检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2025年第1期6卷 51-65页

作者： Liu, Dan-Xuan Gu, Yu-Ran Qian, Chao Mu, Xin Tang, Ke Nanjing University National Key Laboratory for Novel Software Technology School of Artificial Intelligence Nanjing210023 China Peng Cheng Laboratory Shenzhen518000 China Southern University of Science and Technology Department of Computer Science and Engineering Shenzhen518055 China

Migration has been a universal phenomenon, which brings opportunities as well as challenges for global development. As the number of migrants (e.g., refugees) increases rapidly, a key challenge faced by each country is the problem of migrant resettlement. This problem has attracted scientific research attention, from the perspective of maximizing the employment rate. Previous works mainly formulated migrant resettlement as an approximately submodular optimization problem subject to multiple matroid constraints and employed the greedy algorithm, whose performance, however, may be limited due to its greedy nature. In this article, we propose a new framework called migrant resettlement by evolutionary multiobjective optimization (MR-EMO), which reformulates migrant resettlement as a biobjective optimization problem that maximizes the expected number of employed migrants and minimizes the number of dispatched migrants simultaneously, and employs a multiobjective evolutionary algorithm (MOEA) to solve the biobjective problem. We implement MR-EMO using three MOEAs: the popular nondominated sorting genetic algorithm II (NSGA-II), MOEA based on decomposition (MOEA/D) as well as the theoretically grounded global simple evolutionary multiobjective optimizer (GSEMO). To further improve the performance of MR-EMO, we propose a specific MOEA, called GSEMO using matrix-swap mutation and repair mechanism (GSEMO-SR), which has a better ability to search for feasible solutions. We prove that MR-EMO using either GSEMO or GSEMO-SR can achieve better theoretical guarantees than the previous greedy algorithm. Experimental results under the interview and coordination migration models clearly show the superiority of MR-EMO (with either NSGA-II, MOEA/D, GSEMO or GSEMO-SR) over previous algorithms, and that using GSEMO-SR leads to the best performance of MR-EMO. © 2024 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of LSTM Models on Sentiment Analysis 6

A Comparative Study of LSTM Models on Sentiment Analysis

引用

6th International Conference on Computational Intelligence and Networks, CINE 2024

作者： Choudhury, Ritabrata Roy Dey, Soumik Paul, Prithwineel Kalinga Institute of Industrial Technology School of Computer Engineering Odisha Bhubaneswar India Institute of Engineering & Management University of Engineering & Management Centre of Excellence for Quantum Computing Department of Computer Science and Engineering West Bengal Kolkata India

ISBN: (纸本)9798331516796

In this paper, we conduct a comparative analysis of LSTM (Long Short-Term Memory) architectures, including GPU LSTM and Convolutional LSTM, for sentiment analysis tasks on an e-commerce dataset. The evaluation is based on precision, recall, and F1-score metrics for classifying positive and negative sentiments in product reviews. Both GPU LSTM and Convolutional LSTM models demonstrate strong performance in classifying positive sentiments. Moreover, these models achieve high precision, recall, and F1-score. However, they struggle with negative sentiment classification, exhibiting zero precision, recall, and F1-score for this class. Overall, both models achieve an accuracy of 0.97, indicating their effectiveness in sentiment analysis tasks. Furthermore, our study underscores the importance of further research to enhance the ability of the LSTM model to classify negative sentiments in e-commerce datasets accurately. © 2024 IEEE.

关键词： Convolutional LSTM E-commerce F1-score GPU LSTM LSTM Precision Recall Sentiment Analysis

来源：评论

学校读者我要写书评

暂无评论

The Crucial Function that Clouds Access Security Brokers Play in Ensuring the Safety of Cloud Computing 2

The Crucial Function that Clouds Access Security Brokers Pla...

引用

2nd IEEE International Conference on Communication, Security and Artificial Intelligence, ICCSAI 2023

作者： Vidhyasagar, B.S. Arvindhan, M. Arulprakash, A. Bharathi, Kannan. SB Kalimuthu, Sivakumar Amrita School of Computing Amrita Vishwa Vidyapeetham Computer Science and Engineering Chennai India ASchool of Computing Science and Engineering Galgotias University UP Greater Noida India Sathyabama Institute of Science and Technology Computer Science and Engineering Chennai India Hindusthan College of Engineering and Technology Computer Science and Engineering Coimbatore India Malaysia Malaysia

