检索结果-内蒙古大学图书馆

A Survey on Small Sample Imbalance Problem: Metrics, Feature Analysis, and Solutions

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhao, Shuxian Gui, Jie Dong, Minjing Yu, Baosheng Gui, Zhipeng Dong, Lu Tang, Yuan Yan Kwok, James Tin-Yau School of Cyber Science d Engineering Southeast University Nanjing210000 China School of Cyber Science and Engineering Southeast University Nanjing211189 China Engineering Research Center of Blockchain Application Supervision and Management Southeast University Nanjing211189 China Purple Mountain Laboratories Nanjing210000 China Department of Computer Science City University of Hong Kong Hong Kong Lee Kong Chian School of Medicine Nanyang Technological University Singapore School of Remote Sensing and Information Engineering Wuhan University Wuhan430079 China Collaborative Innovation Center of Geospatial Technology Wuhan University Wuhan430079 China Department of Computer and Information Science University of Macau China Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong

—The small sample imbalance (S&I) problem is a major challenge in machine learning and data analysis. It is characterized by a small number of samples and an imbalanced class distribution, which leads to poor model performance. In addition, indistinct inter-class feature distributions further complicate classification tasks. Existing methods often rely on algorithmic heuristics without sufficiently analyzing the underlying data characteristics. We argue that a detailed analysis from the data perspective is essential before developing an appropriate solution. Therefore, this paper proposes a systematic analytical framework for the S&I problem. We first summarize imbalance metrics and complexity analysis methods, highlighting the need for interpretable benchmarks to characterize S&I problems. Second, we review recent solutions for conventional, complexity-based, and extreme S&I problems, revealing methodological differences in handling various data distributions. Our summary finds that resampling remains a widely adopted solution. However, we conduct experiments on binary and multiclass datasets, revealing that classifier performance differences significantly exceed the improvements achieved through resampling. Finally, this paper highlights open questions and discusses future trends. Copyright © 2025, The Authors. All rights reserved.

关键词： Taxonomies

Is an Ultra Large Natural Image-Based Foundation Model Superior to a Retina-Specific Model for Detecting Ocular and Systemic Diseases?

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Hou, Qingshan Zhou, Yukun Goh, Jocelyn Hui Lin Zou, Ke Yew, Samantha Min Er Srinivasan, Sahana Wang, Meng Lo, Thaddaeus Lei, Xiaofeng Wagner, Siegfried K. Chia, Mark A. Yang, Dawei Jiang, Hongyang Ran, AnRan Santos, Rui Somfai, Gabor Mark Zhou, Juan Helen Chen, Haoyu Chen, Qingyu Cheung, Carol Yim-Lui Keane, Pearse A. Tham, Yih Chung Department of Ophthalmology Yong Loo Lin School of Medicine National University of Singapore Singapore School of Computer Science and Engineering Northeastern University Shenyang China Centre for Innovation and Precision Eye Health Yong Loo Lin School of Medicine National University of Singapore Singapore Centre for Medical Image Computing University College London London United Kingdom NIHR Biomedical Research Centre Moorfields Eye Hospital NHS Foundation Trust London United Kingdom Department of Medical Physics and Biomedical Engineering University College London London United Kingdom Singapore Eye Research Institute Singapore National Eye Centre Singapore Singapore Singapore Institute of Ophthalmology University College London London United Kingdom Department of Ophthalmology and Visual Sciences Chinese University of Hong Kong Hong Kong Department of Ophthalmology Stadtspital Zürich Zurich Switzerland Spross Research Institute Zurich Switzerland Department of Ophthalmology Semmelweis University Budapest Hungary Centre for Sleep and Cognition Centre for Translational MR Research Yong Loo Lin School of Medicine National University of Singapore Singapore Department of Electrical and Computer Engineering National University of Singapore Singapore Joint Shantou International Eye Center Shantou University the Chinese University of Hong Kong Guangdong Shantou China Shantou University Medical College Guangdong Shantou China Department of Biomedical Informatics and Data Science Yale School of Medicine Yale University New Haven United States Duke-NUS Medical School Singapore

The advent of foundation models (FMs) is transforming medical domain. In ophthalmology, RETFound, a retina-specific FM pre-trained sequentially on 1.4 million natural images and 1.6 million retinal images, has demonstrated high adaptability across clinical applications. Conversely, DINOv2, a general-purpose vision FM pre-trained on 142 million natural images, has shown promise in non-medical domains. However, its applicability to clinical tasks remains underexplored. To address this, we conducted head-to-head evaluations by finetuning RETFound and three DINOv2 models (large, base, small) for ocular disease detection and systemic disease prediction tasks, across eight standardized open-source ocular datasets, as well as the Moorfields AlzEye and the UK Biobank datasets. DINOv2-large model outperformed RETFound in detecting diabetic retinopathy (AUROC=0.850–0.952 vs. 0.823-0.944, across three datasets, all P≤0.007) and multi-class eye diseases (AUROC=0.892 vs. 0.846, P Copyright © 2025, The Authors. All rights reserved.

