检索结果-内蒙古大学图书馆

international conference on Signal processing and Communication (ICSC)

作者： Radhika Gupta Priti Kumari Rashi Jaiswal Tukur Gupta Department of Electronics & Communication Engineering Ajay Kumar Garg Engineering College Ghaziabad India

ISBN: (数字)9798331511890

ISBN: (纸本)9798331511906

Shift registers with parallel-In Serial-Out (PISO) functionality are essential components in digital electronics. they ease data transmission and minimize the amount of wiring needed by converting parallel data into a serial format, and hence used in digital communications, signal processing, and data storage. the significance of these shift registers and their guiding principles is anticipated to grow as digital technology develops, highlighting the need for a thorough analysis of their design constraints. Hence, area and power being two main design constraints for digital circuits need to be estimated. these estimates can be made using current commercial tools, however doing so requires more time because full design cycles must be followed. therefore, challenges for designers lie in accurate estimation of resource utilization and power dissipation at the early stages of designing while working under a tight deadline. this paper develops area and power estimation models for PISO shift register circuit using the curve fitting and regression technique in MATLAB. Vivado Design Suite (2014.4) is used to simulate and synthesize these circuits for various input/output (I/O) configurations targeted to Zynq-family Field-Programmable Gate Array (FPGA) device (xc7z020clg484-1). Furthermore, a user-friendly graphical user interface (GUI) is developed using Python Tkinter prompting designers to enter minimum input parameters and providing quick estimates of look-up tables (LUTs), flip-flops (FFs) and total on-chip power. these values predicted using GUI are compared with those obtained using Vivado tool. Comparison results infer that estimation errors lie in a comparable range. Hence, the proposed models and GUI expedite the design process by early and accurate estimation of area and power for FPGA-based PISO shift registers.

关键词： Machine learning algorithms Signal processing algorithms Predictive models Shift registers Prediction algorithms Table lookup Resource management Integrated circuit modeling Field programmable gate arrays Graphical user interfaces

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Two Matrix Multiplication algorithms Under Current Hardware architectures 30th

A Comparative Study of Two Matrix Multiplication Algorithms...

引用

30th international conference on parallel and Distributed processing Techniques, PDPTA 2024, held as part of the World Congress in Computer Science, Computer Engineering and Applied Computing, CSCE 2024

作者： Olatunde, Samuel Colmenares, Eduardo Department of Computer Science McCoy College of Science Mathematics and Engineering Midwestern State University Wichita FallsTX76308 United States

ISBN: (纸本)9783031856372

A widely used computationally intensive scientific kernel, the matrix multiplication algorithm is at the heart of many scientific routines. Resurging fields, such as artificial intelligence (AI), strongly benefit from fast and accurate processing of large matrices. through the years, multiple efforts have been made to derive new algorithms capable of achieving better performance than the naive matrix multiplication approach Θ(n3). One of those is Strassen’s variant Θ(n2.81). this research compares the benefits and differences of using an optimal version of Strassen’s algorithm versus the naive algorithm. the performance analysis makes use of the two most dominant high-performance computing (HPC) architectures available within the Lonestar6 cluster at Texas Advance Computing Center (TACC), the multi-core (CPU) and many-core (GPU) architectures. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： C programming CUDA GPU Matrix Multiplication Strassen’s TACC

来源：评论

学校读者我要写书评

暂无评论

Special issue on advances in techniques for assessment performance portability of HPC applications

引用

Future Generation Computer Systems 2025年 171卷

作者： Marowka, Ami Stpiczyński, Przemyslaw Wyrzykowski, Roman Parallel Research Lab Petach Tikva49729 Israel Institute of Computer Science Maria Curie-Sklodowska University Lublin20-033 Poland Department of Computer Science Czestochowa University of Technology Czestochowa42-201 Poland

this special issue aims to present new developments and advances in techniques for assessment performance portability of high performance computing applications. It contains revised and extended versions of selected papers presented at the 10th Workshop on Language-Based parallel Programming Models, WLPP 2024, which was a part of 15th international conference on parallel processing and Applied Mathematics, PPAM 2024, held on September 8–11, 2024, in Ostrava, Czech Republic. © 2025

关键词： HPC applications parallel programming languages Performance portability

来源：评论

学校读者我要写书评

暂无评论

ORL-EPM: A Profit-Aware and Load-Driven Heterogeneous Resource Management Scheme with Collaborative Edge Computing 24th

ORL-EPM: A Profit-Aware and Load-Driven Heterogeneous Resou...

