检索结果-内蒙古大学图书馆

Correction: Artificial intelligence for surgical safety during laparoscopic gastrectomy for gastric cancer: Indication of anatomical landmarks related to postoperative pancreatic fistula using deep learning

引用

Surgical endoscopy 2024年第10期38卷 6203页

作者： Yoshimasa Aoyama Yusuke Matsunobu Tsuyoshi Etoh Kosuke Suzuki Shunsuke Fujita Takayuki aiba Hajime Fujishima Shinichiro Empuku Yohei Kono Yuichi Endo Yoshitake Ueda Hidefumi Shiroshita Toshiya Kamiyama Takemasa Sugita Kenichi Morishima Kohei Ebe Tatsushi Tokuyasu Masafumi Inomata Department of Gastroenterological and Pediatric Surgery Faculty of Medicine Oita University Oita Japan. Department of Information Systems and Engineering Faculty of Information Engineering Fukuoka Institute of Technology Fukuoka Japan. Department of Healthcare AI Data Science Faculty of Medicine Oita University Oita Japan. Department of Gastroenterological and Pediatric Surgery Faculty of Medicine Oita University Oita Japan. teto@oita-u.ac.jp. Research Center for GLOBAL and LOCAL Infectious Diseases Oita University 1-1 Idaigaoka Hasama-Machi Oita Oita 879-5593 Japan. teto@oita-u.ac.jp. Faculty of Medicine Oita University Oita Japan. Department of Comprehensive Surgery for Community Medicine Faculty of Medicine Oita University Oita Japan. Advanced AI Technology Research Advanced Software Technology Research Olympus Corporation Tokyo Japan. Information Aided Medical Solutions Development Application Software Engineering Olympus Medical Systems Corporation Tokyo Japan. Clinical Engineering Research Center Faculty of Medicine Oita University Oita Japan.

来源：评论

学校读者我要写书评

暂无评论

Dense Regression Network for Video Grounding

Dense Regression Network for Video Grounding

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Runhao Zeng Haoming Xu Wenbing Huang Peihao Chen Mingkui Tan Chuang Gan School of Software Engineering South China University of Technology China Peng Cheng Laboratory Shenzhen China Department of Computer Science and Technology Beijing National Research Center for Information Science and Technology (BNRist) Tsinghua University MIT-IBM Watson AI Lab

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

We address the problem of video grounding from natural language queries. The key challenge in this task is that one training video might only contain a few annotated starting/ending frames that can be used as positive examples for model training. Most conventional approaches directly train a binary classifier using such imbalance data, thus achieving inferior results. The key idea of this paper is to use the distances between the frame within the ground truth and the starting (ending) frame as dense supervisions to improve the video grounding accuracy. Specifically, we design a novel dense regression network (DRN) to regress the distances from each frame to the starting (ending) frame of the video segment described by the query. We also propose a simple but effective IoU regression head module to explicitly consider the localization quality of the grounding results (i.e., the IoU between the predicted location and the ground truth). Experimental results show that our approach significantly outperforms state-of-the-arts on three datasets (i.e., Charades-STA, ActivityNet-Captions, and TACoS).

关键词： Grounding Training Task analysis Proposals Semantics Magnetic heads Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Constructing a Comprehensive Clinical database Integrating Patients' data from Intensive Care Units and General Wards 12

Constructing a Comprehensive Clinical Database Integrating P...

引用

12th International Congress on Image and Signal Processing, BioMedical engineering and Informatics, CISP-BMEI 2019

作者： Liu, Tongbo Liu, Xiaoli Fan, Yong Xu, Haoran Ng, Yeuk Lam Li, Peiyao Xue, Wanguo Zhang, Zhengbo Chinese PLA General Hospital Department of Computer Management and Application Beijing China School of Biological Science and Medical Engineering Beihang University Beijing China Chinese PLA General Hospital Department of Biomedical Engineering Beijing China University of Toronto Faculty of Arts Science Toronto Canada Medical Big Data Center Chinese PLA General Hospital Beijing China

ISBN: (纸本)9781728148526

Collection and analysis of large volumes of ICU data are invaluable to the advancement of clinical knowledge, and large-scale ICU databases have been effective resources to understand risk factors and perform predictive analysis by using machine learning. This paper introduces the construction of a comprehensive clinical database: PLAGH-ICU database, which integrated data from nine intensive care units, emergency department and general wards. data from several sources were extracted and integrated in the database, including patient demographics, hospital administrative data, physiological data, medications, lab test, fluid balance data, notes and reports etc. Detailed information about the database, such as patient characteristics, disease distribution, category of data, data records were illustrated. As far as we know, this is the first comprehensive ICU database developed and used as a research database in datathon event in China. Such kind of database will promote the research progress in critical care medicine, as well as the development of modern hospital information system in China. © 2019 IEEE.

