检索结果-内蒙古大学图书馆

Learning discrete representations via constrained clustering for effective and efficient dense retrieval

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhan, Jingtao Mao, Jiaxin Liu, Yiqun Guo, Jiafeng Zhang, Min Ma, Shaoping Department of Computer Science and Technology Institute for Artificial Intelligence Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China Beijing Key Laboratory of Big Data Management and Analysis Methods Gaoling School of Artificial Intelligence Renmin University of China Beijing100872 China CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China

Dense Retrieval (DR) has achieved state-of-the-art first-stage ranking effectiveness. However, the efficiency of most existing DR models is limited by the large memory cost of storing dense vectors and the time-consuming nearest neighbor search (NNS) in vector space. Therefore, we present RepCONC, a novel retrieval model that learns discrete Representations via CONstrained Clustering. RepCONC jointly trains dual-encoders and the Product Quantization (PQ) method to learn discrete document representations and enables fast approximate NNS with compact indexes. It models quantization as a constrained clustering process, which requires the document embeddings to be uniformly clustered around the quantization centroids and supports end-to-end optimization of the quantization method and dual-encoders. We theoretically demonstrate the importance of the uniform clustering constraint in RepCONC and derive an efficient approximate solution for constrained clustering by reducing it to an instance of the optimal transport problem. Besides constrained clustering, RepCONC further adopts a vector-based inverted file system (IVF) to support highly efficient vector search on CPUs. Extensive experiments on two popular ad-hoc retrieval benchmarks show that RepCONC achieves better ranking effectiveness than competitive vector quantization baselines under different compression ratio settings. It also substantially outperforms a wide range of existing retrieval models in terms of retrieval effectiveness, memory efficiency, and time efficiency. Copyright © 2021, The Authors. All rights reserved.

关键词： Signal encoding

Interpreting dense retrieval as mixture of topics

学校读者我要写书评

暂无评论

arXiv 2021年

Dense Retrieval (DR) reaches state-of-the-art results in first-stage retrieval, but little is known about the mechanisms that contribute to its success. Therefore, in this work, we conduct an interpretation study of recently proposed DR models. Specifically, we first discretize the embeddings output by the document and query encoders. Based on the discrete representations, we analyze the attribution of input tokens. Both qualitative and quantitative experiments are carried out on public test collections. Results suggest that DR models pay attention to different aspects of input and extract various high-level topic representations. Therefore, we can regard the representations learned by DR models as a mixture of high-level topics. Copyright © 2021, The Authors. All rights reserved.

关键词： Mixtures

Comparative numerical study featuring magnetized nanofluids configured by elongating sheet with thermophoresis and Brownian motion

学校读者我要写书评

暂无评论

Partial Differential Equations in Applied Mathematics 2024年 11卷

作者： Puchakayala, Srinivasa Rao Borra, Shashidar Reddy Kallu, Saritha Formanova, Shoira Khan, M. Ijaz Waqas, M. Ahmad, Furqan Gupta, Manish Department of Mathematics Malla Reddy Engineering College (Autonomous) Dhulapally Telangana Hyderabad 500100 India Department of Mathematics Sreenidhi Institute of Science and Technology Ghatkesar Telangana Hyderabad 501301 India Department of Humanities and Sciences (Mathematics) CVR College of Engineering Ibrahimpatnam Telangana Hyderabad 501510 India Department of Chemistry and Its Teaching Methods Tashkent State Pedagogical University Tashkent Uzbekistan Department of Mechanical Engineering College of Engineering Prince Mohammad Bin Fahd University Al-Khobar Saudi Arabia NUTECH School of Applied Science and Humanities National University of Technology Islamabad 44000 Pakistan Department of Computer Science and Mathematics Lebanese American University Beirut Lebanon Western Caspian University Baku Azerbaijan Division of Research and Development Lovely Professional University Phagwara India

