检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Recent Advances in science and Engineering Technology, ICRASET 2024

作者： Pandiarajan, Rajkumar Jagannathan, J. Ramesh, P.S. Ponmalar, A. Sudha School of Computing Kalasalingam Academy Of Research and Education Department of Information and Technology Krishnankoil Virudhunagar India Vellore Institute of Technology School of Computer Science Engineering and Information Systems Department of Software and Systems Engineering Katpadi Vellore India Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tamilnadu Chennai India R.M.K. Engineering College Tamilnadu Chennai India Saveetha Institute of Medical and Technical Sciences Simats University Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350388602

This research aims to explore the use of modern complex defensive machine learning algorithms in the provision of predictive analytics for health improvement. Incorporating electronic health records, medical image information, and genomic data the work proposes and assesses multiple machine learning models including deep learning, ensemble learning, and reinforcement learning. The main findings shown very high performance in disease prediction, in chronic illness and in the application of efficiency improvements in hospitals as a whole. Overall, such threats as data quality, data privacy, and model interpretability have been discussed in the research and emphasize the importance of the machine learning approach in healthcare. It is highlighted that further development and integration of the interdisciplinary approaches as well as the use of the transparent and interpretable artificial intelligence and machine learning models can be urgent to increase the acceptance among the healthcare staff. This paper enhances the literature on applying machine learning in healthcare systems adding to the repertoire of knowledge for improved patient care. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Securing Multi-Tenant Cloud Environments with Fully Homomorphically Encrypted Secure Multiparty Computation

Securing Multi-Tenant Cloud Environments with Fully Homomorp...

引用

2024 IEEE International Conference on Recent Advances in science and Engineering Technology, ICRASET 2024

作者： Ponmalar, A. Pandiarajan, Rajkumar Sudha, I. Ramesh, P.S. Jagannathan, J. R.M.K. Engineering College Tamilnadu Chennai India School of Computing Kalasalingam Academy Of Research and Education Department of Information and Technology Krishnankoil Virudhunagar India Saveetha Institute of Medical and Technical Sciences Simats University Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu Chennai India Vellore Institute of Technology School of Computer Science Engineering and Information Systems Department of Software and Systems Engineering Katpadi Vellore India

ISBN: (纸本)9798350388602

The aim of this work is to examine the application of FHE-SMPC as a viable security model for protecting the tenant isolation in multi-tenant cloud model. In multi-tenant environments, where various customers use the same cloud system, controlling the data leakage and protecting privacy is a major issue. Actual safeguards fail to meet the needs of data protection during processing, therefore, the introduction of highly elaborate encryption processes must happen. This research work focuses on the use of FHE technique and SMPC such that data can undergo processing while the plaintext remains unknown to any party. A kind of approach is based on the acquisition of synthetic and real data sets, system-level architecture, and cryptographic algorithms using open-source libraries with cloud service providers. The results of such implementation indicate that despite the fact that the FHE-SMPC system has a considerable computational overhead in comparison with classical schemes it is very secure and protected against different types of cryptographic attacks. The problem of scalability is still an open issue, but the complex is quite efficient with various data types that is why it can be used in various cloud applications. This paper offers a pertinent solution for security of data that is housed in multitenant environment and will go along way in creating fertile ground for research and innovation in secure clouding. © 2024 IEEE.

关键词： Cloud security

来源：评论

学校读者我要写书评

暂无评论

Advanced Multi-Spectral Image Processing Techniques for Enhanced Remote Sensing and Comprehensive Environmental Monitoring in Diverse Ecosystems

Advanced Multi-Spectral Image Processing Techniques for Enha...

引用

2024 IEEE International Conference on Recent Advances in science and Engineering Technology, ICRASET 2024

作者： Jagannathan, J. Ponmalar, A. Pandiarajan, Rajkumar Sudha, I. Ramesh, P.S. Vellore Institute of Technology School of Computer Science Engineering and Information Systems Department of Software and Systems Engineering Katpadi Vellore India R.M.K. Engineering College Tamilnadu Chennai India School of Computing Kalasalingam Academy Of Research and Education Department of Information and Technology Krishnankoil Virudhunagar India Saveetha Institute of Medical and Technical Sciences Simats University Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tamilnadu Chennai India

ISBN: (纸本)9798350388602

The research is aimed at improvement of multi-spectral image analysis for remote sensing and monitoring the environment at various ecosystems. A combined spectral imagery encompasses several spectrums at a time compared to single spectral imagery that takes only one spectrum at an instance or at a given area to cover all these spectrums. The study employs digital high resolution satellite images and ground based data to quantify the vegetation vigour, water quality, soil characteristics and changes in land cover. Features, indexes, and classification routines are employed to process the data that is collected with the aid of avionics and other peripherals. This provincial level modelling highlights important gains in environmental status, which includes the general improvement in vegetation condition, water quality as well as physical properties of the soil in the province. This study focuses on the complementary possibilities of integration of multi-spectral imaging with other remote sensing technologies and the high performance of data processing. These techniques play significant roles if used to give current and comprehensive information in the management and conservation of the environment as highlighted in the study. © 2024 IEEE.

