检索结果-内蒙古大学图书馆

11th International Conference on Networking, Systems and Security, NSysS 2024

作者： Hasana, Maoyejatun Rahaman, Masfiqur Abedin, Razin Reaz Tahmid, Md Toki Tarin, Ishika Saha, Sudipa Tithi, Sutapa Dey Promi, Zarin Tasnim Noor, Kazi Abdun Sanjid, M.D. Zahidul Islam Dhrubo, Mahir Shahriar Akter, Samira Rahman, Tauhidur Al Islam, A.B.M. Alim Department of Computer Science and Engineering Bangladesh University of Engineering and Technology Dhaka Bangladesh Halıcıoğlu Data Science Institute University of California San Diego San DiegoCA United States Department of Computer Science and Engineering Brac University Dhaka Bangladesh Halıcıoğlu Data Science Institute University of California San Diego La Jolla CA United States

ISBN: (纸本)9798400711589

The changing climate is anticipated to result in more frequent and extended heat waves having catastrophic effects on urban areas. Prolonged exposure to extreme heat is believed to adversely affect both physiological and psychological well-being, particularly for outdoor workers. This study analyzed the effects of hot weather conditions on the brainwaves of rickshaw pullers by examining changes in EEG signals before and after driving rickshaws at different air temperatures and relative humidity levels. We selected six rickshaw pullers as participants for six levels of air temperature (°C) and humidity condition (%) in various outdoor areas in Dhaka city, Bangladesh, while driving rickshaws for a duration of 20 to 30 minutes. The acquired EEG data assists in assessing the effects of heat exposure on cerebral activity. Our statistical analysis shows that there is a positive association between heat stress and the alpha band power of brainwaves. © 2024 Copyright held by the owner/author(s).

关键词： Brain

来源：评论

学校读者我要写书评

暂无评论

Development of an Interface for Digital Neuromorphic Hardware Based on an FPGA

Development of an Interface for Digital Neuromorphic Hardwar...

引用

UNIfied Conference of International Workshop on Defence Applications of Multi-Agent Systems, DAMAS 2023, International Conference on Maintenance engineering, IncoME-V 2023, International conference on the Efficiency and Performance engineering Network, TEPEN 2023

作者： Harmann, René Sohlbach, Lukas Perez-Peña, Fernando Schmidt, Karsten Department of Computer Science and Engineering Frankfurt University of Applied Sciences Nibelungenplatz 1 Frankfurt60318 Germany Department of Automation Electronics and Computer Architecture and Networks School of Engineering University of Cadiz Avda. de la Universidad 10 Puerto Real11519 Spain

ISBN: (纸本)9783031494208

Exploring and understanding the functioning of the human brain is one of the greatest challenges for current research. Neuromorphic engineering tries to address this challenge by abstracting biological mechanisms and translating them into technology. Via the abstraction process and experiments with the resulting technical system, an attempt is made to obtain information about the biological counterpart. One subsection of Neuromorphic engineering (NE) is Spiking Neural Networks (SNN), which describe the structures of the human brain more and more closely than Artificial Neural Networks (ANN). Together with their dedicated hardware, SNNs provide a good platform for developing new algorithms for information processing. In the context of these neuromorphic hardware platforms, this paper aims to develop an interface for a digital hardware platform (SPINN-3 Development Board) to enable the use of industrial or conventional sensors and thus create new approaches for experimental research. The basis for this endeavor is a Field Programmable Gate Array (FPGA), which is placed as a gateway between the sensors and the neuromorphic hardware. Overall, the developed system provides a robust solution for a wide variety of investigations related to neuromorphic hardware and SNNs. Furthermore, the solution also offers suitable possibilities to monitor all processes within the system in order to obtain suitable measurements, which can be examined in search of meaningful results. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Modeling Locomotion with Body Angular Movements in Virtual Reality 25

Modeling Locomotion with Body Angular Movements in Virtual R...

