检索结果-内蒙古大学图书馆

PSO-DBNet for Peak-to-Average Power Ratio Reduction Using Deep Belief Network

computer Systems Science & engineering 2023年第5期45卷 1483-1493页

作者： A.Jameer Basha M.Ramya Devi S.Lokesh P.Sivaranjani D.Mansoor Hussain Venkat Padhy Department of Computer Science and Engineering Hindusthan Institute of TechnologyCoimbatore641032India Department of Computer Science and Engineering Hindusthan College of Engineering and TechnologyCoimbatore641032India Department of Electronics and Communication Engineering Kongu Engineering CollegeErode638060India Department of Computer Science and Engineering Sri Krishna College of Engineering and TechnologyCoimbatore641008India School of Computing Science&Engineering VIT Bhopal UniversityBhopal466114India

Data transmission through a wireless network has faced various signal problems in the past *** orthogonal frequency division multiplexing(OFDM)technique is widely accepted in multiple data transfer patterns at various frequency bands.A recent wireless communication network uses OFDM in longterm evolution(LTE)and 5G,among *** main problem faced by 5G wireless OFDM is distortion of transmission signals in the *** transmission loss is called peak-to-average power ratio(PAPR).This wireless signal distortion can be reduced using various *** study uses machine learning-based algorithm to solve the problem of PAPR in 5G wireless *** transmit sequence(PTS)helps in the fast transfer of data in wireless *** is merged with deep belief neural network(DBNet)for the efficient processing of signals in wireless 5G *** indicates that the proposed system outperforms other existing ***,PAPR reduction in OFDM by DBNet is optimized with the help of an evolutionary algorithm called particle swarm ***,the specified design supports in improving the proposed PAPR reduction architecture.

关键词： 5G wireless network orthogonal frequency division multiplexing signal distortion peak to average power ratio partial transmit sequence deep belief network

来源：评论

学校读者我要写书评

暂无评论

AHP-Powered LLM Reasoning for Multi-Criteria Evaluation of Open-Ended Responses

AHP-Powered LLM Reasoning for Multi-Criteria Evaluation of O...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Lu, Xiaotian Li, Jiyi Takeuchi, Koh Kashima, Hisashi Department of Intelligence Science and Technology Graduate School of Informatics Kyoto University Kyoto Japan Department of Computer Science and Engineering University of Yamanashi Kofu Japan

ISBN: (纸本)9798891761681

Question answering (QA) tasks have been extensively studied in the field of natural language processing (NLP). Answers to open-ended questions are highly diverse and difficult to quantify, and cannot be simply evaluated as correct or incorrect, unlike close-ended questions with definitive answers. While large language models (LLMs) have demonstrated strong capabilities across various tasks, they exhibit relatively weaker performance in evaluating answers to open-ended questions. In this study, we propose a method that leverages LLMs and the analytic hierarchy process (AHP) to assess answers to open-ended questions. We utilized LLMs to generate multiple evaluation criteria for a question. Subsequently, answers were subjected to pairwise comparisons under each criterion with LLMs, and scores for each answer were calculated in the AHP. We conducted experiments on four datasets using both ChatGPT-3.5-turbo and GPT-4. Our results indicate that our approach more closely aligns with human judgment compared to the four baselines. Additionally, we explored the impact of the number of criteria, variations in models, and differences in datasets on the results. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Two Stage Video Classification Approach Using Convolution Neural Network 2

Two Stage Video Classification Approach Using Convolution Ne...

引用

2nd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2024

作者： Veena, H.N. Rajani Gowda, Naveen Chandra Ramani, D Roja SJB Institute of Technology Department of Computer Science and Engineering Bengaluru India School of Computer Science and Engineering REVA University Bengaluru India Newhorizon College of Engineering Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350327533

This research study focuses on video categorization, which is a crucial area of computer vision with uses in entertainment, education, and surveillance. Convolutional Neural Networks (CNNs) are used in a two-stage approach in the suggested methodology. The video is first broken down into frames, which are subsequently supplied into a CNN model. Another CNN model that predicts the video class uses the output from this model as input. A publicly accessible dataset is used to assess the efficacy of this approach, demonstrating its competitive accuracy performance in comparison to the most advanced techniques. The outcomes indicate that the technique can effectively classify videos and has the potential to be used in a variety of real-world scenarios. © 2024 IEEE.

