检索结果-内蒙古大学图书馆

The Journal of Machine Learning Research 2020年第1期21卷 785-844页

作者： Sandeep Kumar Jiaxi Ying José Vinícius De M. Cardoso Daniel P. Palomar Department of Industrial Engineering and Data Analytics The Hong Kong University of Science and Technology Clear Water Bay Hong Kong Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Clear Water Bay Hong Kong Department of Electronic and Computer Engineering Department of Industrial Engineering and Data Analytics The Hong Kong University of Science and Technology Clear Water Bay Hong Kong

Graph learning from data is a canonical problem that has received substantial attention in the literature. Learning a structured graph is essential for interpretability and identification of the relationships among data. In general, learning a graph with a specific structure is an NP-hard combinatorial problem and thus designing a general tractable algorithm is challenging. Some useful structured graphs include connected, sparse, multi-component, bipartite, and regular graphs. In this paper, we introduce a unified framework for structured graph learning that combines Gaussian graphical model and spectral graph theory. We propose to convert combinatorial structural constraints into spectral constraints on graph matrices and develop an optimization framework based on block majorization-minimization to solve structured graph learning problem. The proposed algorithms are provably convergent and practically amenable for a number of graph based applications such as data clustering. Extensive numerical experiments with both synthetic and real data sets illustrate the effectiveness of the proposed algorithms. An open source R package containing the code for all the experiments is available at https://***/package=spectralGraphTopology.

关键词： structured graph learning spectral graph theory Markov random field Gaussian graphical model Laplacian matrix clustering adjacency matrix bipartite structure spectral similarity

来源：评论

学校读者我要写书评

暂无评论

Energetic Content based Image Retrieval Scheme using Improved Deep Learning Strategy with Image Analysis Technique

Energetic Content based Image Retrieval Scheme using Improve...

引用

International Conference on Smart Structures and Systems (ICSSS)

作者： S. Karkuzhali P. Malathi A Thenmozhi Velu Aiyyasamy Keerthika A G.S. Uthayakumar Department of General Engineering R.M.K. Engineering College Chennai Tamil Nadu India Department of Data Analytics Saveetha College of Liberal Arts and Sciences SIMATS Department of Electronics and Communication Engineering Kings Engineering College Chennai Tamil Nadu India Department of Electronics and Communication Engineering Meenakshi Sundararajan Engineering College Chennai Tamil Nadu India Department of Computer Science and Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai Tamil Nadu India Department of ECE St. Joseph’s Institute of Technology Chennai Tamil Nadu India

One popular approach to retrieving images from huge, unprocessed datasets is content-based image retrieval, or CBIR. The conventional ways of data retrieval, however, are not meeting the needs of consumers. The number of consumer-accessible photographs also keeps growing, and there are an abundance of digital platforms for development and dissemination. Consequently, digital image processing is both ubiquitous and permanent in many fields. Consequently, effective strategies are required for both the speedy access to these massive picture databases and the recovery of comparable photos from this massive number of images based on a specific picture (query). The computation of depiction of features and resemblance is crucial to the efficiency of a CBIR system. We introduce LAIRS, a cutting-edge deep learning method that integrates the extraction of features and aims to do this with classification to facilitate rapid picture retrieval. For a transparent evaluation of the proposed scheme’s efficiency, the suggested logic is cross-validated using Convolutional Neural Networks (CNNs), a classic deep learning paradigm. Several in-depth observational experiments for various CBIR tasks employing an image database have shown encouraging results, teaching us important lessons for making CBIR system more efficient. With the use of CBIR structures, a different collection can find similar pictures to the query image. There is little doubt that Google’s search per photo tool is perhaps the most widely used CBIR approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Leveraging Probe data and Machine Learning to Derive and Interpret Macroscopic Fundamental Diagrams Across U.S. Cities

Leveraging Probe Data and Machine Learning to Derive and Int...

