检索结果-内蒙古大学图书馆

13th IEEE International Conference on Communication Systems and Network Technologies, CSNT 2024

作者： Dwivedi, Shashi Prakash Himabindu, Modi Revathi, V. Gupta, Manish Patel, Neeraj Almusawi, Muntather Lloyd Institute of Engineering & Technology Uttar Pradesh Greater Noida201322 India Institute of Aeronautical Engineering Dundigal Hyderabad India New Horizon College of Engineering Department of Applied Sciences Bangalore India Lovely Professional University Phagwara India Ies Insititute of Technology and Management Ies University Department of Computer Science & Engineering M. P. Bhopal India The Islamic University Najaf Iraq

ISBN: (纸本)9798350305463

Crime pattern analysis and other forms of predictive policing are becoming indispensable tools for today's police forces. Hybrid Blockchain-Machine Learning Predictive Policing (HBL-PP) is a new method introduced by this study that aims to transform the sector by bringing together the best features of blockchain technology and machine learning algorithms. SecureCrimeChain guarantees the safe handling of crime-related data, while Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) are used for advanced crime pattern analysis in HBL-PP. When compared to conventional approaches, HBL-PP performs much better in experimental evaluations. SecureCrimeChain guarantees the best degree of accuracy, precision, recall, and F1 score, outperforming other techniques. DeepCrimeNet has comparable performance and comes in a close second. FairPredict Pro, although fairness-aware, maintains a balance between equity and prediction accuracy. © 2024 IEEE.

关键词： Crime

来源：评论

学校读者我要写书评

暂无评论

High-performance computing at a crossroads

引用

science (New York, N.Y.) 2025年第6736期387卷 829-831页

作者： Deelman, Ewa Dongarra, Jack Hendrickson, Bruce Randles, Amanda Reed, Daniel Seidel, Edward Yelick, Katherine Information Sciences Institute University of Southern California Marina del Rey CA United States Department of Electrical Engineering and Computer Science University of Tennessee Knoxville TN United States Oak Ridge National Laboratory Oak Ridge TN United States Department of Mathematics University of Manchester Manchester United Kingdom Computing Directorate Lawrence Livermore National Laboratory Livermore CA United States Department of Biomedical Engineering Duke University Durham NC United States Scientific Computing and Imaging Institute University of Utah Salt Lake City UT United States Office of the President University of Wyoming Laramie WY United States Department of Electical Engineering and Computer Sciences University of California Berkeley Berkeley CA United States

Long-term plans and comprehensive vision are needed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fast multiplication of random dense matrices with sparse matrices

Fast multiplication of random dense matrices with sparse mat...

引用

International Symposium on Parallel and Distributed Processing (IPDPS)

作者： Tianyu Liang Riley Murray Aydın Buluç James Demmel Electrical Engineering and Computer Science Department UC Berkeley Computational Research Division Lawrence Berkeley National Lab International Computer Science Institute Sandia National Laboratories

ISBN: (数字)9798350387117

ISBN: (纸本)9798350387124

This work focuses on accelerating the multiplication of a dense random matrix with a (fixed) sparse matrix, which is frequently used in sketching algorithms. We develop a novel scheme that takes advantage of blocking and recomputation (on-the-fly random number generation) to accelerate this operation. The techniques we propose decrease memory movement, thereby increasing the algorithm’s parallel scalability in shared memory architectures. On the Intel Frontera architecture, our algorithm can achieve 2x speedups over libraries such as Eigen and Intel MKL on some examples. In addition, with 32 threads, we can obtain a parallel efficiency of up to 45%.We also present a theoretical analysis for the memory movement lower bound of our algorithm, showing that under mild assumptions, it’s possible to beat the data movement lower bound of general matrix-matrix multiply (GEMM) by a factor of M, where M is the cache size. Finally, we incorporate our sketching method into a randomized algorithm for overdetermined least squares with sparse data matrices. Our results are competitive with SuiteSparse for highly overdetermined problems; in some cases, we obtain a speedup of 10x over SuiteSparse.

