检索结果-内蒙古大学图书馆

2022 IEEE Future Networks World Forum (FNWF)

作者： Gourish Goudar Sanket Mishra Dept. of Artificial Intelligence and Data Science Nitte Meenakshi Institute of Technology (NMIT) Bengaluru India School of Computer Science and Engineering VITAP University Amaravati Amaravati India

With the escalating demands for data-intensive content, and the convergence of mobile and connected devices, there is a growing requirement of high bandwidth speeds in multimedia applications. 5G will be a game-changer in the business operations and in providing a engaging customer experience. The 5G vision promises to deliver high-speed downloads with low latency. Managing the exponential growth in data traffic is one of the mobile operator's most challenging issues in 5G networks. Mobile data offloading is a potential and low-cost method for alleviating cellular network congestion. To make this conceivable, we need a new paradigm for hybrid networks that capitalizes on the presence of several alternative communication ways. This entails significant modifications in how data is handled, thereby influencing the behavior of network protocols. This paper presents various techniques for data offloading in cellular 5G networks, discussing the requirements, advantages, and limitations. The research work in this paper provides a detailed presentation of the gaps identified in 5G networks data offloading techniques, the requirements and challenges, and a way forward to solve the challenges, including the most recent technological advancements such as deep learning, edge computing, WiFi-6, social networks and software-defined networks (considering the heterogeneity aspect of the network).

关键词： Cellular networks Deep learning Protocols 5G mobile communication Social networking (online) Device-to-device communication Software defined networking

来源：评论

学校读者我要写书评

暂无评论

Stochastic cluster head selection model for energy balancing in IoT enabled heterogeneous WSN

引用

Measurement: Sensors 2024年 35卷

作者： Anto Pravin, R. Murugan, K. Thiripurasundari, C. Ranjith Christodoss, Prasanna Puviarasi, R. Abdul Lathif, Syed Ismail Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Tamil Nadu India Department of Electronics and Communication Engineering Bannari Amman Institute of Technology Tamil Nadu India Department of Electronics and Communication Engineering KSK College of Engineering and Technology Tamil Nadu India Department of Computing Mathematics and Physics Messiah University Mechanicsburg PA United States Department of Electronics and Communication Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamil Nadu India Department of Data Science and Business Systems SRM Institute of Science and Technology Tamil Nadu India

Energy dissipation is the most important design limitation for Internet of Things (IoT) enabled Wireless Sensor Networks (WSNs). In order to prolong the life of WSNs, the energy of nodes must be used in an effective way. Clustering is a strategy that may effectively use the energy of the sensors, extending the life and scalability by managing the network load balance. The energy usage for network operation is reduced by using an evolutionary algorithm called Genetic Algorithm (GA). The Stochastic Cluster Head Selection Model (SCHSM) is described in the proposed protocol by taking the factors such as distance, node energy, density and capacity of nodes for developing the fitness function. The proposed protocol is designed for multiple movable sink nodes and this greatly improves the energy balancing factor in the network. For minimizing the communication gap among sensors and sinks, movable sinks can be placed carefully. Simulation results are analyzed for the system effectiveness. © 2024 The Authors

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Cross-Modality Translation with Generative Adversarial Networks to Unveil Alzheimer’s Disease Biomarkers

Cross-Modality Translation with Generative Adversarial Netwo...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Reihaneh Hassanzadeh Anees Abrol Hamid Reza Hassanzadeh Vince D. Calhoun School of Electrical and Computer Engineering Georgia Institute of Technology Atlanta GA USA Tri-Institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS) Georgia State University Atlanta GA USA Courtesy Faculty Appointment College of Pharmacy University of Florida

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

Generative approaches for cross-modality transformation have recently gained significant attention in neuroimaging. While most previous work has focused on case-control data, the application of generative models to disorder-specific datasets and their ability to preserve diagnostic patterns remain relatively unexplored. Hence, in this study, we investigated the use of a generative adversarial network (GAN) in the context of Alzheimer’s disease (AD) to generate functional network connectivity (FNC) and T1-weighted structural magnetic resonance imaging data from each other. We employed a cycle-GAN to synthesize data in an unpaired data transition and enhanced the transition by integrating weak supervision in cases where paired data were available. Our findings revealed that our model could offer remarkable capability, achieving a structural similarity index measure (SSIM) of 0.89 ± 0.003 for T1s and a correlation of 0.71 ± 0.004 for FNCs. Moreover, our qualitative analysis revealed similar patterns between generated and actual data when comparing AD to cognitively normal (CN) individuals. In particular, we observed significantly increased functional connectivity in cerebellar-sensory motor and cerebellar-visual networks and reduced connectivity in cerebellar-subcortical, auditory-sensory motor, sensory motor-visual, and cerebellar-cognitive control networks. Additionally, the T1 images generated by our model showed a similar pattern of atrophy in the hippocampal and other temporal regions of Alzheimer’s patients.