This study investigates the heat and mass transfer characteristics of MHD rotating Fe₃O₄-Al₂O₃/H₂O hybrid nanofluid flow over a three-dimensional stretching surface. Comparative analysis was conducted among the base fluid H₂O, Al₂O₃-H₂O nanofluid, and Fe₃O₄-Al₂O₃/H₂O hybrid nanofluid, focusing on velocity, temperature, and concentration distributions influenced by thermophoresis, Brownian motion, Hall current, temperature ratio, magnetic parameter, rotation, and thermal radiation. The governing nonlinear partial differential equations were transformed into ordinary differential equations using similarity adaptations and solved numerically with the BVP-5C method in MATLAB. Results indicate that increasing the thermophoresis and Brownian motion parameters elevates the temperature profile while affecting the concentration distribution differently. The hybrid nanofluid exhibited a higher temperature distribution compared to the nanofluid and base fluid, whereas the base fluid showed a greater concentration gradient. © 2024 The Author(s)

关键词： Brownian motion Elongating sheet Hall current Hybrid nanofluid Joule heating Thermophoresis

*** - An interactive catalog of business process modeling patterns literature

学校读者我要写书评

暂无评论

*** - An interactive catalog of business process modeling pa...

2019 Dissertation Award, Doctoral Consortium, and Demonstration Track at BPM, BPMT 2019

作者： Laue, Ralf Koschmider, Agnes Fellmann, Michael Schoknecht, Andreas Vetter, Arthur University of Applied Sciences Zwickau Department of Computer Science Dr.-Friedrichs-Ring 2a Zwickau08056 Germany Process Analytics Group Kiel University Kiel24098 Germany Institute of Computer Science University of Rostock Rostock Germany KIT Institute for Applied Informatics and Formal Description Methods

Patterns-descriptions of proven and well-documented solutions for recurring problems { have gained widespread interest and acceptance in the area of business process modeling. In the past years, a large number of such patterns have been documented in the literature. However, it is still difficult to find patterns that can be useful in a given context. The reason is that the relevant publications are spread in various journals and other types of publications, and there is no guidance for locating a pattern that can be useful for solving a given problem. In this demo, we present an interactive web-site that provides a comprehensive overview on published work in the field of business process modeling patterns. It allows finding publications on business process modeling patterns based on various search criteria. It is intended to be useful both for business process modeling practitioners as for researchers in need of sound literature references. Currently, this catalog (meant to be a growing resource) provides an categorization of 95 publications on patterns as well as 50 publication on anti-patterns. © 2019 CEUR-WS. All rights reserved.

关键词： Systems engineering

Explaining cognitive complaints in obstructive sleep apnea (OSA) with OSA severity, depression symptoms, and sleep architecture: a path model analysis

学校读者我要写书评

暂无评论

Neuroscience Applied 2023年 2卷

作者： B. Gailer E. Richert E.S. Arnardóttir K.R. Jóhannsdóttir Research Methods and Evaluation in Psychology Department of Psychology Chemnitz Germany Reykjavik University Sleep Institute Psychology Reykjavík Iceland Reykjavik University Sleep Institute Department of Psychology- Department of Engineering and Department of Computer Science Reykjavík Iceland Reykjavik University Sleep Institute Psychology Reykjaík Iceland

Optimizing melting heat effect in flow of dusty boger hybrid nanofluid with elastic deformation for industrial heat transfer applications

学校读者我要写书评

暂无评论

International Journal of Thermofluids 2025年 27卷

作者： Okasha, Mostafa Mohamed Abbas, Munawar Ghaeb, Fadhil A. Shernazarov, Iskandar Younis, Jihad Tharwan, Mohammed Agha, Afnan Al Garalleh, Hakim AL Department of Mechanical Engineering College of Engineering Northern Border University Arar Saudi Arabia Department of Mathematics Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Tamil Nadu Chennai602105 India Department of Mathematics The Islamia University of Bahawalpur Bahawalpur63100 Pakistan Petroleum and Mining Engineering Department Tishk International University Erbil Iraq Department of Chemistry and Its Teaching Methods Tashkent State Pedagogical University Tashkent Uzbekistan Department of Mathematics Aden University P.O.Box 6014 Aden Yemen Department of Mechanical Engineering College of Engineering and Computer Sciences Jazan University P. O. Box 45142 Jazan Saudi Arabia Department of Mathematical Science College of Engineering University of Business and Technology Jeddah21361 Saudi Arabia

