检索结果-内蒙古大学图书馆

Find truth in the hands of the few:acquiring specific knowledge with crowdsourcing

Frontiers of computer science 2021年第4期15卷 5-16页

作者： Tao HAN Hailong SUN Yangqiu SONG Yili FANG Xudong LIU SKLSDE Lab School of Computer Science and EngineeringBeihang UniversityBeijing 100191China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang UniversityBeijing 100191China Department of Computer Science and Engineering Hong Kong University of Science and TechnologyClearwater BayHong Kong 999077China School of Computer and Information Engineering Zhejiang Gongshang UniversityHangzhou 310018China

Crowdsourcing has been a helpful mechanism to leverage human intelligence to acquire useful ***,when we aggregate the crowd knowledge based on the currently developed voting algorithms,it often results in common knowledge that may not be *** this paper,we consider the problem of collecting specific knowledge via *** the help of using external knowledge base such as WordNet,we incorporate the semantic relations between the alternative answers into a probabilisticmodel to determine which answer is more *** formulate the probabilistic model considering both worker’s ability and task’s difficulty from the basic assumption,and solve it by the expectation-maximization(EM)*** increase algorithm compatibility,we also refine our method into semi-supervised *** results show that our approach is robust with hyper-parameters and achieves better improvement thanmajority voting and other algorithms when more specific answers are expected,especially for sparse data.

关键词： crowdsourcing knowledge acquisition EM algorithm label aggregation

来源：评论

学校读者我要写书评

暂无评论

Correction of Read Biases Induced by Complex Reference Genome Regions for Improving Copy Number Variation Detection Using a Gaussian Mixture Model

Correction of Read Biases Induced by Complex Reference Genom...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Wang, Xuwen Chang, Zhili Wang, Shenjie Liu, Ruoyu Liu, Yuqian Zhu, Xiaoyan Shao, Yang Lai, Xin Yang, Shuanying Wang, Jiayin Second Affiliated Hospital Xi'an Jiaotong University Department of Respiratory Medicine Xi'an710003 China Xi'an Jiaotong University School of Computer Science and Technology Xi'an710049 China Xi'an Jiaotong University Shaanxi Engineering Research Center of Medical and Health Big Data Xi'an710049 China Nanjing Geneseeq Technology INC. China

ISBN: (纸本)9798350386226

Copy number variations are crucial in cancer research, but their detection through next-generation sequencing is often hindered by read biases, particularly in complex genomic regions. Existing bias-correction methods address common issues like GC content but often fail in regions with repetitive sequences or segmental duplications, leading to false-positive CNVs. We propose refMask, a hybrid Gaussian model-based method that dynamically identifies low-confidence regions in the reference genome, correcting read biases and improving CNV detection accuracy. By integrating features from hg38 and T2T genomes, refMask tailors a custom blacklist for each sequencing sample, enhancing the reliability of CNV detection across diverse conditions. Our method provides a more accurate and flexible solution compared to current fixed blacklists, offering improved performance in challenging genomic regions. © 2024 IEEE.

关键词： Copy number variation Gaussian model Next-generation sequencing Read biase

来源：评论

学校读者我要写书评

暂无评论

Poplar: Efficient Scaling of Distributed DNN Training on Heterogeneous GPU Clusters

arXiv

引用

arXiv 2024年

作者： Zhang, Wenzheng Hu, Yang Shi, Jing Bai, Xiaoying School of Computer Science Peking University China Information Research Center of Military Science PLA Academy of Military Science China Advanced Institute of Big Data China

Scaling Deep Neural Networks (DNNs) requires significant computational resources in terms of GPU quantity and compute capacity. In practice, there usually exists a large number of heterogeneous GPU devices due to the rapid release cycle of GPU products. It is highly needed to efficiently and economically harness the power of heterogeneous GPUs, so that it can meet the requirements of DNN research and development. The paper introduces Poplar, a distributed training system that extends Zero Redundancy Optimizer (ZeRO) with heterogeneous-aware capabilities. We explore a broader spectrum of GPU heterogeneity, including compute capability, memory capacity, quantity and a combination of them. In order to achieve high computational efficiency across all heterogeneous conditions, Poplar conducts fine-grained measurements of GPUs in each ZeRO stage. We propose a novel batch allocation method and a search algorithm to optimize the utilization of heterogeneous GPUs clusters. Furthermore, Poplar implements fully automated parallelism, eliminating the need for deploying heterogeneous hardware and finding suitable batch size. Extensive experiments on three heterogeneous clusters, comprising six different types of GPUs, demonstrate that Poplar achieves a training throughput improvement of 1.02 ∼ 3.92x over current state-of-the-art heterogeneous training systems. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Resource abstraction and data placement for distributed hybrid memory pool

