检索结果-内蒙古大学图书馆

2nd International Conference on Self Sustainable Artificial Intelligence Systems, ICSSAS 2024

作者： Manjunathan, N. Prabaharan, G. Prathik, A. Jaganathan, D. Manikandan, N.K. Muthulingam, S. Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Avadi Chennai India Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Dept. of Cse Avadi Chennai India Madanapalle Institute of Technology & Science Department of Artificial Intelligence India Alliance University Dept. of Cse Bangalore India

ISBN: (纸本)9798350368413

Financial analysis plays a pivotal role in understanding market trends and making informed investment decisions. This research leverages the power of Wavelet Packet Transform (WPT) to extract valuable insights from financial time series data. By applying WPT to financial data, complex patterns and trends can be uncovered, enabling more accurate forecasting and analysis. The study utilizes Plotly's interactive line charts to visualize these insights effectively. The proposed approach has demonstrated exceptional performance, achieving an accuracy rate of 99.5%. This high level of accuracy empowers stakeholders and financial advisors to navigate the dynamic financial landscape with greater confidence. By providing deeper insights into market behavior, this research contributes to improved decision-making and risk management in the financial industry. © 2024 IEEE.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

Detecting Facial Image Manipulations with Multi-Layer CNN Models

arXiv

引用

arXiv 2024年

作者： Montejano, Alejandro Marco Perez, Angela Sanchez Barrachina, Javier Ortiz-Perez, David Benavent-Lledo, Manuel Garcia-Rodriguez, Jose Facephi Research Laboratory Alicante Spain Dept. of Computer Science and Technology University of Alicante Alicante Spain

The rapid evolution of digital image manipulation techniques poses significant challenges for content verification, with models such as stable diffusion and mid-journey producing highly realistic, yet synthetic, images that can deceive human perception. This research develops and evaluates convolutional neural networks (CNNs) specifically tailored for the detection of these manipulated images. The study implements a comparative analysis of three progressively complex CNN architectures, assessing their ability to classify and localize manipulations across various facial image modifications. Regularization and optimization techniques were systematically incorporated to improve feature extraction and performance. The results indicate that the proposed models achieve an accuracy of up to 76% in distinguishing manipulated images from genuine ones, surpassing traditional approaches. This research not only highlights the potential of CNNs in enhancing the robustness of digital media verification tools, but also provides insights into effective architectural adaptations and training strategies for low-computation environments. Future work will build on these findings by extending the architectures to handle more diverse manipulation techniques and integrating multi-modal data for improved detection capabilities. © 2024, CC BY-NC-SA.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Ontology Mapping-Based Semantic Reasoning with OPC UA for Heterogeneous Industrial Devices

Ontology Mapping-Based Semantic Reasoning with OPC UA for He...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Jing Bi Rina Wu Haitao Yuan Ziqi Wang Jia Zhang MengChu Zhou College of Computer Beijing University of Technology Beijing China School of Automation Science and Electrical Engineering Beihang University Beijing China Dept. of Computer Science in Lyle School of Engineering Southern Methodist University Dallas TX USA Dept. of Electrical and Computer Engineering New Jersey Institute of Technology Newark NJ USA

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

The advent of smart manufacturing in Industry 4.0 signifies the arrival of the era of connections. As an excellent communication protocol, Object linking and embedding for Process Control Unified Architecture (OPC UA) can address most semantic heterogeneity issues. However, its semantics are not formally defined at the application layer. To address the information silo problem caused by semantic heterogeneity, a method named Querying of Ontology Mapping-based OPC UA (QOMOU) is proposed. It extracts the information models of OPC UA servers into resource description framework triples, utilizes web ontology language for semantic enrichment and inference, and employs a semantic similarity model for event ontology mapping to improve query efficiency. The method's effectiveness is validated through functional queries using the SPARQL protocol in Apache Jena. The query efficiency is 5% higher on average compared to both structured query and extensible markup languages. Moreover, by employing a keyword-matching algorithm, the query accuracy of the existing heterogeneous data integration scheme is improved by 4% on average. This enhancement can boost the operational efficiency of Internet of Things systems based on the OPC UA architecture.

关键词： Accuracy Protocols Semantics OWL XML Process control Ontologies Production facilities Fourth Industrial Revolution Servers

来源：评论

学校读者我要写书评

暂无评论

Driver Drowsiness Detection From Multiple Facial Features Using Mobile Devices

Driver Drowsiness Detection From Multiple Facial Features Us...

