检索结果-内蒙古大学图书馆

9th IEEE International Conference on Smart Structures and Systems, ICSSS 2023

作者： Arivazhagi, P. Kumar, C. Sathish Anand Kandaswamy, Vijay Bala Murugan, P. Sundara Sripriya, T. Kanchana, D. Arasu Engineering College Department of Electronics and Communication Engineering Tamil Nadu Kumbakonam India Dhanalakshmi Srinivasan Engineering College Department of Electronics and Communication Engineering Tamil Nadu Perambalur India R.M.K. Engineering College Department of Electronics and Communication Engineering Tamil Nadu Chennai India St.Joseph's Institute of Technology Department of Management Studies Tamil Nadu Chennai India Jeppiaar Institute of Technology Department of Ece Tamil Nadu Chennai India Srm Institute of Science and Technology Ramapuram Department of Computer Applications Tamil Nadu Chennai India

ISBN: (纸本)9798350384208

Storage external outsourcing, with its emphasis on data from outside distribution, has been growing in popularity in recent years. A number of intriguing issues regarding security and privacy are raised by this development. The lack of responsibility from external storage of information suppliers is a major worry. In order to help consumers verify the availability and integrity of their outsourcing data on insecure storage devices, this paper provides a comprehensive analysis of two schemas/algorithms. The schemas that have been examined are Provable-Data-Possession (PDP) and Proof-of-Retrievability (POR, which stand for indications of accessibility. In order to reassure customers that their data is safe on untrusted data storages, both protocols use cryptography. Lightweight Cipher Policy Assisted Cloud Data Handler (LCPCDH) is a new model for managing highly secure, lightweight cloud storage. It is cross-validated with the traditional RSA based Cloud Storage Scheme (RSACSS) to assess its performance. A hybrid of RSA with a standard cloud storage solution is the only tried-and-true approach here. According to this new model, the public verifier and the cloud provider neither have access to the actual signatures that authenticate cloud data. However, there are still reliable methods for checking the legitimacy of cloud-based data. For certain unique cases, such as outsourcing electronic checks and contracts, it might be helpful. In order to safeguard the confidentiality of the authentication system and enable blockless confirmation, we have developed a new authenticator named LCPCDH. In this paper, we build the first remote information ownership verification system for cloud storage using privacy-preserving authenticators, based on LCPCDH. Our suggested approach is tested through theoretical analysis and simulated tests to ensure its security and efficiency. The outcomes validate the safety and efficacy of our suggested paradigm. © 2023 IEEE.

关键词： Cloud storage

来源：评论

学校读者我要写书评

暂无评论

Automated Digitally Modulated Signal Recognition and Classification using Machine Learning with Multimodal Information 2

Automated Digitally Modulated Signal Recognition and Classif...

引用

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

作者： Kalaiarasi, N. Walid, Md. Abul Ala Das, Shyamali Nanmaran, R. Srimathi, S. Beschi, I.S. Rmk College of Engineering and Technology Department of Ece India Department of Computer Science and Engineering India Cmr Institute of Technology Department of Artificial Intelligence and Machine Learning Bengaluru India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Electronics and Communication Engineering Tamilnadu Chennai India Saveetha School of Engineering Simats Department of Bio Technology Tamilnadu Chennai India Department of Computer Applications Chennai India

ISBN: (纸本)9798350325799

Recently, the pattern detection of communication modulation signals takes obtained important attention in many application regions like civilian field, military, and so on. It develops vital to proposal a safe and robust feature extraction (FE) system to effectively detect the many signal modulation varieties in a difficult platform. Many works have developed novel approaches for extracting the feature parameters like instant features, fractal features, etc. Besides, machine learning (ML) algorithms are generally utilized for modulation signal classification. This study develops an Automated Digitally Modulated Signal Recognition and Classification using Machine Learning (ADMSR-ML) technique. The aim of the ADMSR-ML approach lies in the proficient recognition and categorization of various kinds of digitally modulated signals. At the initial stage, Sevcik Fractal Dimension (SFD) model is employed to produce a set of feature vectors. For modulation detection and classification, deep extreme learning machine (DELM) model is applied. Eventually, Artificial Bee Colony (ABC) optimization algorithm was used for the optimal parameter selection of the DELM model. To examine the classification results of the ADMSR-ML approach, series of experiment are made. The extensive outcomes indicate the superior performance of the ADMSR-ML technique over other models. © 2023 IEEE.

关键词： Fractal dimension

来源：评论

学校读者我要写书评

暂无评论

An Efficient IoT-based Patient Monitoring System for Heart Disease Prediction and Categorization using Optimized Cell Attention based Spiking Neural Network 8

An Efficient IoT-based Patient Monitoring System for Heart D...