关键词： Distributed processing Scalability Instruction sets Memory management Memory architecture Libraries Sparse matrices

来源：评论

学校读者我要写书评

暂无评论

Abnormal Vibration Detection by $2\mathrm{D}$ Digital Image Correlation Analysis

Abnormal Vibration Detection by $2\mathrm{D}$ Digital Image ...

引用

IEEE Symposium on Product Compliance engineering - Asia (ISPCE-CN)

作者： Yuan-Heng Sun Hao-Chun Yue Yan-Ann Chen Cheng-Kuan Lin Yu-Chee Tseng Department of Computer Science National Yang Ming Chiao Tung University Taiwan Industrial Technology Research Institute Taiwan Department of Computer Science and Engineering Yuan Ze University Taiwan

ISBN: (数字)9798331523008

ISBN: (纸本)9798331523015

In industrial IoT, sensors are embedded in machinery to monitor critical factors such as bearing wear, motor degradation, and environmental conditions. Traditional sensor-based IoT setups are costly and invasive. With the advancements in computer vision, image-based defect detection has made significant progress across various domains. This study proposes to integrate deep learning, via a high-speed camera, with DIC (digital image correlation) techniques for non-intrusive, full-field anomaly detection of a vibrating object, such as industrial motors. Through image processing, the surface of the vibrating object is partitioned into sub-regions, each undergone FFT analysis. By combining the results from all sub-regions, the normal/abnormal state of the vibrating object is determined. Experimental results demonstrate the feasibility of this approach. We also contribute a dataset with detailed annotations collected from our experimental environment for future work.

关键词： Vibrations Deep learning Correlation Digital images Motors Cameras Sensors Monitoring Anomaly detection Surface treatment

来源：评论

学校读者我要写书评

暂无评论

Optimizing Renewable Energy Integration in Smart Grids through IoT-Driven Management Systems 2

Optimizing Renewable Energy Integration in Smart Grids throu...

引用

2nd International Conference on Advancement in Computation and computer Technologies, InCACCT 2024

作者： Dankan Gowda, V. Surya, S.G. Kumar, N.M.G. Prasad, K.D.V. Satya Prasad, V.K. Kaur, Mandeep BMS Institute of Technology and Management Department of Electronics and Communication Engineering Bangalore India SCMS School of Engineering and Technology Karukutty Department of Computer science and Engineering Kerala Ernakulam India Mohan Babu University Sree Vidyanikethan Engineering College Department of Electrical and Electronics Engineering Andhar Pradesh Tirupathi India Symbiosis Institute of Business Management Department of Research Hyderabad India Pune India Symbiosis Institute of Business Management Hyderabad India Punjabi University Department of Electronics and Communication Engineering Punjab Patiala India

ISBN: (纸本)9798350371314

The incorporation of renewable energy sources into smart grid systems does basically signify a significant move of achieving sustainable energy consumption and management. On the contrary, due to the unpredictability of renewables and the energy grids' increased complexity, there remain certain issues to be tackled. This study explores enhancing of the capacity of energy to be derived from renewable sources through IoT linked management systems. Through the utilization of modern IoT technologies which contribute towards maximizing the effectiveness of smart grid operations the study aims to accomplish this thereby enhancing the efficiency, reliability, sustainability of smart grids, which in turn facilitate the balancing of energy supply and demand and optimal energy distribution followed by the ready integration of renewable energy sources. This paper focuses on a holistic solution that includes the utilization of IoT sensors and devices to perform real-time energy monitoring, devising smart algorithms for an energy management system, and harnessing the power of cloud computing to analyze data. This part involves implementation explaining the practical steps done to work out the framework: system's architecture design, IoT devices selection, data management activities and the control mechanism's integration. Simulation results represent the ability of distributed IoT systems to advance smart grid practices by showing a decrease in energy transportation losses, AC grid stability and the integration of RES potential. Problems that come up during the course of project, like scalability and security, are described, and solutions to those problems proposed. © 2024 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Degradability of Modified Landau-Streater Type Low-Noise Quantum Channels in High Dimensions

arXiv

引用

arXiv 2024年

作者： Lo, Yun-Feng Lee, Yen-Chi Hsieh, Min-Hsiu Department of Electrical and Computer Engineering Georgia Institute of Technology AtlantaGA United States Quantum Computing Research Center Hon-Hai Research Institute Taipei Taiwan