引用

Advanced Computing and Communication Technologies for High Performance Applications

作者： Jyothish K John Jenat Jose Deepu Cyriac Harishankar A Allen K Prince Dept. of Computer Science and Engg. Federal Institute of Science And Technology(FISAT) Angamaly India Dept. of Computer Science and Engg. FISAT Angamaly India

One of the crucial features in advanced driver assistance systems for minimizing catastrophic accidents caused by drivers is drowsiness detection. Drowsy driving has resulted in numerous fatalities or serious injuries for pedestrians and drivers. Being a victim of micro sleeps, a tired driver is probably much more dangerous on the road than a fast motorist. With the help of many technological solutions, automotive researchers and manufacturers are attempting to control this issue before it becomes a crisis. One potential use for intelligent car systems is the identification of sleepy drivers. Therefore, it is a significant task to create a driver drowsiness detection and prevention approach in order to avert these losses of life and property. The current challenges are the increasedcomplexity to produce such a method and also the high costassociated with the development of the method. These challenges can be overcome by using image processing for decreasing the complexity of the systems and using existing hardware like smart phones for drowsiness detection which can in turn decrease the cost associated with the development of the method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PixMamba: Leveraging State Space Models in a Dual-Level Architecture for Underwater Image Enhancement

arXiv

引用

arXiv 2024年

作者： Lin, Wei-Tung Lin, Yong-Xiang Chen, Jyun-Wei Hua, Kai-Lung Dept. of Computer Science and Information Engineering National Taiwan University of Science and Technology Taiwan Microsoft Taiwan

Underwater Image Enhancement (UIE) is critical for marine research and exploration but hindered by complex color distortions and severe blurring. Recent deep learning-based methods have achieved remarkable results, yet these methods struggle with high computational costs and insufficient global modeling, resulting in locally under- or over-adjusted regions. We present PixMamba, a novel architecture, designed to overcome these challenges by leveraging State Space Models (SSMs) for efficient global dependency modeling. Unlike convolutional neural networks (CNNs) with limited receptive fields and transformer networks with high computational costs, PixMamba efficiently captures global contextual information while maintaining computational efficiency. Our dual-level strategy features the patch-level Efficient Mamba Net (EMNet) for reconstructing enhanced image feature and the pixel-level PixMamba Net (PixNet) to ensure fine-grained feature capturing and global consistency of enhanced image that were previously difficult to obtain. PixMamba achieves state-of-the-art performance across various underwater image datasets and delivers visually superior results. Code is available at: https://***/weitunglin/pixmamba. © 2024, CC BY.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

An IRS-Assisted Secure Dual-Function Radar-Communication System

An IRS-Assisted Secure Dual-Function Radar-Communication Sys...

引用

Asilomar Conference on Signals, Systems & computers

作者： Yi-Kai Li Athina Petropulu Dept. of Electrical and Computer Engineering Rutgers University Piscataway NJ USA Dept. of Electrical and Computer Engineering and Technology Minnesota State University Mankato MN USA

In dual-function radar-communication (DFRC) sys-tems the probing signal contains information intended for the communication users, which makes that information vulnerable to eavesdropping by the targets. We propose a novel design for enhancing the physical layer security (PLS) of DFRC systems, via the help of intelligent reflecting surface (IRS) and artificial noise (AN), transmitted along with the probing waveform. The radar waveform, the AN jamming noise and the IRS parameters are designed to optimize the communication secrecy rate while meeting radar signal-to-noise ratio (SNR) constrains. Key chal-lenges in the resulting optimization problem include the fractional form objective, the SNR being a quartic function of the IRS parameters, and the unit-modulus constraint of the IRS parameters. A fractional programming technique is used to transform the fractional form objective of the optimization problem into more tractable non-fractional polynomials. Numerical results are provided to demonstrate the convergence of the proposed system design algorithm, and also show the impact of the power assigned to the AN on the secrecy performance of the designed system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploring emerging spreaders through GCN-based link prediction and a novel centrality method

Exploring emerging spreaders through GCN-based link predicti...

引用

International Communication Systems and Networks and Workshops, COMSNETS

作者： Suman Nandi Giridhar Maji Animesh Dutta Dept. of Computer Science and Engineering National Institute of Technology Durgapur West Bengal India Dept. of Electrical Engineering Asansol Polytechnic West Bengal India

ISBN: (数字)9798331531195

ISBN: (纸本)9798331531201

Exploring influential spreaders and predicting missing links in complex networks is essential for understanding and effectively controlling network dynamics. This paper presents a Graph Convolutional Network (GCN)-based link prediction method to estimate the probability of future link formation. We incorporate node features that capture local and global topological connectivity structures and feed these into the GCN model, where convolutional layers aggregate neighboring information and transform node features. This approach enables the model to capture structural patterns by integrating local and global information from neighboring nodes. In the final layer, the GCN model computes a prediction score representing the likelihood of an edge’s existence, using insights gained during training. Finally, considering the predicted links, we update the network structure and introduce a novel centrality method called Emerging Spreader Centrality (ESC) to identify emerging spreaders within this augmented network. We conduct two separate experiments to evaluate the performance of the GCN-based link prediction and the ESC method, comparing their effectiveness with various state-of-the-art methods. Results demonstrate that our approach not only effectively predicts future links but also identifies emerging spreaders in the augmented networks.