关键词： Neuroimaging Biological system modeling Magnetic resonance imaging Generative adversarial networks Motors Particle measurements data models Indexes Alzheimer's disease engineering in medicine and biology

来源：评论

学校读者我要写书评

暂无评论

DeepCare: Deep Learning-Based Smart Healthcare Framework using 5G Assisted Network Slicing

DeepCare: Deep Learning-Based Smart Healthcare Framework usi...

引用

2022 IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2022

作者： Basu, Deborsi Krishnakumar, Vikram Ghosh, Uttam Datta, Raja Indian Institute of Technology G. S. Sanyal School of Telecommunications Kharagpur India SASTRA Deemed Univ. Dept. of Electronics and Communication Engineering Tamil Nadu Thanjavur India School of Applied Computational Sciences MMC Dept. of Data Science and Computer Science United States Indian Institute of Technology Dept. of Electronics and Electrical Comm. Engg. Kharagpur India

ISBN: (纸本)9781665473408

5G and beyond communication networks require satisfying very low latency standards, high reliability, high-speed user connectivity, more security, improved capacity and better service demands. Augmenting such a wide range of KPIs (Key Performance Indicators) needs a smart, intelligent and programmable solution for TSPs (Telecommunication Service Providers). Resource availability and quality sustainability are challenging parameters in a heterogeneous 5G environment. Programmable Dynamic Network Slicing (PDNS) is a key technology enabling parameter that can allow multiple tenants to bring their versatile applications simultaneously over shared physical infrastructure. Latest emerging technologies like virtualized Software-Defined Networks (vSDN) and Artificial Intelligence (AI) play a pivotal supporting role in solving the above-mentioned constraints. Using the PDNS framework, we have proposed a novel slice backup algorithm leveraging Deep Learning (DL) neural network to orchestrate network latency and load efficiently. Our model has been trained using the available KPIs and incoming traffic is analyzed. The proposed solution performs stable load balancing between shared slices even if certain extreme conditions (slice unavailability) through intelligent resource allocation. The framework withstands service outage and always select the most suitable slice as a backup. Our results show latency-aware resource distribution for better network stability. © 2022 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Innovative Urban Planning for Harnessing Blockchain and Edge Artificial Intelligence for Smart City Solutions

Innovative Urban Planning for Harnessing Blockchain and Edge...

引用

Intelligent Cyber Physical Systems and Internet of Things (ICoICI), International Conference on

作者： K. E. Purushothaman N. Ragavendran S. P. Ramesh V. Ganesh Karthikeyan G. Uma Maheswari R. Saravanakumar Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Artificial Intelligence and Data Science Engineering RMK College of Engineering and Technology Chennai Tamil Nadu India Department of Computer Science and Engineering School of Computing Science & Engineering Galgotias University Greater Noida Uttar Pradesh India School of Computing (SoC) SASTRA Deemed to be University Thanjavur Tamil Nadu India RMK College of Engineering and Technology Chennai Tamil Nadu India Iconix Software Solution Tirunelveli Tamil Nadu India

ISBN: (数字)9798331540661

ISBN: (纸本)9798331540678

This research explores the potential of blockchain and edge AI to revolutionize smart city planning and management. By incorporating these emerging technologies, cities can address current urban challenges, including traffic congestion, energy management, and data security. This research study highlights the benefits of blockchain, such as simplified processes, reduced costs, enhanced security, and transparency. Additionally, this study reviews the applications of edge AI in smart transportation, focusing on vehicle detection, counting, and identification algorithms. The potential of blockchain technology in smart energy trading, vehicle transfer, and encrypted communication is also discussed. Overall, this research study provides valuable insights for researchers to explore new application areas for blockchain and edge AI in the context of smart cities.

