检索结果-内蒙古大学图书馆

A parallel computing approach to CNN-based QbE-STD using kernel-based matching

JOURNAL OF SUPERcomputing 2025年第1期81卷 1-26页

作者： Gaonkar, Manisha Naik Thenkanidiyoor, Veena Dileep, Aroor Dinesh Natl Inst Technol Goa Comp Sci & Engn Dept Cuncolim 403703 Goa India Indian Inst Technol Dharwad Comp Sci & Engn Dept Belur Karnataka India Goa Coll Engn Comp Engn Dept Ponda 403401 Goa India

In query-by-example spoken term detection (QbE-STD), reference utterances are matched with an audio query. A matching matrix-based approach to QbE-STD needs to compute a matching matrix between a query and reference utterance using an appropriate similarity metric. Recent approaches use kernel-based matching to compute this matching matrix. The matching matrices are converted to grayscale images and given to a CNN-based classifier. In this work, we propose to speed up QbE-STD by computing the matching matrix in parallel using a coarse-grained data parallelism approach. We explore two approaches to coarse-grained data parallelism: In the first approach, we compute parts of the matching matrix in parallel and then combine them to form a matching matrix, while in the second one, we propose to compute matrices in parallel. We also propose to convert the matching matrices into two-colored images using the threshold and use these images for QbE-STD. The efficacy of the proposed parallel computation approach is explored using the TIMIT dataset.

关键词： Spoken term detection parallel computing Matching matrix Dynamic time warping Kernel-based matching

来源：评论

学校读者我要写书评

暂无评论

Long railway track modelling - A parallel computing approach

引用

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART F-JOURNAL OF RAIL AND RAPID TRANSIT 2025年第1期239卷 3-16页

作者： Agustin, Dan Wu, Qing Zhu, Shengyang Spiryagin, Maksym Cole, Colin Cent Queensland Univ Ctr Railway Engn Bruce Highway Rockhampton QLD 4702 Australia Southwest Jiaotong Univ State Key Lab Rail Vehicle Syst Chengdu Peoples R China

This paper presents the development of a dynamics model for long track sections. It is based on an established short track model that utilises the Finite Element Method to describe rails and block models to describe sleepers, ballast and subballast. By implementing a parallel computing method, this innovation enables the construction of a true long track model: by segmenting the long track into shorter segments that are easier to compute. The model facilitates simulations to be run in parallel, thereby permitting simultaneous calculations of various numerical track variables. The model employs a Message Passing Interface framework to seamlessly link the track segments, handling the flow of data among the computing cores designated to each subdivided section. This strategic framework allows the long track model with the capability to simulate tracks of virtually any length, with the only constraints being the available computational resources and time. The claimed contribution about modelling capability is verified using two case studies on a 6km-long track involving different practical and conceptual train operational scenarios: emergency braking and constant braking force with constant train speed. These case studies show the flexibility and scalability of the method and its capability to handle complex track dynamic systems.

关键词： Railway track dynamics zhai model parallel computing loop track long track

来源：评论

学校读者我要写书评

暂无评论

Semantically enhanced selective image encryption scheme with parallel computing

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 279卷

作者： Liu, Buyu Song, Wei Zheng, Mingyi Fu, Chong Chen, Junxin Wang, Xingwei Northeastern Univ Sch Comp Sci & Engn Shenyang 110819 Peoples R China Minist Educ Engn Res Ctr Secur Technol Complex Network Syst Shenyang Peoples R China Dalian Univ Technol Sch Software Dalian 116621 Peoples R China

Recently, an increasing number of ROI (regions of interest) encryption algorithms have been proposed to efficiently encrypt the sensitive regions of image. Due to the powerful feature extraction capabilities of deep learning (DP), many DP-based object detection models have been increasingly applied to ROI encryption. However, some models with a large number of parameters are inefficient and not suitable for real-time detection, and the detected ROI often include some redundant regions. Moreover, the following encryption operations are always in serial manner, leaving room for improvement. To address these issues, we present a semantically enhanced selective image encryption scheme with parallel computing. The deep salient object detection (SOD) model is first lightweighted to improve detection efficiency. Then, the sensitive region is cropped based on the boundary information from the output saliency map, resulting in an ROI that removes redundant regions without revealing sensitive object information. In encryption stage, the three color channels of each pixel are assigned to a group and encrypted in parallel to further improve the efficiency. Furthermore, to enhance the practicality, we embedded the side information of the ROI into the image, eliminating the need to separately distribute the image and the corresponding side information. Finally, we carry out security and efficiency analyses, and the results demonstrate that the proposed encryption scheme can enable efficient and secure detection of sensitive regions, along with corresponding encryption protection.

