检索结果-内蒙古大学图书馆

Event-triggered reachable set estimation for synchronization of Markovian jump complex-valued delayed neural networks under cyber-attacks

引用

The European Physical Journal Special Topics 2024年 1-21页

作者： Vadivel, R. Sabarathinam, S. Zhai, Guisheng Gunasekaran, Nallappan Department of Mathematics Faculty of Science and Technology Phuket Rajabhat University Phuket Thailand Faculty of Computer Science National Research University (HSE University) Moscow Russia Department of Mathematical Sciences Shibaura Institute of Technology Omiya Japan Eastern Michigan Joint College of Engineering Beibu Gulf University Qinzhou China

This paper focuses on the reachable set estimation for synchronizing of complex-valued neural networks (CVNNs) using an event-triggered (ET) approach and cyber-attacks. The system parameters are set up using Markovian switching rules. The proposed controller effectively saves the communication resources for the designed CVNNs. The main objective of this paper is to find an ellipsoid that can contain the state trajectory of the system as small as possible in the presence of control. From a physics point of view, the system can be likened to a dynamic system subjected to external perturbations, where the goal is to contain the trajectory of the system’s state within a bounded region, similar to confining particle motion in phase space. To achieve this objective, we propose a novel approach based on the reachable set technique, which allows us to obtain an ellipsoid that contains the state trajectory of the system while minimizing its size. Utilizing the standard Lyapunov–Krasovskii functional (LKF), integral inequality approaches, some sufficient stability formed in terms of linear matrix inequalities (LMIs) are derived for the synchronization of CVNNs under the ET scheme, which can be solved using MATLAB’s YALMIP toolbox. These conditions ensure that the states of the CVNNs converge to zero and that the synchronization error is bounded. Finally, numerical simulation results are provided to demonstrate the practicality and effectiveness of the proposed theoretical results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Heuristic-Based Service Allocation and Price Determination in Cloud Manufacturing Operations for Industrial Parks

Heuristic-Based Service Allocation and Price Determination i...

引用

IEEE International Conference on Automation science and engineering (CASE)

作者： Adarsh Mishra Aastha Jain Muhammad Alfas Shaurya Shriyam Amit Kumar Department of Mechanical Engineering Indian Institute of Technology Delhi New Delhi India Operations Research team at Optym Bengaluru India Department of Computer Science and Engineering Indian Institute of Technology Delhi New Delhi India

Cloud manufacturing enables the delivery of manufacturing services in an on-demand and pay-per-use mode based on a centralized online platform. An important aspect of such cloud manufacturing paradigms that will provide more benefits to the providers and consumers is the deployment of techniques for the optimal allocation of services. This work aims to build heuristic solutions for the manufacturing cloud service allocation (MCSA) problem. A general MCSA problem is formulated and two solution methodologies are proposed, viz., genetic algorithm and iterative double auction mechanism. These two algorithms are tested by using two different methods of market clearance price computation. The double auction method is shown to provide better results in terms of computational efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Constructing the ChatGPT for PDF Files with Langchain – AI

Constructing the ChatGPT for PDF Files with Langchain – AI

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： T. Prem Jacob Beatriz Lucia Salvador Bizotto Mithileysh Sathiyanarayanan Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India Department of Social and Applied Sciences University Center Unifacvest Lages Brazil South America Research & Innovation MIT Square London

ISBN: (数字)9798350359299

ISBN: (纸本)9798350359305

Queries in PDFs can be time-consuming and labor-intensive because of the unstructured nature of the PDF document type and the need for accurate and relevant search results. By applying cutting-edge algorithms for natural language processing to examine PDF documents and extract relevant data, LangChain solves these difficulties. It makes use of an easy search interface, adjustable filters, and efficient indexing and retrieval mechanisms to enhance the search experience. To efficiently retrieve relevant information from PDF documents, users can annotate critical portions, store queries, and create bookmarks with LangChain. The characteristics of LangChain improve overall productivity and greatly simplify PDF querying. Semantic search, driven by the latest Transformer language models, represents a significant evolution in information retrieval systems. This research work explores the capabilities of semantic search to efficiently retrieve documents from large collections in response to natural language queries. Unlike traditional keyword-based approaches, semantic search connects the power of Transformer models to discern meaning, providing users with more contextually relevant and accurate results within seconds. This technology not only enhances the user experience by delivering superior matches from document collections but also lays the foundation for tackling more intricate tasks, like text summarization and question-answering. The research investigates the impact of semantic search on information retrieval efficiency and accuracy, comparing its performance with conventional methods. The findings presented herein not only showcase the immediate benefits of semantic search but also open paths for future research and development in natural language processing and its applications.