关键词： Ophthalmology

Why is the Winner the Best?

学校读者我要写书评

暂无评论

Why is the Winner the Best?

Conference on computer Vision and Pattern Recognition (CVPR)

作者： M. Eisenmann A. Reinke V. Weru M. D. Tizabi F. Isensee T. J. Adler S. Ali V. Andrearczyk M. Aubreville U. Baid S. Bakas N. Balu S. Bano J. Bernal S. Bodenstedt A. Casella V. Cheplygina M. Daum M. De Bruijne A. Depeursinge R. Dorent J. Egger D. G. Ellis S. Engelhardt M. Ganz N. Ghatwary G. Girard P. Godau A. Gupta L. Hansen K. Harada M. Heinrich N. Heller A. Hering A. Huaulmé P. Jannin A. E. Kavur O. Kodym M. Kozubek J. Li H. Li J. Ma C. Martín-Isla B. Menze A. Noble V. Oreiller N. Padoy S. Pati K. Payette T. Rädsch J. Rafael-Patiño V. Singh Bawa S. Speidel C. H. Sudre K. Van Wijnen M. Wagner D. Wei A. Yamlahi M. H. Yap C. Yuan M. Zenk A. Zia D. Zimmerer D. Aydogan B. Bhattarai L. Bloch R. Brüngel J. Cho C. Choi Q. Dou I. Ezhov C. M. Friedrich C. Fuller R. R. Gaire A. Galdran Á. García Faura M. Grammatikopoulou S. Hong M. Jahanifar I. Jang A. Kadkhodamohammadi I. Kang F. Kofler S. Kondo H. Kuijf M. Li M. Luu T. Martinčič P. Morais M. A. Naser B. Oliveira D. Owen S. Pang J. Park S. Park S. Płotka E. Puybareau N. Rajpoot K. Ryu N. Saeed A. Shephard P. Shi D. Štepec R. Subedi G. Tochon H. R. Torres H. Urien J. L. Vilaça K. A. Wahid H. Wang J. Wang L. Wang X. Wang B. Wiestler M. Wodzinski F. Xia J. Xie Z. Xiong S. Yang Y. Yang Z. Zhao K. Maier-Hein P. F. Jäger A. Kopp-Schneider L. Maier-Hein Division of Intelligent Medical Systems German Cancer Research Center (DKFZ) Heidelberg Germany Helmholtz Imaging German Cancer Research Center (DKFZ) Heidelberg Germany Faculty of Mathematics and Computer Science Heidelberg University Heidelberg Germany Division of Biostatistics German Cancer Research Center (DKFZ) Heidelberg Germany Division of Medical Image Computing German Cancer Research Center (DKFZ) Heidelberg Germany Faculty of Engineering and Physical Sciences School of Computing University of Leeds Leeds UK Institute of Informatics School of Management HES-SO Valais-Wallis University of Applied Sciences and Arts Western Switzerland Sierre Switzerland Department of Nuclear Medicine and Molecular Imaging Lausanne University Hospital Lausanne Switzerland Technische Hochschule Ingolstadt Ingolstadt Germany Center for Artificial Intelligence and Data Science for Integrated Diagnostics (AI2D) and Center for Biomedical Image Computing and Analytics (CBICA) University of Pennsylvania Philadelphia PA USA Department of Pathology and Laboratory Medicine Perelman School of Medicine University of Pennsylvania Philadelphia PA USA Department of Radiology Perelman School of Medicine University of Pennsylvania Philadelphia PA USA Department of Radiology University of Washington Seattle WA USA Department of Computer Science Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS) University College London London UK Universitat Autònoma de Barcelona & Computer Vision Center Barcelona Spain Division of Translational Surgical Oncology National Center for Tumor Diseases (NCT/UCC) Dresden Dresden Germany Department of Advanced Robotics Istituto Italiano di Tecnologia Italy Department of Electronics Information and Bioengineering Politecnico di Milano Milan Italy IT University of Copenhagen Copenhagen Denmark Department of General Visceral and Transplantation Surgery Heidelberg University Hospital Heidelberg Germany Department of Radiology and Nuc