This paper delves into the degradability of quantum channels, with a specific focus on high-dimensional extensions of qubit depolarizing channels in low-noise regimes. We build upon the foundation of η-approximate degradable channels, as established by Sutter et al. and Leditzky et al., to introduce and examine the Modified Landau-Streater (MLS) channels. These channels expand upon the qubit depolarizing and the recently proposed modified Werner-Holevo channels by Roofeh and Karimipour, extending them to higher-dimensional Hilbert spaces (with dimension d = 2j + 1, where j are positive half-integers). Our investigation centers on their conformity to the O(Ε2) degradability pattern, aligning with and extending Leditzky et al.’s findings in the d = 2 case. By replacing the SU(2) generators with SU(d) in our treatment, we may explore the potential inclusion of generalized Gell-Mann matrices in future research. Our results enhance the understanding of super-additivity in quantum channels within the low-noise regime and lay the groundwork for future explorations into conditions and structures that could lead to O(Ε2) degradability across a broader spectrum of quantum channels. © 2024, CC BY.

关键词： Quantum entanglement

来源：评论

学校读者我要写书评

暂无评论

Transition Waste Optimization for Coded Elastic computing

引用

IEEE Transactions on Information Theory 2023年第7期69卷 4442-4465页

作者： Dau, Son Hoang Gabrys, Ryan Huang, Yu-Chih Feng, Chen Luu, Quang-Hung Alzahrani, Eidah J. Tari, Zahir The School of Computing Technologies RMIT University MelbourneVIC3000 Australia The California Institute for Telecommunications and Information Technology University of California La Jolla San DiegoCA92093 United States The Institute of Communications Engineering National Yang Ming Chiao Tung University Hsinchu30010 Taiwan KelownaBCV1V 1V7 Canada The Department of Computing Technologies School of Science Computing and Engineering Technologies Swinburne University of Technology HawthornVIC3122 Australia The Department of Civil Engineering Monash University ClaytonVIC3800 Australia The Department of Computer Science Al-Baha University Al Bahah65545 Saudi Arabia

Distributed computing, in which a resource-intensive task is divided into subtasks and distributed among different machines, plays a key role in solving large-scale problems. Coded computing is a recently emerging paradigm where redundancy for distributed computing is introduced to alleviate the impact of slow machines (stragglers) on the completion time. We investigate coded computing solutions over elastic resources, where the set of available machines may change in the middle of the computation. This is motivated by recently available services in the cloud computing industry (e.g., EC2 Spot, Azure Batch) where low-priority virtual machines are offered at a fraction of the price of the on-demand instances but can be preempted on short notice. Our contributions are three-fold. We first introduce a new concept called transition waste that quantifies the number of tasks existing machines must abandon or take over when a machine joins/leaves. We then develop an efficient method to minimize the transition waste for the cyclic task allocation scheme recently proposed in the literature (Yang et al. ISIT’19). Finally, we establish a novel solution based on finite geometry achieving zero transition wastes given that the number of active machines varies within a fixed range. © 2023 IEEE.

关键词： Toys

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach for Song Recommendation System Using Deep Neural Networks

A Novel Approach for Song Recommendation System Using Deep N...

