检索结果-内蒙古大学图书馆

18th IEEE Conference on Industrial Electronics and Applications, ICIEA 2023

作者： Qiu, Haomeng Liao, Yizhi Chen, Yan Xie, Longhan South China University of Technology Shien-Ming Wu School of Intelligent Engineering Guangzhou China University of Melbourne School of Computing and Information Systems Melbourne Australia Liz Medical Technology Co. Ltd Guangzhou China

ISBN: (纸本)9798350312201

In Internet of Things (IoT) services, wearable devices have been widely used for gesture recognition applications. Recently, gesture recognition based on high-density surface electromyogram (HD-sEMG) has attracted growing attention because its ability to recognize various gestures and achieve good performance. However, most previous studies based on HD-sEMG focused on the forearm while people prefer wrist-worn IoT devices like smartwatches. Although some studies have used single-end sEMG for wrist-worn gesture recognition, its recognition accuracy needs to be improved. An ideal gesture recognition should balance comfort and accuracy. In this work, we propose and design a gesture recognition system based on wrist-worn HD-sEMG. This wearing method is more intuitive and comfortable to use compared to the forearm-worn method. In the test, our proposed gesture recognition system achieves 98.08% accuracy. Our method facilitates a more comfortable gesture recognition without compromising the accuracy. © 2023 IEEE.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Classification of Helpful and Unhelpful Online Customer Reviews Using XLNet and BERT Variants 1

引用

International Conference on Green Energy, computing, and Intelligent technology, GEn-CITy 2023

作者： Bilal, Muhammad Arshad, Muhammad Haseeb Ramzan, Muhammad Department of Computing and Information Systems School of Engineering and Technology Sunway University Petaling Jaya Malaysia Department of Computer Science National University of Computer and Emerging Sciences Chiniot-Faisalabad Campus Chiniot Pakistan Department of Software Engineering University of Sargodha Sargodha Pakistan School of Electronics and Computer Science University of Southampton Malaysia Iskandar Puteri Malaysia

ISBN: (数字)9789819998333

ISBN: (纸本)9789819998326

The majority of businesses have made public appearances on various social media platforms as a result of recent advances in e-commerce and the popularity of social media websites. Customers can share their experiences in the form of online customer reviews, which can assist potential customers in determining the quality of a company and making purchasing decisions. Due to the large volume of published reviews, it becomes difficult for customers to read all of the reviews and assess the quality of the business, resulting in the problem of information overload. Several solutions have been proposed in the literature by researchers using statistical and machine learning techniques to predict the helpfulness of online customer reviews. However, most of the existing solutions are based on the use of various business, review, and reviewer features, which lead to generalizability issues. Moreover, very limited studies have examined the effectiveness of state-of-the-art pre-trained language models for the classification of helpful and unhelpful reviews. Therefore, this study aims to examine the effectiveness of XLNet, Albert, DistilBert, and Roberta for review helpfulness prediction using textual features. The models were fine-tuned using a publicly available dataset of Yelp reviews. The results showed that XLNet achieved the highest F1-score of 0.730 compared to a benchmark of 0.717 achieved by the BERT base model. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Sales

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

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

Approach to Studying information Dissemination in Social Networks with Simulation Tools

Approach to Studying Information Dissemination in Social Net...

引用

International Conference on Application of information and Communication Technologies (AICT)

作者： Alexander Kolesnikov Elena Zamyatina Lyudmila Lyadova Viacheslav Lanin Department of Computing Systems Software Perm State University Perm Russia Department of Information Technologies in Business HSE University Perm Russia

ISBN: (数字)9798350387537

ISBN: (纸本)9798350387544

To understand information dissemination researchers must combine different methods. The lack of social network research tools combining different analysis methods is a problem for users. An approach to studying social networks based on using simulation system TriadNS is proposed in paper. The important characteristics of social networks and the metrics that allow you to evaluate them are discussed. information dissemination models are described. The paper provides a description of simulation tools to explore both structural characteristics and dynamic behavior of social networks, to study not only virtual networks, but also real ones. The results of calculating and visualizing different metrics and executing simulation experiments are demonstrated.

