检索结果-内蒙古大学图书馆

1st IEEE International Conference on Automation, Computing and Renewable Systems, ICACRS 2022

作者： Krishnamoorthy, N. Amuthadevi, C. Geedtha, M.K. Reddy, Poli Lokeshwara Anitha Rani, K.S. Gopinathan, R. Department of Masters in Computer Application SRM Institute of Science and Technology Ramapuram Campus Tamil Nadu Chennai600089 India Department of Computational Intelligence SRM Institute of Science and Technology Tamil Nadu Kattankulathur603203 India Department of Information Technology Vel Tech Multi Tech Dr. Rangarajan Dr. Sakunthala Engineering College Tamil Nadu Chennai600062 India Department of Electronics and Communication Engineering Anurag University Telangana Hyderabad500088 India School of CSA REVA University Karnataka Bangalore560064 India Department of Mechatronics Engineering Sri Krishna College of Engineering and Technology Tamil Nadu Coimbatore641008 India

ISBN: (纸本)9781665460842

The use of digital images has become more important in numerous industries, including journalism, medical diagnosis, law enforcement, and forensics. Images could be easily modified due to the availability of photo-altering tools and software, which can distort the original information. The availability of low-cost and simple image-editing software has also drastically decreased the time and money needed to engage in image tampering. This destroys the purity of the image, making it vulnerable to misuse by anyone. Copy-move, splicing, and enhancement falsification are prominent methods used to create fake images. Using a combination of two or more images, a new image is created called splicing, which may be shared across many online channels and used to spread information and impact target audiences. The discovery could have beneficial as well as negative results. Consequently, it is important to provide a method that can identify the splicing forgery in an image. The study used a Deep Learning (DL) model named mobileNet to distinguish between authentic and manipulated images. Both the training and testing of the DL model make use of the CASIA data. Resizing and enhancing methods are used to process the collected data. Accuracy, F1 score, and recall are employed to test the reliability of the created DL model. © 2022 IEEE

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Graph Neural Networks for Graphs with Heterophily: A Survey

arXiv

引用

arXiv 2022年

作者： Zheng, Xin Wang, Yi Liu, Yixin Li, Ming Zhang, Miao Jin, Di Yu, Philip S. Pan, Shirui Monash University Melbourne Australia The Department of Computer Science Zhejiang Normal University Jinhua China Monash University Melbourne Australia The Key Laboratory of Intelligent Education Technology Application of Zhejiang Province Zhejiang Normal University Jinhua China Shenzhen China The School of Computer Science and Technology Tianjin University Tianjin China The Department of Computer Science University of Illinois at Chicago Chicago United States Griffith University QLD Australia

Recent years have witnessed fast developments of graph neural networks (GNNs) that have benefited myriads of graph analytic tasks and applications. In general, most GNNs depend on the homophily assumption that nodes belonging to the same class are more likely to be connected. However, as a ubiquitous graph property in numerous real-world scenarios, heterophily, i.e., nodes with different labels tend to be linked, significantly limits the performance of tailor-made homophilic GNNs. Hence, GNNs for heterophilic graphs are gaining increasing research attention to enhance graph learning with heterophily. In this paper, we provide a comprehensive review of GNNs for heterophilic graphs. Specifically, we propose a systematic taxonomy that essentially governs existing heterophilic GNN models, along with a general summary and detailed analysis. Furthermore, we discuss the correlation between graph heterophily and various graph research domains, aiming to facilitate the development of more effective GNNs across a spectrum of practical applications and learning tasks in the graph research community. In the end, we point out the potential directions to advance and stimulate more future research and applications on heterophilic graph learning with GNNs. Copyright © 2022, The Authors. All rights reserved.

关键词： Message passing

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach of Ecommerce for Sales Prediction Using Hybrid ABC and AdaBoost Approach

A Novel Approach of Ecommerce for Sales Prediction Using Hyb...

引用

Electronics, Computing, Communication and Control technology (ICECCC), International Conference on

作者： N. Kogila R. Rajkumar Sudha Rajesh S. Vennila Department of Commerce B. S. Abdur Rahman Crescent Institute of Science & Technology Chennai Tamil Nadu India Department of Commerce St. Joseph's College of Arts & Science (Autonomous) (Affiliated to Annamalai University Chidambaram) Cuddalore Tamil Nadu India Department of Computational SRMIST Kattankulathur Intelligence School of Computing Chennai Tamil Nadu India Department of Computer Application St. Ann's College of Arts & Science (Affiliated to Annamalai University) Tindivanam Tamil Nadu India