关键词： Intensive care units

来源：评论

学校读者我要写书评

暂无评论

A stochastic learning algorithm for multi-agent game in mobile network: A Cross-Silo federated learning perspective

引用

computer Networks 2025年 269卷

作者： Hongze Liu Junzhe Liu Zhaojiacheng Zhou Shijing Yuan Jiong Lou Chentao Wu Jie Li Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai 200240 China School of Mathematical Sciences Shanghai Jiao Tong University Shanghai 200240 China China Telecom Research Institute Shanghai 200120 China Yancheng Blockchain Research Institute Yancheng China Shanghai Jiao Tong University (Wuxi) Blockchain Advanced Research Center Wuxi China Shanghai Key Laboratory of Trusted Data Circulation Governance and Web3 Shanghai China

Collaboration in mobile network involves multiple servers and smart devices, introducing the challenging of coordination. The inherent challenges arise from incomplete environmental information due to dynamic networks and privacy concerns, making collaboration for all participants a complex task. In this work, we introduce a Multi-agent step Refinement Stochastic Learning Algorithm (MARSL) empowered by neighbor search, achieving superior outcomes with low complexity compared to baseline algorithms. To demonstrate the performance of the proposed algorithm, we provide comprehensive theoretical analysis on the superior properties. We then formulate two Non-IID cross-silo Federated Learning scenarios as typical non-convex cases in mobile network collaboration. By conducting multiple experiments, we illustrate the algorithm’s superior performance in both final utility and computation complexity. This contribution addresses the cooperation challenge in Cross-silo FL, providing an effective solution for scenarios with incomplete environmental information.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A sparse semismooth Newton based proximal majorization-minimization algorithm for nonconvex square-root-loss regression problem

引用

The Journal of Machine Learning research 2020年第1期21卷 9253-9290页

作者： Peipei Tang Chengjing Wang Defeng Sun Kim-Chuan Toh School of Computer and Computing Science Zhejiang University City College Hangzhou China School of Mathematics and National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu China Department of Applied Mathematics The Hong Kong Polytechnic University Hung Hom Hong Kong Department of Mathematics and Institute of Operations Research and Analytics National University of Singapore Singapore

In this paper, we consider high-dimensional nonconvex square-root-loss regression problems and introduce a proximal majorization-minimization (PMM) algorithm for solving these problems. Our key idea for making the proposed PMM to be efficient is to develop a sparse semismooth Newton method to solve the corresponding subproblems. By using the Kurdyka-Łojasiewicz property exhibited in the underlining problems, we prove that the PMM algorithm converges to a d-stationary point. We also analyze the oracle property of the initial subproblem used in our algorithm. Extensive numerical experiments are presented to demonstrate the high efficiency of the proposed PMM algorithm.

关键词： nonconvex square-root regression problems proximal majorization-minimization semismooth Newton method

来源：评论

学校读者我要写书评

暂无评论

A Q-learning-based trust model in underwater acoustic sensor networks (UASNs)

引用

Ad Hoc Networks 2025年 178卷

作者： Mehdi Hosseinzadeh Amir Haider Amir Masoud Rahmani Khursheed Aurangzeb Zhe Liu Mohammad Sadegh Yousefpoor Efat Yousefpoor Sang-Woong Lee Parisa Khoshvaght Pattern Recognition and Machine Learning Lab School of Computing Gachon University Seongnam 13120 Republic of Korea Department of AI and Robotics Sejong University Seoul 05006 Republic of Korea Future Technology Research Center National Yunlin University of Science and Technology Yunlin Taiwan Department of Computer Engineering College of Computer and Information Sciences King Saud University P.O. Box 51178 Riyadh 11543 Saudi Arabia College of Mathematics and Computer Xinyu University Xinyu 338004 China School of Computer Sciences University Sains Malaysia Penang 11800 Malaysia Center of Research and Strategic Studies Lebanese French University Kurdistan Region Iraq Institute of Research and Development Duy Tan University Da Nang Viet Nam School of Engineering and Technology Duy Tan University Da Nang Viet Nam Centre for Research Impact and Outcome Chitkara University Institute of Engineering and Technology Chitkara University Rajpura 140401 Punjab India