关键词： data analysis environmental monitoring image processing techniques machine learning Multi-spectral imaging remote sensing soil properties vegetation health water quality

来源：评论

学校读者我要写书评

暂无评论

Optimizing User Data Privacy and Confidentiality in Cloud Storage systems Through Advanced Obfuscrypt Encryption Methods for Enhanced Security and Efficient Data Protection

Optimizing User Data Privacy and Confidentiality in Cloud St...

引用

2024 IEEE International Conference on Recent Advances in science and Engineering Technology, ICRASET 2024

作者： Ramesh, P.S. Sudha, I. Jagannathan, J. Pandiarajan, Rajkumar Ponmalar, A. Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tamilnadu Chennai India Saveetha Institute of Medical and Technical Sciences Simats University Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India Vellore Institute of Technology School of Computer Science Engineering and Information Systems Department of Software and Systems Engineering Katpadi Vellore India Kalasalingam Academy Of Research and Education School of Computing Department of Information and Technology Krishnankoil Virudhunagar India R.M.K. Engineering College Tamilnadu Chennai India

ISBN: (纸本)9798350388602

With a steady increase in the adoption of cloud storage systems, the client's data are at risk of being leaked. There are several methods of encrypting data which are quite useful but they lack some of the features of today's sophisticated threats. The methodology used in this research propose an encryption framework known as Obfuscrypt to improve the issues of data privacy as well as confidentiality of data stored in cloud storage systems. Obfuscrypt uses conventional encryption strategies incorporated with obfuscation and post-quantum cryptographic algorithms to provide a complex security plan immune to classic and quantum approaches. Some of the proposed other innovations include the decentralised key management with multi-factor authentication and RBAC-ABE as the fine-grained access control techniques. These features make it possible for only the authorized personnel to be in a position to be in a position of decrypting and retrieving the stored data thereby minimizing the possibility of the data being accessed by unauthorized people. The work also considers the issue of performance efficiency of the cloud storage systems. Similar to other symmetric encryption programs, Obfuscrypt uses light encryption algorithms and brings in to play the hardware acceleration so that it may infuse lesser computational overhead in the process of encryption and decryption. As can be clearly seen from the results, the actual work proves that the proposed framework not only offers a higher level of security but does not affect the system performance to a great extent. Also, the study addresses the post-quantum cryptographic algorithm for making the system resistant to an attack that can be posed by quantum computing systems. With the help of these improved algorithms, Obfuscrypt guarantees the permanent data security in the world of constantly emerging cyber threats. © 2024 IEEE.

关键词： Data obfuscation

来源：评论

学校读者我要写书评

暂无评论

Enhancing Healthcare Data Security in Cloud Computing systems through Advanced Homomorphic Encryption Techniques Integrated with Cuckoo Search Optimization Algorithm

Enhancing Healthcare Data Security in Cloud Computing System...

引用

2024 IEEE International Conference on Recent Advances in science and Engineering Technology, ICRASET 2024

作者： Sudha, I. Ramesh, P.S. Ponmalar, A. Jagannathan, J. Pandiarajan, Rajkumar Saveetha Institute of Medical and Technical Sciences Simats University Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tamilnadu Chennai India R.M.K. Engineering College Tamilnadu Chennai India Vellore Institute of Technology School of Computer Science Engineering and Information Systems Department of Software and Systems Engineering Katpadi Vellore India Kalasalingam Academy of Research and Education School of Computing Department of Information and Technology Krishnankoil Virudhunagar India

ISBN: (纸本)9798350388602

The studies in this research are focused on the mix of homomorphic encryption mechanisms and the Cuckoo Search Optimization Algorithm to promote the security of the healthcare data in the cloud computing system. I have observed that cloud solutions are now at the center of the contemporary health care systems, and security of patient's data remains a top priority. Earlier used encryption techniques, though secure if implemented, have problems in the way that data is to be processed first it has to be decrypted and then made ready for use - it is in this phase that data can be easily hacked into. Homomorphic encryption provides solution to this issue since it enables one to perform computations on encrypted data while maintaining its confidentiality. However, it takes a lot of computation which presents a lot of problems even in terms of simple performance. The Cuckoo Search Algorithm, a new nature-inspired metaheuristic, is incorporated into the encryption process to provide further optimization, whilst preserving the security benefits of the algorithm. The use of the proposed methodology takes place employing Python and its deployment at the cloud platform with elaborated dataset containing anonymized records extracted from electronic health records. The outcome proves that there are great enhancements in encryption and decryption time, computational complexity, and capacity, and thereby making the system appropriate for real-world healthcare solutions. This research offers a strong base for protection of healthcare data in cloud and is useful for the enhancement of adaptive, comprehensive and secure cloud computing systems. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Gaussian Differential Privacy Integrated Machine Learning Model for Industrial Internet of Things

