检索结果-内蒙古大学图书馆

Proceedings of the 34th International Conference on Neural Information Processing Systems

作者： Chu Zhou Hang Zhao Jin Han Chang Xu Chao Xu Tiejun Huang Boxin Shi Key Lab of Machine Perception (MOE) Dept. of Machine Intelligence Peking University Massachusetts Institute of Technology School of Computer Science Faculty of Engineering University of Sydney NELVT Dept. of Computer Science Peking University and Institute for Artificial Intelligence Peking University

ISBN: (纸本)9781713829546

A conventional camera often suffers from over- or under-exposure when recording a real-world scene with a very high dynamic range (HDR). In contrast, a modulo camera with a Markov random field (MRF) based unwrapping algorithm can theoretically accomplish unbounded dynamic range but shows degenerate performances when there are modulus-intensity ambiguity, strong local contrast, and color misalignment. In this paper, we reformulate the modulo image unwrapping problem into a series of binary labeling problems and propose a modulo edge-aware model, named as UnModNet, to iteratively estimate the binary rollover masks of the modulo image for unwrapping. Experimental results show that our approach can generate 12-bit HDR images from 8-bit modulo images reliably, and runs much faster than the previous MRF-based algorithm thanks to the GPU acceleration.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Advancements in machine learning for recommender systems: A focus on NNMFC and particle swarm optimization techniques

引用

AIP Conference Proceedings 2024年第1期3193卷

作者： S. Prema M. Varalatchoumy G. Nirmaladevi S. Vijayakumar S. Kayalvili M. Rajendiran R. Premanand V. Vijayan Department of Information Technology Mahendra Engineering College Namakkal Tamil Nadu 637503 India Department of Artificial Intelligence and Machine Learning Cambridge Institute of Technology Bengaluru Karnataka 560036 India Department of Computer Science Engineering Sri Sairam Institute of Technology Chennai Tamil Nadu 600044 India Department of Mathematics R.M.K. Engineering College Kavarapettai Tamil Nadu 601206 India Department of Artificial Intelligence Kongu Engineering College (Autonomous) Erode Tamil Nadu 638060 India Department of Computer Science and Engineering Panimalar Engineering College Chennai Tamil Nadu 600123 India Department of Humanities and Science (Physics) Sri Sai Ram Engineering College Chennai Tamil Nadu 600044 India Department of Mechanical Engineering K.Ramakrishnan College of Technology Trichy Tamilnadu India

Through the use of interest models, the Recommender System assists users in discovering content that is relevant to them. In order to make product suggestions based on past purchases, content-based recommender systems do not require user ratings. These systems are the subject of this study. Now these systems can profile products and customers using machine learning. Together with Non-Negative Matrix Factorization Clustering (NNMFC), we present a new approach to collaborative learning for online video sites. The research utilizes a sliding window clustering approach that relies on Particle Swarm Optimization (PSO) and gradient descent. We utilized three approaches to assess the model’s performance: sliding window PSO (SWPSO), sliding window gradient descent and gradient descent. The Root Mean Square Error (RMSE) was calculated for each. Outperforming current state-of-the-art methods like UPCSim, K-Mean, and Collaborative Filtering, the suggested work’s result analysis attained the lowest RMSE of 1.02. With a significant improvement of 10.2% over previous techniques, the Sliding Window PSO was shown to be the most effective.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimal Operation of Cryogenic Calorimeters Through Deep Reinforcement learning