International benchmarking competitions have become fundamental for the comparative performance assessment of image analysis methods. However, little attention has been given to investigating what can be learnt from these competitions. Do they really generate scientific progress? What are common and successful participation strategies? What makes a solution superior to a competing method? To address this gap in the literature, we performed a multicenter study with all 80 competitions that were conducted in the scope of IEEE ISBI 2021 and MICCai 2021. Statistical analyses performed based on comprehensive descriptions of the submitted algorithms linked to their rank as well as the underlying participation strategies revealed common characteristics of winning solutions. These typically include the use of multi-task learning (63%) and/or multi-stage pipelines (61%), and a focus on augmentation (100%), image preprocessing (97%), data curation (79%), and post-processing (66%). The “typical” lead of a winning team is a computer scientist with a doctoral degree, five years of experience in biomedical image analysis, and four years of experience in deep learning. Two core general development strategies stood out for highly-ranked teams: the reflection of the metrics in the method design and the focus on analyzing and handling failure cases. According to the organizers, 43% of the winning algorithms exceeded the state of the art but only 11% completely solved the respective domain problem. The insights of our study could help researchers (1) improve algorithm development strategies when approaching new problems, and (2) focus on open research questions revealed by this work.

关键词：

Deep Learning Techniques for Automatic Lateral X-ray Cephalometric Landmark Detection: Is the Problem Solved?

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Hongyuan Wang, Ching-Wei Muzakky, Hikam Dai, Juan Li, Xuguang Ma, Chenglong Wu, Qian Cui, Xianan Xu, Kunlun He, Pengfei Guo, Dongqian Wang, Xianlong Lee, Hyunseok Zhong, Zhangnan Zhu, Zhu Huang, Bingsheng Medical AI Lab School of Biomedical Engineering Shenzhen University Medical School Shenzhen University Shenzhen518060 China Guangdong Key Laboratory of Biomedical Measurements and Ultrasound Imaging School of Biomedical Engineering Shenzhen University Medical School Shenzhen University Shenzhen518060 China Graduate Institute of Biomedical Engineering National Taiwan University of Science and Technology Taiwan Department of Stomatology Shenzhen University General Hospital Shenzhen University Shenzhen518055 China Institute of Stomatological Research Shenzhen University Shenzhen518055 China Chohotech Technology Co. Ltd. Lianchuang Street Yuhang District Hangzhou311422 China Singapore School of Computer Science Wuhan University Wuhan430072 China Wangxuan Institute of Computer Technology Peking University Beijing100871 China School of Artificial Intelligence Xidian University Xi’an710126 China State Key Laboratory of Internet of Things for Smart City University of Macau Taipa China The Faculty of Information Science and Engineering Ocean University of China Qingdao266100 China Digital Healthcare Department Daegu-Gyeongbuk Medical Innovation Foundation Daegu427724 Korea Republic of School of Life Science South China Normal University Guangzhou510631 China Information and Data Department Children’s Hospital Zhejiang University School of Medicine Hangzhou310000 China

Localization of the craniofacial landmarks from lateral cephalograms is a fundamental task in cephalometric analysis. The automation of the corresponding tasks has thus been the subject of intense research over the past decades. In this paper, we introduce the "Cephalometric Landmark Detection (CL-Detection)" dataset, which is the largest publicly available and comprehensive dataset for cephalometric landmark detection. This multi-center and multi-vendor dataset includes 600 lateral X-ray images with 38 landmarks acquired with different equipment from three medical centers. The overarching objective of this paper is to measure how far state-of-the-art deep learning methods can go for cephalometric landmark detection. Following the 2023 MICCai CL-Detection Challenge, we report the results of the top ten research groups using deep learning methods. Results show that the best methods closely approximate the expert analysis, achieving a mean detection rate of 75.719% and a mean radial error of 1.518 mm. While there is room for improvement, these findings undeniably open the door to highly accurate and fully automatic location of craniofacial landmarks. We also identify scenarios for which deep learning methods are still failing. Both the dataset and detailed results are publicly available online, while the platform will remain open for the community to benchmark future algorithm developments at https: //***/. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep learning

Statistical modeling: The three cultures

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Daoud, Adel Dubhashi, Devdatt Department of Sociology and Work Science University of Gothenburg Gothenburg Sweden Center for Population and Development Studies Harvard University Cambridge United States Data Science and AI division Department of Computer Science and Engineering Gothenburg Sweden