引用

Frontiers of computer science 2021年第3期15卷 47-57页

作者： Tingting CHEN Haikun LIU Xiaofei LIAO Hai JIN National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab/Gluster and Grid Computing LabSchool of Gomputing Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China

Emerging byte-addressable non-volatile memory(NVM)technologies offer higher density and lower cost than DRAM,at the expense of lower performance and limited write *** have been many studies on hybrid NVM/DRAM memory management in a single physical ***,it is still an open problem on how to manage hybrid memories efficiently in a distributed *** paper proposes Alloy,a memory resource abstraction and data placement strategy for an RDMA-enabled distributed hybrid memory pool(DHMP).Alloy provides simple APIs for applications to utilize DRAM or NVM resource in the DHMP,without being aware of the hardware details of the *** propose a hotness-aware data placement scheme,which combines hot data migration,data replication and write merging together to improve application performance and reduce the cost of *** evaluate Alloy with several micro-benchmark workloads and public benchmark *** results show that Alloy can significantly reduce the DRAM usage in the DHMP by up to 95%,while reducing the total memory access time by up to 57%compared with the state-of-the-art approaches.

关键词： load balance distributed hybrid memory clouds

来源：评论

学校读者我要写书评

暂无评论

Mamba in Speech: Towards an Alternative to Self-Attention

IEEE Transactions on Audio, Speech and Language Processing

引用

IEEE Transactions on Audio, Speech and Language Processing 2025年 33卷 1933-1948页

作者： Xiangyu Zhang Qiquan Zhang Hexin Liu Tianyi Xiao Xinyuan Qian Beena Ahmed Eliathamby Ambikairajah Haizhou Li Julien Epps School of Electrical Engineering and Telecommunications The University of New South Wales (UNSW) Sydney NSW Australia College of Computing and Data Science Nanyang Technological University Singapore School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China Guangdong Provincial Key Laboratory of Big Data Computing The Chinese University of Hong Kong (Shenzhen) Shenzhen China Shenzhen Research Institute of Big Data Shenzhen China

Transformer and its derivatives have achieved success in diverse tasks across computer vision, natural language processing, and speech processing. To reduce the complexity of computations within the multi-head self-attention mechanism in Transformer, Selective State Space Models (i.e., Mamba) were proposed as an alternative. Mamba exhibited its effectiveness in natural language processing and computer vision tasks, but its superiority has rarely been investigated in speech signal processing. This paper explores solutions for applying Mamba to speech processing by discussing two typical speech processing tasks: speech recognition, which requires semantic and sequential information, and speech enhancement, which focuses primarily on sequential patterns. The experimental results confirm that bidirectional Mamba (BiMamba) consistently outperforms vanilla Mamba, highlighting the advantages of a bidirectional design for speech processing. Moreover, experiments demonstrate the effectiveness of BiMamba as an alternative to the self-attention module in the Transformer model and its derivates, particularly for the semantic-aware task. The crucial technologies for transferring Mamba to speech are then summarized in ablation studies and the discussion section, offering insights for extending this research to a broader scope of tasks.

关键词： Transformers Speech enhancement Speech recognition Convolution Computational modeling Natural language processing Training Random access memory Kernel Semantics

来源：评论

学校读者我要写书评

暂无评论

Enhancing malware detection performance: leveraging K-Nearest Neighbors with Firefly Optimization Algorithm

引用

Multimedia Tools and Applications 2025年第12期84卷 10071-10094页

作者： Al Saaidah, Adeeb Abualhaj, Mosleh M. Shambour, Qusai Y. Abu-Shareha, Ahmad Adel Abualigah, Laith Al-Khatib, Sumaya N. Alraba’nah, Yousef H Department of Networks and Cybersecurity Al-Ahliyya Amman University Amman Jordan Department of Software Engineering Al-Ahliyya Amman University Amman Jordan Department of Data Science and Artificial Intelligence Al-Ahliyya Amman University Amman Jordan Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman19328 Jordan Research Center University of Tabuk Tabuk71491 Saudi Arabia MEU Research Unit Middle East University Amman11831 Jordan Department of Electrical and Computer Engineering Lebanese American University Byblos13-5053 Lebanon College of Engineering Yuan Ze University Taoyuan32003 Taiwan Applied Science Research Center Applied Science Private University Amman11931 Jordan School of Engineering and Technology Sunway University Malaysia Petaling Jaya27500 Malaysia