引用

24th international conference on algorithms and architectures for parallel processing, ICA3PP 2024

作者： Huang, Fengyi Zhang, Yutao Wang, Wenhua Guo, Jianxiong Xu, Yang Fan, Wentao Wang, Tian Hong Kong Baptist University Hong Kong China Hong Kong Baptist University United International College Beijing Normal University Zhuhai China Beijing Normal University Zhuhai China College of Computer Science and Electronic Engineering Hunan University Changsha China

ISBN: (纸本)9789819615414

To address the limitations of energy-efficient but computationally limited ARM64-based AI edge devices and general-purpose edge servers, this paper proposes a Decentralized Collaborative Heterogeneous Edge Computing (DCEC) architecture. this architecture combines edge servers with embedded AI devices to achieve low latency and enhanced computational capabilities. Commercially, the DCEC framework is divided into edge private clouds and edge public clouds, aiming to maximize the profits of Edge Service Providers (ESPs) through dynamic resource management. Considering task dynamism, complexity, and resource heterogeneity, this complex problem is formulated as a multi-stage mixed-integer nonlinear programming (MINLP) problem. We developed the ORL-EPM resource management framework—a three-layer optimization system that adjusts task scheduling based on varying latency sensitivity weights and heterogeneous resource demands. Additionally, we introduced a resource collaboration system based on resource leasing to manage resource overloads and accommodate diverse task complexities. this system includes three Economic Payment Models (EPMs) designed to achieve efficient and profitable resource utilization. Extensive simulation results indicate that this method ensures convergence and closely approximates optimal solutions across various scenarios, significantly outperforming existing methods. Testbed experiments demonstrate that the DCEC architecture can reduce latency by up to 21.83% in real-world applications, notably exceeding previous approaches. © the Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

An Empirical Study of Loss Functions for Aspect Category Detection in Imbalanced Data Scenario

An Empirical Study of Loss Functions for Aspect Category Det...

引用

international conference on Signal processing and Communication (ICSC)

作者： Nilanjana Das Shahin Ara Begum Department of Computer Science Assam University Silchar Assam India

ISBN: (数字)9798331511890

ISBN: (纸本)9798331511906

One of the key challenges in the Aspect Category Detection task is dealing with class imbalance in the data, which can significantly affect the performance of machine learning models. In this study, different loss functions have been analyzed to tackle the problem of class imbalance for Aspect Category Detection from textual data. A comprehensive comparative analysis of loss functions, including Binary Cross-Entropy (BCE), Weighted Binary Cross-Entropy (WBCE), Class-Balanced Cross-Entropy (CBCE), and Focal Loss have been conducted, across Bi-LSTM and Bi-GRU architectures. the performance of the models has been evaluated on two imbalanced datasets using key metrics such as precision, recall, macro $f$ 1-score, accuracy and MCC. the results indicate that focal loss consistently outperforms other loss functions, particularly when used with the Bi-LSTM model, achieving the highest scores and demonstrating superior handling of class imbalance issue.

关键词： Measurement Deep learning Analytical models Accuracy Attention mechanisms Confusion matrices Transfer learning Multi label classification Signal processing Data models

来源：评论

学校读者我要写书评

暂无评论

Advancing Grammatical Error Correction for English Text: A Comparative Study of Bahdanau Attention and Multi-Head Attention Models

Advancing Grammatical Error Correction for English Text: A C...

引用

international conference on Signal processing and Communication (ICSC)

作者： Khushi Garg Samarth Soni Richa Gupta Neetu Singh Computer Science and Engineering Jaypee Institute of Information Technology Noida Uttar Pradesh India Electronics and Communication Engineering Jaypee Institute of Information Technology Noida Uttar Pradesh India Artificial Intelligence Bobble AI Gurugram Haryana India

ISBN: (数字)9798331511890

ISBN: (纸本)9798331511906

English Grammatical Error Correction (GEC) is a vital aspect of Natural Language processing (NLP), aimed at enhancing text accuracy and readability by resolving grammatical errors. this study examines the performance of two models: the Multi-Head Attention-Based Seq2Seq model and the Bahdanau Attention model, tested on multiple datasets. While the Multi-Head Attention model achieves strong results, the Bahdanau Attention model outperforms it, achieving a higher accuracy of 99.72%. the Bahdanau model's ability to capture contextual nuances more effectively contributes to its superior performance in correcting grammatical mistakes. these findings position the Bahdanau model as a state-of-the-art approach in GEC, demonstrating its advanced capability to handle complex linguistic structures. the research underscores the potential for the refinement of grammatical correction techniques through innovative model architectures.

关键词： Deep learning Accuracy Linguistics Natural language processing Real-time systems Error correction Grammar Optimization Context modeling

来源：评论

学校读者我要写书评

暂无评论

30th international conference on parallel and Distributed processing Techniques, PDPTA 2024, held as part of the World Congress in Computer Science, Computer Engineering and Applied Computing, CSCE 2024

30th International Conference on Parallel and Distributed Pr...