关键词： Training Graph convolutional networks Communication systems Computational modeling Aggregates Transforms Complex networks Predictive models Feeds

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study for Half-duplex and Full-duplex Multi-hop Routing in Software Defined Networks 9

A Comparative Study for Half-duplex and Full-duplex Multi-ho...

引用

9th International Conference on Software Defined Systems, SDS 2022

作者： Alnabelsi, Sharhabeel H. Salameh, Haythem Bany Darabkh, Khalid A. Al-Balqa Applied University Faculty of Engineering Technology Computer Eng. Dept. Al-Salt19117 Jordan College of Engineering Al Ain University United Arab Emirates Yarmouk University Telecommunications Eng. Dept. Irbid21163 Jordan The University of Jordan Computer Eng. Dept. Jordan

ISBN: (纸本)9798350346718

Full-duplex (FD) transmission capabilities have recently become more practical due to the effective self interference-cancellation-and-suppression techniques introduced in the literature for wireless communication. This capability is used for multi-hop routing in wireless networks because it increases the end-to-end throughput compared to Half-duplex (HD) transmission capabilities. There are two types of FD capability, In-band FD (IB-FD) and Out-of-Band FD (OB-FD). The IB- FD allows the device to transmit and receive at the same channel, while in the OB-FD the device must transmit and receive over different channels. In this paper, for Cognitive Radio Networks (CRNs), we analyze the channel assignment condition that achieves the maximum capacity when the FD techniques (IB-FD and OB-FD) are used. Moreover, we compare their throughput with respect to the HD capability. In general, the IB-FD has a higher throughput than OB-FD. However, it needs higher hardware complexity and cost. Also, we showed that the HD channel assignment produces lower throughput than the FD. © 2022 IEEE.

关键词： Cognitive radio

来源：评论

学校读者我要写书评

暂无评论

Optimization of New Radio Physical Uplink Shared Channel Resources Allocation with Efficient Demodulated Referenced Signals and PT-RE Deployment

Optimization of New Radio Physical Uplink Shared Channel Res...

引用

Electrical Electronics and Computing Technologies (ICEECT), International Conference on

作者： Deepak Upadhyay Mridul Gupta Kunj Bihari Sharma Abhay Upadhyay Satya Prakash Yadav Dept. of Computer Science and Engineering Graphic Era Hill University Dehradun India Dept. of Electronics and Communication Engineering Graphic Era Deemed to be University Dehradun India Dept. of Computer Science and Engineering Graphic Era Deemed to be University Dehradun India School of Computer Science Engineering and Technology Bennett University Greater Noida India

ISBN: (数字)9798350378092

ISBN: (纸本)9798350378108

This paper explores the resource allocation optimisation of New Radio Physical Uplink Shared Channels with an emphasis on the effective implementation of Phase Tracking Reference Signals and Demodulation Reference Signals in 5G networks. Understanding how important these reference signals are to dependable communication, we created a Python framework to model and display their distribution on a time-frequency grid. By carefully modifying important factors including mapping type, PRB allocation, and symbol allocation, our method greatly increased resource efficiency, decreased overhead, and improved signal quality. The results show how sophisticated resource allocation techniques may be used to maximise system performance, providing important information for the creation of more reliable and effective 5G NR communication systems

关键词： Wireless communication Time-frequency analysis System performance Symbols New Radio Resource management Reliability Uplink Optimization Demodulation

来源：评论

学校读者我要写书评

暂无评论

Deep Variational Sequential Monte Carlo for High-Dimensional Observations

arXiv

引用

arXiv 2025年

作者： van Nierop, Wessel L. Shlezinger, Nir van Sloun, Ruud J.G. Dept. of Electrical Engineering Eindhoven University of Technology Eindhoven Netherlands Dept. of Electrical and Computer Engineering Ben-Gurion University of the Negev Beer-Sheva Israel

Sequential Monte Carlo (SMC), or particle filtering, is widely used in nonlinear state-space systems, but its performance often suffers from poorly approximated proposal and state-transition distributions. This work introduces a differentiable particle filter that leverages the unsupervised variational SMC objective to parameterize the proposal and transition distributions with a neural network, designed to learn from high-dimensional observations. Experimental results demonstrate that our approach outperforms established baselines in tracking the challenging Lorenz attractor from high-dimensional and partial observations. Furthermore, an evidence lower bound based evaluation indicates that our method offers a more accurate representation of the posterior distribution. © 2025, CC BY-NC-ND.

关键词： State space methods

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：