引用

2025 CHI Conference on Human Factors in Computing Systems, CHI 2025

作者： Mai, Zijun Gao, BoYu Tu, Huawei Li, Dasheng Kim, HyungSeok Luo, Weiqi College of Information Science and Technology/Cyber Security Jinan University Guangzhou China Department of Computer Science and Information Technology La Trobe University Melbourne Australia College of Cyber Security/Guangdong Institute of Smart Education Jinan University Guangdong Guangzhou China Vr Lab Department of Computer Science and Engineering Konkuk University Seoul South Korea

ISBN: (纸本)9798400713941

This study proposes a time prediction model for locomotion along a polyline path with body angular movements in Virtual Reality (VR). We divide such locomotion into two components: navigating in multiple line-segment paths and turning at line-segment intersections. In the first component, locomotion in each line-segment path consists of acceleration, maximum velocity, and deceleration phases. We formulate equations to estimate the locomotion time for each phase and accumulated them to model the total time. In the second component, a linear relationship was revealed between task time and turning angles. We established an integrated model based on the equations of the two components and verified the effectiveness of the model with three experiments. The results indicate that our model outperformed two baseline models with a greater R² and a smaller gap between the predicted and actual time. Our study benefits VR locomotion design with body angular movements. © 2025 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Body angular movements Locomotion model Locomotion time prediction Virtual Reality

来源：评论

学校读者我要写书评

暂无评论

Adaptive Video Streaming: An AI-Driven Approach Leveraging Cloud and Edge Computing

Adaptive Video Streaming: An AI-Driven Approach Leveraging C...

引用

2023 IEEE International Conference on Artificial Intelligence, Blockchain, and Internet of Things, AIBThings 2023

作者： Darwich, Mahmoud Khalil, Kasem Ismail, Yasser Bayoumi, Magdy University of Mount Union Department of Mathematics and Computer Science AllianceOH44601 United States University of Mississippi University Department of Electrical and Computer Engineering MS38677 United States Southern University and AandM College Electrical Engineering Department Baton RougeLA70807 United States University of Louisiana at Lafayette Department of Electrical and Computer Engineering LA70504 United States

ISBN: (纸本)9798350322347

Video streaming efficiency remains a major challenge, with increasing demands for high-resolution content and minimal buffering times. We propose a novel solution to enhance user experiences. Our approach combines adaptive streaming, AI algorithms predicting network conditions, and edge computing to optimize task allocation. These technologies aim to reduce latency, lower network traffic, and facilitate seamless transitions in video quality. Our results improve the streaming services and enable real-time video applications in remote or mobile environments, presenting substantial implications for the future of video streaming. © 2023 IEEE.

关键词： Video streaming

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cloud-Based Video Streaming Efficiency using Neural Networks

Enhancing Cloud-Based Video Streaming Efficiency using Neura...

引用

2023 IEEE International Conference on Omni-layer Intelligent Systems, COINS 2023

作者： Darwich, Mahmoud Khalil, Kasem Ismail, Yasser Bayoumi, Magdy University of Mount Union Department of Mathematics and Computer Science AllianceOH44601 United States University of Mississippi Department of Electrical and Computer Engineering UniversityMS38677 United States Southern University and AandM College Electrical Engineering Department Baton RougeLA70807 United States University of Louisiana at Lafayette Department of Electrical and Computer Engineering LA70504 United States