Underwater acoustic sensor networks (UASNs) play a pivotal role in various civil and military fields. However, due to their open nature, they are susceptible to multiple security threats. As such, developing robust and reliable security strategies is essential to ensure the normal operation of UASNs. This paper proposes a Q-learning-based trust model (QLTM) for UASNs. To detect hostile nodes, each underwater sensor node is required to collect trust evidence –namely energy trust evidence, data trust evidence, and communication trust evidence–through communication and interaction with its neighboring nodes. After gathering the trust evidence, QLTM presents a distributed Q-learning-based trust management model that adapts to dynamic underwater environments. It continuously updates the trust parameters based on ongoing interactions between the agent and the environment. The Q-learning-based trust management model includes a state set with three states: trust, distrust, and uncertain. Additionally, the reward function is calculated according to the gathered trust evidence, and the weight of each trust evidence is determined such that evidence with a lower value carries more weight, thus having a greater effect on the generated reward. Experimental results demonstrate the effectiveness of QLTM compared to other trust mechanisms, so that QLTM improves the detection accuracy rate by 5.04%. However, when the attack mode changes in the network, QLTM performs approximately 4.29% worse than TUMRL in detecting malicious nodes. On the other hand, QLTM reduces the false alarm rate by about 7.39% and increases energy efficiency by approximately 4.26%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamical multiple polynomial-based neural networks classifier realized with the aid of dropfilter and dual statistical selection

引用

engineering applications of Artificial Intelligence 2025年 157卷

作者： Zhen Wang Sung-Kwun Oh Zunwei Fu Seok-Beom Roh Witold Pedrycz Research Center for Big Data and Artificial Intelligence Linyi University Linyi 276005 China School of Automation and Electrical Engineering Linyi University Linyi 276005 Shandong China School of Electrical & Electronic Engineering The University of Suwon 17 Wauan-gil Bongdam-eup Hwaseong-si Gyeonggi-do 18323 South Korea Department of Electronic Engineering Seokyeong University Seoul 02713 South Korea Department of Computer Science The University of Suwon 17 Wauan-gil Bongdam-eup Hwaseong-si Gyeonggi-do 18323 South Korea Department of Electrical and Computer Engineering University of Alberta Edmonton AB T6G 2R3 Canada Systems Research Institute Polish Academy of Sciences 00-901 Warsaw Poland Department of Computer Engineering Faculty of Engineering and Natural Sciences Istinye University Sariyer Istanbul Turkiye

Polynomial neural networks (PNN) have emerged as an effective regression modeling methodology in computational intelligence, relying on its interpretable polynomial nodes to fit complex nonlinear data relationships and the adaptive nature of self-organizing networks. To break the bottleneck of PNN structure in the field of multi-classification, this study designs a dynamical multiple polynomial-based neural networks (DMPNN) classifier, focusing on developing a flexible polynomial network classification methodology that enhances predictive capabilities without sacrificing the advantages of PNN structures. Our approach effectively addresses the challenges of multi-class classification with uncertain class boundaries and reduces computational complexity, which is achieved through the synergy of several proposed techniques. Three key issues underpin the proposed DMPNN: (a) The integration of PNN regression models using the one-against-all strategy can provide effective and scalable solutions to multi-class classification problems, especially for uncertain class boundary issues. (b) The dual statistical selection (DSS) approach aims to eliminate redundant inputs during data processing, reduce the computational burden, and increase the variety of neural network nodes in the model neuron selection stage. (c) The synergy of regularization methods including the ℓ2 norm-based method (ℓ2-LSM) and the DropFilter, is exploited to mitigate potential overfitting in coefficient estimation and enhance the generalization capabilities of the proposed classifier. A series of ablation experiments and parameter analysis were conducted to demonstrate the stability and reliability of the proposed model. Then, we applied DMPNN to 17 publicly available datasets and two engineering applications: Recycling of black plastic wastes and phased resolved partial discharge. The performance results show that the DMPNN model outperforms five classical classifiers and four state-of-the-art (SOTA) class