关键词： Measurement Analytical models Visualization Social networking (online) Simulation Data visualization Static analysis Programming Ontologies Data models

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

Unimodular Complete Complementary Sequence with Optimal Trade-off between Auto- and Cross-ambiguity Functions for MIMO Radars

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-11页

作者： Li, Yuke Zhou, Yongxing Li, Xueru Wang, Junbo Wang, Yutong Fan, Lili Wang, Fei-Yue Waytous Co. Ltd. Beijing China Consumer BG Huawei Technologies Co. Ltd Beijing China School of Software Northwestern Polytechnical University Xi'an China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Beijing China School of Information and Electronics Beijing Institute of Technology Beijing China

It is difficult to design unimodular sequences with both good auto-ambiguity functions (AF) and cross-ambiguity functions (CAF), due to its nonconvex and higher cardinality property. To address this problem, we propose a Pareto optimization framework to reach an optimal tradeoff between AF and CAF. Besides, we also propose a novel convolution-based multi-objective optimization algorithm to optimize the conventional metrics including peak sidelobe level (PSL) and integrated sidelobe level (ISL). In this way, the generated sequences are Doppler resilient with the desired shape of aperiodic or periodic AFs. Compared with the state-of-the-art methods, simulation experimental results indicate the PSL metric of AF and CAF can be both suppressed to -72dB under the same system parameters, obtaining a minimum of 7 dB gain. IEEE

关键词： Multiobjective optimization

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

QCNN—A Conceptual Framework for Duplicate Removal in Big Data Using Quality Assured Crowd Sourcing Coupled with Neural Networks 1

引用

International Conference on Advances in Communication technology and Computer Engineering, ICACTCE 2023

作者： Shantha Kumari, K. Ashik, Mohamed Gowrishankar, K. Kanmani, P. Data Science and Business Systems SRM Institute of Science and Technology Chengalpattu India College of Computing and Information University of Technology and Applied Sciences Salalah Oman Electrical and Electronics Engineering AMET University Tamil Nadu Chennai India

ISBN: (数字)9783031371646

ISBN: (纸本)9783031371639

Success of an Enterprise depends on the quality of the data available in its backup. The data need to be consistent, error-free and maintain its integrity irrespective of any threats in any form. Quality data is aka clean data helps in the decision-making process of the Enterprise. However due to multiple entry points available in populating a database, there exists the problem of duplication data, which is one form of dirty data. This duplication data has to be removed without compromising the privacy and integrity of the data. The automated computing algorithms have been limited in its capability for the tasks such as labelling, filtering, translating or transcribing data etc. Hence, crowd sourcing famously referred as human computing are used as supplement to identify and eliminate the duplications available in data. However, it is important to understand that the human crowd is prone in error making and it is essential to choose a qualified crowd that does less error. Because the data labelled by the human crowd is fed to the Neural networks further to identify and eliminate the duplication. This paper provides a conceptual framework that aims to identify the duplicate data through qualified crowds and remove the identified duplication using neural network techniques. The framework explains how to qualify the best crowd to do work, so that clean data is assured with the help of ANNs. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

Analysing the Roles of Robotics in Manufacturing Organizations in the Era of Industry 4.0

Analysing the Roles of Robotics in Manufacturing Organizatio...

引用

2024 International Conference on Science, Engineering and Business for Driving Sustainable Development Goals, SEB4SDG 2024

作者： Adetunla, Adedotun Akinlabi, Esther Jen, Tien Chien Ajibade, Samuel-Soma University of Johannesburg Dept. of Mechanical Engineering Science South Africa Northumbria University Dept. of Mechanical & Construction Engineering Newcastle United Kingdom Sunway University School of Engineering & Technology Dept. of Computing & Information Systems Malaysia

ISBN: (纸本)9798350358155

The era of Industry 4.0 has ushered in a new approach in manufacturing, leveraging advanced technologies to transform traditional production methods. Robotics is the science of using robots to improve manufacturing processes with automation, flexibility, and efficiency. This article aims to comprehensively examine the role of robotics in manufacturing within the context of Industry 4.0. It seeks to explore the fundamental principles underlying robotics, their integration with Industry 4.0 technologies, applications across diverse manufacturing sectors, challenges faced in implementation, and the future directions of robotics in shaping the manufacturing landscape. © 2024 IEEE.

关键词： Smart manufacturing

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：