ISBN: (纸本)9798350369960

The cloud is a vast network of interconnected servers and other devices that provide computing, communication, and storage services. The cloud market is dynamic, with ever-changing user needs and resource demands. Resource availability may be impacted by changes in the market, such as the addition or removal of service providers. When it comes to policies, standards, and preferences, cloud service providers and new line users are worlds apart. Even though several CSPs provide the same services, new line Access to and pricing for these services can seem different from one provider to the next. There are many advantages to using cloud computing, such as reduced overhead due to centralization, the ability to work remotely from anywhere with an Internet connection, and increased productivity. More research is needed into the cloud's privacy and security risks. To manage the degree of dimensionality, heterogeneity, and ambiguity associated with cloud services, a Cloud Access Security Broker (CASB) can be deployed between consumers of cloud services and cloud applications in a cloud computing (CC) environment. They allow the company to expand its security measures beyond its structure, into third-party software and data storage. To better understand how service users deploy CASBs to provide acceptable security solutions for cloud systems, and to figure out the elements that support or hinder the adoption of CASBs by organizations using remote computing technologies, an analysis based on themes was performed. This paper will provide an in-depth analysis of the security challenges experienced by various stakeholders in cloud computing, including cloud service providers, data owners, and cloud environments. © 2023 IEEE.

关键词： Access control

来源：评论

学校读者我要写书评

暂无评论

Pareto-Optimal Hybrid Beamforming for Finite-Blocklength Millimeter Wave Systems

引用

IEEE Transactions on Vehicular technology 2025年第6期74卷 9910-9915页

作者： Singh, Jitendra Naveen, Banda Srivastava, Suraj Jagannatham, Aditya K. Hanzo, Lajos Indian Institute of Technology Kanpur Department of Electrical Engineering Kanpur208016 India Indian Institute of Technology Jodhpur Department of Electrical Engineering Jodhpur342030 India University of Southampton School of Electronics and Computer Science SouthamptonSO17 1BJ United Kingdom

Short-packet communication (SPC) is essentially synonymous with ultra-reliable low-latency communication (uRLLC), which must meet stringent latency and reliability requirements. However, achieving efficient hybrid beamforming (HBF) in SPC-based millimeter wave (mmWave) systems is challenging due to the constraints of finite block lengths, limited number of radio frequency chains (RFCs), and owing to the complex optimization of transmit precoders (TPCs). In this work, we investigate the achievable rate region of an SPC-based mmWave downlink system. We harness the HBF for finite block lengths low-latency communication, relying on a low number of RFCs. We formulate a Pareto optimization problem for characterizing the achievable rate region, while considering the transmit power, mmWave hardware, and block length constraints. To solve this highly non-convex problem, we propose a bisection search-based block coordinate descent (Bi-BCD) algorithm, in which we optimize the RF TPC, the baseband (BB) TPC, and the block length. Specifically, we jointly optimize the RF and BB TPCs for a fixed block length, which involves both Remanian conjugate gradient (RCG) and second-order cone programming (SOCP) techniques, and then we optimize the block length by the mixed integer programming method. Subsequently, we update the achievable rate via the bisection search method. Finally, we present simulation results and quantify the efficiency of the proposed scheme. © 2025 IEEE.

关键词： Integer programming

来源：评论

学校读者我要写书评

暂无评论

ToMFIR and Auxiliary Signals based Active Incipient Fault Detection for Autonomous Underwater Vehicle Thrusters 43

ToMFIR and Auxiliary Signals based Active Incipient Fault De...

引用

43rd Chinese Control Conference, CCC 2024

作者： Zhu, Zefan Wu, Yunkai Zhou, Yang Zhu, Zhiyu Soh, YengChai Jiangsu University of Science and Technology College of Automation Zhenjiang212100 China Jiangsu University of Science and Technology School of Computer Science and Engineering Zhenjiang212100 China Nanyang Technological University School of Electrical and Electronic Engineering Singapore Singapore

ISBN: (纸本)9789887581581

This article proposes an active fault detection method combining the Total Measurable Fault Information Residual (ToMFIR) and auxiliary signals to address the incipient faults of autonomous underwater vehicle (AUV) thrusters. Firstly, the Takagi-Sugeno (T-S) fuzzy medelling of AUV dynamics is establised. Secondly, an auxiliary signal and redundant actuator module are introduced. The auxiliary signal is capable of amplifying the active ToMFIR in the event of a fault, while the redundant actuator ensures that the auxiliary signal does not interfere with the active ToMFIR in fault-free scenarios. Performance indicators and fixed thresholds are provided to assist in designing the parameters of the redundant actuator. This is done by maximizing the impact of the auxiliary signal on ToMFIR signals and minimizing any disturbances. Finally, simulation results demonstrate the effectiveness of the proposed method in improving the sensitivity for incipient faults in AUV propulsion systems. © 2024 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Autonomous underwater vehicles