ISBN: (纸本)9798350346473

The growing demand for high-quality video streaming services has increased the need for efficient utilization of cloud resources. This research proposes a novel solution to this challenge by utilizing neural networks to enhance video streaming performance in the cloud. Specifically, the research introduces a neural network architecture capable of dynamically adjusting video quality based on network conditions and user preferences. By combining convolutional and recurrent neural networks, the proposed model learns patterns in video streams and predicts the optimal bit rate for each frame. The architecture also considers network conditions such as bandwidth, latency, and packet loss to adapt video quality in real-Time. The proposed approach aims to improve quality of service while reducing cloud resource utilization, leading to cost-effective and scalable video streaming services. Extensive simulations and experiments were conducted to evaluate the feasibility and effectiveness of the approach. The proposed neural network architecture achieved up to 30% and 40% higher PSNR and SSIM scores, respectively, than the baseline approach. These results demonstrate the effectiveness of the proposed approach in enhancing video streaming efficiency in the cloud. Overall, this research provides valuable insights into designing efficient video streaming systems and highlights the potential benefits of neural networks in cloud-based video streaming services. © 2023 IEEE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Edge Computing for Efficient Storage and Low-latency Video Streaming in Cloud Environments

Edge Computing for Efficient Storage and Low-Latency Video S...

引用

2023 IEEE International Conference on Artificial Intelligence, Blockchain, and Internet of Things, AIBThings 2023

ISBN: (纸本)9798350322347

Efficient storage and low-latency video streaming are critical for delivering high-quality multimedia experiences in cloud environments. This research explores the potential of edge computing as a solution to address these challenges. By strategically deploying computational resources at the network edge, edge computing minimizes latency and enhances storage capabilities, leading to an improved user experience. We propose a cutting-edge prototype system that integrates edge computing into the cloud infrastructure. Through rigorous experiments, we evaluate key performance metrics, including latency, bitrate, and storage utilization, the results show the effectiveness of the proposed approach for video streaming in the cloud. Particularly, it reduces the latency by up to 25% and storage utilization by up to 15%. © 2023 IEEE.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Set-Membership Filtering for Discrete-Time Nonlinear Systems

引用

IEEE/CAA Journal of Automatica Sinica 2022年第6期9卷 1026-1036页

作者： Jingyang Mao Xiangyu Meng Derui Ding Department of Control Science and Engineering University of Shanghai for Science and TechnologyShanghai 200093China Division of Electrical and Computer Engineering Louisiana State UniversityBaton RougeLA70803 USA IEEE School of Science Computing and Engineering TechnologiesSwinburne University of TechnologyMelbourneVIC 3122Australia

In this article,the problem of state estimation is addressed for discrete-time nonlinear systems subject to additive unknown-but-bounded noises by using fuzzy set-membership ***,an improved T-S fuzzy model is introduced to achieve highly accurate approximation via an affine model under each fuzzy ***,compared to traditional prediction-based ones,two types of fuzzy set-membership filters are proposed to effectively improve filtering performance,where the structure of both filters consists of two parts:prediction and *** the locally Lipschitz continuous condition of membership functions,unknown membership values in the estimation error system can be treated as multiplicative noises with respect to the estimation ***-time recursive algorithms are given to find the minimal ellipsoid containing the true ***,the proposed optimization approaches are validated via numerical simulations of a one-dimensional and a three-dimensional discrete-time nonlinear systems.

关键词： Affine model membership functions set-membership filtering stability Takagi-Sugeno fuzzy modeling

来源：评论

学校读者我要写书评

暂无评论

Measuring the Privacy Leakage via Graph Reconstruction Attacks on Simplicial Neural Networks 37

Measuring the Privacy Leakage via Graph Reconstruction Attac...

引用

37th AAAI Conference on Artificial Intelligence, AAAI 2023

作者： Zhan, Huixin Zhang, Kun Lu, Keyi Sheng, Victor S. Department of Computer Science Texas Tech University Box 43104 LubbockTX79409-3104 United States Department of Computer Science Xavier University of Louisiana New OrleansLA70125 United States Department of Computer Science and Engineering Ohio State University ColumbusOH43210 United States