关键词： 3D CNN Autoencoder Convolution Neural Networks (CNN) Long-Term Recurrent Convolutional Network (LRCN) Recurrent Neural Network(RNN)

来源：评论

学校读者我要写书评

暂无评论

CRAFT: Criticality-Aware Fault-Tolerance Enhancement Techniques for Emerging Memories-Based Deep Neural Networks

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2023年第10期42卷 3289-3300页

作者： Nguyen, Thai-Hoang Imran, Muhammad Choi, Jaehyuk Yang, Joon-Sung Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of Department of Electrical Engineering School of Electrical Engineering and Computer Science National University of Sciences and Technology Islamabad44000 Pakistan Department of Semiconductor Systems Engineering Sungkyunkwan University Suwon16419 Korea Republic of School of Electrical and Electronic Engineering Department of System Semiconductor Engineering Yonsei University Seoul03722 Korea Republic of

Deep neural networks (DNNs) have emerged as the most effective programming paradigm for computer vision and natural language processing applications. With the rapid development of DNNs, efficient hardware architectures for deploying DNN-based applications on edge devices have been extensively studied. Emerging nonvolatile memories (NVMs), with their better scalability, nonvolatility, and good read performance, are found to be promising candidates for deploying DNNs. However, despite the promise, emerging NVMs often suffer from reliability issues, such as stuck-at faults, which decrease the chip yield/memory lifetime and severely impact the accuracy of DNNs. A stuck-at cell can be read but not reprogrammed, thus, stuck-at faults in NVMs may or may not result in errors depending on the data to be stored. By reducing the number of errors caused by stuck-at faults, the reliability of a DNN-based system can be enhanced. This article proposes CRAFT, i.e., criticality-aware fault-tolerance enhancement techniques to enhance the reliability of NVM-based DNNs in the presence of stuck-at faults. A data block remapping technique is used to reduce the impact of stuck-at faults on DNNs accuracy. Additionally, by performing bit-level criticality analysis on various DNNs, the critical-bit positions in network parameters that can significantly impact the accuracy are identified. Based on this analysis, we propose an encoding method which effectively swaps the critical bit positions with that of noncritical bits when more errors (due to stuck-at faults) are present in the critical bits. Experiments of CRAFT architecture with various DNN models indicate that the robustness of a DNN against stuck-at faults can be enhanced by up to 105 times on the CIFAR-10 dataset and up to 29 times on ImageNet dataset with only a minimal amount of storage overhead, i.e., 1.17%. Being orthogonal, CRAFT can be integrated with existing fault-tolerance schemes to further enhance the robustness of DNNs aga

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

Distribution Matching for Multi-Task Learning of Classification Tasks: A Large-Scale Study on Faces & Beyond 38

Distribution Matching for Multi-Task Learning of Classificat...

引用

38th AAAI Conference on Artificial Intelligence, AAAI 2024

作者： Kollias, Dimitrios Sharmanska, Viktoriia Zafeiriou, Stefanos School of Electronic Engineering and Computer Science Queen Mary University of London United Kingdom School of Engineering and Informatics University of Sussex United Kingdom Department of Computing Imperial College London United Kingdom

ISBN: (纸本)1577358872

Multi-Task Learning (MTL) is a framework, where multiple related tasks are learned jointly and benefit from a shared representation space, or parameter transfer. To provide sufficient learning support, modern MTL uses annotated data with full, or sufficiently large overlap across tasks, i.e., each input sample is annotated for all, or most of the tasks. However, collecting such annotations is prohibitive in many real applications, and cannot benefit from datasets available for individual tasks. In this work, we challenge this setup and show that MTL can be successful with classification tasks with little, or non-overlapping annotations, or when there is big discrepancy in the size of labeled data per task. We explore task-relatedness for co-annotation and co-training, and propose a novel approach, where knowledge exchange is enabled between the tasks via distribution matching. To demonstrate the general applicability of our method, we conducted diverse case studies in the domains of affective computing, face recognition, species recognition, and shopping item classification using nine datasets. Our large-scale study of affective tasks for basic expression recognition and facial action unit detection illustrates that our approach is network agnostic and brings large performance improvements compared to the state-of-the-art in both tasks and across all studied databases. In all case studies, we show that co-training via task-relatedness is advantageous and prevents negative transfer (which occurs when MT model's performance is worse than that of at least one single-task model). Copyright © 2024, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based human activity recognition using CNN, ConvLSTM, and LRCN