Two decades ago, Leo Breiman (2001) identified two cultures for statistical modeling. The data modeling culture (DMC) refers roughly to practices aiming to conduct statistical inference, βĜ, on one or several quantities of interest. The algorithmic modeling culture (AMC) refers to practices defining a machine-learning (ML) procedure that generates accurate predictions, ŶŶ, about an event of interest (outcome). Breiman argued that statisticians should give more attention to AMC than to DMC, because AMC provides novel procedures for prediction. While twenty years later, DMC has perhaps lost some of its dominant role in statistics because of the data-science revolution, we observe that this culture is still the modus operandi—the leading practice of a group—in the natural and social sciences. DMC is the modus operandi because of the influence of the established scientific method, called the hypothetico-deductive scientific method. Despite the incompatibilities of AMC with the hypothetico-deductive scientific method, among some research groups, AMC and DMC cultures mix intensely. We argue that this mixing has formed a fertile spawning pool for a mutated culture: a hybrid modeling culture (HMC) where prediction and inference have fused into new procedures where they reinforce one another. This article identifies key characteristics of HMC, thereby facilitating the scientific endeavor and fueling the evolution of statistical cultures towards better practices. By better, we mean increasingly reliable, valid, and efficient statistical practices in analyzing causal relationships. In combining inference and prediction, the result of HMC is that the distinction between ŶŶ and βĜ—taken to its limit—melts away. We qualify our "melting-away" argument by describing three HMC practices, where each practice captures an aspect of the scientific cycle: ML for causal inference, ML for data acquisition, and ML for theory prediction. Copyright © 2020, The Authors. All rights reserved.

关键词： Forecasting

Secure Physical Layer Communications for Low-Altitude Economy Networking: A Survey

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Cai, Lingyi Wang, Jiacheng Zhang, Ruichen Zhang, Yu Jiang, Tao Niyato, Dusit Wang, Xianbin Jamalipour, Abbas Shen, Xuemin Research Center of 6G Mobile Communications School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China College of Computing and Data Science Nanyang Technological University Singapore Department of Electrical and Computer Engineering Western University LondonONN6A 5B9 Canada School of Electrical and Computer Engineering University of Sydney Australia Department of Electrical and Computer Engineering University of Waterloo WaterlooONN2L 3G1 Canada

The Low-Altitude Economy Networking (LAENet) is emerging as a transformative paradigm that enables an integrated and sophisticated communication infrastructure to support aerial vehicles in carrying out a wide range of economic activities within low-altitude airspace. However, the physical layer communications in the LAENet face growing security threats due to inherent characteristics of aerial communication environments, such as signal broadcast nature and channel openness. These challenges highlight the urgent need for safeguarding communication confidentiality, availability, and integrity. In view of the above, this survey comprehensively reviews existing secure countermeasures for physical layer communication in the LAENet. We explore core methods focusing on anti-eavesdropping and authentication for ensuring communication confidentiality. Subsequently, availability-enhancing techniques are thoroughly discussed for anti-jamming and spoofing defense. Then, we review approaches for safeguarding integrity through anomaly detection and injection protection. Furthermore, we discuss future research directions, emphasizing energy-efficient physical layer security, multi-drone collaboration for secure communication, ai-driven security defense strategy, space-air-ground integrated security architecture, and 6G-enabled secure UAV communication. This survey may provide valuable references and new insights for researchers in the field of secure physical layer communication for the LAENet. Copyright © 2025, The Authors. All rights reserved.

关键词： aircraft communication

Machine learning with data assimilation and uncertainty quantification for dynamical systems: a review

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Cheng, Sibo Quilodrán-Casas, César Ouala, Said Farchi, Alban Liu, Che Tandeo, Pierre Fablet, Ronan Lucor, Didier Iooss, Bertrand Brajard, Julien Xiao, Dunhui Janjic, Tijana Ding, Weiping Guo, Yike Carrassi, Alberto Bocquet, Marc Arcucci, Rossella Data Science Institute Department of Computing Imperial College London LondonSW7 2AZ United Kingdom Department of Earth Science and Engineering Imperial College London LondonSW7 2AZ United Kingdom Department of Computer Science and Engineering Hong Kong University of Science and Technology 999077 Hong Kong IMT Atlantique Lab-STICC UMR CNRS 6285 France and Odyssey Inria/IMT France RIKEN Center for Computational Science Kobe Japan CEREA École des Ponts and EDF R&D île-de-France France The Laboratoire Interdisciplinaire des Sciences du Numérique CNRS Paris-Saclay University OrsayF-91403 France 78401 Chatou France Institut de Mathématiques de Toulouse Toulouse31062 France SINCLAIR AI Lab Saclay France Bergen Norway School of Mathematical Sciences Tongji University Shanghai200092 China Mathematical Institute for Machine Learning and Data Science KU Eichstätt-Ingolstadt Bavaria Germany School of Information Science and Technology Nantong University Nantong226019 China Department of Physics and Astronomy Augusto Righi University of Bologna Bologna40124 Italy

