检索结果-内蒙古大学图书馆

Design, Automation and Test in Europe Conference and Exhibition

作者： Renzhi Xiao Dan Feng Yuchong Hu Yucheng Zhang Lanlan Cui Lin Wang School of Software Engineering Jiangxi University of Science and Technology Nanchang China Wuhan National Laboratory for Optoelectronics Huazhong University of Science and Technology Wuhan China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Shenzhen Huazhong University of Science and Technology Research Institute School of Computer Science and Engineering XI'AN University of Technology Xi'an China

ISBN: (数字)9783982674100

ISBN: (纸本)9798331534646

A hashing index provides rapid search performance by swiftly locating key-value items. Non-volatile memory (NVM) technologies have driven research into hashing indexes for NVM, combining hard disk persistence with DRAM-level performance. Nevertheless, current NVM-based hashing indexes must tackle data inconsistency challenges caused by NVM write reordering or partial writes, and mitigate rapid local wear due to frequent updates, considering NVM's limited endurance. The temporary allocation of buckets in NVM-based chained hashing to resolve hash collisions prolongs the critical path for writing, thus hampering write performance. This paper presents WOPHI, a write-optimized persistent hash index scheme for NVM. By utilizing log-free failure-atomic writes, WOPHI minimizes data consistency overhead and addresses hash conflicts with bucket pre-allocation. Experimental results underscore WOPHI's significant performance enhancements, with insertion latency slashed by up to 88.2% and deletion latency boosted by up to 82.6% compared to existing state-of-the-art schemes. Moreover, WOPHI substantially mitigates data consistency overhead, reducing cache line flushes by 59.3%, while maintaining robust write throughput for insert and delete operations.

关键词： Nonvolatile memory Europe Writing Throughput Hard disks Indexes Resource management

来源：评论

学校读者我要写书评

暂无评论

Exploration and Practice of Deep Learning Classroom Teaching of “computer Network” Course Based on the Integration of Specialization and Innovation

Exploration and Practice of Deep Learning Classroom Teaching...

引用

Information engineering (ACIE), IEEE Asia Conference on

作者： Min Huang ShaoWu Peng Hua Yuan School of Software Engineering South China University of Technology Guangzhou P.R. China School of Computer Science South China University of Technology Guangzhou P.R. China

ISBN: (数字)9798331528409

ISBN: (纸本)9798331528416

In the era of rapid development of artificial intelligence technologies, traditional teaching models are unable to meet the employment needs of enterprises, and talent cultivation in universities faces more challenges, so teachers should consider how to better cultivate students' innovative abilities in classroom teaching and guiding them in practical applications. The paper focuses on teaching reform and practice of “computer Networks” course by deep learning classroom, which mainly includes three aspects: 1) Integrating ideological and political education and innovative education into the process of professional education of in the curriculum, by which to enhance students' professional innovation awareness; 2) Inviting experts from enterprises to participate in classroom teaching and practical guidance to help students learn about the ability requirements and related positions in the IT enterprises for talents in the era of AI; 3) Designing practice projects and guiding students to implement them by ‘design thinking’ methods, and also adopting an evaluation method that can reflect the innovative ability of students. Works of the paper can better reflect the support and deepening the teaching philosophy of studentcentered, and provide an attempt to improve teaching effectiveness and talent cultivation quality.

关键词： Deep learning Industries Training Technological innovation Philosophical considerations Pain Education computer networks Artificial intelligence Optimization

来源：评论

学校读者我要写书评

暂无评论

Magnifier: A Chiplet Feature-Aware Test Case Generation Method for Deep Learning Accelerators

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2025年

作者： Li, Boyu Zhu, Zongwei Liu, Weihong Cao, Qianyue Li, Changlong Ji, Cheng Li, Xi Zhou, Xuehai University of Science and Technology of China School of Computer Science and Technology Hefei230026 China University of Science and Technology of China Suzhou Institute for Advanced Research Suzhou215123 China University of Science and Technology of China School of Software Engineering Hefei230026 China University of Science and Technology of China China and Suzhou Institute for Advanced Research Suzhou215123 China East China Normal University School of Computer Science and Technology Shanghai200063 China Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing210094 China

The development of deep learning has led to increasing demands for computation and memory, making multi-chiplet accelerators a powerful solution. Multi-chiplet accelerators require more precise consideration of hardware configurations and mapping schemes in terms of computation, memory, and communication patterns compared to monolithic designs, in order to avoid underutilization of performance. However, there is currently a lack of performance testing methods specifically tailored for multi-chiplet accelerators. Existing testing methods primarily focus on correctness testing and do not address potential performance issues from a hardware perspective. To address these issues, this paper proposes Magnifier: A test case generation method for performance testing of multi-chiplet accelerators. Firstly, we analyze typical multi-chiplet accelerator prototype from the perspectives of computation, memory, and communication patterns, and summarize a chiplet feature-Aware operator task set. Next, we define the test evaluation metric IPPstd and use a candidate operator set to construct a sampling space for model-level test cases. Finally, we build a GAN to learn the distribution of high-diversity test cases, enabling the rapid generation of high-quality test cases. We validate the proposed method on both simulated and real multi-chiplet accelerators. Experiments show that Magnifier can improve the metric of test cases by up to 3.42 times and significantly reduce generation time, providing valuable insights for optimizing the hardware and software of multi-chiplet accelerators. © 1982-2012 IEEE.