引用

International Journal of Cognitive Computing in engineering 2024年第1期5卷 259-268页

作者： Uddin, Md. Ashraf Talukder, Md. Alamin Uzzaman, Muhammad Sajib Debnath, Chandan Chanda, Moumita Paul, Souvik Islam, Md. Manowarul Khraisat, Ansam Alazab, Ammar Aryal, Sunil School of Information Technology Deakin University Waurn Ponds Campus Geelong Australia Department of Computer Science and Engineering International University of Business Agriculture and Technology Dhaka Bangladesh Department of Computer Science and Engineering Jagannath University Dhaka Bangladesh Centre for Artificial Intelligence and Optimization Torrens University Australia Department of Electrical and Computer Engineering University of Ottawa Canada

Human activity recognition (HAR) plays a crucial role in assisting the elderly and individuals with vascular dementia by providing support and monitoring for their daily activities. This paper presents a deep learning (DL)-based approach to HAR, leveraging convolutional neural network (CNN), convolutional long short-term memory (ConvLSTM), and long-term recurrent convolutional network (LRCN) architectures. These models are designed to extract spatial features and capture temporal dependencies in video data, enhancing the accuracy of activity classification. We conducted experiments on the UCF50 and HMDB51 video datasets, encompassing diverse human activities. Our evaluation demonstrates that the ConvLSTM model achieves an accuracy of 82% on UCF50 and 68% on HMDB51, while the LRCN model gives accuracies of 93.44% and 71.55%, respectively. Finally, the CNN model outperforms with an accuracy rate of 99.58% for the UCF50 and 92.70% for the HMDB51 datasets. These significant improvements showcase the effectiveness of integrating convolutional and recurrent neural networks for HAR tasks. Our research contributes to advancing HAR systems with potential applications in healthcare, assisted living, and surveillance. By accurately recognizing human activities, our models can assist in remote patient monitoring, fall detection, and public safety initiatives. These findings underscore the importance of DL in enhancing the quality of life and safety for individuals in various contexts. © 2024 The Authors

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Performance and Implementation Comparison of Knuth-Morris-Pratt and Boyer-Moore String Search Algorithms 2

Performance and Implementation Comparison of Knuth-Morris-Pr...

引用

2nd International Conference on Advanced Innovations in Smart Cities, ICAISC 2025

作者： Saleh, Taj Ergin, Fatma Corut Malkawi, Malek Alhajj, Reda Department of Computer Engineering Marmara University Istanbul Turkey Department of Computer Engineering Istanbul Medipol University Istanbul Turkey Department of Computer Science University of Calgary Alberta Canada Department of Heath Informatics University of Southern Denmark Odense Denmark

ISBN: (纸本)9798331506995

String search algorithms play an important role in many research areas such as data mining and bioinformatics. While there exist a number of algorithms that handles the topic, we are exploring the the Knuth-Morris-Pratt (KMP) and Boyer-Moore algorithms due to their efficiency and versatility. In this work, we compared the algorithms in terms of characteristics, performance and implementation details. We also tested both the algorithms with various patterns and texts that differs in size. We also analyzed the performance of the algorithms on 4 different processors to understand the technological advancements effects on their performance. Our findings suggest that the BM algorithm perform better with large texts and patterns, while the KMP algorithm is better suited for smaller ones. Also, while newer processor generally exhibit improved performance, the significance of these enhancements may vary. Thus, we should rather be looking specific architectural advancements within generations rather than focusing solely on the generational gap. © 2025 IEEE.

关键词： String searching algorithms

来源：评论

学校读者我要写书评

暂无评论

A Subspace Projective Clustering Approach for Backdoor Attack Detection and Mitigation in Deep Neural Networks

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第7期5卷 3497-3509页

作者： Wang, Yue Li, Wenqing Sarkar, Esha Shafique, Muhammad Maniatakos, Michail Jabari, Saif Eddin New York University Abu Dhabi Division of Engineering Abu Dhabi129188 United Arab Emirates New York University Department of Electrical and Computer Engineering Tandon School of Engineering BrooklynNY11201 United States New York University Department of Civil and Urban Engineering Tandon School of Engineering BrooklynNY11201 United States