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Suryawanshi, P.B. Rawat, Ruchira Deepa, Battu Chakraborty, Subhra Mohanty, Aparajita Taqui, Syed Noeman Ibmrd Po Midc Nr College of Engineering Department of Mba Viladghat Ahmednagar Maharashtra Ahmednagar414 111 India Graphic Era Deemed to be University Department of Computer Science & Engineering Dehradun248 002 India Sv College of Engineering Department of Electronics and Communication Engineering Andhra Pradesh Tirupati517520 India Nitte Meenakshi Institute of Technology Department of Electronics and Communication Engineering Karnataka Bangalore560064 India Viman Nagar Maharashtra Pune411014 India Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Vlsi Microelectronics Tamil Nadu Chennai602105 India

ISBN: (纸本)9798350376425

The smart healthcare patient monitoring system based on Internet of Things (IoTs) capabilities continuously gathers physiological information through wearable sensors attached to the person's body. In this concern, the proposed study presents a novel smart healthcare patient monitoring system based on Cell Attention Spiking Neural Network (CASNN). The proposed CASNN model is obtained by integrating Cell Attention Network (CAN) with Spiking Neural Network (SNN) that provides enhanced performance during heart disease prediction and classification. Initially, preprocessing is performed to remove unwanted noises and duplicate values from the raw physiological data. Secondly, selection of optimal feature subsets is carried out by utilizing Hybrid Mud Ring Osprey Optimization Algorithm (HMROOA). Finally, cardiac disease prediction and categorization is accomplished with the help of CASNN, in which the hyper parameters are optimized using War Strategy Optimization (WSO). As a result, the proposed model accurately identifies the presence or absence of heart disease, which helps in timely diagnosis of heart illness. The physiological data used for analysis is taken from UCI Heart Disease Kaggle Dataset in which 75% of data is used for training and 25% of data are used for testing. The investigational results show that the developed system achieves greater detection accurateness of 99.7%, which is better than the conventional heart disease prediction models. © 2024 IEEE.

关键词： Heart

来源：评论

学校读者我要写书评

暂无评论

Exploratory Data Analysis Based on Micro grids Generation for Control Communication and Monitoring via Wireless Sensor Network 2

Exploratory Data Analysis Based on Micro grids Generation fo...

引用

2nd International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2022

作者： Jain, Bharti Sirdeshpande, Shrinivas Gowtham, M.S. Josephson, P Joel Chakravarthi, M. Kalyan Pant, Bhasker Iftm University Department of Electrical Engineering Uttar Pradesh Moradabad India Vdit Department of Computer Science and Engineering VTU Haliyal India Karpagam Institute of Technology ECE Tamilnadu Coimbatore India St Martin's Engineering College Department of ECE India School of Electronics Engineering VIT-AP University Amaravathi India Graphic Era Deemed to Be University Department of Computer Science & Engineering Uttarakhand Dehradun India

ISBN: (纸本)9781665437899

Modern-day scientists have experienced a wide utilization of wireless sensor networking benefits for offering better cyber-security measures. With the application of WSNs over a smart micro-grid generation, critical security protocols, controlling communication, and monitoring the entire smart power grid system have become easier these days. Due to the application of WSNs systems in recent times, all the complex controlling and monitoring issues have been resolved with enhanced cyber security scopes for a sustainable future. In order to examine the particular research topic, researchers have performed a primary data gathering method by quantitative analysis. Through processing three relevant survey questions, they have conducted a probability sampling method for gathering the responses of almost 70 participants regarding the research topic. All the research outcomes reflect that around 52% of the participants have strongly agreed with the use of WSNs for better communication controlling and monitoring facilities. Apart from this, around 55% of the people have supported that WSNs can aid in more accurate cyber security measures for protecting authentic information. On the other hand, almost 50% of the participants have expressed their negative responses over the use of WSNs towards more error reduction rate in controlling and measuring the overall smart-grid system. Researchers, therefore, are going to investigate the contributions of WSNs to understand their advantages for better smart micro-grid generation management in the sustainable future. © 2022 IEEE.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Boosting the Performance of Transformer Architectures for Semantic Textual Similarity

arXiv

引用

arXiv 2023年

作者： Rep, Ivan Čeperić, Vladimir Department of Electronics Microelectronics Computer and Intelligent Systems Faculty of Electrical Engineering and Computing Zagreb Croatia

Semantic textual similarity is the task of estimating the similarity between the meaning of two texts. In this paper, we fine-tune transformer architectures for semantic textual similarity on the Semantic Textual Similarity Benchmark by tuning the model partially and then end-to-end. We experiment with BERT, RoBERTa, and DeBERTaV3 cross-encoders by approaching the problem as a binary classification task or a regression task. We combine the outputs of the transformer models and use handmade features as inputs for boosting algorithms. Due to worse test set results coupled with improvements on the validation set, we experiment with different dataset splits to further investigate this occurrence. We also provide an error analysis, focused on the edges of the prediction range. © 2023, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

HDLCP: Experimental Analysis and Development of Hybrid Deep Learning Methodology for Crime Scenario Assesment and Prediction 1

HDLCP: Experimental Analysis and Development of Hybrid Deep ...

