检索结果-内蒙古大学图书馆

EK-Net++: Real-time scene text detection with expand kernel distance and Epoch Adaptive Weight

Expert systems with Applications 2025年 267卷

作者： Zhu, Boyuan Chen, Xi Tang, Quan Chen, C.L. Philip Liu, Fagui Computer Science and Engineering South China University of Technology Guangzhou510006 China Cyberspace Security Research Center Peng Cheng Laboratory Shenzhen518066 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100080 China

Recently, scene text detection has received significant attention due to its wide applications. Accurate detection in complex scenes of multiple scales, orientations, and curvature remains a challenge. Component-based methods have emerged as the dominant approach for offering a more flexible way to achieve superior performance. However, Component-based methods employ the Vatti clipping algorithm for multi-instance training to handle the difficulty of arbitrary-shaped text. Yet we identify several bias results from these approaches called the "shrinked kernel" leading to decreased accuracy. Additionally, almost all text detection methods fail to consider the characteristics of different datasets and directly assign fixed loss weights to multi-instances. To address these limitations, we propose a new approach named Expand Kernel Network (EK-Net++), which presents the expand kernel distance map to compensate for the previous deficiency and incorporates three-stage regression to complete integral instance detection. Furthermore, we design the Epoch Adaptive Weight algorithm which dynamically distinguishes the characteristics of different datasets. EK-Net++ not only achieves precise positioning of arbitrary-shaped text but also strikes a balance between performance and speed. Evaluation results show that EK-Net++ attains state-of-the-art or competitive performance compared to other advanced methods, e.g., F-measure of 86.72% at 35.42 FPS on ICDAR 2015, F-measure of 85.83% at 40.13 FPS on CTW1500. © 2024 Elsevier Ltd

关键词： Epoch Adaptive Weight Expand kernel distance Real-time Scene text detection

来源：评论

学校读者我要写书评

暂无评论

First-in-human orbital tumor surgery guided by near-infrared II window fluorescence imaging: A feasibility study

INTERDISCIPLINARY MEDICINE

引用

INTERDISCIPLINARY MEDICINE 2025年第1期3卷

作者： Zhang, Zeyu Guo, Lishuang Yao, Lan Li, Yueyue Hei, Yan Wang, Qi Wang, Xiaoyi Ma, Rui Yang, Xinji Hu, Zhenhua Wu, Wei Beihang Univ Beijing Adv Innovat Ctr Big Data Based Precis Med Sch Engn Med Beijing Peoples R China Beihang Univ Key Lab Big Data Based Precis Med Minist Ind & Informat Technol Beijing Peoples R China Chinese Peoples Liberat Army Gen Hosp Med Ctr 3 Sr Dept Ophthalmol Beijing 100143 Peoples R China Chinese Acad Sci CAS Key Lab Mol Imaging Inst Automat Beijing Key Lab Mol Imaging Beijing 100190 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing Peoples R China

Precise resection of orbital tumors is a critically important but elusive issue. Fluorescence imaging in the near-infrared II window (NIR-II) holds the potential to provide the surgeons with real-time identification for orbital tumors. Here, for the first time, we evaluated the feasibility and clinical value of NIR-II fluorescence imaging in orbital tumor surgery. To establish the method of NIR-II fluorescence imaging for orbital tumors, we developed a NIR-II fluorescence imaging system and indocyanine green (ICG) served as the fluorescent contrast agent. Twenty-two patients diagnosed with orbital tumors and scheduled for standard-of-care surgery were enrolled in this study. Time-course NIR-II fluorescence imaging of two patients with superficial orbital tumors showed the optimum imaging time was 2 h post injection of ICG. Fifteen patients were allocated for diagnostic test, which showed that both the in situ and ex vivo NIR-II fluorescence imaging showed better sensitivity and specificity than the surgeon judgment. In the feasibility trial of the remaining five patients, the surgeon encountered 34 suspicious regions and surgical decisions were changed nine times due to NIR-II fluorescence imaging. The resultant seven additional resections were justified by histopathology and the two conservative treatments did not result in recurrence. Based on these findings, we suggested that ICG-based NIR-II fluorescence imaging was feasible to guide precise resection of orbital tumors. A future randomized controlled trial with a larger cohort is encouraged to further verify the clinical value.