关键词： Image ROI encryption Salient object detection Chaos Simultaneous permutation-diffusion parallel computing

来源：评论

学校读者我要写书评

暂无评论

Stress-constrained topology optimization of geometrically nonlinear continuum structures by using parallel computing strategy

引用

ADVANCES IN ENGINEERING SOFTWARE 2025年 199卷

作者： Zhao, Lei Zheng, Jiaxin Cai, Jinhu Hu, Jiayi Han, Yan Rong, Jianhua Changsha Univ Sci & Technol Key Lab Safety Control Bridge Engn Minist Educ Changsha 410114 Hunan Peoples R China Changsha Univ Sci & Technol Sch Civil Engn Changsha 410076 Hunan Peoples R China Changsha Univ Sci & Technol Sch Automot & Mech Engn Changsha 410076 Hunan Peoples R China

Stress-constrained topology optimization under geometrical nonlinear conditions is still an open topic as it often encounter difficulties such as mesh distortion, inaccurate stress evaluation and low computational efficiency. For this purpose, this paper develops a novel parallel-computing based topology optimization methodology for geometrically nonlinear continuum structures with stress constraints. To alleviate the mesh distortions in the low-density regions, a smooth material interpolation scheme from with different penalization for the elastic and nonlinear stiffness is proposed. Moreover, a new hybrid stress finite element formulation is included into the geometrically nonlinear topology optimization to capture a more accurate stress distribution that is less sensitive to mesh distortions. Then, to improve the computational efficiency of geometrically nonlinear and sensitivity analysis, a parallel computing framework based on the assembly free iterative solution is established. Meanwhile, an efficient sparse matrix-vector multiplication strategy, which is applicable to solve the geometrically nonlinear problems, is proposed to exploit the computing power of GPU effectively. Finally, several numerical examples are given to illustrate the efficiency and feasibility of the proposed method.

关键词： Topology optimization Geometrical nonlinearity Hybrid stress finite element Stress constraint parallel computing Sparse matrix-vector multiplication

来源：评论

学校读者我要写书评

暂无评论

An introductory-level undergraduate CS course that introduces parallel computing

引用

JOURNAL OF parallel AND DISTRIBUTED computing 2025年 199卷

作者： Newhall, Tia Webb, Kevin C. Chaganti, Vasanta Danner, Andrew Swarthmore Coll Comp Sci Dept Swarthmore PA 19081 USA

We present the curricular design, pedagogy, and goals of an introductory-level course on computer systems that introduces parallel and distributed computing (PDC) to students who have only a CS1 background. With the ubiquity of multicore processors, cloud computing, and hardware accelerators, PDC topics have become fundamental knowledge areas in the undergraduate CS curriculum. As a result, it is increasingly important for students to learn a common core of introductory parallel and distributed computing topics and to develop parallel thinking skills early in their CS studies. Our introductory-level course focuses on three main curricular goals: 1) understanding how a computer runs a program, 2) evaluating system costs associated with running a program, and 3) taking advantage of the power of parallel computing. We elaborate on the goals and details of our course's key modules, and we discuss our pedagogical approach that includes active-learning techniques. We also include an evaluation of our course and a discussion of our experiences teaching it since Fall 2012. We find that the PDC foundation gained through early exposure in our course helps students gain confidence in their ability to expand and apply their understanding of PDC concepts throughout their CS education.

关键词： CS curriculum parallel computing Introductory CS

来源：评论

学校读者我要写书评

暂无评论

Globally optimal sequencing of optimal reactive dispatch control adjustments to minimize operational losses in transmission systems by graph shortest path, parallel computing, and dynamic programming

引用

EUROPEAN JOURNAL OF OPERATIONAL RESEARCH 2025年第1期320卷 239-255页

作者： Barros, Rafael Martins Lage, Guilherme Guimaraes Rabelo, Ricardo de Andrade Lira Univ Fed Ceara UFC Ave Profa Machadinha Lima s-n BR-63708825 Crateus CE Brazil Univ Fed Sao Carlos UFSCar Dept Engn Elect Rod Washington Luis SP-310 km 235 BR-13565905 Sao Carlos SP Brazil Campus Univ Minist Petronio Portella Univ Fed Piaui UFPI Dept Ciencia Computacao BR-64049550 Teresina PI Brazil