关键词： Semantic search Probability density function Portable document format Information retrieval Chatbots Transformers User experience

来源：评论

学校读者我要写书评

暂无评论

DARKFARSEER: Inductive Spatio-temporal Kriging via Hidden Style Enhancement and Sparsity-Noise Mitigation

arXiv

引用

arXiv 2025年

作者： Liang, Zhuoxuan Li, Wei Zhang, Dalin Chen, Yidan Wang, Zhihong Zheng, Xiangping Youssef, Moustafa The College of Computer Science and Technology Harbin Engineering University Harbin150001 China The Spatial Information Research Institute Hangzhou Dianzi University Hangzhou310018 China The American University Cairo Egypt

With the rapid growth of the Internet of Things (IoT) and Cyber-Physical Systems (CPS), widespread sensor deployment has become essential. However, the high costs of building sensor networks limit their scale and coverage, making fine-grained deployment challenging. Inductive Spatio-Temporal Kriging (ISK) addresses this issue by introducing virtual sensors. Based on graph neural networks (GNNs) extracting the relationships between physical and virtual sensors, ISK can infer the measurements of virtual sensors from physical sensors. However, current ISK methods rely on conventional message-passing mechanisms and network architectures, without effectively extracting spatio-temporal features of physical sensors and focusing on representing virtual sensors. Additionally, existing graph construction methods face issues of sparse and noisy connections, destroying ISK performance. To address these issues, we propose DARKFARSEER, a novel ISK framework with three key components. First, we propose the Neighbor Hidden Style Enhancement module with a style transfer strategy to enhance the representation of virtual nodes in a temporal-then-spatial manner to better extract the spatial relationships between physical and virtual nodes. Second, we propose Virtual-Component Contrastive Learning, which aims to enrich the node representation by establishing the association between the patterns of virtual nodes and the regional patterns within graph components. Lastly, we design a Similarity-Based Graph Denoising Strategy, which reduces the connectivity strength of noisy connections around virtual nodes and their neighbors based on their temporal information and regional spatial patterns. We examine existing graph construction approaches with preliminary experiments, identify their limitations, and motivate our work. Extensive experiments demonstrate that DARKFARSEER significantly outperforms existing ISK methods, e.g., the improvement in MAE score reaching as high as 10.58%. Copyright

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Perceptual Study of Emotions: A Comparative Analysis on Audio-Visual Signal of Tamil Children

Perceptual Study of Emotions: A Comparative Analysis on Audi...

引用

IEEE India Conference (INDICON)

作者： Nersisson Ruban A. Mary Mekala Elena Lyakso Olga Frolova M Thenmozhi J Mary Annie Sujitha School of Electrical Engineering Vellore Institute of Technology Vellore India School of Computer Science and Engineering Vellore Institute of Technology Vellore India The Child Speech Research Group St. Petersburg State University St. Petersburg Russia School of Social Sciences and Languages Vellore Institute of Technology Vellore India

ISBN: (数字)9798350391282

ISBN: (纸本)9798350391299

The significance of language is recognizing the emotion is vital. Perceptual studies can reduce the significance of language in understanding the emotions in children. The findings of a perceptual experiment conducted by Russian and Indian specialists to identify Indian children's emotional states through audio and video modalities are presented in this paper. Among various emotions, the children's expressions of joy, neutrality (calm state), sadness, and anger were captured on video and audio. The children were asked to portray these states through their facial expressions and voice pronunciation of words and phrases. The study methodology is explained, and the audio and video clips that specialists from Russia and India accurately identified are examined. It came to light that by observing Indian children's facial expressions, voices, and speech, specialists from Russia and India could identify the primary emotions of “joy, sadness, and anger” as well as their neutral condition. Both cultures have universal and distinctive traits that enable them to identify the emotions of their offspring. The paper describes limitations and depicts future research.