data Assimilation (DA) and Uncertainty quantification (UQ) are extensively used in analysing and reducing error propagation in high-dimensional spatial-temporal dynamics. Typical applications span from computational fluid dynamics (CFD) to geoscience and climate systems. Recently, much effort has been given in combining DA, UQ and machine learning (ML) techniques. These research efforts seek to address some critical challenges in high-dimensional dynamical systems, including but not limited to dynamical system identification, reduced order surrogate modelling, error covariance specification and model error correction. A large number of developed techniques and methodologies exhibit a broad applicability across numerous domains, resulting in the necessity for a comprehensive guide. This paper provides the first overview of the state-of-the-art researches in this interdisciplinary field, covering a wide range of applications. This review aims at ML scientists who attempt to apply DA and UQ techniques to improve the accuracy and the interpretability of their models, but also at DA and UQ experts who intend to integrate cutting-edge ML approaches to their systems. Therefore, this article has a special focus on how ML methods can overcome the existing limits of DA and UQ, and vice versa. Some exciting perspectives of this rapidly developing research field are also discussed. © 2023, CC BY-NC-SA.

关键词： Dynamical systems

A survey of hybrid human-artificial intelligence for social computing

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wang, Wenxi Ning, Huansheng Shi, Feifei Dhelim, Sahraoui Zhang, Weishan Chen, Liming School of Computer and Communication Engineering University of Science and Technology Beijing Beijing100083 China Beijing Engineering Research Center for Cyberspace Data Analysis and Applications Beijing100083 China Department of Software Engineering China University of Petroleum Qingdao266580 China School of Computing Ulster University United Kingdom

Along with the development of modern computing technology and social sciences, both theoretical research and practical applications of social computing have been continuously extended. In particular with the boom of artificial intelligence (ai), social computing is significantly influenced by ai. However, the conventional technologies of ai have drawbacks in dealing with more complicated and dynamic problems. Such deficiency can be rectified by hybrid human-artificial intelligence (H-ai) which integrates both human intelligence and ai into one unity, forming a new enhanced intelligence. H-ai in dealing with social problems shows the advantages that ai can’t surpass. This paper firstly introduces the concepts of H-ai. ai is the intelligence in the transition stage of H-ai, so the latest research progresses of ai in social computing are reviewed. Secondly, it summarizes typical challenges faced by ai in social computing, and makes it possible to introduce H-ai to solve these challenges. Finally, the paper proposes a holistic framework of social computing combining with H-ai, which consists of four layers: object layer, base layer, analysis layer, and application layer. It represents Hai has significant advantages over ai in solving social problems. Copyright © 2021, The Authors. All rights reserved.

关键词： Social sciences computing

Deep Learning on Parkinson's Rat behavior Point Sets in Open Field 20

学校读者我要写书评

暂无评论

Deep Learning on Parkinson's Rat behavior Point Sets in Open...

2020 International Symposium on Artificial Intelligence in Medical sciences, ISaiMS 2020

作者： Wu, Lei He, Quan Cao, Hezhi Liu, Long Research Center for Big Data and Intelligent Decision Making School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan Hunan province China Department of Biology and Chemistry National University of Defense Technology Changsha Hunan province China College of Electronic Science and Technology National University of Defense Technology Changsha Hunan province China

ISBN: (纸本)9781450388603

Parkinson's disease (PD) is one of the common progressive neurodegenerative disorder with motor deficits. A substantial volume of research has reported various methods to characterize Parkinson's rat model, but the performances are unsatisfactory. Because of the complexity of behavior data, we can hardly recognize the non-trivial behavioral traits and distinguish the difference between ill rat and the healthy. In this paper, we construct a deep learning model to analyze PD rat behavior data, which is obtained from an optical motion capture system. This system is widely used in movement analysis, robotics, making animations, and can provide high resolution of spatiotemporal information. By using the three-dimensional motion capture technology with retro-reflective optical markers placed in locations that represents rat head and body axis, we can get real-time three-dimensional coordinate information of rat's motion in open field. After the preprocessing, we fed the data set to our model to get a global feature via three abstraction layers and then process them by fully connected layers to obtain the final classification result. The results have shown that this method is robust enough to identify biomechanical and kinematic changes in response to Parkinson's rat with unilateral Striatum lesion. © 2020 ACM.

关键词： Rats