关键词： fluorescence imaging ICG NIR-II imaging orbital tumor

来源：评论

学校读者我要写书评

暂无评论

Qingda Granule Attenuates Hypertension-Induced Cardiac Damage via Regulating Renin-Angiotensin System Pathway

引用

Chinese Journal of Integrative Medicine 2025年第5期31卷 402-411页

作者： LONG Lin-zi TAN Ling XU Feng-qin YANG Wen-wen LI Hong-zheng LIU Jian-gang WANG Ke ZHAO Zhi-ru WANG Yue-qi WANG Chao-ju WEN Yi-chao HUANGMing-yan QU Hua FU Chang-geng CHEN Ke-ji Department of Geriatrics Xiyuan Hospital of China Academy of Chinese Medical SciencesBeijing100091China Department of Traditional Chinese Medicine the Eighth Affiliated Hospital of Sun Yat-Sen UniversityShenzhenGuangdong Province518033China Xiyuan Hospital National Cardiovascular Clinical Medical Research Center of Traditional MedicineBeijing100091China Graduate School of Beijing University of Chinese Medicine Beijing100091China Cardiovascular Department the Second Affiliated HospitalShanxi University of Chinese MedicineTaiyuan030002China Key Laboratory of Molecular Imaging Beijing Key Laboratory of Molecular Imagingthe State Key Laboratory of Management and Control for Complex SystemsInstitute of AutomationChinese Academy of SciencesBeijing100090China Cadre 2 Ward Xinjiang Uygur Autonomous Region Institute of Traditional Chinese MedicineUrumqi830000China Academy of Integrative Medicine Fujian Univrsity of Traditional Chinese MedicineFuzhou350122China

Objective:To assess the efficacy of Qingda Granule(QDG)in ameliorating hypertensioninduced cardiac damage and investigate the underlying mechanisms ***:Twenty spontaneously hypertensive rats(SHRs)were used to develope a hypertension-induced cardiac damage *** 10Wistar Kyoto(WKY)rats were used as normotension *** were administrated intragastrically QDG[0.9 g/(kg·d)]or an equivalent volume of pure water for 8 *** pressure,histopathological changes,cardiac function,levels of oxidative stress and inflammatory response markers were ***,to gain insights into the potential mechanisms underlying the protective effects of QDG against hypertensioninduced cardiac injury,a network pharmacology study was *** results were validated by Western blot,radioimmunoassay immunohistochemistry and quantitative polymerase chain reaction,***:The administration of QDG resulted in a significant decrease in blood pressure levels in SHRs(P<0.01).Histological examinations,including hematoxylin-eosin staining and Masson trichrome staining revealed that QDG effectively attenuated hypertension-induced cardiac ***,echocardiography demonstrated that QDG improved hypertension-associated cardiac ***-linked immunosorbent assay and colorimetric method indicated that QDG significantly reduced oxidative stress and inflammatory response levels in both myocardial tissue and serum(P<0.01).Conclusion:Both network pharmacology and experimental investigations confirmed that QDG exerted its beneficial effects in decreasing hypertensioninduced cardiac damage by regulating the angiotensin converting enzyme(ACE)/angiotensinⅡ(AngⅡ)/AngⅡreceptor type 1 axis and ACE/AngⅡ/AngⅡreceptor type 2 axis.

关键词： blood pressure cardiac damage hypertension Qingda Granule renin-angiotensin system

来源：评论

学校读者我要写书评

暂无评论

Contextual Multi-Armed Bandit-Based Dynamic Cooperative Link Configuration for AUV in UWASNs With Energy Harvesting

引用

IEEE Transactions on Cognitive Communications and Networking 2025年

作者： Dai, Jun Li, Xinbin Han, Song Yu, Junzhi Liu, Zhixin Yanshan University Key Lab of Industrial Computer Control Engineering of Hebei Province Qinhuangdao066004 China Yanshan University Key Laboratory of Intelligent Rehabilitation and Neuromodulation of Hebei Province Qinhuangdao066004 China Peking University State Key Laboratory for Turbulence and Complex Systems Department of Advanced Manufacturing and Robotics BIC-ESAT College of Engineering Beijing100871 China