引用

SN computer science 2023年第5期4卷 1-7页

作者： Lazar, Arokia Jesu Prabhu Soundararaj, Sivaprakash Sonthi, Vijaya Krishna Palanisamy, Vishnu Raja Subramaniyan, Vanithamani Sengan, Sudhakar Department of Computer Science and Engineering AI & ML CMR Institute of Technology Telangana Hyderabad 501401 India Department of Software Systems School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore 632014 India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram 522502 India Department of Computer Science and Engineering Kongu Engineering College Tamil Nadu Perundurai 638060 India Master of Computer Applications M. Kumarasamy College of Engineering Tamil Nadu Karur 638060 India Department of Computer Science and Engineering PSN College of Engineering and Technology Tamil Nadu Tirunelveli 627152 India

Agriculture, energy, mining, healthcare, and transportation are a few of the top industries transformed by the industrial internet of things (IIoT). Industry 4.0 mainly relies on machine learning (ML) to use the vast interconnectedness and large amounts of IIoT data that IIoT primarily drives. ML approaches are trained on confidential data generated by the IIoT environment often exposes privacy to adversarial assaults. Blockchain-based ML is established in the proposed secured IIoT research work to safeguard and enhance privacy. This research proposes a Gaussian differential privacy-integrated machine learning model (GDPIMLM), created for a scalable and controlled IIoT system, fully connected (FC) layer, implemented blockchain benefits to create a privacy-preserving mechanism while considering other limitations and reasonable time. A probability test using two altered Gaussian distributions (GD) forms the basis for defining Gaussian differential privacy (GDP). Due to a central restriction theorem for differential privacy, GDP is the primary privacy term within the family of Federal differential privacy (f-DP) policies. Ethereum is used to implement experimental evaluations. Data collections show that the recommended method enhances digital data privacy with industry-leading security without reducing performance. The performance analysis of the proposed model of secured industrial internet of things (IIoT) is studied using the accuracy of comparison with existing methods and for diverse distributed entities (DE). The proposed secured IIoT attains a minimal time consumption (TC) of 790 Sec—the highest accuracy of 92%, outperforming the existing method. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Blockchain Industry Industry 4.0 Learning Privacy Security Smart objects

来源：评论

学校读者我要写书评

暂无评论

Improving the Educational Value of Operating systems 23

Improving the Educational Value of Operating Systems

引用

23rd RoEduNet Conference: Networking in Education and Research, RoEduNet 2024

作者： Sava, Cezar Deaconescu, Razvan Kroning, Martin Monti, Antonello Turcanu, Dinu POLITEHNICA of Bucharest Computer Science and Engineering Department Bucharest Romania RWTH Aachen University Institute for Automation of Complex Power Systems Aachen Germany Fraunhofer Center Digital Energy Fraunhofer FIT Aachen Germany University of Moldova Department of Software Engineering and Automatics Technical Chişinǎu Moldova

ISBN: (纸本)9798331540388

Educational operating systems are crucial for facilitating learning in the digital age, as they exist at the intersection of technology and education. While their technical role is well understood, improving their educational value requires enhancing traditional approaches. This paper explores ways to enrich educational operating systems not just through technological advancement, but also by integrating pedagogical principles. In an ever-changing world, the need for an adaptive and responsive educational operating system to meet diverse student needs is crucial. Through case studies, we analyze how design, interactivity, and accessibility can transform these systems into effective and appealing learning environments. We propose a series of recommendations for the future development of educational operating systems, focusing on enhancing the learning experience and promoting student autonomy, thereby offering a fresh perspective on how technology and education can blend harmoniously and efficiently. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Intrusion Detection for IoT Networks

Deep Learning Based Intrusion Detection for IoT Networks

引用

Ubiquitous Computing and Intelligent Information systems (ICUIS), International Conference on

作者： P. Ananthi K. Nirmaladevi Mothika G Department of Computer Technology-PG Kongu Engineering College Erode Tamilnadu Department of Computer Applications Madanapalle Institute of Technology &Science MSc Software Systems Kongu Engineering College Erode India

ISBN: (数字)9798331529635

ISBN: (纸本)9798331529642

Intrusion detection is crucial for securing IoT networks amid the rapid proliferation of devices, posing significant security challenges. This study offers a unique intrusion detection model for IoT deep learning methods used in networks include Convolutional Neural Networks (CNN), TabNet, and the Transient Search Optimization (TSO) method. The project starts by developing and evaluating distinct intrusion detection components. CNN, specializing in feature extraction, analyzes network traffic for potential intrusions. TabNet, known for interpretability and effectiveness with structured data, captures intricate relationships. The novel TSO algorithm improves the system's ability to detect temporary anomalies. Each component's performance is assessed individually, highlighting unique strengths. TabNet excels in structured IoT data pattern identification, surpassing CNN. The TSO algorithm strengthens temporary anomaly recognition, enhancing IoT network security. An ensemble technique combines CNN and TabNet predictions, reducing false positives and negatives to elevate overall detection accuracy. The ensemble, using both CNN and TabNet, achieves an impressive accuracy rate exceeding 99%, demonstrating significant gains in intrusion detection performance.

