检索结果-内蒙古大学图书馆

International Conference on System Modeling & Advancement in Research Trends (SMART)

作者： J. Akshya M. Manochitra R. Indu Poornima T. Jeevitha M. Saravanakumar M. Sundarrajan Mani Deepak Choudhry Department of Computational Intelligence SRM Institute of Science and Technology Chennai Computer Science and Engineering (Cyber Security) Dr. N.G.P. Institute of Technology Coimbatore Department of Information Technology KGiSL Institute of Technology Coimbatore Department of Artificial Intelligence and Data Science Nehru Institute of Engineering and Technology Coimbatore Department of Networking and Communications SRM Institute of Science and Technology Chennai Deportment of Computing Technologies SRM Institute of Science and Technology Chennai

ISBN: (数字)9798350380583

ISBN: (纸本)9798350380590

With broad applicability in surveillance, delivery, and environmental monitoring, multi-drone path planning has received a great deal of attention recently. So far, wide applicability has been explored by various applications of Genetic Algorithms, Particle Swarm Optimization, and Ant Colony Optimization, which have already established reliable solutions to navigation and coverage through drone path optimization. However, in dynamic, obstacle-dense environments, these algorithms fail to adapt in real-time with energy efficiency. Traditional GA and PSO approaches can be effective for generating an initial path but fail to respond to collision avoidance and efficient resource management. In complex and unpredictable conditions, ACO fails to converge rapidly, which leads to suboptimal paths and increased energy consumption. To overcome such barriers, we present here an HGARL for enhanced multi-drone path optimization. The proposed algorithm thus combines the population-based search capability of GA with RL's adaptive learning ability, therefore providing an algorithm that in addition to finding optimal paths adjusts the paths according to changing environmental situations. HGARL presents better performance compared to existing methods. In path convergence, it reaches up to 15%, and in energy consumption, it reduces up to 20% with safe collision-free navigation. The strong potential of HGARL for robust, efficient, and adaptive solutions of real-time multi-drone operation in complex and dynamic environments has set a new benchmark for UAV path planning.

关键词： Energy consumption Navigation Heuristic algorithms Reinforcement learning Path planning Real-time systems Reliability Genetic algorithms Drones Convergence

来源：评论

学校读者我要写书评

暂无评论

Topological Characteristics of 5d Spatially Dynamic Brain Networks in Schizophrenia

Topological Characteristics of 5d Spatially Dynamic Brain Ne...

引用

IEEE International Symposium on Biomedical Imaging

作者： Mustafa S. Salman Armin Iraji Noah Lewis Vince D. Calhoun School of Electrical and Computer Engineering Georgia Institute of Technology Tri-Institutional Center for Translational Research in Neuroimaging & Data Science (TReNDS) Georgia Institute of Technology Georgia State University & Emory University School of Computational Science and Engineering Georgia Institute of Technology Atlanta GA USA

The last decade of rich data-driven research on functional magnetic resonance imaging (fMRI) has provided novel insights into human brain function and aberrant behavior in brain disorders. Independent component analysis (ICA) is a widely-used technique for data-driven analysis of fMRI data. Spatial ICA is the most prominent variation of ICA and provides replicable and interpretable intrinsic connectivity network (ICN). It assumes common spatial activation across time. However, very recent studies indicate that there is utility in adopting a dynamic spatial activation modeling approach. Characterizing dynamics for both temporal and spatial domains means we have a multitude of decompositions of the already high-dimensional, multi-dataset, and multi-subject fMRI data. Hence making sense of the derived data becomes a significant issue. Here we use topological data analysis (TDA) to identify topological descriptors of the windowed spatially dynamic components of fMRI data. We discover and summarize differences in the spatial dynamics of controls and schizophrenia patients (SZs). We discover that SZs generally have lower Betti numbers and higher Wasserstein distance between spatiotemporal brain states, which provide intuitive summaries of the reduced dynamism SZs exhibit in resting-state fMRI studies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Problems and Solutions of Point Cloud Mapping for VR and CAVE Environments for data Visualization and Physics Simulation

Problems and Solutions of Point Cloud Mapping for VR and CAV...

引用

Applied Imagery Pattern Recognition Workshop (AIPR)

作者： Nicholas Dewberry Issa W. AlHmoud Shuva Chowdhury Balakrishna Gokaraju Computer Science North Carolina A&T State University Greensboro NC Computational Data Science & Engineering North Carolina A&T State University Greensboro NC Civil Architectural & Environmental Engineering North Carolina A&T State University Greensboro NC

ISBN: (数字)9798350359527

ISBN: (纸本)9798350359534

In this paper, we explore the utilization of point clouds to enhance the visual fidelity and realism of VR environments. A pipeline was successfully developed to take point cloud data, process it through optimization algorithms such as spatial subsampling, and then virtualize it in a VR environment with custom scripted interactivity. Also, a multitude of problems such as frames-per-second (FPS) optimization, nausea reduction, point cloud sparsity minimization and controller interactivity all need to be addressed before progress can be made.