Background: Examining the effects of elastic deformation and melting phenomena on mass and heat transmission while examining the constant two-dimensional flow of a dusty hybrid nanofluid over a sheet containing gyrotactic microbes and porous media is the primary objective of this investigation. Method: The controlling partial differential equations are converted into ordinary differential equations by using the proper similarity transformation. The system of equations is then numerically solved using an efficient bvp4c approach. Applications: In the realm of bioengineering, this model is very useful, especially when constructing sophisticated cooling systems for biomedical devices where accurate temperature control is essential. The model's insights are also useful in environmental engineering, where they can be used to improve pollutant removal methods in water treatment procedures by enhancing bioconvective flows. This research also offers greater control over manufacturing operations that need precise temperature and fluid dynamic management in industrial processes involving the manipulation of non-Newtonian fluids. Outcomes: As the elastic deformation increases, the concentration and temperature distributions decrease. The velocity, microorganism's, thermal and concentration field enhance as augments the value of melting parameter. © 2025

关键词： Non Newtonian flow

Guidance of development,validation,and evaluation of algorithms for populating health status in observational studies of routinely collected data (DEVELOP-RCD)

学校读者我要写书评

暂无评论

Military Medical Research 2025年第5期 788-798页

作者： Wen Wang Ying-Hui Jin Mei Liu Qiao He Jia-Yue Xu Ming-Qi Wang Guo-Wei Li Bo Fu Si-Yu Yan Kang Zou Xin Sun Institute of Integrated Traditional Chinese and Western Medicine Chinese Evidence-Based Medicine and Cochrane China CenterWest China HospitalSichuan University NMPA Key Laboratory for Real World Data Research and Evaluation in Hainan Sichuan Center of Technology Innovation for Real World Data Center for Evidence-Based and Translational Medicine Zhongnan Hospital of Wuhan University Department of Health Research Methods Evidence and ImpactMcMaster University Center for Clinical Epidemiology and Methodology Guangdong Second Provincial General Hospital Biostatistics Unit Research Institute at St.Joseph's Healthcare Hamilton School of Computer Science and Engineering University of Electronic Science and Technology of China West China School of Public Health and West China Fourth Hospital Sichuan University

Background:In recent years,there has been a growing trend in the utilization of observational studies that make use of routinely collected healthcare data (RCD).These studies rely on algorithms to identify specific health conditions (e.g.,diabetes or sepsis) for statistical ***,there has been substantial variation in the algorithm development and validation,leading to frequently suboptimal performance and posing a significant threat to the validity of study ***,these issues are often ***:We systematically developed guidance for the development,validation,and evaluation of algorithms designed to identify health status (DEVELOP-RCD).Our initial efforts involved conducting both a narrative review and a systematic review of published studies on the concepts and methodological issues related to algorithm development,validation,and ***,we conducted an empirical study on an algorithm for identifying *** on these findings,we formulated specific workflow and recommendations for algorithm development,validation,and evaluation within the ***,the guidance underwent independent review by a panel of 20 external experts who then convened a consensus meeting to finalize ***:A standardized workflow for algorithm development,validation,and evaluation was *** by specific health status considerations,the workflow comprises four integrated steps:assessing an existing algorithm’s suitability for the target health status;developing a new algorithm using recommended methods;validating the algorithm using prescribed performance measures;and evaluating the impact of the algorithm on study ***,13 good practice recommendations were formulated with detailed ***,a practical study on sepsis identification was included to demonstrate the application of this ***:The establishment of guidance is intended to aid researchers and clinician