关键词： Partial discharges

来源：评论

学校读者我要写书评

暂无评论

Roadmap on Deep Learning for Microscopy

arXiv

引用

arXiv 2023年

作者： Volpe, Giovanni Wählby, Carolina Tian, Lei Hecht, Michael Yakimovich, Artur Monakhova, Kristina Waller, Laura Sbalzarini, Ivo F. Metzler, Christopher A. Xie, Mingyang Zhang, Kevin Lenton, Isaac C.D. Rubinsztein-Dunlop, Halina Brunner, Daniel Bai, Bijie Ozcan, Aydogan Midtvedt, Daniel Wang, Hao Sladoje, Nataša Lindblad, Joakim Smith, Jason T. Ochoa, Marien Barroso, Margarida Intes, Xavier Qiu, Tong Yu, Li-Yu You, Sixian Liu, Yongtao Ziatdinov, Maxim A. Kalinin, Sergei V. Sheridan, Arlo Manor, Uri Nehme, Elias Goldenberg, Ofri Shechtman, Yoav Moberg, Henrik K. Langhammer, Christoph Špačková, Barbora Helgadottir, Saga Midtvedt, Benjamin Argun, Aykut Thalheim, Tobias Cichos, Frank Bo, Stefano Hubatsch, Lars Pineda, Jesus Manzo, Carlo Bachimanchi, Harshith Selander, Erik Homs-Corbera, Antoni Fränzl, Martin de Haan, Kevin Rivenson, Yair Korczak, Zofia Adiels, Caroline Beck Mijalkov, Mite Veréb, Dániel Chang, Yu-Wei Pereira, Joana B. Matuszewski, Damian Kylberg, Gustaf Sintorn, Ida-Maria Caicedo, Juan C. Cimini, Beth A. Bell, Muyinatu Lediju A. Saraiva, Bruno M. Jacquemet, Guillaume Henriques, Ricardo Ouyang, Wei Le, Trang Gómez-De-Mariscal, Estibaliz Sage, Daniel Muñoz-Barrutia, Arrate Lindqvist, Ebba Josefson Bergman, Johanna Department of Physics University of Gothenburg Gothenburg41296 Sweden Dept. IT and SciLifeLab Uppsala University Sweden Department of Electrical and Computer Engineering Boston University BostonMA02215 United States Department of Biomedical Engineering Boston University BostonMA02215 United States Görlitz Germany Department of Renal Medicine Division of Medicine University College London Royal Free Hospital Campus London United Kingdom Artificial Intelligence for Life Sciences CIC Dorset United Kingdom Roche Pharma International Informatics Roche Diagnostics GmbH Mannheim Germany Department of Electrical Engineering and Computer Sciences UC Berkeley United States Technische Universität Dresden Faculty of Computer Science Dresden Germany Max Planck Institute of Molecular Cell Biology and Genetics Center for Systems Biology Dresden Dresden Germany University of Maryland College Park United States Klosterneuburg3400 Austria School of Mathematics and Physics The University of Queensland Brisbane4072 Australia Australian Research Council Centre of Excellence for Engineered Quantum Systems The University of Queensland Brisbane4072 Australia Département d’Optique P. M. Duffieux Institut FEMTO-ST Université Franche-Comté CNRS UMR 6174 Besançon France Department of Electrical and Computer Engineering University of California Los Angeles Los AngelesCA United States Department of Information Technology Uppsala University Sweden Department of Biomedical Engineering Rensselaer Polytechnic Institute TroyNY12180 United States Elephas 1 Erdman Pl. Madison53705 United States University of Wisconsin–Madison Department of Medical Physics MadisonWI53705 United States Department of Molecular and Cellular Physiology Albany Medical College AlbanyNY12208 United States Research Laboratory of Electronics Electrical Engineering and Computer Science Massachusetts Institute of Technology BostonMA United States Center for Nanophase Materials Sciences Oak R

Through digital imaging, microscopy has evolved from primarily being a means for visual observation of life at the micro- and nano-scale, to a quantitative tool with ever-increasing resolution and throughput. Artificial intelligence, deep neural networks, and machine learning are all niche terms describing computational methods that have gained a pivotal role in microscopy-based research over the past decade. This Roadmap is written collectively by prominent researchers and encompasses selected aspects of how machine learning is applied to microscopy image data, with the aim of gaining scientific knowledge by improved image quality, automated detection, segmentation, classification and tracking of objects, and efficient merging of information from multiple imaging modalities. We aim to give the reader an overview of the key developments and an understanding of possibilities and limitations of machine learning for microscopy. It will be of interest to a wide cross-disciplinary audience in the physical sciences and life sciences. Copyright © 2023, The Authors. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Multivariate Analysis on Performance Gaps of Artificial Intelligence Models in Screening Mammography