关键词： Smart cities Vehicle detection Scalability Urban planning Edge AI Blockchains Smart transportation Energy management Sustainable development Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

GrabDAE: An Innovative Framework for Unsupervised Domain Adaptation Utilizing Grab-Mask and Denoise Auto-Encoder

arXiv

引用

arXiv 2024年

作者： Chen, Junzhou Wen, Xuan Zhang, Ronghui Ren, Bingtao Wu, Di Xu, Zhigang Wang, Danwei The Guangdong Provincial Key Laboratory of Intelligent Transport System School of Intelligent Systems Engineering Sun Yat-sen University Guangzhou510275 China The School of Transportation Science and Engineering Beihang University State Key Lab of Intelligent Transportation System Beijing100191 China The School of Computer Science and Engineering Sun Yat-sen University Guangzhou510006 China The Guangdong Key Laboratory of Big Data Analysis and Processing Guangdong510006 China The School of Information Engineering Chang’an University Shaanxi Xi’an710064 China The School of Electrical and Electronic Engineering Nanyang Technological University Singapore639798 Singapore

Unsupervised Domain Adaptation (UDA) aims to adapt a model trained on a labeled source domain to an unlabeled target domain by addressing the domain shift. Existing Unsupervised Domain Adaptation (UDA) methods often fall short in fully leveraging contextual information from the target domain, leading to suboptimal decision boundary separation during source and target domain alignment. To address this, we introduce GrabDAE, an innovative UDA framework designed to tackle domain shift in visual classification tasks. GrabDAE incorporates two key innovations: the Grab-Mask module, which blurs background information in target domain images, enabling the model to focus on essential, domain-relevant features through contrastive learning;and the Denoising Auto-Encoder (DAE), which enhances feature alignment by reconstructing features and filtering noise, ensuring a more robust adaptation to the target domain. These components empower GrabDAE to effectively handle unlabeled target domain data, significantly improving both classification accuracy and robustness. Extensive experiments on benchmark datasets, including VisDA-2017, OfficeHome, and Office31, demonstrate that GrabDAE consistently surpasses state-of-the-art UDA methods, setting new performance benchmarks. By tackling UDA’s critical challenges with its novel feature masking and denoising approach, GrabDAE offers both significant theoretical and practical advancements in domain adaptation. © 2024, CC BY-NC-SA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Tile Classification Based Viewport Prediction with Multi-modal Fusion Transformer

arXiv

引用

arXiv 2023年

作者： Zhang, Zhihao Chen, Yiwei Zhang, Weizhan Yan, Caixia Zheng, Qinghua Wang, Qi Chen, Wangdu School of Computer Science and Technology Xi'an Jiaotong University Key Laboratory of Intelligent Networks and Network Security Ministry of Education Xi'an Jiaotong University Xi’an China School of Computer Science and Technology Xi'an Jiaotong University & National Engineering Lab for Big Data Analytics Xi'an Jiaotong University Xi’an China MIGU Video Shanghai China

Viewport prediction is a crucial aspect of tile-based 360◦ video streaming system. However, existing trajectory based methods lack of robustness, also oversimplify the process of information construction and fusion between different modality inputs, leading to the error accumulation problem. In this paper, we propose a tile classification based viewport prediction method with Multi-modal Fusion Transformer, namely MFTR. Specifically, MFTR utilizes transformer-based networks to extract the long-range dependencies within each modality, then mine intra- and inter-modality relations to capture the combined impact of user historical inputs and video contents on future viewport selection. In addition, MFTR categorizes future tiles into two categories: user interested or not, and selects future viewport as the region that contains most user interested tiles. Comparing with predicting head trajectories, choosing future viewport based on tile's binary classification results exhibits better robustness and interpretability. To evaluate our proposed MFTR, we conduct extensive experiments on two widely used PVS-HM and Xu-Gaze dataset. MFTR shows superior performance over state-of-the-art methods in terms of average prediction accuracy and overlap ratio, also presents competitive computation efficiency. © 2023, CC BY.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Gaf-Net: Graph Attention Fusion Network for Multi-View Semi-Supervised Classification

SSRN

引用

SSRN 2023年

作者： Song, Na Du, Shide Wu, Zhihao Zhong, Luying Wang, Shiping School of Computer Science and Technology Hainan University Hainan570228 China School of Mechanical Electrical and Information Engineering Putian University Putian351100 China College of Computer and Data Science Fuzhou University Fuzhou350116 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350116 China