来源：评论

学校读者我要写书评

暂无评论

Runtime Verification of Neural-Symbolic Systems 10th

Runtime Verification of Neural-Symbolic Systems

引用

10th International Symposium on Dependable Software engineering: Theories, Tools and Applications, SETTA 2024

作者： Deng, Shaojun Liu, Wanwei Zhang, Miaomiao College of Computer Science and Technology National University of Defense Technology Changsha China School of Software Engineering Tongji Uniersity Shanghai China

ISBN: (纸本)9789819606016

Neural-symbolic systems (NSSs), which are typically cyber-physical systems integrated with artificial intelligence modules, have received much attention in both academic and industrial fields. However, thorough verification (such as model checking) of such systems in general leads to prohibitively high costs due to the scale of the state space, and this makes it barely accomplishable within desired time-span. Consequently, light-weight verification techniques are introduced to deal with such cases, e.g., runtime verification (RV, for short). In this paper, we investigate an RV framework for NSSs against signal temporal logic (STL) properties. To guarantee that the on-line monitoring could be accomplished in time, we utilize Euler-prediction to sample the system under scrutiny at discrete time-steps. Our framework supports both qualitative and quantitative on-line monitoring of STL specifications, and thus it terminates whenever a property is satisfied and/or violated by a finite prefix of the trajectory, and it can also provide the bounds of the quantitative satisfaction/violation w.r.t. the remaining execution. Notably, for the so-called piece-wise linear NSSs against affine STL formulas, our approach is exact. On top of it, a prototype tool is implemented, and is experimentally evaluated. The results demonstrate the feasibility of the presented runtime verification approach. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Model checking

来源：评论

学校读者我要写书评

暂无评论

GEOMETRY-AWARE PROJECTIVE MAPPING FOR UNBOUNDED NEURAL RADIANCE FIELDS 12

GEOMETRY-AWARE PROJECTIVE MAPPING FOR UNBOUNDED NEURAL RADIA...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Lee, Junoh Jung, Hyunjun Park, Jin-Hwi Bae, Inhwan Jeon, Hae-Gon School of Electrical Engineering and Computer Science Gwangju Korea Republic of AI Graduate School Gwangju Institute of Science and Technology Gwangju Korea Republic of

Estimating neural radiance fields (NeRFs) is able to generate novel views of a scene from known imagery. Recent approaches have afforded dramatic progress on small bounded regions of the scene. For an unbounded scene where cameras point in any direction and contents exist at any distance, certain mapping functions are used to represent it within a bounded space, yet they either work in object-centric scenes or focus on objects close to the camera. The goal of this paper is to understand how to design a proper mapping function that considers per-scene optimization, which remains unexplored. We first present a geometric understanding of existing mapping functions that express the relation between the bounded and unbounded scenes. Here, we exploit a stereographic projection method to explain failures of the mapping functions, where input ray samples are too sparse to account for scene geometry in unbounded regions. To overcome the failures, we propose a novel mapping function based on a p-norm distance, allowing to adaptively sample the rays by adjusting the p-value according to scene geometry, even in unbounded regions. To take the advantage of our mapping function, we also introduce a new ray parameterization to properly allocate ray samples in the geometry of unbounded regions. Through the incorporation of both the novel mapping function and the ray parameterization within existing NeRF frameworks, our method achieves state-ofthe-art novel view synthesis results on a variety of challenging datasets. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Decentralized Security in IoT: Lightweight Blockchain with Optimized CA-LSTM for Improved Performance and Privacy 5

Decentralized Security in IoT: Lightweight Blockchain with O...

引用

5th International Conference on Data Intelligence and Cognitive Informatics, ICDICI 2024

作者： Selvakumarasamy, K. Kumar, T. Rajesh Meenambika, A. Balamanigandan, R. Mahaveerakannan, R. Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Electronics and Communication Engineering Chennai602105 India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Tamil Nadu Chennai602105 India Psna College of Engineering and Technology Computer Science and Business Systems India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350389609