引用

Computing and Software for Big Science 2024年第1期8卷 1-25页

作者： Angloher, G. Banik, S. Benato, G. Bento, A. Bertolini, A. Breier, R. Bucci, C. Burkhart, J. Canonica, L. D’Addabbo, A. Di Lorenzo, S. Einfalt, L. Erb, A. v. Feilitzsch, F. Fichtinger, S. Fuchs, D. Garai, A. Ghete, V.M. Gorla, P. Guillaumon, P.V. Gupta, S. Hauff, D. Ješkovský, M. Jochum, J. Kaznacheeva, M. Kinast, A. Kuckuk, S. Kluck, H. Kraus, H. Langenkämper, A. Mancuso, M. Marini, L. Mauri, B. Meyer, L. Mokina, V. Niedermayer, K. Olmi, M. Ortmann, T. Pagliarone, C. Pattavina, L. Petricca, F. Potzel, W. Povinec, P. Pröbst, F. Pucci, F. Reindl, F. Rothe, J. Schäffner, K. Schieck, J. Schönert, S. Schwertner, C. Stahlberg, M. Stodolsky, L. Strandhagen, C. Strauss, R. Usherov, I. Wagner, F. Wagner, V. Willers, M. Zema, V. Heitzinger, C. Waltenberger, W. Max-Planck-Institut für Physik Föhringer Ring 6 München 80805 Germany Institut für Hochenergiephysik Österreichischen Akademie der Wissenschaften Nikolsdorfer Gasse 18 Wien 1050 Austria Atominstitut Technische Universität Wien Stadionallee 2 Wien 1020 Austria INFN Laboratori Nazionali del Gran Sasso Via G. Acitelli Assergi 67100 Italy Faculty of Mathematics Physics and Informatics Comenius University Bratislava 84248 Slovakia Physik-Department TUM School of Natural Sciences Technische Universität München Garching 85747 Germany Eberhard-Karls-Universität Tübingen Tübingen 72076 Germany Department of Physics University of Oxford Oxford OX1 3RH United Kingdom Institute of Information Systems Engineering Technische Universität Wien Wien 1040 Austria Center for Artificial Intelligence and Machine Learning Technische Universität Wien Wien 1040 Austria also at: LIBPhys-UC Departamento de Fisica Universidade de Coimbra Coimbra 3004-516 Portugal also at: Walther-Meißner-Institut für Tieftemperaturforschung Garching 85748 Germany also at: GSSI-Gran Sasso Science Institute L’Aquila 67100 Italy also at: Dipartimento di Ingegneria Civile e Meccanica Università degli Studi di Cassino e del Lazio Meridionale Cassino 03043 Italy

Cryogenic phonon detectors with transition-edge sensors achieve the best sensitivity to sub-GeV/c2 dark matter interactions with nuclei in current direct detection experiments. In such devices, the temperature of the ... 详细信息

Cryogenic phonon detectors with transition-edge sensors achieve the best sensitivity to sub-GeV/c² dark matter interactions with nuclei in current direct detection experiments. In such devices, the temperature of the thermometer and the bias current in its readout circuit need careful optimization to achieve optimal detector performance. This task is not trivial and is typically done manually by an expert. In our work, we automated the procedure with reinforcement learning in two settings. First, we trained on a simulation of the response of three Cryogenic Rare Event Search with Superconducting Thermometers (CRESST) detectors used as a virtual reinforcement learning environment. Second, we trained live on the same detectors operated in the CRESST underground setup. In both cases, we were able to optimize a standard detector as fast and with comparable results as human experts. Our method enables the tuning of large-scale cryogenic detector setups with minimal manual interventions. © The Author(s) 2024.

关键词： Cryogenic calorimeter Dark matter Reinforcement learning Transition-edge sensor

来源：评论

学校读者我要写书评

暂无评论

Enhancing fruit disease classification with an advanced 3D shallow deep neural network for precise and efficient identification

引用

Expert Systems with Applications 2025年

作者： Hridaynath Pandurang Khandagale Sangram Tukaram Patil Vikram Sampat Gavali Amrita Arvind Manjrekar Pratap Pandurang Halkarnikar Research Scholar Department of Technology D Y Patil Agricultural and Technical University Talsande Kolhapur Maharashtra India Department of Technology Shivaji University Kolhapur Maharashtra India School of Engineering & Technology D Y Patil Agriculture & Technical University Warana – Wathar Road Talsande Fata Talsande Kolhapur India Department of Artificial Intelligence & Machine Learning New Institute of Technology Kolhapur Maharashtra India Computer Science and Technology Department of Technology Shivaji University Kolhapur Maharashatra India Dept of Computer Engineering Dr. D.Y.Patil Institute of Engineering Management & Research Akurdi Pune India

Diseases in fruits cause major problems in the agricultural industry and lead to significant economic loss. These diseases reduce yields, degrade the variety and can lead to crops being withdrawn from cultivation. Existing methods rely on heavy-weight architectures, which require higher storage capacity and expensive training operations due to the large number of parameters involved. In this paper, Enhancing Fruit Disease Classification with an Advanced 3D Shallow Deep Neural Network for Precise and Efficient Identification (EFDDNN-EI) is proposed. Here, the input images are taken from two datasets: (i) Strawberry Diseases dataset, (ii) Apple Fruit Disease dataset. The input images from both datasets are pre-processed by Regularized Bias-Aware Ensemble Kalman Filtering (RBAEKF) to eliminate unwanted noise. The pre-processed images are fed to the Newton Time-Extracting Wavelet Transform (NTEWT) to extract relevant attributes, such as color, texture, shape, size. The extracted features are fed into the 3D Shallow Deep Neural Network (3DSDNN). The 3DSDNN classifies the input images from the Strawberry Diseases dataset as botrytis cinerea, slugs, aphids, sunburn, thrips, root rot, vegetable green insects, viral diseases, powdery mildew and healthy leaves. Similarly, images from the Apple Fruit Disease dataset are classified into categories, like Blotch Apple, Normal Apple, Rot Apple, Scab Apple. Finally, Crisscross Harris Hawks Optimizer (CCHHO) is employed to enhance EFDDNN-EI that can classify the fruit diseases by maximizing the accuracy and minimizing the computation time. The proposed EFDDNN-EI approach is implemented, and the performance metrics, like recall, f1-score, precision, testing accuracy, testing loss and ROC to assess the efficacy of the method. The EFDDNN-EI technique achieves 16.89%, 18.57% and 27.68% higher testing accuracy, and 18.81%, 26.53% and 30.62% higher recall compared to the existing approaches: Strawberry Disease Detection under Transfer Lea