This paper investigates the cooperative link configuration problem for Autonomous Underwater Vehicle (AUV) in Underwater Acoustic (UWA) sensor networks with Energy Harvesting (EH), which aims to maximize long-term cumulative capacity by jointly optimizing cooperation relay, AUV transmission power, and relay transmission power. Subject to unknown time-varying Channel state Information (CSI), unpredictable stochastic EH, and variable communication topology caused by AUV mobility, the proposed problem is an unknown dynamic combination decision optimization problem. To resist the change of the dynamic UWA communication topology with unknown time-varying CSI and EH, a novel collaborative contextual multi-armed bandit learning framework is proposed, which allows relay nodes to learn cooperatively and enriches the learning information of relays. Consequently, the proposed learning framework can resist the change of the dynamic UWA communication topology efficiently, thereby achieving the superior link configuration quickly. Besides, a learning-rate adjustment rule for the dynamic UWA communication topology is proposed to adaptively balance the exploration-exploitation, thereby avoiding missing the real superior joint relay-power configuration. Finally, simulation results show the significantly superiority of the proposed scheme. © 2015 IEEE.

关键词： Cooperative communication

来源：评论

学校读者我要写书评

暂无评论

Deep Rank-Consistent Pyramid Model for Enhanced Crowd Counting

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING systems 2025年第1期36卷 299-312页

作者： Gao, Jiaqi Huang, Zhizhong Lei, Yiming Shan, Hongming Wang, James Z. Wang, Fei-Yue Zhang, Junping Fudan Univ Shanghai Key Lab Intelligent Informat Proc Sch Comp Sci Shanghai 200433 Peoples R China Fudan Univ Inst Sci & Technol Brain Inspired Intelligence Shanghai 200433 Peoples R China Fudan Univ MOE Frontiers Ctr Brain Sci Shanghai 200433 Peoples R China Shanghai Ctr Brain Sci & Brain Inspired Technol Shanghai 201210 Peoples R China Penn State Univ Coll Informat Sci & Technol University Pk PA 16802 USA Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Macau Univ Sci & Technol Inst Syst Engn Taipa Macao Peoples R China Macau Univ Sci & Technol Inst Syst Engn Int Acad Advisory Comm Taipa Macao Peoples R China Qingdao Acad Intelligent Ind Qingdao 266109 Peoples R China

Most conventional crowd counting methods utilize a fully-supervised learning framework to establish a mapping between scene images and crowd density maps. They usually rely on a large quantity of costly and time-intensive pixel-level annotations for training supervision. One way to mitigate the intensive labeling effort and improve counting accuracy is to leverage large amounts of unlabeled images. This is attributed to the inherent self-structural information and rank consistency within a single image, offering additional qualitative relation supervision during training. Contrary to earlier methods that utilized the rank relations at the original image level, we explore such rank-consistency relation within the latent feature spaces. This approach enables the incorporation of numerous pyramid partial orders, strengthening the model representation capability. A notable advantage is that it can also increase the utilization ratio of unlabeled samples. Specifically, we propose a Deep Rank-consist Ent pyrAmid Model (DREAM), which makes full use of rank consistency across coarse-to-fine pyramid features in latent spaces for enhanced crowd counting with massive unlabeled images. In addition, we have collected a new unlabeled crowd counting dataset, FUDAN-UCC, comprising 4000 images for training purposes. Extensive experiments on four benchmark datasets, namely UCF-QNRF, ShanghaiTech PartA and PartB, and UCF-CC-50, show the effectiveness of our method compared with previous semi-supervised methods. The codes are available at https://***/bridgeqiqi/DREAM.

关键词： Feature extraction Training Task analysis Head labeling Predictive models Magnetic heads Crowd counting feature pyramid ranking semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Dissecting and Mitigating Semantic Discrepancy in Stable Diffusion for Image-to-Image Translation