Minimizing operational losses in transmission systems through the Optimal Reactive Dispatch (ORD), a non- convex mixed-integer nonlinear programming problem, is crucial for operational cost reduction, resource optimization, and greenhouse gas emission mitigation. Besides all intricacies associated with solving ORDs, transmission system operators encounter the challenge of determining sequences in which ORD control adjustments must be implemented before significant changes occur in generators scheduled power output and system loading. Sequencing ORD control adjustments, in spite of not being novel, remains modestly scrutinized in the literature. This paper introduces a two-phase framework that tackles the globally optimal sequencing of n ORD control adjustments over n ! potential paths by solving the ORD to minimize operational losses in transmission systems in the first phase, and optimally sequencing ORD control adjustments employing fast power flow calculations, graph shortest path, parallel computing, and dynamic programming in the second phase. We discuss the framework's second phase asymptotic time complexity, which is exponential over factorial for brute-force approaches, and its capability to guarantee globally optimal paths toward minimal operational losses determined in the framework's first phase. ORD control adjustments for transmission systems with up to 27 controllable variables are benchmarked against two mixed-integer nonlinear programming solvers: BARON, a global non-convex solver, and Knitro, a local solver (assuming convexity around local optima). Globally optimal sequences of ORD control adjustments over n ! potential paths (more than 10 28 for sequencing 27 control adjustments) and average algorithm runtimes validate the straightforward application and, more importantly, effectiveness of such a comprehensive framework.

关键词： OR in energy Dynamic programming Graph shortest path Optimal power flow parallel computing

来源：评论

学校读者我要写书评

暂无评论

Time Complexity of Training DNNs With parallel computing for Wireless Communications

IEEE OPEN JOURNAL OF VEHICULAR TECHNOLOGY

引用

IEEE OPEN JOURNAL OF VEHICULAR TECHNOLOGY 2025年 6卷 359-384页

作者： Cong, Pengyu Yang, Chenyang Han, Shengqian Han, Shuangfeng Wang, Xiaoyun Beihang Univ Beijing 100191 Peoples R China China Mobile Res Inst Beijing 100053 Peoples R China

Deep neural networks (DNNs) have been widely used for learning various wireless communication policies. While DNNs have demonstrated the ability to reduce the time complexity of inference, their training often incurs a high computational cost. Since practical wireless systems require retraining due to operating in open and dynamic environments, it is crucial to analyze the factors affecting the training complexity, which can guide the DNN architecture selection and the hyper-parameter tuning for efficient policy learning. As a metric of time complexity, the number of floating-point operations (FLOPs) for inference has been analyzed in the literature. However, the time complexity of training DNNs for learning wireless communication policies has only been evaluated in terms of runtime. In this paper, we introduce the number of serial FLOPs (se-FLOPs) as a new metric of time complexity, accounting for the ability of parallel computing. The se-FLOPs metric is consistent with actual runtime, making it suitable for measuring the time complexity of training DNNs. Since graph neural networks (GNNs) can learn a multitude of wireless communication policies efficiently and their architectures depend on specific policies, no universal GNN architecture is available for analyzing complexities across different policies. Thus, we first use precoder learning as an example to demonstrate the derivation of the numbers of se-FLOPs required to train several DNNs. Then, we compare the results with the se-FLOPs for inference of the DNNs and for executing a popular numerical algorithm, and provide the scaling laws of these complexities with respect to the numbers of antennas and users. Finally, we extend the analyses to the learning of general wireless communication policies. We use simulations to validate the analyses and compare the time complexity of each DNN trained for achieving the best learning performance and achieving an expected performance.

关键词： Training Complexity theory Wireless communication Time complexity parallel processing Precoding Measurement Time measurement Runtime Hardware DNN parallel computing precoding se-FLOPs time complexity

来源：评论

学校读者我要写书评

暂无评论

A faster heterogeneous parallel computing method for Tucker decomposition

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2025年 152卷

作者： Peng, Xiaosong Yang, Laurence T. Li, Jie Jiang, Wenjun Hainan Univ Renmin Ave 58 Haikou 570228 Peoples R China Zhengzhou Univ Sci Ave 100 Zhengzhou 450001 Peoples R China Hunan Univ Lushan Rd S Changsha 410082 Peoples R China Hainan Univ Sch Informat & Commun Engn Haikou Hainan Peoples R China Hainan Univ Sch Comp Sci & Technol Haikou Hainan Peoples R China Huazhong Univ Sci & Technol Sch Cyber Sci & Engn Wuhan Peoples R China St Francis Xavier Univ Dept Comp Sci Antigonish NS Canada Zhengzhou Univ Sch Comp Sci & Artificial Intelligence Zhengzhou Peoples R China Hunan Univ Coll Comp Sci & Elect Engn Changsha Peoples R China

Artificial intelligence (AI) technology is developing explosively in application fields such as speech recognition, semantic understanding, and computer vision. In particular, the new generation of knowledge enhancement large language models have gradually become the infrastructure of social productivity. With the development of large models towards multi-mode, the input data and model parameters characterized by tensors are becoming increasingly large. This puts high demands on computation and storage. Tucker decomposition obtains the optimal low-rank representation of the natural tensor by factor matrices and a core tensor, reducing storage and computation requirements in big data and artificial intelligence applications. However, the existing Tucker decomposition methods show limited computational speed and convergence performance. In this paper, a general heterogeneous computing framework of the Tucker decomposition method is proposed, which analyzes the row independence of factor matrices and the column independence of Kruskal matrices, and updates the Kruskal matrices instead of the core tensor in a column-wise manner and factor matrices in a row-wise manner respectively to reduce the storage overhead in computation. Further, the proposed method employs a heterogeneous computing platform to speed up the computing bottlenecks and takes full advantage of finegrained parallel optimization technology to improve memory access efficiency. The experimental results show that the computation speed achieves a 3.1 to 75.4 times improvement compared to the latest methods. Among all the methods, it exhibits the best convergence performance.