Multi-view semi-supervised classification is a typical task to classify data using a small amount of supervised information, which has attracted a lot of attention from researchers in past years. In practice, existing methods focus more on extracting spatial or spectral features using graph convolutional neural networks without considering the diversity and variability of graph structures and the contributions of different views. To address this challenge, a network framework termed graph attention fusion network is proposed, which is comprised of two phases: view-specific feature embedding and graph embedding fusion. In the former feature extraction stage, view-specific feature embedding module can flexibly focus on the neighborhood calculation operation to learn a weight for each neighboring node. In the latter feature fusion stage, the graph embedding fusion module is performed by complementarity and consistency to fuse these embeddings for semi-supervised classification tasks. We conduct extensive experiments in terms of semi-supervised classification on real-world datasets to validate the superiority of the proposed method over various existing state-ofthe-art methods. © 2023, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Optimizing Blockchain Mining Decisions Using Deep Reinforcement Learning Algorithms

Optimizing Blockchain Mining Decisions Using Deep Reinforcem...

引用

Machine Learning and Autonomous Systems (ICMLAS), International Conference on

作者： Anne Sreyas Venkatesam Karnati Shainy Reddy Shanmugasundaram Hariharan Bibhuti Bhsan Dash Subrata Chowdhury Sudhansu Shekhar Patra Department of Artificial Intelligence and Data Science Vardhaman College of Engineering Hyderabad India School of Computer Applications Kalinga Institute of Industrial Technology (KIIT) Deemed to be University Bhubaneswar Odisha India Department of CSE Sreenivasa Institute of Technology and Management Studies Chittoor Anthra Pradesh India

ISBN: (数字)9798331505745

ISBN: (纸本)9798331505752

Blockchain technology is a distributed database that records the transactions across a network of computers. Blockchain technology ensures security and transparency of the data. Blockchain mining refers to the process of verifying the transactions in a blockchain network. However, blockchain mining consumes high energy and solving complex mathematical problems and puzzles. We this study addressed these challenges of blockchain mining using Reinforcement Learning (RL). We have developed a custom environment, BlockchainMiningEnv using openAIGym framework. This environment specifies key factors of blockchain mining like difficulty level and energy cost. These are used to create a realistic model for training an intelligent agent. The agent is trained with algorithms like proximal policy optimizing (PPO) Soft Actor-Critic (SAC) and Advantage Actor-Critic(A2C) to learn how to deal with these computational resources. The main aim of the agent is to maximize rewards by increasing mining efficiency and minimizing the energy consumption. In this paper we have combined blockchain technology with Reinforcement Learning (RL) to improve efficiency and sustainability of blockchain mining by maintaining the security and transparency of the data.

关键词： Training Scalability Reinforcement learning Robustness Mathematical models Blockchains data mining Security Sustainable development Tuning

来源：评论

学校读者我要写书评

暂无评论

Animal Behavior Monitoring Based on Sequence to Sequence Model

Animal Behavior Monitoring Based on Sequence to Sequence Mod...

引用

International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR)

作者： Qing-Zhe Cui Xin Yuan Justine Partoon Alexandra L. Whittaker Li-Xiang Xu Lei Liu Peng Shi School of Computer Engineering and Science Shanghai University Shanghai China College of Artificial Intelligence and Big Data Hefei University Hefei China School of Electrical and Mechanical Engineering The University of Adelaide Adelaide Australia Zoos South Australia Adelaide Australia School of Animal and Veterinary Sciences The University of Adelaide Adelaide Australia Anhui Jiaoxin Technology Co. Ltd. Hefei China

ISBN: (数字)9798331528072

ISBN: (纸本)9798331528089

Object tracking is a core task in the field of computer vision, with wide-ranging applications in scenarios such as video surveillance and autonomous driving. This paper focuses on the application of the SeqTrack method, a sequence-to-sequence (Seq2Seq) model-based approach for object tracking, to animal behavior monitoring video datasets. The SeqTrack method leverages an encoder-decoder architecture to capture the temporal dependencies of objects, enabling accurate object localization and bounding box prediction. To validate the performance of SeqTrack in practical scenarios, we conducted comparative experiments on a self-made Adelaide Zoo dataset, comparing SeqTrack with three other mainstream object tracking algorithms: ToMP, OSTrack, and MixFormer. The experimental results show that SeqTrack outper-forms in terms of both precision and success rate, demonstrating its superior capability in handling challenges such as fast object movements, complex backgrounds, and partial occlusions. These findings indicate that SeqTrack is well-suited for high-precision tracking scenarios like animal behavior monitoring.

关键词： Location awareness Analytical models Accuracy Animal behavior Wavelet analysis Video surveillance Prediction algorithms Pattern recognition Object tracking Monitoring

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：