ISBN: (数字)9798350371802

ISBN: (纸本)9798350371819

For online stores to offer speedier shipping times, precise sales forecasting is essential. Online advertising campaigns and the competitive nature of comparable but distinct products are only two of many potential variables that could make accurate sales forecasting more difficult. Typically, these characteristics are disregarded in this approach since traditional methods that rely on time series analysis primarily take sales data into account. Preprocessing, feature selection, and training the model must be carried out in an exact sequence. Data quality concerns, missing information, and product grouping are all part of the preprocessing process. In feature selection, a statistical method known as principal component analysis (PCA) is used to reduce the dimensionality of a dataset that contains multiple linked variables. To train the model, Hybrid-ABC-AdaBoost was utilized. Incredibly, the data show that an accuracy of 97.22 % was reached.

关键词： Training Support vector machines Accuracy Data integrity Computational modeling Time series analysis Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Empirical Analysis of Prediction of Crime and Forecasting With IGWO-SVM Approach

Empirical Analysis of Prediction of Crime and Forecasting Wi...

引用

International Conference on Edge Computing and applications (ICECAA)

作者： R Vasuki Neha Ganvir Rohita Sharma K Senthil Kumar SVHN Krishna Kumari Kamlesh Singh Department of Computer Application Mannar Thirumalai Naicker College Madurai Tamilnadu India KJ College of Engineering and Management Pune Maharashtra India Fine Arts Lovely Professional University Punjab India Department of and Communications School of Computing College of Engineering and Technology SRM Institute of Science and Technology Chennai Tamil Nadu India Department of CSE (Artificial Intelligence and Machine Learning) Vardhaman College of Engineering Telangana India Department of Computer Science and Engineering Graphic Era Hill University Dehradun India

In order to understand the nuances of the crime data from recent years, in-depth analysis is necessary. Involved parties in law enforcement will benefit from this procedure in terms of making arrests and guiding efforts to reduce crime. Strategically or tactically, it benefits from having a better understanding of where, when, and how crimes will occur in the future. However, given the rising incidence of crime in the modern world, developing an effective method for predicting future criminal behavior is a difficult issue. As a result, it is crucial to develop a strategy for predicting criminal activity in order to prevent further crimes and lower crime rates. Researchers are currently attempting to predict criminal behavior based on a variety of factors. SVM, CNN and ANN are just few of the prediction approaches that can be used to assess a model's accuracy. Although their studies have yielded encouraging findings, there are still major blind spots that preclude an accurate prediction of crime hubs. There have been many earlier publications of academic papers on this subject. So, the results are compiled and conducted a comprehensive assessment of all of them in this report. Proposed goal is to catalog the various forms the crime prediction method has taken and the ways in which it might be improved in the future. Preprocessing, feature extraction, and model training are the three main components of the proposed method. Preprocessing includes activities including data cleansing, integration, transformation, reduction, and discretization. It uses principal component analysis to glean features. The model is trained with IGWO-SVM. When compared to two existing models, the proposed model performs exceptionally well.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-view clustering guided by unconstrained non-negative matrix factorization

引用

Knowledge-Based Systems 2023年 266卷

作者： Deng, Ping Li, Tianrui Wang, Dexian Wang, Hongjun Peng, Hong Horng, Shi-Jinn School of Computer and Software Engineering Xihua University Chengdu610039 China School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu611756 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu611756 China Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province Chengdu611756 China Department of Computer Science and Information Engineering National Taiwan University of Science and Technology Taipei106 Taiwan

Multi-view clustering based on non-negative matrix factorization (NMFMvC) is a well-known method for handling high-dimensional multi-view data. To satisfy the non-negativity constraint of the matrix, NMFMvC is usually solved using the Karush–Kuhn–Tucker (KKT) conditions. However, this optimization method is poorly scalable. To this end, we propose an unconstrained non-negative matrix factorization multi-view clustering (uNMFMvC) model. First, the objective function was constructed by decoupling the elements of the matrix and combining the elements with a non-linear mapping function in a non-negative value domain. The objective function was then optimized using the stochastic gradient descent (SGD) algorithm. Subsequently, three uNMFMvC methods were constructed based on different mapping functions and detailed reasoning was provided. Finally, experiments were conducted on eight public datasets and compared with cutting-edge multi-view clustering methods. The experimental results demonstrate that the proposed model has significant advantages. © 2023 Elsevier B.V.

关键词： Non-negative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Aided Intelligent Framework for Condition Monitoring of Electrical Machinery

A Deep Learning Aided Intelligent Framework for Condition Mo...