引用

IEEE International Conference on Big data

作者： Ling Jin Xiaodan Xu Yuhan Wang Kaveh Farokhi Sadabadi Alina Lazar Duleep Rathgamage Don Zachary Needell C Anna Spurlock Mahyar Amirgholy Mona Asudegi Energy Technology Area Berkeley National Laboratory Berkeley CA Center for Advanced Transportation Technology University of Maryland College Park MD Department of Computer Science and Information Youngstown State University Youngstown OH School of Data Science and Analytics Kennesaw State University Marietta GA Energy Analysis and Environmental Impacts Division Lawrence Berkeley National Laboratory Berkeley CA Civil and Environmental Engineering Department Kennesaw State University Marietta GA Office of Transportation Policy Studies Federal Highway Administration Washington DC D.C.

Macroscopic fundamental diagram (MFD) captures an orderly relationship among traffic flow, density, and speed at the network level. Understanding network-wide traffic through MFDs can optimally allocate demand to existing networks, improving performance by maximizing network production and avoiding congestion. However, due to historical data limitations, empirically derived MFD models are sparse in the literature, especially for the U.S. cities. Leveraging a large-scale and granular census-tract-level flow and density derived from vehicle probe data, this research is the first to develop a machine learning approach to both derive MFD models and interpret their underlying difference among urban networks across the entire United States. Among the four machine learning methods tested here XGBoost is found to deliver the best performance to predict the network traffic flow for given vehicular density and location attributes. Interaction Shapley Additive explanation (SHAP) values are used to interpret the factors, such as land use, transportation infrastructure, and network topology, that influence the flow-density relationships among locations. The analysis framework developed in this work can generate datadriven MFDs and a deeper understanding of their shape dependence on network, infrastructure, and land use characteristics, which can be used by transportation authorities to derive and optimize location-specific MFDs facilitating more informed management and planning decisions at the network level.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Big data = Big Insights? Operationalising Brooks’ Law in a Massive GitHub data Set

arXiv

引用

arXiv 2022年

作者： Gote, Christoph Schweitzer, Frank Mavrodiev, Pavlin Scholtes, Ingo Department of Systems Design ETH Zurich Weinbergstrasse 56/58 Zurich8092 Switzerland Department of Computer Science XV - Machine Learning for Complex Networks Julius-Maximilians-Universität Würzburg Friedrich-Bergius-Ring 30 Würzburg97076 Germany Data Analytics Group University of Zurich Binzmühlestrasse 14 Zurich8050 Switzerland

Massive data from software repositories and collaboration tools are widely used to study social aspects in software development. One question that several recent works have addressed is how a software project’s size and structure influence team productivity, a question famously considered in Brooks’ law. Recent studies using massive repository data suggest that developers in larger teams tend to be less productive than smaller teams. Despite using similar methods and data, other studies argue for a positive linear or even super-linear relationship between team size and productivity, thus contesting the view of software economics that software projects are diseconomies of scale. In our work, we study challenges that can explain the disagreement between recent studies of developer productivity in massive repository data. We further provide, to the best of our knowledge, the largest, curated corpus of GitHub projects tailored to investigate the influence of team size and collaboration patterns on individual and collective productivity. Our work contributes to the ongoing discussion on the choice of productivity metrics in the operationalisation of hypotheses about determinants of successful software projects. It further highlights general pitfalls in big data analysis and shows that the use of bigger data sets does not automatically lead to more reliable insights. Copyright © 2022, The Authors. All rights reserved.

关键词： Productivity

来源：评论

学校读者我要写书评

暂无评论

GLOBAL OPTIMALITY OF ELMAN-TYPE RNNS IN THE MEAN-FIELD REGIME

arXiv

引用

arXiv 2023年

作者： Agazzi, Andrea Lu, Jianfeng Mukherjee, Sayan Department of Mathematics Università Di Pisa Pisa Italy Department of Mathematics Duke University DurhamNC27708 United States Department of Physics Duke University DurhamNC27708 United States Department of Chemistry Duke University DurhamNC27708 United States Center for Scalable Data Analytics and Artificial Intelligence Universität Leipzig Leipzig Germany Max Planck Institute for Mathematics in the Sciences Leipzig Germany Department of Statistical Science Duke University DurhamNC27708 United States Department of Computer Science Duke University DurhamNC27708 United States Department of Biostatistics & Bioinformatics Duke University DurhamNC27708 United States