关键词：

Anatomy-informed Data Augmentation for Enhanced Prostate Cancer Detection

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Kovacs, Balint Netzer, Nils Baumgartner, Michael Eith, Carolin Bounias, Dimitrios Meinzer, Clara Jäger, Paul F. Zhang, Kevin S. Floca, Ralf Schrader, Adrian Isensee, Fabian Gnirs, Regula Görtz, Magdalena Schütz, Viktoria Stenzinger, Albrecht Hohenfellner, Markus Schlemmer, Heinz-Peter Wolf, Ivo Bonekamp, David Maier-Hein, Klaus H. Heidelberg Germany Division of Radiology DKFZ Heidelberg Germany Medical Faculty Heidelberg Heidelberg University Heidelberg Germany Faculty of Mathematics and Computer Science Heidelberg University Germany Helmholtz Imaging DKFZ Heidelberg Germany Interactive Machine Learning Group DKFZ Heidelberg Germany Department of Urology University of Heidelberg Medical Center Germany Junior Clinical Cooperation Unit’Multiparametric methods for early detection of prostate cancer’ DKFZ Heidelberg Germany Institute of Pathology University of Heidelberg Medical Center Germany Mannheim University of Applied Sciences Mannheim Germany Pattern Analysis and Learning Group Department of Radiation Oncology Heidelberg University Hospital Heidelberg Germany

Data augmentation (DA) is a key factor in medical image analysis, such as in prostate cancer (PCa) detection on magnetic resonance images. State-of-the-art computer-aided diagnosis systems still rely on simplistic spatial transformations to preserve the pathological label post transformation. However, such augmentations do not substantially increase the organ as well as tumor shape variability in the training set, limiting the model’s ability to generalize to unseen cases with more diverse localized soft-tissue deformations. We propose a new anatomy-informed transformation that leverages information from adjacent organs to simulate typical physiological deformations of the prostate and generates unique lesion shapes without altering their label. Due to its lightweight computational requirements, it can be easily integrated into common DA frameworks. We demonstrate the effectiveness of our augmentation on a dataset of 774 biopsy-confirmed examinations, by evaluating a state-of-the-art method for PCa detection with different augmentation settings. Copyright © 2023, The Authors. All rights reserved.

关键词： Magnetic resonance

Leveraging Neural Networks to Profile Health Care Providers with Application to Medicare Claims

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wu, Wenbo Li, Fan Liu, Richard Li, Yiting McAdams-DeMarco, Mara Geras, Krzysztof J. Schaubel, Douglas E. Díaz, Iván Division of Biostatistics Department of Population Health NYU Grossman School of Medicine United States Division of Nephrology Department of Medicine NYU Grossman School of Medicine United States Center for Data Science New York University United States Department of Biostatistics Yale School of Public Health United States Center for Methods in Implementation and Prevention Science Yale School of Public Health United States Department of Surgery NYU Grossman School of Medicine United States Division of Epidemiology Department of Population Health NYU Grossman School of Medicine United States Department of Radiology NYU Grossman School of Medicine United States Department of Computer Science Courant Institute of Mathematical Sciences New York University United States Department of Biostatistics Epidemiology and Informatics University of Pennsylvania Perelman School of Medicine United States

Encompassing numerous nationwide, statewide, and institutional initiatives in the United States, provider profiling has evolved into a major health care undertaking with ubiquitous applications, profound implications, and high-stakes consequences. In line with such a significant profile, the literature has accumulated a number of developments dedicated to enhancing the statistical paradigm of provider profiling. Tackling wide-ranging profiling issues, these methods typically adjust for risk factors using linear predictors. While this approach is simple, it can be too restrictive to characterize complex and dynamic factor-outcome associations in certain contexts. One such example arises from evaluating dialysis facilities treating Medicare beneficiaries with end-stage renal disease. It is of primary interest to consider how the coronavirus disease (COVID-19) affected 30-day unplanned readmissions in 2020. The impact of COVID-19 on the risk of readmission varied dramatically across pandemic phases. To efficiently capture the variation while profiling facilities, we develop a generalized partially linear model (GPLM) that incorporates a neural network. Considering provider-level clustering, we implement the GPLM as a stratified sampling-based stochastic optimization algorithm that features accelerated convergence. Furthermore, an exact test is designed to identify under- and over-performing facilities, with an accompanying funnel plot to visualize profiles. The advantages of the proposed methods are demonstrated through simulation experiments and profiling dialysis facilities using 2020 Medicare claims from the United States Renal Data System. © 2023, CC BY.

关键词： Optimization