关键词： Emotion recognition Accuracy Cross-cultural communication Cultural differences

来源：评论

学校读者我要写书评

暂无评论

PERSON RETRIEVAL IN PHYSICAL WORLD

PERSON RETRIEVAL IN PHYSICAL WORLD

引用

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Huang, Wenxin Li, Dongyang Hu, Ruimin Liang, Chao Zhong, Xian School of Computer and Information Engineering Hubei University China National Engineering Research Center for Multimedia Software Wuhan University China Research Institute of Wuhan University Shenzhen China School of Computer Science and Technology Wuhan University of Technology China

ISBN: (纸本)9781665438643

Person re-identification (re-ID) gains plenty of achievements as a retrieval problem in constrained camera networks. However, most of the researches are concentrated on visual appearance, they still suffer from the complicated environments in unconstrained urban/campus surveillance scenario due to unreliable visual representations with extremely challenging problems as lack of training samples, amounts of irrelevant crowds, etc. Besides, most of the existing person re-ID datasets neglect the physical truth of realistic investigation application: 1) investigators search only few suspects among amounts of crowds. Moreover, he may not go through by every camera in the surveillance area and may appear in the same camera several times;and 2) the corresponding characteristic in multi-space of the same ID can be verified with each other. Therefore, we propose a person retrieval in physical world (PRPW) dataset with large-scale unconstrained surveillance scenario. It contains over 1.4 million bounding boxes, including 20 labeled IDs and numerous irrelevant crowds captured by 86 cameras. Furthermore, over 30,000 records of 20 mobile trajectories are collected in this dataset, and the 20 mobile trajectories are partially overlapped while passing by 86 cameras. Finally, based on two common senses and a verification experiment, we provide a proposal to tackle with PRPW task on the basis of trajectory association which utilizes global optimization to compensate for the errors caused by visual expression on local observation points. The comparison experiments with two typical unsupervised person re-ID methods are implemented on the constructed dataset. © 2021 IEEE

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Text Mining for Intelligent Information Processing and Analysis

Text Mining for Intelligent Information Processing and Analy...

引用

Smart Generation Computing, Communication and Networking (SMART GENCON), International Conference on

作者： Adarsh Srivastav G. Indira Shweta A. Tiwaskar Avni Garg Shweta Singh Sunanda Das Department of Computer Science & Engineering Vivekananda Global University Jaipur India Department of Electrical and Electronics Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai Department of Computer Engineering Vishwakarma Institute of Information Technology Pune INDIA Centre of Interdisciplinary Research in Business and Technology Chitkara University Institute of Engineering and technology Chitkara University Punjab India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Department of Computer Science and Engineering Faculty of Engineering and Technology Bangalore Karnataka India

textual content Mining is the process of extracting meaningful information from large volumes of unstructured text. it's far a form of synthetic intelligence used to investigate and interpret files along with consumer feedback, emails, transcripts, net logs, surveys, and on line documents. Its intention is to discover hidden shape, patterns, institutions, and correlations in textual facts in order to draw inferences and broaden new insights. textual content Mining allows a deeper level of intelligence and selection-making by means of uncovering which means from unstructured textual facts. by means of utilising present day statistical strategies and herbal Language Processing (NLP), text Mining can produce automatic fashions that interpret and translate textual content into intelligent information which can be used to make correct predictions and provide actionable insights. textual content Mining is also being used to find out new trends, categorize client sentiment, locate correlations in purchaser comments, and section document collections. eventually, text Mining is being used to assist automate selection-making by automating workflows, processing massive volumes of text in a fragment of time, and providing deep insights into patron conversations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and Development of Embedded Controller with Wireless Sensor for Power Monitoring through Smart Interface Design Models 2

Design and Development of Embedded Controller with Wireless ...

引用

2nd International Conference on Augmented Intelligence and Sustainable Systems, ICAISS 2023

作者： Ramesh, S.M. Rajeshkannan, S. Pundir, Sumit Dhaliwal, Navdeep Mishra, Sanjay Saravana, B Shanthi Kpr Institute of Engineering and Technology Department of Electronics and Communication Engineering Tamil Nadu Coimbatore India St.Joseph's College of Engineering Omr Department of Electronics and Communication Engineering Tamil Nadu Chennai India Graphic Era Deemed to Be University Department of Computer Science and Engineering Uttarakhand Dehradun India Lovely Professional University Division of Research and Development Punjab Phagwara India Uttaranchal University Division of Research and Innovation Uttarakhand Dehradun India Adhiparasakthi College of Engineering Department of Electrical and Electronics Engineering Tamil Nadu Kalavai India