关键词： Acceleration

来源：评论

学校读者我要写书评

暂无评论

FeedbackEval: A Benchmark for Evaluating Large Language Models in Feedback-Driven Code Repair Tasks

arXiv

引用

arXiv 2025年

作者： Dai, Dekun Liu, MingWei Li, Anji Cao, Jialun Wang, Yanlin Wang, Chong Peng, Xin Zheng, Zibin School of Software Engineering Sun Yat-sen University Zhuhai China The Hong Kong University of Science and Technology Hong Kong School of Computer Science and Engineering Nanyang Technological University Singapore School of Computer Science Fudan University Shanghai China

Code repair is a fundamental task in software development, facilitating efficient bug resolution and software maintenance. Although large language models (LLMs) have demonstrated considerable potential in automated code repair, their ability to comprehend and effectively leverage diverse types of feedback remains insufficiently understood. To bridge this gap, we introduce FeedbackEval, a systematic benchmark for evaluating LLMs’ feedback comprehension and performance in code repair tasks. We conduct a comprehensive empirical study on five state-of-the-art LLMs, including GPT-4o, Claude-3.5, Gemini-1.5, GLM-4, and Qwen2.5, to evaluate their behavior under both single-iteration and iterative code repair settings. Our results show that structured feedback, particularly in the form of test feedback, leads to the highest repair success rates, while unstructured feedback proves significantly less effective. Iterative feedback further enhances repair performance, though the marginal benefit diminishes after two or three rounds. Moreover, prompt structure is shown to be critical: incorporating docstrings, contextual information, and explicit guidelines substantially improves outcomes, whereas persona-based, chain-of-thought, and few-shot prompting strategies offer limited benefits in single-iteration scenarios. This work introduces a robust benchmark and delivers practical insights to advance the understanding and development of feedback-driven code repair using LLMs. All code and data are available at https://***/SYSUSELab/FeedbackEval. Copyright © 2025, The Authors. All rights reserved.

关键词： software design

来源：评论

学校读者我要写书评

暂无评论

Refractive Index Biosensor–Based Detection of Mycobacterium Tuberculosis Using Sea Lion Political Optimizer and Deep Learning

引用

Plasmonics 2025年 1-19页

作者： Ragavan, V. K. Senthil Nithya, N.S. Vengala, Anantharamaiah Subramanian, Balambigai Ambhika, C. Sri Shanmugha College of Engineering and Technology Tamil Nadu Sankari Salem (D.T.) 637 304 India Department of Software Systems School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore India Department of C S E K L E F Andhra Pradesh Vaddeswaram Guntur 522502 India Dept of ECE Karpagam College of Engineering Tamil Nadu Coimbatore India Department of AIML R.M.D Engineering College RSM Nagar Tamil Nadu Kavarapetai India

Mycobacterium tuberculosis (MTB) detection is a major global health concern, requiring accurate and reliable diagnostic tools. According to the World Health Organization (WHO), the global burden of TB is staggering, with approximately 10 million new cases reported annually, leading to a devastating 1.5 million fatalities worldwide every year. The timely detection and treatment of TB are critical components in the fight against this disease, as they play a vital role in preventing its transmission, minimizing the risk of complications and deaths, and enhancing the overall quality of life for affected individuals. Hence, this study presents a novel Sea Lion Political Optimizer_Deep Maxout Network (SLnPO_DMN) for detecting MTB, leveraging a robust processing pipeline to achieve exceptional accuracy. The proposed pipeline involves a series of meticulous steps, including data pre-processing by Min–Max normalization to scale the data to a common range. To enhance model generalizability, data augmentation is carried out by Bootstrap, generating additional training samples by resampling the original data with replacement. The augmented data is then fed into a DMN, optimized by the SLnPO, a hybrid algorithm combining the strengths of sea lion optimization (SLnO) and political optimizer (PO). The SLnPO_DMN model is trained to identify and learn intricate patterns within the data, ultimately attaining optimal performance and demonstrating exceptional capability in detecting Mycobacterium tuberculosis with high accuracy and reliability. The SLnPO_DMN is evaluated using a comprehensive set of metrics, including accuracy, sensitivity, and specificity. The results demonstrate the effectiveness of the SLnPO_DMN model achieving an accuracy (99.12%), sensitivity of (98.74%), and specificity of (98%). © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Deep maxout network Min–Max normalization Mycobacterium tuberculosis Political optimizer Sea lion optimization

