检索结果-内蒙古大学图书馆

A State-Migration Particle Swarm Optimizer for Adaptive Latent Factor Analysis of High-Dimensional and Incomplete Data

引用

IEEE/CAA Journal of Automatica Sinica 2024年第11期11卷 2220-2235页

作者： Jiufang Chen Kechen Liu Xin Luo Ye Yuan Khaled Sedraoui Yusuf Al-Turki MengChu Zhou IEEE the College of Computer Science and Technology Chongqing University of Posts and Telecommunications the Department of Computer Science Columbia University the College of Computer and Information Science Southwest University the Department of Electrical and Computer Engineering Faculty of Engineeringand also with K.A.CARE Energy Research and Innovation CenterKing Abdulaziz University the Center of Research Excellence in Renewable Energy and Power Systems the Department of Electrical and Computer EngineeringFaculty of Engineeringand also with K.A.CARE Energy Research and Innovation CenterKing Abdulaziz University the Department of Electrical and Computer Engineering New Jersey Institute of Technology

High-dimensional and incomplete(HDI) matrices are primarily generated in all kinds of big-data-related practical applications. A latent factor analysis(LFA) model is capable of conducting efficient representation learning to an HDI matrix,whose hyper-parameter adaptation can be implemented through a particle swarm optimizer(PSO) to meet scalable ***, conventional PSO is limited by its premature issues,which leads to the accuracy loss of a resultant LFA model. To address this thorny issue, this study merges the information of each particle's state migration into its evolution process following the principle of a generalized momentum method for improving its search ability, thereby building a state-migration particle swarm optimizer(SPSO), whose theoretical convergence is rigorously proved in this study. It is then incorporated into an LFA model for implementing efficient hyper-parameter adaptation without accuracy loss. Experiments on six HDI matrices indicate that an SPSO-incorporated LFA model outperforms state-of-the-art LFA models in terms of prediction accuracy for missing data of an HDI matrix with competitive computational ***, SPSO's use ensures efficient and reliable hyper-parameter adaptation in an LFA model, thus ensuring practicality and accurate representation learning for HDI matrices.

关键词： Data science generalized momentum high-dimensional and incomplete(HDI)data hyper-parameter adaptation latent factor analysis(LFA) particle swarm optimization(PSO)

来源：评论

学校读者我要写书评

暂无评论

A topical VAEGAN-IHMM approach for automatic story segmentation

引用

Mathematical Biosciences and engineering 2024年第7期21卷 6608-6630页

作者： Yu, Jia Peng, Huiling Wang, Guoqiang Shi, Nianfeng School of Computer and Information Engineering Luoyang Institute of Science and Technology China Software Research Institute Technological University of Shannon Ireland

Feature representations with rich topic information can greatly improve the performance of story segmentation tasks. VAEGAN offers distinct advantages in feature learning by combining variational autoencoder (VAE) and generative adversarial network (GAN), which not only captures intricate data representations through VAE's probabilistic encoding and decoding mechanism but also enhances feature diversity and quality via GAN's adversarial training. To better learn topical domain representation, we used a topical classifier to supervise the training process of VAEGAN. Based on the learned feature, a segmentor splits the document into shorter ones with different topics. Hidden Markov model (HMM) is a popular approach for story segmentation, in which stories are viewed as instances of topics (hidden states). The number of states has to be set manually but it is often unknown in real scenarios. To solve this problem, we proposed an infinite HMM (IHMM) approach which utilized an HDP prior on transition matrices over countably infinite state spaces to automatically infer the state's number from the data. Given a running text, a Blocked Gibbis sampler labeled the states with topic classes. The position where the topic changes was a story boundary. Experimental results on the TDT2 corpus demonstrated that the proposed topical VAEGAN-IHMM approach was significantly better than the traditional HMM method in story segmentation tasks and achieved state-of-the-art performance. © 2024 the Author(s).