ISBN: (纸本)9798350325799

The advanced innovation in the power electronics system paved a numerous ways in the development and monitoring of power consumption. This helps to maintain the demand side management to adopt several measures in limiting the consumption of power. This is implemented through embedded system with artificial intelligence techniques. These systems are highly reliable and stable in performing operations. The important objective of the proposed system includes the power monitoring and controlling through embedded controllers. These systems are integrated with wireless sensor network for enabling data storage in the network with higher security concerns. The stored data are used for optimization process. This includes image processing techniques with feature extraction. The power monitoring system is implemented by automatically evaluating the environmental conditions through sensors and functions based upon the priority. They are implemented with remote monitoring and control systems with providing real time information to the user's mobile phone. The communication network are enhanced through the internet of things. This is enhanced through priority scheduling techniques through random forest algorithm. Thus, the overall system helps in enabling optimum power consumption through machine learning. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Joint Radio Frequency and Optical Spectral Optimization for High-Speed Wide Area Fiber Optic Communications

Joint Radio Frequency and Optical Spectral Optimization for ...

引用

Smart Generation Computing, Communication and Networking (SMART GENCON), International Conference on

作者： Vivek V Aditya Kumar S. Yuvaraj Vaishali A Ashu Katyal Girija Shankar Sahoo Department of Computer Science and Engineering Faculty of Engineering and Technology Bangalore Karnataka India Department of Computer Science & Engineering Vivekananda Global University Jaipur India Department of Electronics and Communication Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai Department of Computer Engineering Vishwakarma Institute of Information Technology Pune INDIA Centre of Interdisciplinary Research in Business and Technology Chitkara University Institute of Engineering and technology Chitkara University Punjab India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India

This paper affords a progressive approach to high-pace wide area fiber optic (WAFO) communications by way of combining radio frequency (RF) and optical spectral optimization strategies. This method presents a new approach to the longstanding task of reaching high-pace, long-distance transmission over current networks. The optimization consists of maximizing the spectral performance of the RF and optical structures with the aid of the use of techniques which includes frequency-agile modulation codec's, linear dispersion compensation, and spectral shaping strategies. Moreover, dynamic optical and RF network routing algorithms are proposed to enhance potential and reduce latency. The proposed optimization is confirmed thru enormous simulation and numerical analysis. Results indicate big overall performance gains in phrases of spectral performance, records price, postpone, and reliability. This joint RF-optical optimization approach is an efficient and value-effective answer for WAFO networks and ought to notably benefit large-scale and future WAFO deployments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A self-supervised network for image denoising and watermark removal

引用

Neural Networks 2024年 174卷 106218页

作者： Tian, Chunwei Xiao, Jingyu Zhang, Bob Zuo, Wangmeng Zhang, Yudong Lin, Chia-Wen PAMI Research Group University of Macau 999078 China School of Computer Science Central South University Changsha410083 China School of Computer Science and Technology Harbin Institute of Technology Harbin150001 China School of Computing and Mathematics University of Leicester LeicesterLE1 7RH United Kingdom Department of Electrical Engineering and the Institute of Communications Engineering National Tsing Hua University Hsinchu300 Taiwan

In image watermark removal, popular methods depend on given reference non-watermark images in a supervised way to remove watermarks. However, reference non-watermark images are difficult to be obtained in the real world. At the same time, they often suffer from the influence of noise when captured by digital devices. To resolve these issues, in this paper, we present a self-supervised network for image denoising and watermark removal (SSNet). SSNet uses a parallel network in a self-supervised learning way to remove noise and watermarks. Specifically, each sub-network contains two sub-blocks. The upper sub-network uses the first sub-block to remove noise, according to noise-to-noise. Then, the second sub-block in the upper sub-network is used to remove watermarks, according to the distributions of watermarks. To prevent the loss of important information, the lower sub-network is used to simultaneously learn noise and watermarks in a self-supervised learning way. Moreover, two sub-networks interact via attention to extract more complementary salient information. The proposed method does not depend on paired images to learn a blind denoising and watermark removal model, which is very meaningful for real applications. Also, it is more effective than the popular image watermark removal methods in public datasets. Codes can be found at https://***/hellloxiaotian/SSNet. © 2024 Elsevier Ltd

关键词： Image denoising

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：