关键词： Point cloud compression Visualization Pipelines data visualization Resists Pattern recognition Mirrors

来源：评论

学校读者我要写书评

暂无评论

Personalized Stress Detection using a Lightweight Machine Learning Framework With Convenient Wrist-Worn Sensors

Personalized Stress Detection using a Lightweight Machine Le...

引用

IEEE Signal Processing in Medicine and Biology Symposium (SPMB)

作者： M. Hasan S. Mithun M. Mahmud S. Baral K. Poudel Computational and Data Science Middle Tennessee State University Murfreesboro TN USA Dept. of Computer Science University of Memphis TN USA Dept. of Electrical and Computer Engineering University of Memphis TN USA Div. of General Internal Medicine Univ. of Tennessee Health Science Center Memphis TN USA Dept. of Computer Science Middle Tennessee State University Murfreesboro TN USA

ISBN: (数字)9798350388572

ISBN: (纸本)9798350388589

Over 70% Americans experience daily stress, making real-time, accurate stress detection crucial for timely intervention, and promoting physical and mental well-being. In this study, we detect stress using machine learning from publicly available wrist-worn sensor data. We examined both population and individual levels, focusing on simple, computation friendly statistical features for reduced processing to facilitate adoptions in real-life mHealth applications. Our framework demonstrates that stress detection achieves over 96% accuracy at both the population and individual levels, with the Extreme Gradient Boosting classifier achieving the highest predictive accuracy. We found significant variability between individuals and achieved an average accuracy of 99.63% with area under the curve (AUC) 99.23%, F1-score 99.00%, precision, and recall 99.22%. This approach offers a promising solution for real-life stress detection due to its high accuracy and simplicity.

关键词： Analytical models Accuracy Focusing Human factors Signal processing Predictive models Feature extraction Boosting Real-time systems Biology

来源：评论

学校读者我要写书评

暂无评论

Performance Disparities between Accents in Automatic Speech Recognition 37

Performance Disparities between Accents in Automatic Speech ...

引用

37th AAAI Conference on Artificial Intelligence, AAAI 2023

作者： DiChristofano, Alex Shuster, Henry Chandra, Shefali Patwari, Neal Division of Computational & Data Sciences Washington University St. Louis United States Department of Computer Science & Engineering Washington University St. Louis United States Department of Women Gender and Sexuality Studies Washington University St. Louis United States Department of History Washington University St. Louis United States Department of Electrical & Systems Engineering Washington University St. Louis United States

ISBN: (纸本)9781577358800

In this work, we expand the discussion of bias in Automatic Speech Recognition (ASR) through a large-scale audit. Using a large and global data set of speech, we perform an audit of some of the most popular English ASR services. We show that, even when controlling for multiple linguistic covariates, ASR service performance has a statistically significant relationship to the political alignment of the speaker's birth country with respect to the United States' geopolitical power. Copyright © 2023, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Overview of Speaker Modeling and Its Applications: From the Lens of Deep Speaker Representation Learning

arXiv

引用

arXiv 2024年

作者： Wang, Shuai Chen, Zhengyang Lee, Kong Aik Qian, Yanmin Li, Haizhou Shenzhen Research Institute of Big Data School of Data Science The Chinese University of Hong Kong Guangdong Shenzhen518172 China Auditory Cognition and Computational Acoustics Lab The Department of Computer Science and Engineering The MoE Key Laboratory of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai200240 China Department of Electrical and Electronic Engineering The Hong Kong Polytechnic University Hong Kong

Speaker individuality information is among the most critical elements within speech signals. By thoroughly and accurately modeling this information, it can be utilized in various intelligent speech applications, such as speaker recognition, speaker diarization, speech synthesis, and target speaker extraction. In this overview, we present a comprehensive review of neural approaches to speaker representation learning from both theoretical and practical perspectives. Theoretically, we discuss speaker encoders ranging from supervised to self-supervised learning algorithms, standalone models to large pretrained models, pure speaker embedding learning to joint optimization with downstream tasks, and efforts toward interpretability. Practically, we systematically examine approaches for robustness and effectiveness, introduce and compare various open-source toolkits in the field. Through the systematic and comprehensive review of the relevant literature, research activities, and resources, we provide a clear reference for researchers in the speaker characterization and modeling field, as well as for those who wish to apply speaker modeling techniques to specific downstream tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Improving hp-Variational Physics-Informed Neural Networks for Steady-State Convection-Dominated Problems

arXiv

引用

arXiv 2024年

作者： Anandh, Thivin Ghose, Divij Jain, Himanshu Sunkad, Pratham Ganesan, Sashikumaar John, Volker Department of Computational and Data Sciences Indian Institute of Science Karnataka Bangalore India Department of Mechanical Engineering Indian Institute of Technology Tamil Nadu Madras India Weierstrass Institute for Applied Analysis and Stochastics Berlin Germany Department of Mathematics and Computer Science Freie University Berlin Germany

This paper proposes and studies two extensions of applying hp-variational physics-informed neural networks, more precisely the FastVPINNs framework, to convection-dominated convection-diffusion-reaction problems. First, a term in the spirit of a SUPG stabilization is included in the loss functional and a network architecture is proposed that predicts spatially varying stabilization parameters. Having observed that the selection of the indicator function in hard-constrained Dirichlet boundary conditions has a big impact on the accuracy of the computed solutions, the second novelty is the proposal of a network architecture that learns good parameters for a class of indicator functions. Numerical studies show that both proposals lead to noticeably more accurate results than approaches that can be found in the literature. © 2024, CC BY-NC-SA.