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

STPM: Spatial-Temporal Token Pruning and Merging for Complex Activity Recognition

引用

IEEE Transactions on Circuits and Systems for Video technology 2024年第6期35卷 5407-5418页

作者： Su, Yumeng Zhang, Jiachao Yan, Rui Li, Pengpeng Xie, Guosen Shu, Xiangbo Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing210094 China Nanjing Institute of Technology Artificial Intelligence Industrial Technology Research Institute Nanjing211167 China Nanjing University Department of Computer Science and Technology Nanjing210023 China

Lightweight video representation techniques have advanced significantly for simple activity recognition, but they still encounter several issues when applied to complex activity recognition: (i) The presence of numerous individuals and varying spatial positions makes it difficult for traditional token pruning methods to maintain accuracy. (ii) Simply discarding entire frames may result in the loss of crucial clues. (iii) To maintain parallel computing, applying the same pruning rate to every frame leads to significant redundancy in frames with low information content. To this end, we propose a lightweight and novel Spatial-Temporal Token Pruning and Merging (STPM) framework, specifically designed for complex action videos where human actors occupy a small spatial resolution within video frames. Our framework considers two critical factors: semantic importance and spatial-temporal redundancy, to further reduce overhead. For semantic importance, STPM captures class-specific attention scores by learning multiple class tokens within the transformer to guide token pruning. For spatial-temporal redundancy, STPM employs an anchor graph and temporal attention to perform spatial and temporal token merging, preserving appearance and temporal cues while eliminating semantic duplication and redundancy. We conduct extensive experiments on JRDB-PAR primarily using recently introduced video transformer backbones, e.g., MViT and ViT. Our framework achieves similar results while requiring 40% less computation. © 1991-2012 IEEE.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

DSF-GAM: a location inference model in social network Twitter

引用

International Journal of computers and Applications 2025年第2期47卷 141-161页

作者： Paul, Amit Changder, Narayan Dutta, Animesh Department of Computer Science and Engineering National Institute of Technology West Bengal Durgapur India TCG CREST Research and Education in Science and Technology West Bengal Kolkata India

Analyzing the social interactions and texts on Twitter can provide valuable insights into users' behavior, opinions, and even their geographical locations. Location inference of users within a social network finds applications in various domains, such as targeted advertising and public health monitoring. Inference techniques through social interactions, such as co-mentions, remain a favored method for constructing user social networks. Co-mentions, however, introduce a substantial number of noisy relationships that impact the overall network structure and prediction of the location of a user. Furthermore, previous approaches have overlooked the examination of cohesive groups or community structures within an individual's ego network for location prediction. This paper introduces a predictive model called DSF-GAM (DS stand for document similarity, F stands for frequencies and GAM stands for Generalized Additive Model). which redesigns social interactions based on mentions to infer user location on Twitter. DSF-GAM introduces a novel and innovative social graph, termed a user relation graph. DSF-GAM employs a generalized additive model (GAM) for location inference. The fundamental contribution of DSF-GAM lies in the representation of data using a new graph structure with enriched community features and edges. The experimental results on well-known datasets demonstrate that DSF-GAM outperforms other state-of-the-art methods based on both content and network approaches and mixed results in hybrid approaches. © 2025 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

Resolution-aware beam scanning for joint detection and communication in ISAC systems

引用

science China(Information sciences) 2025年第5期68卷 250-266页

作者： Yiming XU Dongfang XU Zhanyuan XIE Zheng JIANG Shenghui SONG Derrick Wing Kwan NG Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology China Telecom Research Institute School of Electrical Engineering and Telecommunications University of New South Wales

Beam scanning for joint detection and communication in integrated sensing and communication(ISAC) systems plays a critical role in continuous monitoring and rapid adaptation to dynamic environments. However, the design of sequential scanning beams for target detection with the required sensing resolution has not been tackled in the *** bridge this gap, this paper introduces a resolution-aware beam scanning design. In particular, the transmit information beamformer, the covariance matrix of the dedicated radar signal, and the receive beamformer are jointly optimized to maximize the average sum rate of the system while satisfying the sensing resolution and detection probability requirements.A block coordinate descent(BCD)-based optimization framework is developed to address the non-convex design problem. By exploiting successive convex approximation(SCA), S-procedure, and semidefinite relaxation(SDR), the proposed algorithm is guaranteed to converge to a stationary solution with polynomial time complexity. Simulation results show that the proposed design can efficiently handle the stringent detection requirement and outperform existing antenna-activation-based methods in the literature by exploiting the full degrees of freedom(DoFs) brought by all antennas.