引用

Devices for Integrated Circuit (DevIC)

作者： Biswarup Ganguly Radha Kumari Ray Arunava Chatterjee Subho Paul Electrical Engineering Department Meghnad Saha Institute of Technology Kolkata India Application Development Associate Accenture Kolkata India Electrical Engineering Department Raghunathpur Govt. Polytechnic Purulia India School of Electrical Engineering and Computer Science Washington State University Pullman WA USA

Single-phase induction motors (SPIM) are fairly efficiently employed in household devices and possess wide applications in the industrial system. Typically, current signature-analysis (CSA) based methods have been used for fault diagnosis, but not always been an efficient solution, especially for fractional kW SPIMs that may be replaced entirely iffaulty. This paper presents a deep learning (DL) based fault detection scheme of a SPIM which is in-service in household devices. The fault detection is done employing a wavelet based deep dense convolutional neural network (W-D2CNN), where several wavelets are used as convolutional filters for convolution operation. The convoluted feature maps are further passed through a proposed nonlinearity, i.e., SLReLU, for richer feature extraction. The uniqueness of the proposed method lies in the feature learning ability, where upper-and lower-layer features of the dense block fuse via concatenation operation. Also, the SL-ReLU has been designed to combine logarithmic function, softsign, and ReLU operation. The designed SL-ReLU minimizes the probability of convoluted output and gradient explosion, due to which training has been improved along with feature learning ability. Comprehensive results reveal the efficacy of the proposed work in terms of performance metrics with state-of-the-art DL frameworks using the same dataset. The proposed work can also be extendable to multiphase-induction machines or any other electrical device working in any environment for fault identification.

关键词： Representation learning Fault diagnosis Training Deep learning Fault detection Feature extraction Explosions

来源：评论

学校读者我要写书评

暂无评论

An Analysis of mobile Security Protocols in Wireless Sensor Networks

An Analysis of Mobile Security Protocols in Wireless Sensor ...

引用

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

作者： Sheril. S Priyanka D. More Rahul Mishra Neeraj Das Ramachandran T Zahid Ahmed Department of Mechanical 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 Mechanical Engineering Faculty of Engineering and Technology Bangalore Karnataka India Department of Computer Science & Application Vivekananda Global University Jaipur India

This examines examines the cutting-edge state of security protocols for wi-fi sensor networks within the mobile communications area. We examine the performance of present protection protocols for wi-fi sensor networks that specialize in their effectiveness, strength-efficiency, and scalability. We then endorse an advanced protection protocol which can higher cope with the security challenges of wi-fi sensor networks. Our new protection protocol incorporates cryptographic algorithms tailored for the unique necessities of wi-fi sensor networks, as well as key trade mechanisms that offer more desirable scalability and energy-performance. We evaluate our proposed security protocol, and examine its tradeoffs in evaluation with existing security protocols. Our consequences display that the proposed protocol is extra comfortable, gives higher scalability, and achieves more electricity-efficiency. We also check out the impact of different routing protocols on the security of wireless sensor networks in cellular communications and analyze how they may be tormented by exclusive security protocols. Our findings advise that a hybrid of two current routing protocols provides suitable security for wireless sensor networks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reconstructing suspended sediment concentrations in the Mekong River Basin via semi-supervised-based deep neural networks

引用

science of the Total Environment 2024年 955卷 176758页

作者： Nguyen, Thi Thu Ha Vu, Duc Quang Doan, Ngoc Phu Chi, Huynh Thi Khanh Li, Peixin Binh, Doan Van An, Yimeng Dung, Pham Tuan Hoang, Tuan A. Son, Mai Thai Laboratory of Environmental Sciences and Climate Change Institute for Computational Science and Artificial Intelligence Van Lang University Ho Chi Minh City Viet Nam Faculty of Environment School of Technology Van Lang University Ho Chi Minh City Viet Nam Department of Computer Science and Information System Thai Nguyen University of Education Viet Nam School of Electronics Electrical Engineering and Computer Science Queen's University Belfast United Kingdom College of Economics and Management Nanjing University of Aeronautics and Astronautics China Master program in Water Technology Reuse and Management Faculty of Engineering Vietnamese-German University Binh Duong Province Ben Cat City Viet Nam