关键词： Artificial intelligence Deep learning Tucker decomposition Tensor analysis Heterogeneous computing parallel computing

来源：评论

学校读者我要写书评

暂无评论

GPU-based multi-group discrete ordinates transport calculations: parallel computing implementation in STRAUM

引用

NUCLEAR ENGINEERING AND TECHNOLOGY 2025年第9期57卷

作者： Zhang, Ao Hong, Ser Gi Jeong, Seungil Chen, Jingen Hanyang Univ Dept Nucl Engn 222 Wangsimni Ro Seoul 04763 South Korea Chinese Acad Sci Inst Appl Phys Shanghai 201800 Peoples R China

Discrete ordinates (SN) method with unstructured meshes is highly appropriate for high-fidelity modeling and simulation of radiation shielding problems with complicated geometries. However, the large number of unknowns resulting from discretization of the transport equation on the spatial, angular, and energy variables, necessitates the use of parallel computing to achieve efficient solutions. In this work, a GPU-based SN transport sweep algorithm combined with a GPU-parallel multi-group Krylov subspace solver has been proposed and implemented in the STRAUM (SN Transport for Radiation Analysis with Unstructured Meshes) code. A group chunk decomposition method within the framework of the multi-group Krylov subspace solver has been applied to STRAUM to leverage multi-GPU parallel computing. For the Kobayashi-like and reactor pressure vessel problems, STRAUM typically runs faster by factors of 100 similar to 200 on a single NVIDIA GeForce RTX 4090 GPU and by factors of 70 similar to 120 on a single NVIDIA GeForce RTX 3080 Ti GPU than on a single AMD Ryzen 9 7900X CPU core. For the simulations on dual-GPU systems, the group chunk decomposition method achieves parallel computing efficiencies greater than 90% without degradation in convergence except for cases using very coarse angular divisions. Besides, this method reduces per-GPU memory usage by more than 40% and enables STRAUM to effectively simulate problems with up to ten billion unknowns using two RTX 4090 GPUs.

关键词： Multi-GPUs parallel computing Group chunk decomposition Unstructured SN transport

来源：评论

学校读者我要写书评

暂无评论

EFFSIP: Efficient forest fire system using IoT and parallel computing

引用

EGYPTIAN INFORMATICS JOURNAL 2025年 29卷

作者： Jaber, Khalid Mohammad Alkhatib, Ahmad A. A. Alzytoonah Univ Jordan Amman 1173 Jordan

The escalating issue of forest fires poses severe risks to ecosystems and human habitats, primarily due to the greenhouse effect and sudden climate changes. These fires, mostly occurring naturally, necessitate prompt detection and control. Addressing this, the paper introduces the Efficient Forest Fire System using an innovative Internet of Things (IoT) and parallel computing (EFFSIP) solution. The EFFSIP system leverages a wireless sensor network to efficiently detect and analyze fire behavior, providing real-time data on fire spread, speed, and direction. The system processes environmental parameters such as temperature (T), relative humidity (RH), and the Chandler Burning Index (CBI) against set thresholds to enable early fire detection. Designed for the challenging forest environment, the EFFSIP system prioritizes minimal power usage and simple components, crucial in areas with limited power resources. Its resilient design ensures that the wireless sensor network and sensor nodes withstand harsh weather and fire conditions, maintaining functionality and reliability. The system's efficiency is enhanced through the use of Pthreads for parallel processing, allowing multiple tasks such as data collection, processing, and fire checking to be handled concurrently. This approach significantly reduces response time by processing sensor data in parallel, ensuring rapid detection and accurate prediction of fire behavior. Field tests of the EFFSIP system in various Jordanian forest locations, including Burgish-Ajloun, demonstrated its effectiveness. The system detected afire at 10:42 am with an initial CBI value of 32.5, which increased sharply to 97.92 as the fire progressed. Additionally, the system recorded a decrease in humidity from 53% to 22% and an increase in temperature from 28 degrees C to 48.6 degrees C. For example, the system predicted afire at node 12 would occur in 0.477 min, allowing preemptive actions to betaken before the fire started. The system's abilit

关键词： Forest fires Internet of Things parallel computing WSN Fire detection Fire prediction Fire behavior analysis

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：