来源：评论

学校读者我要写书评

暂无评论

An Encoder-Decoder Model Based On Spiking Neural Networks For Address Event Representation Object Recognition

引用

IEEE Transactions on Cognitive and Developmental Systems 2025年

作者： Du, Sichun Zhu, Haodi Zhang, Yang Hong, Qinghui Hunan University College of Computer Science and Electronic Engineering Changsha418002 China Shenzhen University Computer Vision Institute School of Computer Science and Software Engineering National Engineering Laboratory for Big Data System Computing Technology Guangdong Key Laboratory of Intelligent Information Processing Shenzhen518060 China

Address event representation (AER) object recognition task has attracted extensive attention in neuromorphic vision processing. The spike-based and event-driven computation inherent in the spiking neural network (SNN) provides an energy-saving solution for AER object recognition. However, SNN with spike timing dependent plasticity (STDP) learning rule has not achieved satisfying AER object recognition performance. This work proposes an SNN-based encoder-decoder model to improve the recognition performance of AER objects. An STDP-based locally connected spiking neural network (LC-SNN) is proposed as an encoder to extract rich spatiotemporal features from AER event flows more flexibly. After the encoder extracts and learns primary features, we propose a fully connected spiking neural network (FC-SNN) based on the reward-modulated spike-timing-dependent plasticity (R-STDP) learning rule as a decoder to learn higher-level features for classification. In addition, we improved the winner-take-all (WTA) mechanisms and R-STDP learning rule in the decoder based on the reward and punish decision, enabling the network to perform better. The experiments are performed on the N-MNIST, MNIST-DVS, and the DVS Gesture datasets, improving the accuracy of the best existing plasticity-based SNN by 0.19%, 0.27% and 1.35%, respectively. © 2016 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Personalized Model Partitioning and Aggregation for Federated Human Activity Recognition

引用

IEEE Transactions on Cognitive Communications and Networking 2025年

作者： Zhang, Weidong Wu, Xuangou Zhang, Tao Wang, Xiujun Wang, Jiacheng Zhang, Ruichen Wu, Tong Kang, Jiawen Niyato, Dusit Anhui University of Technology School of Computer Science and Technology Anhui China Beijing Jiaotong University School of Software Engineering Beijing China Nanyang Technological University School of Computer Science and Engineering Nanyang Avenue Singapore Singapore University of Science and Technology Beijing School of Computer and Communication Engineering Beijing China Guangdong University of Technology School of Automation Guangdong China

Federated learning-based human activity recognition (FL-HAR) has emerged as a significant research topic due to its extensive applications, enabling the collective integration of local client data and knowledge without compromising user privacy. A major challenge within FL-HAR is addressing the heterogeneity of data across distributed clients, which leads to varying feature distributions for the same activity across different clients. To overcome this limitation, we propose a novel algorithm for FL-HAR, termed FedPMP, with Adaptive Model Partitioning and Personalized Model Aggregation. This approach customizes individual models for each client, aligned with their individual data distribution. Specifically, our partitioning strategy categorizes the model into globally shared components and locally personalized components, based on layer-wise feature drift. The global components capture general features across the majority of user groups, while the local components extract user-specific personalized features. Furthermore, our personalized model aggregation approach separately consolidates the shared and personalized components, facilitating collaboration among clients in accordance with feature relevance. Notably, we prove that FedPMP converges under feature drift conditions, providing a solid theoretical foundation for its practical deployment. Extensive experiments on various real-world HAR benchmarks demonstrate that FedPMP can effectively address the issue of feature drift in HAR, boosting recognition accuracy for clients and reducing the variance in accuracy among them. Our method enhances recognition accuracy by an average factor of 5%, proving its efficacy and robustness under feature drift conditions. © 2015 IEEE.