关键词： Deep learning Accuracy Intrusion detection Telecommunication traffic Prediction algorithms Ubiquitous computing Convolutional neural networks Internet of Things Transient analysis Optimization

来源：评论

学校读者我要写书评

暂无评论

Learning to Break Deep Perceptual Hashing: The Use Case NeuralHash 22

Learning to Break Deep Perceptual Hashing: The Use Case Neur...

引用

5th ACM Conference on Fairness, Accountability, and Transparency, FAccT 2022

作者： Struppek, Lukas Hintersdorf, Dominik Neider, Daniel Kersting, Kristian Department of Computer Science Technical University of Darmstadt Darmstadt Germany Max Planck Institute for Software Systems Kaiserslautern Germany Safety and Explainability of Learning Systems Carl von Ossietzky University of Oldenburg Kaiserslautern Germany Department of Computer Science and Centre for Cognitive Science Technical University of Darmstadt Darmstadt Germany Hessian Center for Artificial Intelligence Darmstadt Germany

ISBN: (纸本)9781450393522

Apple recently revealed its deep perceptual hashing system NeuralHash to detect child sexual abuse material (CSAM) on user devices before files are uploaded to its iCloud service. Public criticism quickly arose regarding the protection of user privacy and the system's reliability. In this paper, we present the first comprehensive empirical analysis of deep perceptual hashing based on NeuralHash. Specifically, we show that current deep perceptual hashing may not be robust. An adversary can manipulate the hash values by applying slight changes in images, either induced by gradient-based approaches or simply by performing standard image transformations, forcing or preventing hash collisions. Such attacks permit malicious actors easily to exploit the detection system: from hiding abusive material to framing innocent users, everything is possible. Moreover, using the hash values, inferences can still be made about the data stored on user devices. In our view, based on our results, deep perceptual hashing in its current form is generally not ready for robust client-side scanning and should not be used from a privacy perspective.1 © 2022 ACM.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A Robust Development of an Efficient Industrial Monitoring and Fault Identification Model using Internet of Things

A Robust Development of an Efficient Industrial Monitoring a...

引用

2024 IEEE International Conference on Big Data and Machine Learning, ICBDML 2024

作者： Al Belushi, Yahya Yaqoob Obaid Jasmin Dennis, P. Deepa, S. Arulkumar, V. Kanchana, D. Ragini, Y.P. Military Technical College Department of Systems Engineering Oman Vi Institute of Technology Department of Electronics and Communication Engineering Tamil Nadu Chengalpattu India RMD Engineering College Department of Computer Science and Business Systems Tamil Nadu Kavarapettai India Sri Sivasubramaniya Nadar College of Engineering Kalavakkam Department of Information Technology Tamil Nadu Chennai India SRM Institute of Science and Technology Ramapuram Department of Computer Applications Tamil Nadu Chennai India SIMATS Department of Biosciences Saveetha School of Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350374100

Internet of Things (IoT) is rapidly developing technologies and the Internet of Things (IoT) is a network of physical items or effects embedded with computer software, detectors, and network connectivity. The Internet of Things also addresses the issue of centralizing physical bias management online. We are leveraging the Internet of Things (IoT) idea to construct a system that will automatically monitor all artificial processes and issue warnings or expert comments when necessary. nowadays, gas leakage is a serious concern in the house and as well as vigilance. If the gas sense is indeed low, it's because we've been too careless, intolerant, or both to look for it. If the gas position is raised, however, calamity may ensue. In this research, the crucial concept is introduced to prevent this catastrophe from occurring. In this study, we propose an alternate approach to this impending calamity and design a system with integrated sensors, controllers, and some IoT-assisted software. The suggested method, known as the Internet of Things based Industrial Safety System (IoTISS), is compared against the more established Industrial Safety System (ISS) to see how well it performs. In this system, we are monitoring the detection of gas leakages with various warning characteristics as well as other devices are used for monitoring various aspects like humidity and temperature using DHT22 sensor, MQ2 gas monitoring sensor, fire sensor and NodeMCU ESP8266 WiFi module. NodeMCU ESP8266, which doubles as a WiFi module, will receive data from all of these types of sensors. © 2024 IEEE.

关键词： Accident prevention

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：