引用

ISBN: (纸本)9783031856372

the proceedings contain 24 papers. the special focus in this conference is on parallel and Distributed processing Techniques. the topics include: parallel N-Body Performance Comparison: Julia, Rust, and More;REFT: Resource-Efficient Federated Training Framework for Heterogeneous and Resource-Constrained Environments;An Efficient Data Provenance Collection Framework for HPC I/O Workloads;using Minicasts for Efficient Asynchronous Causal Unicast and Byzantine Tolerance;a Comparative Study of Two Matrix Multiplication algorithms Under Current Hardware architectures;Is Manual Code Optimization Still Required to Mitigate GPU thread Divergence? Applying a Flattening Technique to Observe Performance;towards Automatic, Predictable and High-Performance parallel Code Generation;Attack Graph Generation on HPC Clusters;analyzing the Influence of File Formats on I/O Patterns in Deep Learning;inference of Cell–Cell Interactions through Spatial Transcriptomics Data Using Graph Convolutional Neural Networks;natural Product-Like Compound Generation with Chemical Language Models;improved Early–Modern Japanese Printed Character Recognition Rate with Generated Characters;Improved Method for Similar Music Recommendation Using Spotify API;Reconfigurable Virtual Accelerator (ReVA) for Large-Scale Acceleration Circuits;Building Simulation Environment of Reconfigurable Virtual Accelerator (ReVA);vector Register Sharing Mechanism for High Performance Hardware Acceleration;Efficient Compute Resource Sharing of RISC-V Packed-SIMD Using Simultaneous Multi-threading;introducing Competitive Mechanism to Differential Evolution for Numerical Optimization;hyper-heuristic Differential Evolution with Novel Boundary Repair for Numerical Optimization;jump Like a Frog: Optimization of Renewable Energy Prediction in Smart Gird Based on Ultra Long Term Network;vision Transformer-Based Meta Loss Landscape Exploration with Actor-Critic Method;Fast Computation Method for Stopping Condition of Range Restricted

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimizing Brain Tumor Classification Using YOLOv8: A Comparative Study with CNN architectures on MRI Scans

Optimizing Brain Tumor Classification Using YOLOv8: A Compar...

引用

international conference on Signal processing and Communication (ICSC)

作者： Srishti Verma Alakto Choudhury Priyanka Narad Abhishek Sengupta Amity Institute of Biotechnology Amity University Noida Uttar Pradesh Indian Council of Medical Research New Delhi India

ISBN: (数字)9798331511890

ISBN: (纸本)9798331511906

Accurate diagnosis of brain tumors is crucial for effective treatment, and advancements in artificial intelligence (AI) are transforming this process. this study adapts You Only Look Once version 8 (YOLOv8), a state-of-the-art deep learning model, for brain tumor classification using MRI scans across four categories: glioma, meningioma, pituitary tumors, and no tumor. Trained over 20 epochs with preprocessing techniques like resizing and normalization, YOLOv8 achieved a top-1 accuracy of 99.12%, outperforming traditional CNNs (94-96% accuracy). the model demonstrated faster inference, superior generalization, and consistent reductions in training and validation loss, underscoring its robustness. these results position YOLOv8 as a promising tool for early, precise, and automated tumor diagnosis, with potential for clinical deployment. Future work will focus on dataset expansion and further optimization to enhance real-world applicability

关键词： Deep learning Training Accuracy Magnetic resonance imaging Computational modeling Brain tumors Computer architecture Brain modeling Robustness Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A parallel Distributed Algorithm for the Permutation Flow Shop Scheduling Problem

A Parallel Distributed Algorithm for the Permutation Flow Sh...

引用

10th international conference on algorithms and architectures for parallel processing

作者： Kouki, Samia Ladhari, Talel Jemni, Mohamed Ecole Super Sci & Tech Tunis Res Lab UTIC Tunis Tunisia Ecole Super Sci Econ & Commerce Tunis Tunisia

ISBN: (纸本)9783642131356

this paper describes a new parallel Branch-and-Bound algorithm for solving the classical permutation flow shop scheduling problem as well as its implementation on a cluster of six computers. the experimental study of our distributed parallel algorithm gives promising results and shows clearly the benefit of the parallel paradigm to solve large-scale instances in moderate CPU time.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

A New Hybrid parallel Algorithm for MrBayes

A New Hybrid Parallel Algorithm for MrBayes

引用

10th international conference on algorithms and architectures for parallel processing

作者： Zhou, Jianfu Wang, Gang Liu, Xiaoguang Nankai Univ Nankai Baidu Joint Lab Tianjin 300071 Peoples R China

ISBN: (纸本)9783642131189

MrBayes, a popular program for Bayesian inference of phylogeny, has not been fast enough for Biologists when dealing with large real-world data sets. this paper presents a new parallel algorithm that combines the chain-partitioned parallel algorithm with the chain-parallel algorithm to obtain higher concurrency. We test the proposed hybrid algorithm with the two old algorithms on a heterogeneous cluster. the results show that, the hybrid algorithm actually converts more CPU cores into higher speedup compared with the two control algorithms for all of four real-world DNA data sets, therefore is more practical.

关键词： MrBayes hybrid parallel algorithm

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：