引用

1st International Conference on Cognitive, Green and Ubiquitous Computing, IC-CGU 2024

作者： Tamilselvi, M. Ravi, C.N. Jayasudha, S. Shahad, P. Karthikeyan, S. Samuthira Pandi, V. Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Electronics and Communication Engineering Tamil Nadu Chennai India CMR Engineering College Department of Computer Science and Engineering Hyderabad Medchal India Prince Shri Venkateshwara Padmavathy Engineering College Department of Science and Humanities Tamil Nadu Chennai India Andhrapradesh Madanapalle India KSR College of Engineering Department of ECE Tamil Nadu Tiruchengode India Centre for Advanced Wireless Integrated Technology Chennai Institute of Technology Tamil Nadu Chennai India

ISBN: (纸本)9798350361780

For a variety of reasons, prediction is utilized in nearly every industry. Many societal functions, like as crime prediction, are served by it. Data mining tools abound when it comes to traditional prediction. These approaches lack accuracy when dealing with new kinds of data and are somewhat outdated. They take a lot of time as well. In place of the antiquated data mining methods, Artificial Neural Networks function well. This study employs a Hybrid Deep Learning based Crime Prediction (HDLCP) model to forecast criminal activity;the model is then tested for accuracy using the Decision Tree (DT) technique for cross-validation. Using the current datasets, additional information is anticipated to be extracted. Criminal activity is perilous and pervasive, affecting societies all across the globe. Life expectancy, GDP growth, and national prestige are all impacted by crime rates. New methods and sophisticated technologies are required to enhance crime analytics in order to safeguard communities and ensure the safety of society as a whole. A number of crime probabilities in a certain area may be studied, detected, and predicted by the suggested approach. Using a number of data mining approaches, the author explains the many forms of criminal study and crime prediction. © 2024 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Design and Development of a Microcontroller Based Fingerprint-Attendance System 4

Design and Development of a Microcontroller Based Fingerprin...

引用

4th International Conference on Ubiquitous Computing and Intelligent Information Systems, ICUIS 2024

作者： Mbengwa, Kaloso Samikannu, Ravi Rohini, R. Begam, K.Maruliya Kanimozhi, G. Yahya, Abid Botswana International University of Science and Technology Department of Electrical and Communications Systems Engineering Palapye Botswana Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Department of Ece Chennai India Vivekanandha College of Engineering for Women Department of Computer Science and Engineering Tiruchengode India Periyar Maniammai Institute of Science and Technology Department of Electrical and Electronics Engineering Thanjavur India Center for Smart Grid Technologies School of Electrical Engineering Vellore Institute of Technology Tamil Nadu Chennai India

ISBN: (纸本)9798331529635

In the modern era of rapidly advancing technology, organizations across various sectors are continuously seeking innovative solutions to enhance operational efficiency, streamline processes, and improve overall productivity. One area that significantly impacts these goals is the management of employee/student attendance. Traditional manual attendance tracking methods often lead to inaccuracies, inefficiencies, and increased administrative overhead. Recognizing this challenge, this proposal is to bring forth developing a microcontroller-based implementation of a Fingerprint-Based Attendance System. The system uses the power of biometric authentication to improve how attendance is recorded and managed. Firstly, this system provides real-time attendance tracking, reducing the delay in data processing and enabling immediate access to attendance records. Secondly, the proposed system ensures a high level of accuracy in attendance recording. Thirdly, this system promotes enhanced security. © 2024 IEEE.

关键词： Microcontrollers

来源：评论

学校读者我要写书评

暂无评论

Ai Machine Learning: Transformer Models For Enhanced Natural Language Processing - Techniques And Applications 12

Ai Machine Learning: Transformer Models For Enhanced Natural...

引用

12th International Conference on Internet of Everything, Microwave, Embedded, Communication and Networks, IEMECON 2024

作者： Pragith, S. Karthik, G.M. Sripriya, T. Rajasekaran, E. Periannasamy, S. Manthandi Aslam, Mohamed Zubair M.A. Department of Computer Science Engineering Vellore Institute of Technology Tamil Nadu Vellore India Vellore Institute of Technology Tamil Nadu Vellore India Department of ECE Jeppiaar Institute of Technology Tamil Nadu Chennai India Department of Science and Humanities V.S.B Engineering College Tamil Nadu Karur India Department of Electronics and Communication Engineering Mallareddy Engineering College for Women Maisammaguda Hyderabad India Department of AI &DS Dhanalakshmi College of Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350387315