关键词： integrated sensing and communication (ISAC) detection beam scanning resolution beamwidth

来源：评论

学校读者我要写书评

暂无评论

Performance analysis of free space optical system incorporating circular polarization shift keying and mode division multiplexing

引用

Journal of Optical Communications 2024年第2期45卷 347-354页

作者： Meenu Sharma, Anshu Malhotra, Rahul Department of Electronics and Communication Engineering CT Institute of Engineering Research and Technology Greater Kailash Maqsudan Punjab Jalandhar144008 India Computer Science and Engineering CT Institute of Technology & Research Greater Kailash Maqsudan Punjab Jalandhar144008 India Computer Science and Engineering CT Institute of Technology and Management Shahpur Near Lambra Punjab Jalandhar144020 India

In this work, a free-space optical (FSO) communication system with the integration of mode division multiplexing and circular polarization shift keying (CpolSK) is proposed at 2 × 40 Gbps using LG00 and LG01 modes. Effects of diverse weather conditions such as clear weather, light rain, moderate rain, heavy rain, thin fog, thick fog, and heavy fog are studied on system performance. Further, a detailed comparison of CpolSK and polarization shift keying (PolSK) is performed at different FSO lengths in terms of log bit error rate. For implementation, analysis, and comparison, Optiwave Optisystem software is used and results show that CpolSK covers 100 km link distance and PolSK limits to 90 km only. Also, LG00 mode performs better than LG01 mode under all weather instabilities in the proposed system. © 2024 Walter de Gruyter GmbH. All rights reserved.

关键词： Fog

来源：评论

学校读者我要写书评

暂无评论

OptiFog: A Framework for Acquiring State Information and Predicting Resource Availability for Task Offloading in Cooperative Fog-Networks

引用

IEEE Transactions on Services Computing 2024年 1-13页

作者： Alam, Mehbub Ahmed, Nurzaman Ghosh, Shyamal Matam, Rakesh Barbhuiya, Ferdous Ahmed Department of Computer Science and Engineering Indian Institute of Information Technology Guwahati India Department of Computer Science Dartmouth College Hanover USA School of Data Science Indian Institute of Science Education and Research Thiruvananthapuram India

The primary objective of fog computing is to minimize the reliance of IoT devices on the cloud by leveraging the resources of fog network. Typically, IoT devices offload computation tasks to fog to meet different task requirements such as latency in task execution, computation costs, etc. So, selecting such a fog node that meets task requirements is a crucial challenge. To choose an optimal fog node, access to each node's resource availability information is essential. Existing approaches often assume state availability or depend on a subset of state information to design mechanisms tailored to different task requirements. In this paper, OptiFog: a cluster-based fog computing architecture for acquiring the state information followed by optimal fog node selection and task offloading mechanism is proposed. Additionally, a continuous time Markov chain based stochastic model for predicting the resource availability on fog nodes is proposed. This model prevents the need to frequently synchronize the resource availability status of fog nodes, and allows to maintain an updated state information. Extensive simulation results show that OptiFog lowers task execution latency considerably, and schedules almost all the tasks at the fog layer compared to the existing state-of-the-art. IEEE

关键词： computer architecture

来源：评论

学校读者我要写书评

暂无评论

Learning in sinusoidal spaces with physics-informed neural networks

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第3期5卷 985-1000页

作者： Wong, Jian Cheng Ooi, Chin Chun Gupta, Abhishek Ong, Yew Soon Institute of High Performance Computing Agency for Science Technology and Research Singapore138632 Singapore School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore Singapore Institute of Manufacturing Technology Agency for Science Technology and Research Singapore138632 Singapore Agency for Science Technology and Research Singapore138632 Singapore Data Science and Artificial Intelligence Research Centre School of Computer Science and Engineering Nanyang Technological University Singapore138632 Singapore

A physics-informed neural network (PINN) uses physics-Augmented loss functions, e.g., incorporating the residual term from governing partial differential equations (PDEs), to ensure its output is consistent with fundamental physics laws. However, it turns out to be difficult to train an accurate PINN model for many problems in practice. In this article, we present a novel perspective of the merits of learning in sinusoidal spaces with PINNs. By analyzing behavior at model initialization, we first show that a PINN of increasing expressiveness induces an initial bias around flat output functions. Notably, this initial solution can be very close to satisfying many physics PDEs, i.e., falling into a localminimum of the PINN loss that onlyminimizes PDE residuals, while still being far from the true solution that jointly minimizes PDE residuals and the initial and/or boundary conditions. It is difficult for gradient descent optimization to escape from such a local minimum trap, often causing the training to stall. We then prove that the sinusoidalmapping of inputs-in an architecture we label as sf-PINN-is effective to increase input gradient variability, thus avoiding being trapped in such deceptive local minimum. The level of variability can be effectively modulated to match high-frequency patterns in the problem at hand. A key facet of this article is the comprehensive empirical study that demonstrates the efficacy of learning in sinusoidal spaces with PINNs for a wide range of forward and inversemodeling problems spanning multiple physics domains. Impact Statement-Falling under the emerging field of physicsinformed machine learning, PINN models have tremendous potential as a unifying AI framework for assimilating physics theory and measurement data. However, they remain infeasible for broad science and engineering applications due to computational cost and training challenges, especially for more complex problems. Instead of focusing on empirical demonstration of appli