关键词：

来源：评论

学校读者我要写书评

暂无评论

Insightful analysis of historical sources at scales beyond human capabilities using unsupervised machine learning and XAI

arXiv

引用

arXiv 2023年

作者： Eberle, Oliver Büttner, Jochen El-Hajj, Hassan Montavon, Grégoire Müller, Klaus-Robert Valleriani, Matteo Machine Learning Group Technische Universität Berlin Marchstr. 23 Berlin10587 Germany BIFOLD – Berlin Institute for the Foundations of Learning and Data Berlin10587 Germany Max Planck Institute for the History of Science Boltzmannstr. 22 Berlin14195 Germany Department of Mathematics and Computer Science Freie Universität Berlin Arnimallee 14 Berlin14195 Germany Department of Artificial Intelligence Korea University Seoul136-713 Korea Republic of Max Planck Institute for Informatics Stuhlsatzenhausweg 4 Saarbrücken66123 Germany Institute of History and Philosophy of Science Technology and Literature Faculty I - Humanities and Educational Sciences Technische Universität Berlin Straße des 17. Juni 135 Berlin10623 Germany The Cohn Institute for the History and Philosophy of Science and Ideas Faculty of Humanities Tel Aviv University P.O.B. 39040 Ramat Aviv Tel Aviv6139001 Israel

Historical materials are abundant. Yet, piecing together how human knowledge has evolved and spread both diachronically and synchronically remains a challenge that can so far only be very selectively addressed. The vast volume of materials precludes comprehensive studies, given the restricted number of human specialists. However, as large amounts of historical materials are now available in digital form there is a promising opportunity for AI-assisted historical analysis. In this work, we take a pivotal step towards analyzing vast historical corpora by employing innovative machine learning (ML) techniques, enabling in-depth historical insights on a grand scale. Our study centers on the evolution of knowledge within the ‘Sacrobosco Collection’ – a digitized collection of 359 early modern printed editions of textbooks on astronomy used at European universities between 1472 and 1650 – roughly 76,000 pages, many of which contain astronomic, computational tables. An ML based analysis of these tables helps to unveil important facets of the spatio-temporal evolution of knowledge and innovation in the field of mathematical astronomy in the period, as taught at European universities. Copyright © 2023, The Authors. All rights reserved.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

Correction to: GAMe-BiLSTM: a novel modified metaheuristic deep learning technique for non-ST-segment elevation myocardial infarction classification

引用

International Journal of Information technology 2024年 1-1页

作者： Patil, Sachin Sambhaji Mohite-Patil, Tanajirao Bapuso Kalipindi, Murali Sarvani, Chalamalasetty P, Ramesh Babu Maheshwari, Shikha Department of Electronics and Communication Engineering School of Engineering and Sciences MIT Art Design and Technology University Pune India Department of Electronics and Telecommunication Engineering D. Y. Patil College of Engineering and Technology Kasaba Bawada Kolhapur India Department of Artificial Intelligence and Machine Learning Vijaya Institute of Technology for Women (Affiliated to JNTUK) Enikepadu India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Guntur India Department of Computer Science College of Engineering and Technology Wollega University Nekemte Ethiopia Centre for Distance & Online Education Manipal University Jaipur India

来源：评论

学校读者我要写书评

暂无评论

Robust motion averaging under maximum correntropy criterion

arXiv

引用

arXiv 2020年

作者： Zhu, Jihua Hu, Jie Lu, Huimin Chen, Badong Li, Zhongyu Lab of Vision Computing and Machine Learning School of Software Engineering Xi'an Jiaotong University Xi'an710049 China Kyushu Institute of Technology Kitakyushu Japan School of Artificial Intelligence Xian Jiaotong University Xi'an710049 China