ISBN: (纸本)9781577358800

In this paper, we measure the privacy leakage via studying whether graph representations can be inverted to recover the graph used to generate them via graph reconstruction attack (GRA). We propose a GRA that recovers a graph's adjacency matrix from the representations via a graph decoder that minimizes the reconstruction loss between the partial graph and the reconstructed graph. We study three types of representations that are trained on the graph, i.e., representations output from graph convolutional network (GCN), graph attention network (GAT), and our proposed simplicial neural network (SNN) via a higher-order combinatorial laplacian. Unlike the first two types of representations that only encode pairwise relationships, the third type of representation, i.e., SNN outputs, encodes higher-order interactions (e.g., homological features) between nodes. We find that the SNN outputs reveal the lowest privacy-preserving ability to defend the GRA, followed by those of GATs and GCNs, which indicates the importance of building more private representations with higher-order node information that could defend the potential threats, such as GRAs. Copyright © 2023, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Historic preservation

来源：评论

学校读者我要写书评

暂无评论

Discovering Mixtures of Structural Causal Models from Time Series Data 41

Discovering Mixtures of Structural Causal Models from Time S...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Varambally, Sumanth Ma, Yi-An Yu, Rose Halıcıoğlu Data Science Institute University of California La Jolla San Diego United States Department of Computer Science and Engineering University of California La Jolla San Diego United States

Discovering causal relationships from time series data is significant in fields such as finance, climate science, and neuroscience. However, contemporary techniques rely on the simplifying assumption that data originates from the same causal model, while in practice, data is heterogeneous and can stem from different causal models. In this work, we relax this assumption and perform causal discovery from time series data originating from a mixture of causal models. We propose a general variational inference-based framework called MCD to infer the underlying causal models as well as the mixing probability of each sample. Our approach employs an end-to-end training process that maximizes an evidence-lower bound for the data likelihood. We present two variants: MCD-Linear for linear relationships and independent noise, and MCD-Nonlinear for nonlinear causal relationships and history-dependent noise. We demonstrate that our method surpasses state-of-the-art benchmarks in causal discovery tasks through extensive experimentation on synthetic and real-world datasets, particularly when the data emanates from diverse underlying causal graphs. Theoretically, we prove the identifiability of such a model under some mild assumptions. Implementation is available at https://***/Rose-STL-lab/MCD. Copyright 2024 by the author(s)

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing identity and access management using Hyperledger Fabric and OAuth 2.0: A block-chain-based approach for security and scalability for healthcare industry

引用

Internet of Things and Cyber-Physical Systems 2024年第1期4卷 49-67页

作者： Sutradhar, Shrabani Karforma, Sunil Bose, Rajesh Roy, Sandip Djebali, Sonia Bhattacharyya, Debnath Department of Computational Sciences Brainware University West Bengal India Department of Computer Sciences The University of Burdwan West Bengal India Department of Computer Science & Engineering JIS University West Bengal India Pôle universitaire Léonard De Vinci Research Center Paris La Défense 92 916 France Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh522302 India

Block-chain-based Identity and access management framework is a promising solution to privacy and security issues raised during the exchange of patient data in the healthcare industry. This technology ensures the confidentiality and integrity of sensitive information by providing a decentralized and immutable ledger. In our research, we propose an identity and access management system that employs Hyper-ledger Fabric and OAuth 2.0 for improved security and scalability. This combination allows for transparency and immutability of user transactions and minimizes the risk of fraud and unauthorized access. Additionally, Hyper-ledger Fabric's privacy, security, and scalability features enable granular access control to sensitive information, while OAuth 2.0 authorizes only trusted third-party applications to access specific data on the Fabric network. The proposed approach can handle large volumes of data and support multiple applications, thus providing a secure and scalable solution for managing access to the Fabric network. Moreover, our solution employs Role-based access control based on the patient's role, ensuring privacy and confidentiality. Our statistical analysis demonstrates that the proposed approach can efficiently and securely manage patient identity and access, potentially transforming the healthcare industry by enhancing data interoperability, reducing fraud and errors, and improving patient privacy and security. Furthermore, our solution can facilitate compliance with regulatory requirements such as HIPAA and GDPR. © 2023 The Authors

关键词： Scalability

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：