arXiv

引用

arXiv 2023年

作者： Zhang, Linglin Brown-Mulry, Beatrice Nalla, Vineela Hwang, InChan Gichoya, Judy Wawira Gastounioti, aimilia Banerjee, Imon Seyyed-Kalantari, Laleh Woo, MinJae Trivedi, Hari School of Data Science and Analytics Kennesaw State University 3391 Town Point Dr NW KennesawGA30144 United States Department of Information Technology Kennesaw State University 1100 South Marietta Pkwy MariettaGA30060 United States Department of Radiology and Imaging Sciences Emory University 1364 E Clifton Rd NE AtlantaGA30322 United States Computational Imaging Research Center Washington University in St. Louis School of Medicine 4525 Scott Avenue St. LouisMO63110 United States Department of Radiology Mayo Clinic Arizona 13400 E Shea Blvd ScottsdaleAZ85259 United States School of Computing and Augmented Intelligence Arizona State University 699 S Mill Ave TempeAZ85281 United States Department of Electrical Engineering and Computer Science York University 4700 Keele St TorontoONM3J 1P3 Canada

Although deep learning models for abnormality classification can perform well in screening mammography, the demographic, imaging, and clinical characteristics associated with increased risk of model failure remain unclear. This retrospective study uses the Emory BrEast Imaging dataset (EMBED) containing mammograms from 115,931 patients imaged at Emory Healthcare between 2013-2020, with Breast Imaging Reporting and data System (BI-RADS) assessment, region of interest coordinates for abnormalities, imaging features, pathologic outcomes, and patient demographics. Multiple deep learning models were trained to distinguish between abnormal tissue patches and randomly selected normal tissue patches from screening mammograms. We assessed model performance by subgroups defined by age, race, pathologic outcome, tissue density, and imaging characteristics and investigated their associations with false negatives and false positives. We also performed multivariate logistic regression to control for confounding between subgroups. The top-performing model, ResNet152V2, achieved accuracy of 92.6% (95%CI=92.0-93.2%), and area under the receiver operating characteristics curve 0.975 (95%CI=0.972-0.978). Before controlling for confounding, nearly all subgroups showed statistically significant differences in model performance. However, after controlling for confounding, we found lower false negative risk associates with Other race (RR=0.828;p= .050), biopsy-proven benign lesions (RR=0.927;p= .011), and mass (RR=0.921;p= .010) or asymmetry (RR=0.854;p= .040);higher false negative risk associates with architectural distortion (RR=1.037;p Copyright © 2023, The Authors. All rights reserved.

关键词： Mammography

来源：评论

学校读者我要写书评

暂无评论

Efficient product formulas for commutators and applications to quantum simulation

arXiv

引用

arXiv 2021年

作者： Chen, Yu-An Childs, Andrew M. Hafezi, Mohammad Jiang, Zhang Kim, Hwanmun Xu, Yijia Google Quantum AI 340 Main Street VeniceCA90291 United States Department of Physics Joint Quantum Institute NIST University of Maryland College ParkMD20742 United States Condensed Matter Theory Center University of Maryland College ParkMD20472 United States Joint Center for Quantum Information and Computer Science University of Maryland College ParkMD20742 United States Department of Computer Science University of Maryland College ParkMD20742 United States Institute for Advanced Computer Studies University of Maryland College ParkMD20742 United States Department of Electrical and Computer Engineering Institute for Research in Electronics and Applied Physics University of Maryland College ParkMD20742 United States Institute for Physical Science and Technology University of Maryland College ParkMD20742 United States

We construct product formulas for exponentials of commutators and explore their applications. First, we directly construct a third-order product formula with six exponentials by solving polynomial equations obtained using the operator differential method. We then derive higher-order product formulas recursively from the third-order formula. We improve over previous recursive constructions, reducing the number of gates required to achieve the same accuracy. In addition, we demonstrate that the constituent linear terms in the commutator can be included at no extra cost. As an application, we show how to use the product formulas in a digital protocol for counterdiabatic driving, which increases the fidelity for quantum state preparation. We also discuss applications to quantum simulation of one-dimensional fermion chains with nearest- and next-nearest-neighbor hopping terms, and two-dimensional fractional quantum Hall phases. Copyright © 2021, The Authors. All rights reserved.

关键词： Quantum chemistry

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：