction Model Integrating with Syntactic Information 24

Aspect Sentiment Triple Extraction Model Integrating with Sy...

引用

5th International Conference on computer science and Management Technology, ICCSMT 2024

作者： Zhao, Jingsheng Qu, Weilong Zheng, Jiashang Yu, Chen Zhu, Qiaoming School of Information and Control Engineering Qingdao University of Technology Shandong Qingdao China School of Computer Science and Technology Soochow University Jiangsu Suzhou China

ISBN: (纸本)9798400709999

The current mainstream aspect level sentiment analysis methods focus on modeling the relationship between word representations in text and their context, fail to fully utilize the syntactic structure information of the *** paper proposes a sentiment triplet extraction model IS-ASTE(Integrating with Syntactic information model for Aspect Sentiment Triplet Extraction, IS-ASTE).Firstly, the graph attention layer is employed to obtain contextual context ***, based on the syntactic dependency tree to obtain the text element's dependency, lexical and distance information, which is combined with the attention mechanism to augment the sentiment ***, graph convolutional neural networks are integrated to aggregate the feature information of nodes for sentiment *** experimental results indicate that, across four representative datasets, the F1 values are all better than those of the baseline model, demonstrating better performance in sentiment analysis. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Improving graph collaborative filtering with network motifs

引用

Neural Computing and Applications 2025年 1-20页

作者： Zhang, Yuqi Yu, Jian Liu, Zhizhong Wang, Guiling Nguyen, Minh Sheng, Quan Z. Wang, Nancy Department of Computer and Information Sciences Auckland University of Technology Auckland Central1010 New Zealand School of Computer and Control Engineering Yantai University Shandong Yantai264005 China School of Information Science and Technology North China University of Technology Beijing100144 China School of Computing Macquarie University SydneyNSW2109 Australia

Deep learning on graphs, specifically graph convolutional networks (GCNs), has exhibited exceptional efficacy in the domain of recommender systems. Most GCNs have a message-passing architecture that enables nodes to aggregate information from neighbours iteratively through multiple layers. This enables GCNs to learn from higher-order information, but the model does not allow for direct captions of the local structural patterns. Our rationale is to investigate the effectiveness of capturing such local patterns for graph-based collaborative filtering to enhance model’s learning ability per layer. This technique combines lower-order and higher-order interactions during layer-wise propagation. In this paper, we propose MotifGCN to aggregate both lower-order and higher-order information in each graph convolution layer. Specifically, we develop dedicated algorithms of generating motif adjacency matrices. The matrices are then used for motif-enhanced neighbourhood aggregation in each layer. As this paper focuses on recommender systems, MotifGCN is built on the basis of bipartite graphs. Our experiments on four real-world datasets show that MotifGCN has a superior performance compared to various state-of-the-art methods. © The Author(s) 2025.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

A Zero-Sequence Current Analysis Approach for Rotating Machinery Fault Diagnosis of Induction Motor Drivetrain Based on Sparse Learning

引用

IEEE Transactions on Power Electronics 2025年第7期40卷 9800-9810页

作者： Liu, Zhao-Hua Long, Jun-Jie Wei, Hua-Liang Liu, Kan Zhang, Ying-Jie Li, Xiao-Hua Hunan University of Science and Technology School of Information and Electrical Engineering Xiangtan411201 China The University of Sheffield School of Electrical and Electronic Engineering Department of Automatic Control and Systems Engineering SheffieldS1 3JD United Kingdom Hunan University College of Mechanical and Vehicle Engineering Changsha410082 China Hunan University College of Computer Science and Electronic Engineering Changsha410082 China

Fault diagnosis of rotating machinery driven by induction motors has received increasing attention. Current diagnostic methods, which can be performed on existing inverters or current transformers of three-phase induction machines, have become a more economical and reliable alternative to vibration diagnostic methods. Existing references mainly focus on the stator current analysis of single-phase, but most single-phase current analysis methods utilize only a fraction of the total information accessible in the three-phase system. Field experience shows that zero-sequence current (ZSC) has more distinctive fault characteristics compared to single-phase current, and therefore it is better to use in mechanical fault detection and diagnostic tasks. This article proposes a novel sparse learning-based method for ZSC analysis for induction rotating motor drive fault diagnosis. First, it elaborates and compares the effectiveness of ZSC in revealing fault characteristics compared with single-phase current by analyzing the fault diagnosis mechanism of ZSC. In addition, the method proposes a correlation entropy-enhanced sparse learning method for the problem of high-frequency noise and interference in the ZSC signals, so as to enhance the learning of the features of the noise-containing signals. The diagnostic efficacy of the proposed method has been verified through experiments on two real datasets. © 1986-2012 IEEE.

关键词： Induction motors

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：