The Mekong River Basin (MRB) is crucial for the livelihoods of over 60 million people across six Southeast Asian countries. Understanding long-term sediment changes is crucial for management and contingency plans, but the sediment concentration data in the MRB are extremely sporadic, making analysis challenging. This study focuses on reconstructing long-term suspended sediment concentration (SSC) data using a novel semi-supervised machine learning (ML) model. The key idea of this approach is to exploit abundant available hydroclimate data to reduce training overfitting rather than solely relying on sediment concentration data, thus enhancing the accuracy of the employed ML models. Extensive experiments on daily hydroclimate and SSC data obtained from 1979 to 2019 at the three main stations (i.e., Chiang Saen, Nong Khai, and Mukdahan) are conducted to demonstrate the superior performance of the proposed method compared to the state-of-the-art supervised techniques (i.e., Random Forest, XGBoost, CatBoost, MLP, CNN, and LSTM), and surpasses existing semi-supervised methods (i.e., CoReg, ⊓ Model, ICT, and Mean Teacher). This approach is the first semi-supervised method to reconstruct sediment data in the field and has the potential for broader application in other river systems. © 2024 The Author(s)

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Pinching Antennas: Principles, applications and Challenges

arXiv

引用

arXiv 2025年

作者： Yang, Zheng Wang, Ning Sun, Yanshi Ding, Zhiguo Schober, Robert Karagiannidis, George K. Wong, Vincent W.S. Dobre, Octavia A. Fujian Provincial Engineering Technology Research Center of Photoelectric Sensing Application Fujian Normal University Fuzhou350117 China School of Information and Control Engineering China University of Mining and Technology Xuzhou221116 China School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China Khalifa University Abu Dhabi United Arab Emirates University of Manchester ManchesterM1 9BB United Kingdom Germany Group Electrical & Computer Engineering Dept. Aristotle University of Thessaloniki Thessaloniki54 124 Greece Department of Electrical and Computer Engineering The University of British Columbia Vancouver Canada Department of Electrical and Computer Engineering Memorial University St. John’sNL Canada

Flexible-antenna systems, such as fluid antennas and movable antennas, have been recognized as key enabling technologies for sixth-generation (6G) wireless networks, as they can intelligently reconfigure the effective channel gains of the users and hence significantly improve their data transmission capabilities. However, existing flexible-antenna systems have been designed to combat small-scale fading in non-line-of-sight (NLoS) conditions. As a result, they lack the ability to establish line-of-sight links, which are typically 100 times stronger than NLoS links. In addition, existing flexible-antenna systems have limited flexibility, where adding/removing an antenna is not straightforward. This article introduces an innovative flexible-antenna system called pinching antennas, which are realized by applying small dielectric particles to waveguides. We first describe the basics of pinching-antenna systems and their ability to provide strong LoS links by deploying pinching antennas close to the users as well as their capability to scale up/down the antenna system. We then focus on communication scenarios with different numbers of waveguides and pinching antennas, where innovative approaches to implement multiple-input multiple-output and non-orthogonal multiple access are discussed. In addition, promising 6G-related applications of pinching antennas, including integrated sensing and communication and next-generation multiple access, are presented. Finally, important directions for future research, such as waveguide deployment and channel estimation, are highlighted. Copyright © 2025, The Authors. All rights reserved.

关键词： Channel estimation

来源：评论

学校读者我要写书评

暂无评论

Any Bluetooth device can be hacked. Know how?

Cyber Security and Applications

引用

Cyber Security and applications 2024年 2卷

作者： Muraleedhara, Prathibha Christo, Mary Subaja J, Jaya Yuvasini  D College of Technology – Information Security and Program Management University of Houston 77204 TX United States Department of Networking and Communication School of Computing SRM Institute of Science and Technology Kantankulathur Chennai India Department of Electronics and Communication Engineering Hindustan College of Engineering and Technology India Assistant Professor Department of Computer Science and Business Systems Thiagarajar College of Engineering Madurai 625015 India

In today's world, Bluetooth technology is integrated into almost every device we use, from wireless headsets, mice, and keyboards to cars and smart home devices. But with the convenience of this technology comes the risk of privacy and security breaches. Each Bluetooth device has potential vulnerabilities that cybercriminals can exploit and take advantage of. It is important to create awareness about various Bluetooth vulnerabilities, exploits, and ways to prevent them. This article examines the dark side of Bluetooth technology by explaining how hackers can find ways to bypass the advanced security features of laptops, phones, cars, or smart home devices to compromise the devices and steal personal sensitive data. Whether it is a casual user of Bluetooth technology or a business owner with multiple devices, understanding these risks is crucial to protecting yourself and your information. This article begins by explaining the basics of Bluetooth technology and how it works. Followed by a list of security risks involved while using Bluetooth and finally, it highlights the best practices to protect the devices and the data they contain. © 2024

关键词： Ad hoc networks and security risk Bluetooth Exploit Threat Vulnerability

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：