We analyze Elman-type Recurrent Reural Networks (RNNs) and their training in the mean-field regime. Specifically, we show convergence of gradient descent training dynamics of the RNN to the corresponding mean-field formulation in the large width limit. We also show that the fixed points of the limiting infinite-width dynamics are globally optimal, under some assumptions on the initialization of the weights. Our results establish optimality for feature-learning with wide RNNs in the mean-field regime. Copyright © 2023, The Authors. All rights reserved.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

UseGeo - A UAV-based multi-sensor dataset for geospatial research

引用

ISPRS Open Journal of Photogrammetry and Remote Sensing 2024年 13卷

作者： Nex, F. Stathopoulou, E.K. Remondino, F. Yang, M.Y. Madhuanand, L. Yogender, Y. Alsadik, B. Weinmann, M. Jutzi, B. Qin, R. ITC Department of Earth Observation Science Faculty ITC University of Twente Enschede Netherlands 3D Optical Metrology (3DOM) Unit Bruno Kessler Foundation (FBK) Trento Italy Visual Computing Group University of Bath Bath United Kingdom Department of Physical Geography Faculty of Geosciences University of Utrecht Utrecht Netherlands Inter-university Department of Regional & Urban Studies and Planning (DIST) Politecnico di Torino Italy Institute of Photogrammetry and Remote Sensing Karlsruhe Institute of Technology Karlsruhe Germany Geospatial Data Analytics Laboratory The Ohio State University Columbus United States Department of Civil Environmental and Geodetic Engineering The Ohio State University Columbus United States Department of Electrical and Computer Engineering The Ohio State University Columbus United States Translational Data Analytics Institute The Ohio State University Columbus United States

3D reconstruction is a long-standing research topic in the photogrammetric and computer vision communities;although a plethora of open-source and commercial solutions for 3D reconstruction have been released in the last few years, several open challenges and limitations still exist. Undoubtedly, deep learning algorithms have demonstrated great potential in several remote sensing tasks, including image-based 3D reconstruction. State-of-the-art monocular and stereo algorithms leverage deep learning techniques and achieve increased performance in depth estimation and 3D reconstruction. However, one of the limitations of such methods is that they highly rely on large training sets that are often tedious to obtain;even when available, they typically refer to indoor, close-range scenarios and low-resolution images. Especially while considering UAV (Unmanned Aerial Vehicle) scenarios, such data are not available and domain adaptation is not a trivial challenge. To fill this gap, the UAV-based multi-sensor dataset for geospatial research (UseGeo - https://***/home) is introduced in this paper. It contains both image and LiDAR data and aims to support relevant research in photogrammetry and computer vision with a useful training set for both stereo and monocular 3D reconstruction algorithms. In this regard, the dataset provides ground truth data for both point clouds and depth maps. In addition, UseGeo can be also a valuable dataset for other tasks such as feature extraction and matching, aerial triangulation, or image and LiDAR co-registration. The paper introduces the UseGeo dataset and validates some state-of-the-art algorithms to assess their usability for both monocular and multi-view 3D reconstruction. © 2024 The Authors

关键词： 3D reconstruction Deep learning LiDAR Monocular depth estimation Multi-view stereo Stereo matching UAV

来源：评论

学校读者我要写书评

暂无评论

Utilization of machine learning and neural networks to optimize the enclosure angle, magnetic field, and radiation parameter for mixed convection of hybrid nanofluid flow next to assess environmental impact

引用

Engineering Analysis with Boundary Elements 2023年 146卷 252-262页

作者： Tao Hai Hayder A. Dhahad Masood Ashraf Ali Vishal Goyal Sattam Fahad Almojil Abdulaziz Ibrahim Almohana Abdulrhman Fahmi Alali Khaled Twfiq Almoalimi Farah Qasim Ahmed Alyousuf School of Computer and Information Qiannan Normal University for Nationalities Duyun Guizhou 558000 China Key Laboratory of Complex Systems and Intelligent Optimization of Guizhou Duyun Guizhou 558000 China Institute for Big Data Analytics and Artificial Intelligence (IBDAAI) Universiti Teknologi MARA Shah Alam Selangor 40450 Malaysia Mechanical Engineering Department University of Technology Baghdad Iraq Department of Industrial Engineering College of Engineering Prince Sattam bin Abdulaziz University Alkharj 16273 Saudi Arabia Department of Electronics and Communication Engineering GLA University Mathura India Department of Civil Engineering College of Engineering King Saud University P.O. Box 800 Riyadh 11421 Saudi Arabia Department of Information Technology College of Engineering and Computer Science Lebanese French University Kurdistan Region Iraq