引用

IEEE-CAA JOURNAL OF AUTOMATICA SINICA 2025年第4期12卷 705-718页

作者： Yuan, Yifan Yang, Guanqun Wang, James Z. Zhang, Hui Shan, Hongming Wang, Fei-Yue Zhang, Junping Fudan Univ Sch Comp Sci Shanghai Key Lab Intelligent Informat Proc Shanghai 200433 Peoples R China Fuxi Team NetEase Corp Hangzhou Peoples R China Penn State Univ Coll Informat Sci & Technol University Pk PA 16802 USA Beijing Jiaotong Univ Sch Comp & Informat Technol Beijing 100098 Peoples R China Fudan Univ Inst Sci & Technol Brain inspired Intelligence Shanghai 200433 Peoples R China Fudan Univ MOE Frontiers Ctr Brain Sci Shanghai 200433 Peoples R China Shanghai Ctr Brain Sci & Brain inspired Technol Shanghai 200031 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Macau Univ Sci & Technol Inst Syst Engn Macau Peoples R China Qingdao Acad Intelligent Ind Qingdao 266109 Peoples R China

Finding suitable initial noise that retains the original image's information is crucial for image-to-image (I2I) translation using text-to-image (T2I) diffusion models. A common approach is to add random noise directly to the original image, as in SDEdit. However, we have observed that this can result in "semantic discrepancy" issues, wherein T2I diffusion models mis-interpret the semantic relationships and generate content not present in the original image. We identify that the noise introduced by SDEdit disrupts the semantic integrity of the image, leading to unintended associations between unrelated regions after U-Net upsampling. Building on the widely-used latent diffusion model, Stable Diffusion, we propose a training-free, plug-and-play method to alleviate semantic discrepancy and enhance the fidelity of the translated image. By leveraging the deterministic nature of denoising diffusion implicit models (DDIMs) inversion, we correct the erroneous features and correlations from the original generative process with accurate ones from DDIM inversion. This approach alleviates semantic discrepancy and surpasses recent DDIM-inversion-based methods such as PnP with fewer priors, achieving a speedup of 11.2 times in experiments conducted on COCO, ImageNet, and ImageNet-R datasets across multiple I2I translation tasks.

关键词： Translation Correlation Codes Image edge detection Semantics Noise Noise reduction Text to image Diffusion models Erosion DDIM inversion diffusion model image-to-image translation semantic discrepancy stable diffusion

来源：评论

学校读者我要写书评

暂无评论

Policy iteration optimal tracking control for chaotic systems by using an adaptive dynamic programming approach

引用

Chinese Physics B 2015年第3期24卷 87-94页

作者：魏庆来刘德荣徐延才 The State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences

A policy iteration algorithm of adaptive dynamic programming（ADP） is developed to solve the optimal tracking control for a class of discrete-time chaotic systems. By system transformations, the optimal tracking problem is transformed into an optimal regulation one. The policy iteration algorithm for discrete-time chaotic systems is first described. Then,the convergence and admissibility properties of the developed policy iteration algorithm are presented, which show that the transformed chaotic system can be stabilized under an arbitrary iterative control law and the iterative performance index function simultaneously converges to the optimum. By implementing the policy iteration algorithm via neural networks,the developed optimal tracking control scheme for chaotic systems is verified by a simulation.

关键词： adaptive critic designs adaptive dynamic programming approximate dynamic programming neuro-dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Precise planar motion measurement of a swimming multi-joint robotic fish

引用

Science China(Information Sciences) 2016年第9期59卷 183-197页

作者： Jun YUAN Junzhi YU Zhengxing WU Min TAN State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences

This paper presents a method for planar motion measurement of a swimming multi-joint robotic fish. The motion of the robotic fish is captured via image sequences and a proposed tracking scheme is employed to continuously detect and track the robotic fish. The tracking scheme initially acquires a rough scope of the robotic fish and thereafter precisely locates it. Historical motion information is utilized to determine the rough scope, which can speed up the tracking process and avoid possible ambient interference. A combination of adaptive bilateral filtering and k-means clustering is then applied to segment out color markers accurately. The pose of the robotic fish is calculated in accordance with the centers of these markers. Further, we address the problem of time synchronization between the on-board motion control system of the robotic fish and the motion measurement system. To the best of our knowledge, this problem has not been tackled in previous research on robotic fish. With information about both the multi-link structure and motion law of the robotic fish, we convert the problem to a nonlinear optimization problem, which we then solve using the particle swarm optimization(PSO) algorithm. Further, smoothing splines are adopted to fit curves of poses versus time, in order to obtain a continuous motion state and alleviate the impact of noise. Velocity is acquired via a temporal derivative operation. The results of experiments conducted verify the efficacy of the proposed method.