Backdoor attacks in deep neural networks (DNNs) involve an attacker inserting a backdoor into the network by manipulating the training dataset, which causes misclassification of inputs that contain a specific trigger. Detecting and mitigating such attacks are challenging, as only the attacker knows the trigger and target class. Our study demonstrates that the representations, i.e., the neuron activations for a given DNN, of poisoned and genuine data lie in different subspaces, which implies that there exists a certain subspace where the difference of projections from different data can be manifested. To this end, we propose a method based on subspace projective clustering (SPC), which learns a subspace as well as a projection-based weight vector by solving a projection maximization program, and the optimized weight vector can be utilized in a clustering framework to infer the group of data. Based on our theoretical analysis and experimental results, we demonstrate the effectiveness of our method in defending against backdoor attacks that use different settings of poisoned samples on GTSRB, Imagenet, VGGFace2, and PubFig datasets in comparison with the state-of-the-art methods. Our algorithm can detect more than 90% of the infected classes and identify 95% of the poisoned samples. © 2020 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Malware Evasion Attacks Against IoT and Other Devices: An Empirical Study

引用

Tsinghua Science and Technology 2024年第1期29卷 127-142页

作者： Yan Xu Deqiang Li Qianmu Li Shouhuai Xu School of Computer Science and Engineering Nanjing University of Science and TechnologyNanjing 210094China School of Computer Science Nanjing University of Posts and TelecommunicationsNanjing 210023China Department of Computer Science University of Colorado Colorado SpringsColorado SpringsCO 80918USA

The Internet of Things(loT)has grown rapidly due to artificial intelligence driven edge *** enabling many new functions,edge computing devices expand the vulnerability surface and have become the target of malware ***,attackers have used advanced techniques to evade defenses by transforming their malware into functionality-preserving *** systematically analyze such evasion attacks and conduct a large-scale empirical study in this paper to evaluate their impact on *** specifically,we focus on two forms of evasion attacks:obfuscation and adversarial *** the best of our knowledge,this paper is the first to investigate and contrast the two families of evasion attacks *** apply 10 obfuscation attacks and 9 adversarial attacks to 2870 malware *** obtained findings are as follows.(1)Commercial Off-The-Shelf(COTS)malware detectors are vulnerable to evasion attacks.(2)Adversarial attacks affect COTS malware detectors slightly more effectively than obfuscated malware examples.(3)Code similarity detection approaches can be affected by obfuscated examples and are barely affected by adversarial attacks.(4)These attacks can preserve the functionality of original malware examples.

关键词： Android malware obfuscation adversarial examples

来源：评论

学校读者我要写书评

暂无评论

Survey of Resources Allocation Techniques with a Quality of Service (QoS) Aware in a Fog Computing Environment

引用

computers, Materials & Continua 2023年第7期76卷 1291-1308页

作者： Wan Norsyafizan WMuhamad Kaharudin Dimyati Muhammad Awais Javed Suzi Seroja Sarnin Divine Senanu Ametefe School of Electrical Engineering College of EngineeringUniversity Teknologi Mara40450Shah AlamSelangorMalaysia Department of Electrical Engineering Faculty of EngineeringUniversity Malaya50603KualaLumpurMalaysia Department of Electrical and Computer Engineering COMSATS University Islamabad45550Pakistan

The tremendous advancement in distributed computing and Internet of Things(IoT)applications has resulted in the adoption of fog computing as today’s widely used framework complementing cloud ***,suitable and effective applications could be performed to satisfy the applications’latency *** allocation techniques are essential aspects of fog networks which prevent unbalanced load *** resource management techniques can improve the quality of service *** to the limited and heterogeneous resources available within the fog infrastructure,the fog layer’s resources need to be optimised to efficiently manage and distribute them to different applications within the IoT *** has been limited research on resource management strategies in fog networks in recent years,and a limited systematic review has been done to compile these *** article focuses on current developments in resource allocation strategies for fog-IoT networks.A systematic review of resource allocation techniques with the key objective of enhancing QoS is *** involved in conducting this systematic literature review include developing research goals,accessing studies,categorizing and critically analysing the *** resource management approaches engaged in this article are load balancing and task offloading *** the load balancing approach,a brief survey of recent work done according to their sub-categories,including stochastic,probabilistic/statistic,graph theory and hybrid techniques is provided whereas for task offloading,the survey is performed according to the destination of task *** load balancing and task-offloading approaches contribute significantly to resource management,and tremendous effort has been put into this critical ***,this survey presents an overview of these extents and a comparative ***,the study discusses ongoing research issues and potential future directio

关键词： Resource management task offloading load balancing QoS latency energy consumption

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：