Recently, the motion averaging method has been introduced as an effective means to solve the multi-view registration problem. This method aims to recover global motions from a set of relative motions, where the original method is sensitive to outliers due to using the Frobenius norm error in the optimization. Accordingly, this paper proposes a novel robust motion averaging method based on the maximum correntropy criterion (MCC). Specifically, the correntropy measure is used instead of utilizing Frobenius norm error to improve the robustness of motion averaging against outliers. According to the half-quadratic technique, the correntropy measure based optimization problem can be solved by the alternating minimization procedure, which includes operations of weight assignment and weighted motion averaging. Further, we design a selection strategy of adaptive kernel width to take advantage of correntropy. Experimental results on benchmark data sets illustrate that the new method has superior performance on accuracy and robustness for multi-view registration. Copyright © 2020, The Authors. All rights reserved.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Tumor Detection, Segmentation and Classification Challenge on Automated 3D Breast Ultrasound: The TDSC-ABUS Challenge

arXiv

引用

arXiv 2025年

作者： Luo, Gongning Xu, Mingwang Chen, Hongyu Liang, Xinjie Tao, Xing Ni, Dong Jeong, Hyunsu Kim, Chulhong Stock, Raphael Baumgartner, Michael Kirchhoff, Yannick Rokuss, Maximilian Maier-Hein, Klaus Yang, Zhikai Fan, Tianyu Boutry, Nicolas Tereshchenko, Dmitry Moine, Arthur Charmetant, Maximilien Sauer, Jan Du, Hao Bai, Xiang-Hui Raikar, Vipul Pai Montoya-Del-Angel, Ricardo Martí, Robert Luna, Miguel Lee, Dongmin Qayyum, Abdul Mazher, Moona Guo, Qihui Wang, Changyan Awasthi, Navchetan Zhao, Qiaochu Wang, Wei Wang, Kuanquan Wang, Qiucheng Dong, Suyu School of Computer Science and Technology Harbin Institute of Technology Harbin150001 China Department of Mathematics Faculty of Science National University of Singapore Singapore National-Regional Key Technology Engineering Laboratory for Medical Ultrasound School of Biomedical Engineering Shenzhen University Medical School Shenzhen University Shenzhen China Laboratory Shenzhen University Shenzhen China School of Biomedical Engineering and Informatics Nanjing Medical University Nanjing China Pohang Korea Republic of Heidelberg Division of Medical Image Computing Heidelberg Germany Faculty of Mathematics and Computer Science Heidelberg University Germany Heidelberg Germany HIDSS4Health - Helmholtz Information and Data Science School for Health Karlsruhe Heidelberg Germany Pattern Analysis and Learning Group Department of Radiation Oncology Heidelberg University Hospital Germany Department of Biomedical Engineering and Health KTH Royal Institute of Technology Stockholm Sweden France FathomX Singapore Saw Swee Hock School of Public Health National University of Singapore Singapore Philips Research University of Girona Spain Department of Robotics and Mechatronics Engineering DGIST Korea Republic of Department of Interdisciplinary Studies of Artificial Intelligence DGIST Korea Republic of National Heart and Lung Institute Faculty of Medicine Imperial College London London United Kingdom Centre for Medical Image Computing Department of Computer Science University College London London United Kingdom Lab School of Communication and Information Engineering Shanghai University Shanghai China Faculty of Science Mathematics and Computer Science Informatics Institute University of Amsterdam Amsterdam1090 GH Netherlands Department of Biomedical Engineering and Physics Amsterdam UMC Amsterdam1081 HV Netherlands Xi’an Jiaotong-Liverpool University China Department of Ultrasound Harbin Medical University Cancer Hospital No. 150 Haping Road Nangang

Breast cancer is one of the most common causes of death among women worldwide. Early detection helps in reducing the number of deaths. Automated 3D Breast Ultrasound (ABUS) is a newer approach for breast screening, which has many advantages over handheld mammography such as safety, speed, and higher detection rate of breast cancer. Tumor detection, segmentation, and classification are key components in the analysis of medical images, especially challenging in the context of 3D ABUS due to the significant variability in tumor size and shape, unclear tumor boundaries, and a low signal-to-noise ratio. The lack of publicly accessible, well-labeled ABUS datasets further hinders the advancement of systems for breast tumor analysis. Addressing this gap, we have organized the inaugural Tumor Detection, Segmentation, and Classification Challenge on Automated 3D Breast Ultrasound 2023 (TDSC-ABUS2023). This initiative aims to spearhead research in this field and create a definitive benchmark for tasks associated with 3D ABUS image analysis. In this paper, we summarize the top-performing algorithms from the challenge and provide critical analysis for ABUS image examination. We offer the TDSC-ABUS challenge as an open-access platform at https://***/ to benchmark and inspire future developments in1algorithmic research. © 2025, CC BY.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