关键词： Gradient methods

来源：评论

学校读者我要写书评

暂无评论

Image Enhancement via Associated Perturbation Removal and Texture Reconstruction Learning

引用

IEEE/CAA Journal of Automatica Sinica 2024年第11期11卷 2253-2269页

作者： Kui Jiang Ruoxi Wang Yi Xiao Junjun Jiang Xin Xu Tao Lu IEEE the School of Computer Science and Technology Harbin Institute of Technology Zhengzhou Research Institute Harbin Institute of Technology the School of Artificial Intelligence Jianghan University the School of Geodesy and Geomatics Wuhan University the Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan University of Science and Technology the School of Computer Science and Engineering and also with the Hubei Province Key Laboratory of Intelligent Robot Wuhan Institute of Technology

Degradation under challenging conditions such as rain, haze, and low light not only diminishes content visibility, but also results in additional degradation side effects, including detail occlusion and color distortion. However, current technologies have barely explored the correlation between perturbation removal and background restoration, consequently struggling to generate high-naturalness content in challenging scenarios. In this paper, we rethink the image enhancement task from the perspective of joint optimization: Perturbation removal and texture reconstruction. To this end, we advise an efficient yet effective image enhancement model, termed the perturbation-guided texture reconstruction network(PerTeRNet). It contains two subnetworks designed for the perturbation elimination and texture reconstruction tasks, respectively. To facilitate texture recovery,we develop a novel perturbation-guided texture enhancement module(PerTEM) to connect these two tasks, where informative background features are extracted from the input with the guidance of predicted perturbation priors. To alleviate the learning burden and computational cost, we suggest performing perturbation removal in a sub-space and exploiting super-resolution to infer high-frequency background details. Our PerTeRNet has demonstrated significant superiority over typical methods in both quantitative and qualitative measures, as evidenced by extensive experimental results on popular image enhancement and joint detection tasks. The source code is available at https://***/kuijiang94/PerTeRNet.

关键词： Association learning attention mechanism image enhancement perturbation modeling

来源：评论

学校读者我要写书评

暂无评论

Maximizing Learning Outcomes while Minimizing: Costs: A Cost-Effective Approach to M-Learning

International Journal of Interactive Mobile Technologies

引用

International Journal of Interactive Mobile Technologies 2024年第11期18卷 4-14页

作者： Suresh Kumar, B. Hemawathi, M.S. Dhanasekaran, P. Kaliappan, Vishnu Kumar Sivaganesan, D. Department of Electronics and Communication Engineering The Kavery Engineering College Tamil Nadu Salem India Department of Computer Science and Engineering KPR Institute of Engineering and Technology Tamil Nadu Coimbatore India Department of Computer Science and Engineering PSG Institute of Technology and Applied Research Tamil Nadu Coimbatore India

In the realm of education, the pursuit of effective learning outcomes often faces the challenge of limited resources. This paper explores the intersection of maximizing learning outcomes and minimizing costs through a cost-effective approach to mobile learning (m-learning). Recognizing the ubiquitous presence of mobile devices and their potential to revolutionize learning, this study explores strategies that leverage the capabilities of mobile technology while being mindful of budgetary constraints. By leveraging the flexibility and accessibil- ity offered by m-learning platforms, educators can design engaging and interactive learning experiences that cater to diverse learners needs. The paper investigates various cost-effective methodologies, including utilizing open-source software, repurposing existing resources, and adopting collaborative learning environments. Furthermore, it examines the role of scalable technologies and adaptive learning algorithms in optimizing resource allocation and per- sonalizing learning experiences. Through case studies and empirical analysis, this research illustrates how institutions and educators can achieve significant cost savings without com- promising the quality of educational delivery. Ultimately, the findings highlight the transfor- mative potential of a cost-effective approach to m-learning in enhancing learning outcomes and widening access to education. © 2024 by the authors of this article.

关键词： Contrastive Learning

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：