An existing infrastructure can be linked to billions of devices, or "things,"through the Internet of Things (IoT). This allows for machine-to-machine communication as well as human-to-human communication. Massive volumes of data are being generated due to the proliferation of devices globally, which permeates every facet of everyday life. Thus, new problems are emerging as a result of the development and use of existing technologies, and these problems pertain to new applications, regulations, cloud computing, security, and privacy. With its decentralized nature, the blockchain has the potential to protect users' and data's privacy. This study introduces a novel method that makes use of lightweight blockchain technology to significantly lessen the computing load usually seen in traditional blockchain systems. Implementation time and computational complexity can be significantly reduced by connecting this lightweight blockchain with IoT devices. Improved safety is achieved by the use of CA-LSTM (channel attention long short-term memory) technology for attack detection. In order to improve the CA-LSTM algorithm's solution, the suggested system uses the RMSSO algorithm as a hyperparameter tuning technique. Similarly, to found very little power consumption and physical memory utilization;for example, Raspberry Pi devices used 0.2 GB of memory and NVIDIA Jetson devices used 0.42 GB. With the deployed model, power consumption increased by an average of 15% per device. This technology makes it easier to build certain types of business models and gives decentralized apps the ability to securely compute on encrypted data without compromising user privacy. The findings confirm that the proposed system is very secure, on par with conventional blockchain implementations. © 2024 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

HTDcr:a job execution framework for high-throughput computing on supercomputers

引用

science China(Information sciences) 2024年第1期67卷 69-85页

作者： Jiazhi JIANG Dan HUANG Hu CHEN Yutong LU Xiangke LIAO School of Computer Science and Engineering Sun Yat-sen University School of Software Engineering South China University of Technology

High-throughput computing(HTC) is a computing paradigm that aims to accomplish jobs by easily breaking them into smaller,independent ***,it requires a large amount of computing power for a long *** existing HTC frameworks are job-oriented without support for coscheduling with hardware architecture and task-level ***,most of the frameworks reach a limited scale,and their usability needs further ***,we present HTDcr,a job execution framework for the HTC on *** study aims to improve the throughput,task dispatching,and usability of the *** detail,the throughput optimizations include a sophisticated designed task management system,a hierarchical scheduler,and the co-optimization of the task-scheduling strategy with the application and hardware *** optimizations for usability include a programable execution workflow,mechanisms for more robust and reliable service qualities,and a fine-grained resource allocation system for the colocation of multiple *** to our evaluations,HTDcr can achieve outstanding scalability and high throughput on large-scale clusters for the HTC *** evaluate HTDcr with several microbenchmarks and real-world applications on Tianhe-2 and Sunway TaihuLight to demonstrate its effects on existing design *** instance,the task scheduling for two real-world applications integrated with the application and hardware characteristics achieves 1.7× and 1.9× speedups over the basic task-scheduling strategy.

关键词： high-throughput computing supercomputer task scheduling middleware password guessing

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning-Based Method for Classifying Yoga Poses using Deep Convolutional Neural Networks

Transfer Learning-Based Method for Classifying Yoga Poses us...

引用

2023 Innovations in Power and Advanced Computing Technologies, i-PACT 2023

作者： Vallabhaneni, Nagalakshmi Panneer, Prabhavathy Sundaram, Venkatesan Meenakshi School of Computer Science Engineering and Information Systems VIT University Vellore India Department of Computer Science and Engineering National Institute of Technology Puducherry India

ISBN: (纸本)9798350325188

Yoga is a popular practice that aims to improve one's health and well-being through physical postures, breathing exercises, and meditation. The growing popularity of yoga has prompted researchers to focus on automating the process of classifying yoga poses. Using deep convolutional neural networks (CNNs) and transfer learning, we present a deep learning-based method for correctly categorizing yoga postures in this research. The primary goal of this study is to develop an efficient method for automatically recognizing and categorizing yoga poses in given photographs. The impressive success of deep CNNs in picture classification tasks is exploited here to accomplish this goal. We also use transfer learning, a method for customizing pre-trained CNN models for our unique yoga posture categorization task. This paper presents a Transfer Learning based Method for Yoga Poses classification using Deep Convolutional Neural Networks (TLMYPC-DCNN). The proposed model uses the Yoga Posture Dataset for classification of images. Initially, this model starts with pre-processing the input images by splitting input data into three groups such as training set, validation set and test data. The deep learning CNN model will be trained using the training data, and then its parameters will be tweaked using the validation data. Finally, the test data will be used to assess how well the data performs. A convolutional neural network (CNN) model called MobileNetV2 will be applied to the model photos. The experimental results show that the suggested TLMYPC-DCNN based technique with transfer learning is effective at accurately and reliably classifying yoga poses. © 2023 IEEE.

关键词： Deep Convolutional Neural Networks MobileNetV2 Transfer Learning Yoga Pose classification

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：