MOEA/D-UR based infrared feature extraction for hypervelocity impact spacecraft damage detection and assessment

引用

NDT & E International 2025年

作者： Yan Gao Chun Yin Xuegang Huang Jiuwen Cao Sara Dadras Zhiqi Hou Anhua Shi School of Automation Engineering University of Electronic Science and Technology of China Chengdu 611731 PR China Hypervelocity Aerodynamics Institute China Aerodynamics Research & Development Center Mianyang 621000 PR China The Machine Learning and I-Health International Cooperation Base of Zhejiang Province and the Artificial Intelligence Institute Hangzhou Dianzi University Zhejiang 310018 PR China Electrical and Computer Engineering Department Utah State University Logan UT 84321 USA

In this paper, a decomposition-based multi-objective evolutionary algorithm updating weights when required (MOEA/D-UR) infrared feature extraction method is proposed for damage detection. Due to the complexity of the damage caused by hypervelocity impact (HVI), it is difficult to visually characterise the coupling defects in pulse thermography in reflection mode. After obtaining a multi-objective optimisation problem, an adaptive metric was utilised to determine when to adjust the weights and divide the objective space. On the actual infrared data, we introduce the sample distribution objective, the data structure objective, and the local pixel relationship objective, based on which we establish a multi-objective optimization problem. The experimental results show that the detection framework is able to detect different HVI damages and realize visual evaluation. The proposed method can effectively classify point impact and surface impact damage caused by HVI. The method successfully identified 17 optimal Pareto solutions from 250 selected TTRs, using a block of 327,680 pixels. The detection framework demonstrates robust performance in practical infrared applications, precisely discriminating HVI-induced defective regions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-component attention graph convolutional neural network for QoS-aware cloud job scheduling and resource management enhancing efficiency and performance in cloud computing

Results in Engineering

引用

Results in engineering 2025年 27卷

作者： Deepak Dharrao Sarika Deokate Nagamma Hudgi Shrinivas Shirkande Vinod Mahajan Madhuri Pangavhane Anupkumar Bongale Department of Computer Science and Engineering Symbiosis Institute of Technology Pune Campus Symbiosis International (Deemed University) Lavale Pune Maharashtra 412115 India Department of Computer Engineering Pimpri Chinchwad College of Engineering Pune Maharashtra India Department of Computer Science Engineering (Cyber Security) Akash College of Engineering and Technology Bangalore Karnataka India S B Patil College of Engineering Indapur India AGM(L/A) Bharat Sanchar Nigam LTD. Rajgurunagar Pune Maharashtra India Department of Artificial Intelligence and Machine Learning Symbiosis Institute of Technology Pune Campus Symbiosis International (Deemed University) Lavale Pune Maharashtra 412115 India

Cloud computing is one of the most promising technologies for online business services, scheduling real-time cloud jobs with excellent Quality of Service (QoS) remains a challenge with current methodologies. However, in reinforced rewards are typically unavailable until all jobs have been scheduled. In this paper, Multi-Component Attention Graph Convolutional Neural Network for QoS-Aware Cloud Job Scheduling and Resource Management Enhancing Efficiency and Performance in Cloud Computing ( MCAGCN-QOS-CJS ) is proposed. The cloud typically follows a long trajectory; to find trajectories with large rewards, resulting in concerns such as inefficient scheduling policies. Here, scheduling user requests improve job success rates and reduces response time. Initially, QoS based Job scheduling and resource management using Multi-Component Attention Graph Convolutional Neural Network ( MCAGCN ) to maximize Success Rates in the Cloud. However, MCAGCN does not include optimization strategies for determining optimal parameters for enhanced resource allocation in cloud computing. Hence Multi-Agent Cubature Kalman Optimizer ( MACKO ) is used to enhance weight parameters of MCAGCN . The performance measures including success rate, Average Response Time, Throughput, and Job Completion Time is considered. The MCAGCN-QOS-CJS method attains 23.10 %, 27.54 % and 25.72 %, higher Throughput, 21.48 %, 17.73 %, 25.32 % higher Utilization Rate and 20.98 %, 26.66 % and 16.32 % lower Average Response Time, 10.78 %, 20.47 %, and 12.86 % lower Job Completion Time are compared with existing techniques.

关键词： Cloud computing Job scheduling Multi-component attention graph convolutional neural network Multi-agent cubature Kalman optimizer

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：