关键词： Data Heterogeneity Federated Learning Human Activity Recognition Model Partition Personalized Aggregation

来源：评论

学校读者我要写书评

暂无评论

Compromising Rechargeable Sensor Networks in Marine Environment

引用

IEEE Transactions on Mobile Computing 2025年

作者： Wang, Qiwei Lin, Chi Dai, Haipeng Obaidat, Mohammad S. Hsiao, Kuei-Fang Fan, Xin Dalian University of Technology School of Software Technology & DUT-RU International School of Information Science and Engineering China Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province Dalian116620 China Nanjing University State Key Laboratory for Novel Software Technology Nanjing210023 China University of Science and Technology Beijing School of Computer and Communication Engineering Beijing100083 China SRM University Department of Computational Intelligence School of Computing SRM Nagar TN Kattankulathur603203 India The Amity University School of Engineering UP Noida201301 India The King Abdullah II School of Information Technology The University of Jordan Amman11942 Jordan

Marine Wireless Rechargeable Sensor Networks (MWRSNs), enhanced by recent Wireless Power Transfer (WPT) technology, present a significant advancement in extending network life. Traditional methods improve network performance through algorithm optimization, but neglect charging security, exposing networks to potential attacks. This paper addresses this problem from an adversarial view and develops a novel attack for MWRSN through Denying of Charge (DoC) to maximize network destructiveness. We start by establishing a generalized on-demand charging model, essential for developing DoC tactics. Subsequently, we unveil the Collaborative DoC (CoDoC) algorithm, capable of manipulating and falsifying charging requests. Central to CoDoC is the Request Prediction Method (RPM), which forecasts the initiation of charging requests and facilitates rapid request surges to enhance the attack's efficacy. CoDoC is able to disguise the presence of the attack, which is able to escape from being detected by the base station. Theoretical analyses are provided to explore the features of the proposed scheme. To demonstrate the outperformed features of the proposed schemes, extensive simulations and test-bed experiments are conducted. Our analysis and extensive simulations demonstrate that CoDoC increases sensor node failures by 20% to 142% compared to traditional methods, highlighting its effectiveness in marine environments. © 2002-2012 IEEE.

关键词： Charging stations

来源：评论

学校读者我要写书评

暂无评论

Optimized Autonomous Computing with Trusted Resilient Data Management for IoT Emerging Networks

引用

IEEE Sensors Journal 2025年第11期25卷 20778-20785页

作者： Shafique, Ayesha Cheng, Benmao Zhao, Bo Alwakid, Ghadah Naif Haq, Muhammad Inaam Ul Laboratory of Intelligent IOT Technology and Applications in Universities China Jouf University College of Computer and Information Sciences Department of Computer Science Al Jowf Sakaka72341 Saudi Arabia Quanzhou University of Information Engineering School of Computer Science and Software Engineering Quanzhou362000 China

The innovative city network integrates numerous computational and physical components to develop real-time systems. These systems can capture sensor data and distribute it to end stations. Most solutions have been presented based on the centralized computing paradigm, which effectively and systematically increases data flow;however, distributed wireless technologies and heterogeneous network services continue to raise significant research problems. These challenges lower the optimization criteria and reflect communication structure around the network edges. In this research, we proposed a sustainable development for smart networks using efficient big data management with collaborative decisions for network devices. It differs from most existing work in the mentioned aspect. It applies computational lightweight intelligence for forwarding collected data using mobile collectors and reduces the congestion flow between devices on the limited bandwidth of wireless links. Moreover, the energy load is efficiently managed with edge-driven methods, and the incorporation of trusted devices ensures the integrity of the smart network. It also tackles potential communication threats smartly. Based on the experiments conducted in Network Simulator (NS-3), the proposed model enhances the efficacy of smart networks for performance metrics with reliability and effective management of resources in Internet of Things (IoT) network. © 2025 IEEE.

关键词： Autonomous Computing Emerging Networks Mobile devices Smart network Trusted Data Management

来源：评论

学校读者我要写书评

暂无评论

PB-UAP: Hybride Universal Adversarial Attack for Image Segmentation

PB-UAP: Hybride Universal Adversarial Attack for Image Segme...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yufei Song Ziqi Zhou Minghui Li Xianlong Wang Hangtao Zhang Menghao Deng Wei Wan Shengshan Hu Leo Yu Zhang Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology School of Computer Science and Technology Huazhong University of Science and Technology School of Software Engineering Huazhong University of Science and Technology School of Information and Communication Technology Griffith University

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

With the rapid advancement of deep learning, the model robustness has become a significant research hotspot, i.e., adversarial attacks on deep neural networks. Existing works primarily focus on image classification tasks, aiming to alter the model’s predicted labels. Due to the output complexity and deeper network architectures, research on adversarial examples for segmentation models is still limited, particularly for universal adversarial perturbations. In this paper, we propose a novel universal adversarial attack method designed for segmentation models, which includes dual feature separation and low-frequency scattering modules. The two modules guide the training of adversarial examples in the pixel and frequency space, respectively. Experiments demonstrate that our method achieves high attack success rates surpassing the state-of-the-art methods, and exhibits strong transferability across different models.

关键词： Training Image segmentation Perturbation methods Semantics Scattering Signal processing Predictive models Network architecture Robustness Speech processing

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：