Malware detection plays a crucial role in ensuring robust cybersecurity amidst the ever-evolving cyber threats. This research paper delves into the realm of machine learning (ML) algorithms for malware detection, with a specific emphasis on the K-Nearest Neighbors (KNN) algorithm, utilizing tailored parameter settings and the Firefly Optimization Algorithm (FOA). The study leverages the MalMem-2022 dataset to assess the efficacy of KNN and KNN with FOA in malware detection. The impact of parameter tuning and feature selection on classification is elucidated by comparing the performance of both approaches. Encouragingly, the results reveal promising advancements in one of the multiclass classification scenarios when employing KNN with FOA, yielding noteworthy enhancements in Accuracy, Recall, Precision, Matthews Correlation Coefficient, TNR, and F1-score by 2.65%, 2.65%, 2.47%, 3.59%, 0.17%, and 2.61%, respectively. These findings accentuate the significance of optimizing KNN’s parameters and implementing FOA for feature selection, culminating in heightened accuracy in malware detection. The symbiotic fusion of KNN and FOA exhibits remarkable effectiveness in augmenting the classification model’s performance, thus offering valuable insights for bolstering cybersecurity measures. Adopting ML algorithms, particularly KNN with specific parameter settings and FOA, presents a promising avenue for enhancing malware detection capabilities. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

An Unsupervised Network Architecture Search Method for Solving Partial Differential Equations

arXiv

引用

arXiv 2025年

作者： Li, Qing Chen, Jingrun School of Artificial Intelligence and Data Science University of Science and Technology of China China School of Mathematical Sciences Suzhou Institute for Advanced Research University of Science and Technology of China China Suzhou Big Data & AI Research and Engineering Center China

Solving partial differential equations (PDEs) has been indispensable in scientific and engineering applications. Recently, deep learning methods have been widely used to solve high-dimensional problems. The interplay between deep learning and numerical PDEs has resulted in a variety of new methods, one of which is the physics-informed neural network (PINN). Typically, a deep learning method has three main components: a neural network, a loss function, and an optimizer. While the construction of the loss function is rooted in the definition of solution space, how to choose a optimal neural network is somewhat ad hoc, leaving much room for improvement. In the framework of PINN, we propose an unsupervised network architecture search method for solving PDEs, termed PINN-DARTS, which applies the differentiable architecture search (DARTS) to find the optimal network architecture structure in a given set of neural networks. In this set, the number of layers and the number of neurons in each layer can change. In the searching phase, both network and architecture parameters are updated simultaneously, so the running time is close to that of PINN with a pre-determined network structure. Unlike available works, our approach is unsupervised and purely based on the PDE residual without any prior usage of solutions. PINN-DARTS outputs the optimal network structure as well as the associated numerical solution. The performance of PINN-DARTS is verified on several benchmark PDEs, including elliptic, parabolic, wave, and Burgers’ equations. Compared to traditional architecture search methods, PINN-DARTS achieves significantly higher architectural accuracy. Another interesting observation is that both the solution complexity and the PDE type have a prominent impact on the optimal network architecture. Our study suggests that architectures with uneven widths from layer to layer may have superior performance across different solution complexities and different PDE types. Copyright © 202

关键词： Wave equations

来源：评论

学校读者我要写书评

暂无评论

Random Forest and Sobol Method Based data center PUE Prediction 12

Random Forest and Sobol Method Based Data Center PUE Predict...