引用

applied Intelligence and computing (AIC), IEEE World Conference on

作者： Gunde Eliyajer B Natarajan R Bhuvaneswari R Elakkiya Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India Department of Computer Science Birla Institute of Technology and Science Dubai United Arab Emirates

The song recommendation model is a powerful tool for improving user experience and engagement with streaming music services. Depending on user emotion recognition, the proposed Song suggester Convolutional Neural Network (CNN). The proposed model uses facial expressions to recognize the user's emotions, which are then used to recommend songs that match their mood. The model is trained on a large dataset of facial expressions and songs with emotional labels. The facial expression images are pre-processed using various image augmentation techniques and then fed into the CNN model for feature extraction. The extracted features are then used to predict the user's emotions, which are mapped to the corresponding emotional labels of songs. The recommended songs are then presented to the user, who can choose to add them to their playlist. The proposed model outperforms existing emotion-based song recommendation models and has the potential to enhance user experience in music streaming services with an accuracy of 93%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards harmless rawlsian fairness regardless of demographic prior 24

Towards harmless rawlsian fairness regardless of demographic...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Xuanqian Wang Jing Li Ivor W. Tsang Yew-Soon Ong School of Computer Science and Engineering Beihang University China Institute of High-Performance Computing Agency for Science Technology and Research Singapore and Centre for Frontier AI Research Agency for Science Technology and Research Singapore Institute of High-Performance Computing Agency for Science Technology and Research Singapore and Centre for Frontier AI Research Agency for Science Technology and Research Singapore and College of Computing and Data Science Nanyang Technological University Singapore

ISBN: (纸本)9798331314385

Due to privacy and security concerns, recent advancements in group fairness advocate for model training regardless of demographic information. However, most methods still require prior knowledge of demographics. In this study, we explore the potential for achieving fairness without compromising its utility when no prior demographics are provided to the training set, namely harmless Rawlsian fairness. We ascertain that such a fairness requirement with no prior demographic information essential promotes training losses to exhibit a Dirac delta distribution. To this end, we propose a simple but effective method named VFair to minimize the variance of training losses inside the optimal set of empirical losses. This problem is then optimized by a tailored dynamic update approach that operates in both loss and gradient dimensions, directing the model towards relatively fairer solutions while preserving its intact utility. Our experimental findings indicate that regression tasks, which are relatively unexplored from literature, can achieve significant fairness improvement through VFair regardless of any prior, whereas classification tasks usually do not because of their quantized utility measurements. The implementation of our method is publicly available at https://***/wxqpxw/VFair.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fidelity and diversity metrics for validating hierarchical synthetic data: Application to residential energy demand

Fidelity and diversity metrics for validating hierarchical s...

引用

2022 IEEE International Conference on Big Data, Big Data 2022

作者： Thorve, Swapna Vullikanti, Anil Mortveit, Henning S Swarup, Samarth Marathe, Madhav V. Department of Computer Science Biocomplexity Institute University of Virginia United States Department of Engineering Systems and Environment Biocomplexity Institute University of Virginia United States Network Systems Science and Advanced Computing Biocomplexity Institute University of Virginia United States

ISBN: (纸本)9781665480451

Synthetic data is gaining rapid importance in many application domains due to privacy issues, bias, lack, or simply unavailability of real data. It is important that the synthetic data be a good representation of real data for successfully completing the task at hand. Thus, devising characteristic validation metrics is crucial and remains an open problem in many domains (e.g., image generation). Good validation metrics must be able to disentangle the differences between the quality and the variability coverage of the synthetic data. We propose to use a 3-dimensional metric (precision α, recall β, coverage γ) to describe the fidelity and diversity of the synthetic data. In this paper, we improve on existing definitions of precision, recall, and coverage to extend to large scale time series data. Traditional nearest neighbor manifolds from the literature are replaced by unsupervised learning techniques such as clustering to deal with large scale fine resolution time series while computing the validation metrics. The proposed metrics are employed to validate synthetic data in the domain of residential energy demand. In addition, we extend these definitions to datasets that have a natural hierarchical structure. We propose a hierarchical data-tree model in which precision, recall, and coverage can be computed at multiple inherent (and/or custom) levels of groupings of the data. © 2022 IEEE.

关键词： Time series

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：