关键词： motion measurement robotic fish time synchronization visual tracking localization

来源：评论

学校读者我要写书评

暂无评论

Short-term wind power forecast with turning weather based on DBSCAN-RFE-LightGBM

引用

Renewable Energy 2025年 251卷

作者： Wu, Zhenlong Fan, Xinyu Bian, Guibin Liu, Yanhong Zhang, Xiaoke Chen, YangQuan School of Electrical and Information Engineering Zhengzhou University Zhengzhou450001 China State Key Laboratory of Intelligent Agricultural Power Equipment Zhengzhou University Luoyang471000 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China Electric Power Research Institute of State Grid Henan Electric Power Company Zhengzhou450052 China Lab Department of Mechanical Engineering School of Engineering University of California MercedCA95343 United States

At present, the wind power prediction technology is becoming more and more mature, however, the turning weather brings a decrease in prediction accuracy due to its suddenness and instability. In this paper, a wind power prediction method considering the turning period and non-turning period respectively is proposed to weaken the adverse effects caused by turning weather. Firstly, the prediction effects of multiple models are compared, density-based spatial clustering of applications with noise (DBSCAN) is selected as the outlier processing method, recursive feature elimination (RFE) is used as the feature selection method, and Light gradient boosting machine (LightGBM) is used for prediction. The combined prediction method based on DBSCAN-RFE-LightGBM can reduce the influence of abnormal data and redundant features and improve the prediction effect. Then, the sliding window is set to detect the turning period. Considering that the turning weather is an emergency and does not happen frequently, the amount of data is small, which leads to the inability to train the model well. Generative adversarial networks (GAN) are applied to expand the turning period data. The LightGBM is trained and predicted by using the expended turning period data. Finally, the time-division prediction results are merged. Using the data collected from wind farms for short-term power prediction experiments, the time-segment prediction method proposed in this paper with GAN reduces MAE by 1.913 and RMSE by 3.351 on a single unit compared with the non-differentiated period. © 2025 Elsevier Ltd

关键词： Merging

来源：评论

学校读者我要写书评

暂无评论

AutoMine: A Multimodal Dataset for Robot Navigation in Open-Pit Mines

引用

JOURNAL OF FIELD ROBOTICS 2025年第4期42卷 1523-1536页

作者： Li, Yuchen Teng, Siyu Wang, Junhui Ai, Yunfeng Tian, Bin Zhe, Xuanyuan Bing, Zhenshan Knoll, Alois C. Wang, Fei-Yue Chen, Long WAYTOUS R&D Ctr Beijing Peoples R China Beijing Normal Univ Hong Kong Baptist Univ Fac Sci & Technol United Int Coll Zhuhai Peoples R China Hong Kong Baptist Univ Fac Sci Hong Kong Peoples R China Tech Univ Munich Dept Informat Munich Germany Macau Univ Sci & Technol Fac Innovat Engn Macau Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing Peoples R China Chinese Acad Sci State Key Lab Management & Control Complex Syst Inst Automat Beijing Peoples R China Xi An Jiao Tong Univ Inst Artificial Intelligence & Robot Xian Peoples R China Guangdong Lab Artificial Intelligence & Digital Ec Dept Artificial Intelligence Shenzhen Peoples R China

In the past decade, autonomous driving has witnessed significant advancements, largely attributable to the evolution of precise algorithms and efficient computing platforms. Nevertheless, the open-pit mine, a typical scenario within closed-field environments, has garnered limited attention in autonomous driving, primarily owing to the scarcity of data and experimental benchmarks. This work presents original data collected from five platforms, comprising one passenger vehicle, three wide-body trucks, and one mining truck, across eight different mining sites. We provide a comprehensive elucidation of platform types, sensors, calibration methodologies, synchronization techniques, data collection approaches, and a thorough analysis of the data characteristics. In addition, we offer a detailed benchmark comparison of short and long odometry and navigation performance across multiple vehicles in open-pit mines. With comprehensive data characteristics, experimental performance evaluations, and thorough analysis, we believe that this work establishes a robust research foundation for navigation and fusion methods in open-pit mines, thereby constituting a significant contribution to the autonomous driving and field robotics communities.

关键词： Open pit mining

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：