关键词： Stabilization

来源：评论

学校读者我要写书评

暂无评论

Personalized Federated Learning for Smart Healthcare Using SDN-Driven Edge Computing

Personalized Federated Learning for Smart Healthcare Using S...

引用

2025 IEEE SoutheastCon, SoutheastCon 2025

作者： Basu, Deborsi Chaudhary, Ritu Ghosh, Uttam Datta, Raja G. S. Sanyal School of Telecommunications Indian Institute of Technology Kharagpur India Indian Institute of Technology Dept. of Electronics and Electrical Communication Engineering Kharagpur India School of Applied Computational Sciences Dept. of Computer Science and Data Science Mmc TN United States

ISBN: (纸本)9798331504847

The advancement in distributed Federated Learning (FL) techniques is transforming next-generation edge computing, especially in e-Helathcare systems where data integrity and security are critical concerns. Collecting, processing and analyzing such substantial medical data is highly challenging due to their non-identical and versatile nature. Conventional FL approaches often show unsatisfactory and inaccurate results while operating on those data. Traditional FL methods also lack optimal dynamic management mechanisms for edge devices in ehealthcare, which is crucial to ensure that only authorized devices participate in handling any system failures and new registrations. To tackle such important aspects, in this work, we propose a personalized FL technique to handle abrupt label shifts among clients' data. The proposed approach further targets to achieve personalized models for local edge clients. A statistical batch normalization is proposed on customized edge servers, keeping the data specificity intact. To make the proposed system more secure and robust, a Software Defined Network-based (SDN-based) centralized server is used that allows only authorized and efficient edge clients to participate. The proposed comprehensive experiments on two healthcare datasets demonstrate better accuracy than traditional FL methods with enhanced security and privacy. © 2025 IEEE.

关键词： mHealth

来源：评论

学校读者我要写书评

暂无评论

Large-scale group decision-making method based on knowledge differentiation and the grouping of alternatives into modifiable scenarios

引用

Procedia computer science 2022年 214卷 927-934页

作者： José Ramón Trillo Enrique Herrera-Viedma María José Higueras-Ruiz Sergio Alonso Juan Antonio Morente-Molinera Francisco Javier Cabrerizo Department of Computer Science and Artificial Intelligence Andalusian Research Institute of Data Science and Computational Intelligence DaSCI University of Granada Granada 18071 Spain Department of Information and Communication University of Granada Granada 18071 Spain Department of Software Engineering Andalusian Research Institute in Data Science and Computational Intelligence DaSCI University of Granada Granada 18071 Spain

Nowadays, group decision-making is an everyday event, since we usually live in a community. Nevertheless, when the number of participants is large, it starts to generate a lot of information that is complex to manage, and unlike group decision-making, where the participants are usually experts, when the number of participants increases, not all of them are, which generates a conflict of interest because the value of the vote of an expert and a (non-expert) user is worth the same. Moreover, it may happen that not all participants who start a process will finish it and not all of them will be able to make all the assessments, since they do not know all the options. Therefore, to solve all the drawbacks, this paper presents a large-scale group decision-making system in a modifiable scenario environment that groups participants according to their preferred alternative and also performs knowledge differentiation, clustering them into experts and users. This allows for optimising the consensus process, as the consensus is made by comparing the clusters and the participants with each other.

关键词： Large-Scale Group Decision-Making Consensus Clustering Modifiable Scenarios Knowledge Differentiation

来源：评论

学校读者我要写书评

暂无评论

ACCELERATING ILL-CONDITIONED HANKEL MATRIX RECOVERY VIA STRUCTURED NEWTON-LIKE DESCENT∗

arXiv

引用

arXiv 2024年

作者： Cai, Hanqin Huang, Longxiu Lu, Xiliang You, Juntao Department of Statistics and Data Science Department of Computer Science University of Central Florida OrlandoFL32816 United States Department of Computational Mathematics Science and Engineering Department of Mathematics Michigan State University East LansingMI48823 United States School of Mathematics and Statistics Hubei Key Laboratory of Computational Science Wuhan University Wuhan430072 China Institute for Advanced Study Shenzhen University Shenzhen518000 China

This paper studies the robust Hankel recovery problem, which simultaneously removes the sparse outliers and fulfills missing entries from the partial observation. We propose a novel non-convex algorithm, coined Hankel Structured Newton-Like Descent (HSNLD), to tackle the robust Hankel recovery problem. HSNLD is highly efficient with linear convergence, and its convergence rate is independent of the condition number of the underlying Hankel matrix. The recovery guarantee has been established under some mild conditions. Numerical experiments on both synthetic and real datasets show the superior performance of HSNLD against state-of-the-art *** Codes 15A29, 15A83, 47B35, 90C17, 90C26, 90C53 Copyright © 2024, The Authors. All rights reserved.

关键词： Recovery

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：