引用

12th IEEE International Conference on Information and Communication Networks, ICICN 2024

作者： Yan, Longchuan Luan, Zhaofang He, Ling Jiang, Congfeng Liu, Junming Xu, Chuanqi Zhang, Liangbin State Grid Corporation of China Information & Telecommunication Branch Beijing China School of Computer Science and Technology Hangzhou Dianzi University Hangzhou China Information Technology Center Hangzhou Dianzi University Hangzhou China College of Big Data and Software Engineering Zhejiang Wanli University Ningbo China

ISBN: (纸本)9798350355802

data centers are critical infrastructures that support a multitude of business loads such as big data, artificial intelligence, and cloud computing. While providing the necessary computing power, the problem of high energy consumption in data centers has become a major obstacle limiting their scale-up, reliability and quality of service. Improving the power usage effectiveness (PUE) of data centers is an important way to improve the energy efficiency of data centers. With the development of theories and methods of machine learning, modeling, analysis and prediction of data center energy consumption using machine learning techniques has become a feasible option. In this study, several accurate PUE prediction models are constructed using neural networks and machine learning techniques for the PUE of a small air-cooled data center in actual operation, among which the mean absolute error of the optimal model reaches 0.29%. In addition, this paper also uses Random Forest and Sobol methods to model and conduct sensitivity analyses of key factors affecting data center PUE, revealing the relationship between data center operating parameters and PUE, and finding that the cooling system exhibits different energy consumption patterns under different IT equipment power conditions, which has a decisive impact on PUE. Based on these sensitivity analyses, we argue that for small air-cooled data centers, improving internal insulation and humidity is an important strategy for optimizing PUE. © 2024 IEEE.

关键词： Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

data-Driven Active Power Dispatch for Wind Farms 13

Data-Driven Active Power Dispatch for Wind Farms

引用

13th IEEE data Driven Control and Learning Systems Conference, DDCLS 2024

作者： Jiao, Xuguo Zhang, Daoyuan Wang, Xin Ma, Zhaoxing Zhang, Zhenyong Liu, Wenfeng School of Information and Control Engineering Qingdao University of Technology Qingdao266520 China College of Control Science and Engineering Zhejiang University State Key Laboratory of Industrial Control Technology Hangzhou310027 China Ministry of Education Shandong Computer Science Center Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Jinan250014 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan250014 China College of Computer Science and Technology Guizhou University State Key Laboratory of Public Big Data Guiyang550025 China School of Civil Engineering Qingdao University of Technology Qingdao266520 China

ISBN: (纸本)9798350361674

Active power dispatch of wind farms plays an important role in power grid scheduling. In this paper, a data-driven active power dispatch strategy for wind farms is proposed, which uses the key point of minimizing the standard deviation of wind turbines' output power series to reduce their fluctuations. First, to build the optimization problem, the historical active power output data of each wind turbine is collected from the Supervisory Control And data Acquisition (SCADA) system. Then, the objective function is developed based on the idea of minimizing the standard deviation of the output power time series. Meanwhile, considering the constraints of wind turbines' output power and active power balance of the grid, the feasible domain of the cost function is constructed. Further, to solve the proposed nonlinear optimization problem with equality and inequality constraints, the trust region interior point method (TRIPM) is employed to explore optimal solution within the feasible domain. Finally, actual data collected from wind farms is used to test effectiveness of the designed approach and experimental results show that our method can achieve better output power smoothing performance than conventional Proportional Dispatch (PD) method. © 2024 IEEE.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Unlearnable 3D Point Clouds: Class-wise Transformation Is All You Need

arXiv

引用

arXiv 2024年

作者： Wang, Xianlong Li, Minghui Liu, Wei Zhang, Hangtao Hu, Shengshan Zhang, Yechao Zhou, Ziqi Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Hubei Engineering Research Center on Big Data Security Hubei Key Laboratory of Distributed System Security School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China

Traditional unlearnable strategies have been proposed to prevent unauthorized users from training on the 2D image data. With more 3D point cloud data containing sensitivity information, unauthorized usage of this new type data has also become a serious concern. To address this, we propose the first integral unlearnable framework for 3D point clouds including two processes: (i) we propose an unlearnable data protection scheme, involving a class-wise setting established by a category-adaptive allocation strategy and multi-transformations assigned to samples;(ii) we propose a data restoration scheme that utilizes class-wise inverse matrix transformation, thus enabling authorized-only training for unlearnable data. This restoration process is a practical issue overlooked in most existing unlearnable literature, i.e., even authorized users struggle to gain knowledge from 3D unlearnable data. Both theoretical and empirical results (including 6 datasets, 16 models, and 2 tasks) demonstrate the effectiveness of our proposed unlearnable framework. Our code is available at https://***/CGCL-codes/UnlearnablePC Copyright © 2024, The Authors. All rights reserved.

关键词：

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：