Modern technologies are needed to strengthen network security defenses because of the increase in cyber attacks in recent years. Because deep learning in particular allows for real-time threat identification and thorough performance evaluation, artificial intelligence (AI) has become a powerful tool for improving cybersecurity measures. This study examines how deep learning methods can be used in AI cybersecurity frameworks, with an emphasis on how well they can detect and counteract changing cyberthreats. The use of convolutional neural networks (CNNs) and deep neural networks (DNNs) for anomaly detection and pattern identification in network traffic is specifically discussed. The study also investigates the integration of AI-driven analytics to assess the performance and efficacy of security protocols, offering insights into optimizing defensive strategies against sophisticated cyber attacks. By leveraging AI capabilities, organizations can achieve proactive threat management, enhance incident response times, and fortify their networks against emerging cyber threats. This abstract sets the stage for a comprehensive exploration of AI's role in cybersecurity, highlighting its transformative impact on network security operations. © 2024 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

The Design and implementation of a double layered Security Network with an Authentication System through Block chain Technology 3

The Design and implementation of a double layered Security N...

引用

3rd International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2023

作者： Shakeel, Mohammed Krishnammal, P. Muthu Vekariya, Vipul Akram, Shaik Vaseem Kumar, Parvathapuram Pavan Kapila, Dhiraj Invertis University Faculty of Computer Applications Bareilly India VIT-AP University School of Electronics Engineering Andhra Pradesh Amaravati India Parul University Department of PIET India Uttaranchal University Uttaranchal Institute of Technology India St. Martin's Engineering College Department of ECE Telangana Secunderabad India Lovely Professional University Department of Computer Science & Engineering Punjab Phagwara India

ISBN: (纸本)9798350399264

With more and more connected devices joining IoT networks, protecting their communications is becoming more difficult. The distributed ledger technology known as blockchain has the potential to solve the security issues plaguing 5G-enabled IoT networks. This article provides a layered blockchain security strategy to protect Internet of Things networks and make their deployment simpler. Using clustering, the complex multi-layer structure is simplified. The K-unknown clusters in the IoT network are generated by use of a hybrid Evolutionary Computation Methodology involving Simulated Annealing and Genetic Algorithms. The chosen cluster chiefs have authority over local authentication and permissions. By creating a private blockchain network on a local level, cluster administrators and critical nodes can streamline their interactions. This type of blockchain also facilitates authentication on a network, but it also adds an extra layer of security and integrity. The proposed framework makes use of Hyperledger Fabric, an open-source implementation of Distributed ledger technology. The encryption of data transmitted between nodes is ensured by the use of a global distributed ledger technology, which is instated in the base stations. As opposed to previously disclosed methods, simulation results show that the proposed clustering algorithm is effective. Finally, it is shown that the envisaged portable cryptocurrency architecture achieves a better latency/capacity tradeoff than a conventional global blockchain. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Medical Image Segmentation Using Deep Learning Techniques: Advancement and Challenges 3

Medical Image Segmentation Using Deep Learning Techniques: A...

引用

3rd International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2023

作者： Gopinath, B. Vinay Kumar, V. Kag, Hitesh Joshi, Kapil Rajput, Akshay Kapila, Dhiraj Kumaraguru College of Technology Department of Electronics and Communication Engineering Tamilnadu Coimbatore641049 India Anurag University Department of Ece Telangana Hyderabad India Marwadi University Department of CE-AI Rajkot India Uttaranchal University Uttaranchal Institute of Technology India Graphic Era Deemed to Be University Department of Computer Science & Engineering Uttarakhand Dehradun248002 India Lovely Professional University Department of Computer Science & Engineering Punjab Phagwara India

ISBN: (纸本)9798350399264

An abundance of articles documenting the efficacy of deep learning in the area of medical picture segmentation attest to its widespread adoption and application for this purpose. A comprehensive topical overview of deep learning algorithms for medical picture segmentation is provided. There are two novel additions to this study. As a first step, we classify the most popular literatures according to a multi-level structure that ranges from coarse to fine, in contrast to traditional questionnaires that straightforwardly divide literatures of deep learning on medical image segmentation into several groups and incorporate articles in depth for each group. Second, although unsupervised learning methods were introduced in many older surveys, they are not widely used now, therefore this work only covers supervised and poorly supervised methods. We provide a literature review of supervised learning strategies, focusing on three key areas: network block design, backbone network selection, and loss function optimization. We explore the literature on weakly supervised learning strategies in terms of data enhancement, transfer learning, and interactive categorization, each of which stands on its own. This study organizes the literatures in a totally different way from previous ones, making it easier for readers to comprehend the key logic and leading them to consider acceptable advances in medical picture segmentation utilizing deep learning methodologies. © 2023 IEEE.

关键词： Deep learning

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：