This paper examines the mixed convective heat transfer (HTR) of nanofluid (NFD) flow in a rectangular enclosure with the upper moving wall numerically. The lower wall has a high temperature and a number of semi-circular obstacles with the same temperature are installed on it. The upper moving wall has a low temperature and the other two walls are insulated. The enclosure can change from horizontal to vertical. Radiation HTR is considered in the enclosure and there is a magnetic field (MGF) that can change the angle from horizontal to vertical affecting the NFD. This study is carried out for different angles of the enclosure and MGF from horizontal to vertical for radiation parameters (RDP) of 0 to 3 and a constant MGF with Hartmann number of 20 and Richardson number of 10. The aim is to estimate the Nusselt number (Nu), entropy generation (ETG), and Bejan number (Be). The SIMPLE algorithm is utilized using FORTRAN software, and optimization is done using artificial intelligence to find the maximum and minimum output values. The results demonstrate that the maximum value of Nu and Bes corresponds to the MGF angle and enclosure angle of 90°. The minimum value of the Nu and the maximum amount of ETG corresponds to the horizontal MGF and horizontal enclosure when the RDP is 1.5. An increment in the RDP enhances the amount of Nu. The maximum amount of ETG, i.e. 12.87, corresponds to the enclosure with an angle of 45° for the horizontal MGF and the absence of RDP. corresponds to the enclosure with an angle of 45° for the horizontal MGF and the absence of RDP. It was also found that most environmental impacts, and hence values for different environmental factors, arise from the production of nanoparticles; thus, it is a significant contributor to environmental impacts.

关键词： Machine learning Entropy generation Numerical calculations Convection Nanofluid

来源：评论

学校读者我要写书评

暂无评论

ConBERT-RL: A policy-driven deep reinforcement learning based approach for detecting homophobia and transphobia in low-resource languages

Natural Language Processing Journal

引用

Natural Language Processing Journal 2024年 6卷

作者： Vivek Suresh Raj Chinnaudayar Navaneethakrishnan Subalalitha Lavanya Sambath Frank Glavin Bharathi Raja Chakravarthi University of Calgary Calgary Alberta Canada Department of Computing Technologies SRM Institute of Science and Technology Chennai India Department of Information Technology Madras Institute of Technology Chennai India Insight SFI Research Centre for Data Analytics School of Computer Science University of Galway Galway Ireland School of Computer Science University of Galway Galway Ireland

In this work, we present a novel framework for discriminatory comment classification in targeted low-resource languages thereby enabling identification of discriminatory comments for promoting safer online environment in linguistically diverse contexts. Recently proposed literatures with Bidirectional Encoder Representations from Transformers (BERT) and its variants, have produced promising results, particularly in the case of transliterated Tamil words in English. Such approaches are seen as transfer learning and fine-tuning between a general environment and targeted downstream task. However, for an effective transfer of knowledge, from a source task to a targeted task, their feature space has to be correlated (similarity measure as metric, to measure knowledge transfer), which is unexplored in the previous literature works. In practice, such similarity conditions are often violated. We propose a Con catenated representation, powered with BERT in R einforcement L earning (RL) - ConBERT-RL framework, to capture problem-specific features, as well as to understand nuances in case of transliterated Tamil words into English, to make decision in classifying discriminatory comments. ConBERT-RL incorporates a fusion of learned hidden-state representation from our pre-trained Classifier-Model (CM), along with the broader contextualized representation (pooled output) from BERT. The key idea is to utilize this concatenated representation to drive our policy network for hate comment classification. To effectively learn such a policy, we use the REINFORCE algorithm in a reinforcement learning setting, to guide our ConBERT-RL agent, in making informative decisions. To demonstrate the general aspects of ConBERT-RL, we conduct experiments for offensive comment classification on transliterated Tamil words in English dataset. ConBERT-RL obtains results, where it significantly improved the score of micro average accuracy with 90% ( ≈ 1 . 0 % absolute improvement over BERT+FC), 93% (

关键词： Deep reinforcement learning Low resourced language Homophobia detection Transphobia detection

来源：评论

学校读者我要写书评

暂无评论

Causal Vector Autoregression Enhanced with Covariance and Order Selection

arXiv

引用

arXiv 2022年

作者： Bolla, Marianna Ye, Dongze Wang, Haoyu Ma, Renyuan Frappier, Valentin Thompson, William Donner, Catherine Baranyi, Máté Abdelkhalek, Fatma Department of Stochastics Budapest University of Technology and Economics Hungary Department of Computer Science University of Southern California United States Department of Computational and Applied Mathematics University of Chicago United States Department of Statistics Yale University United States UFR Sciences and Techniques Nantes University France Lindner College of Business University of Cincinnati United States Data Science and Analytics Institute University of Oklahoma in Norman United States Department of Statistics Mathematics and Insurance Faculty of Commerce Assiut University Egypt

A causal vector autoregressive (CVAR) model is introduced for weakly stationary multivariate processes, combining a recursive directed graphical model for the contemporaneous components and a vector autoregressive model longitudinally. Block Cholesky decomposition with varying block sizes is used to solve the model equations and estimate the path coefficients along a directed acyclic graph (DAG). If the DAG is decomposable, i.e. the zeros form a reducible zero pattern (RZP) in its adjacency matrix, then covariance selection is applied that assigns zeros to the corresponding path coefficients. Real life applications are also considered, where for the optimal order p ≥ 1 of the fitted CVAR(p) model, order selection is performed with various information *** Codes 15B05, 62M10, 65F99, 65F30 Copyright © 2022, The Authors. All rights reserved.

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

The Future of data Protection: Empowering data Security with Identity-Centric Blockchain Technology

The Future of Data Protection: Empowering Data Security with...

引用

Communication & Computing (WCONF), World Conference on

作者： A. Heney Juliet Vinithra Banu T K. Suresh Kumar D Kirubakaran M Dinesh K. Thilagam Department of Data Analytics Saveetha College of Liberal Arts and Sciences Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India Department of Mechanical Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai Tamil Nadu India Department of MBA Panimalar Engineering College Chennai Tamil Nadu India Department of Computer Science and Engineering R.M.K Engineering College Chennai Tamil Nadu India Department of VLSI Microelectronics Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences (SIMATS) Saveetha University Chennai Tamil Nadu India Department of Electronics and Communication Engineering Velammal Engineering College Chennai Tamil Nadu India

ISBN: (数字)9798350395327

ISBN: (纸本)9798350395334

In response to the formidable challenges surrounding data security, particularly in the face of evolving threats and vulnerabilities, this study introduces the Advanced Blockchain-Enhanced data Security Protocol (ABE-DSP) as a cutting-edge solution. Acknowledging the complexities of safeguarding sensitive information, ABE-DSP is a meticulously crafted and sophisticated framework that aims to fortify the security and integrity of data transactions through the integration of blockchain technology. This protocol addresses the pressing challenge of ensuring robust data security by placing a primary focus on enhancing overall system security and refining user authentication processes. Within the context of these challenges, the study explores the intricacies of ABE-DSP's design and implementation. Furthermore, the proposed method demonstrates its effectiveness by achieving a remarkable success rate, processing 97% of received packets with precision. This high percentage underscores the protocol's efficacy and reliability, positioning it as a robust and advanced tool for overcoming the contemporary challenges associated with data security. This study contributes valuable insights to the ongoing discourse on leveraging blockchain technology for identity-centric data security, offering a promising avenue for addressing and mitigating the challenges faced in the dynamic landscape of information protection.

关键词： Protocols Navigation data security Face recognition Refining Authentication Pressing Blockchains Reliability Protection

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：