检索结果-内蒙古大学图书馆

Face Attribute Convolutional Neural Network System for Data Security with Improved Crypto Biometrics

computer Systems science & engineering 2023年第6期45卷 2351-2362页

作者： S.Aanjanadevi S.Aanjankumar K.R.Ramela V.Palanisamy Department of Computer Applications Alagappa UniversityKaraikudi630003TamilnaduIndia Department of Computer Science and Engineering Sri Raaja Raajan College of Engineering and TechnologyAmaravathipudur630301TamilnaduIndia Department of Electrical and Electronics Engineering Ultra College of Engineering and TechnologyMadurai625020TamilnaduIndia

Due to the enormous usage of the internet for transmission of data over a network,security and authenticity become major *** challenges encountered in biometric system are the misuse of enrolled biometric templates stored in database *** describe these issues various algorithms are implemented to deliver better protection to biometric traits such as physical(Face,fingerprint,Ear etc.)and behavioural(Gesture,Voice,tying etc.)by means of matching and verification *** this work,biometric security system with fuzzy extractor and convolutional neural networks using face attribute is proposed which provides different choices for supporting cryptographic processes to the confidential *** proposed system not only offers security but also enhances the system execution by discrepancy conservation of binary *** Face Attribute Convolutional Neural Network(FACNN)is used to generate binary codes from nodal points which act as a key to encrypt and decrypt the entire data for further *** Artificial Intelligence(AI)into the proposed system,automatically upgrades and replaces the previously stored biometric template after certain time period to reduce the risk of ageing difference while *** codes generated from face templates are used not only for cryptographic approach is also used for biometric process of enrolment and *** main face data sets are taken into the evaluation to attain system performance by improving the efficiency of matching performance to verify *** system enhances the system performance by 8%matching and verification and minimizes the False Acceptance Rate(FAR),False Rejection Rate(FRR)and Equal Error Rate(EER)by 6 times and increases the data privacy through the biometric cryptosystem by 98.2%while compared to other work.

关键词： FACNN biometric cryptography AI FAR FRR EER

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Based Enhancing the Power by Reducing the Harmonics in Grid Connected Inverters

引用

Distributed Generation and Alternative Energy Journal 2024年第1期39卷 137-164页

作者： Sarma, Subramanya S. Sarada, K. Jithendar, P. Maddileti, Telugu Kumar, G. Nanda Kishor Department of EEE Ramachandra College of Engineering Vatluru Andhra Pradesh Eluru534007 India Department of Electrical & Electronics Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram India Department of Electrical and Electronics Engineering MLR institute of Technology Hyderabad India Telangana 500100 India Computer Science and Engineering Malla Reddy University Telangana Hyderabad India

The increasing use of renewable energy systems has led to a rise in the number of grid-connected inverters, which can have a detrimental effect on the superiority and constancy of grid electricity due to the injected current harmonics. In this study, the proportional integral (PI) and proportional resonant (PR) controllers have been investigated for their effectiveness inreducing harmonics in grid-connected inverters. The study also investigates the impact of harmonics compensators (HC) on the control strategies. The results of the study suggest that the implementation of PI and PR controllers in the synchronous frame can effectively reduce the injected current harmonics in grid-connected inverters. The use of harmonics compensators can further enhance the performance of the controllers by reducing the distortion and improving the stability of the grid. The efficiency of the regulator strategies be contingent on the type and level of harmonics in the grid, as well as the design and tuning of the controllers and compensators. The statement that the "PR+HC controller has a superior quality output current" is more specific and suggests that this control method may be more effective than the others in reducing harmonics and enlightening the value of the productivity current. The comparison of the IEEE 1547 standard by three viable inverters from diverse constructors is also noteworthy, as it can provide insights into the compatibility and performance of different types of inverters with the standard. The use of deep learning with the RCNN network for analyzing harmonics and providing information about power is an interesting application of machine learning in power systems research. This approach may have the probable to development the accuracy and competence of harmonics analysis as well as power monitoring in grid-connected inverters. Overall, the study highlights the importance of effective control strategies for managing harmonics in grid-connected inverters, parti

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Dynamic Fair Node Representation Learning 48

Dynamic Fair Node Representation Learning

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Kose, Oyku Deniz Shen, Yanning University of California Irvine Department of Electrical Engineering and Computer Science United States

ISBN: (纸本)9781728163277

Many real-world networks such as social networks, traffic networks vary over time, which can be modeled as dynamic graphs. Despite the significant number of systems that can facilitate from the algorithmic tools over dynamic graphs, dynamic graph representation learning is an under-explored research area. Furthermore, while the fairness of algorithms is essential for their deployment in real-world systems, this issue has never been considered in the context of dynamic graphs to the best of our knowledge. Motivated by this, the present study proposes an efficient online node representation learning framework over dynamic graphs that can also mitigate bias. Specifically, the proposed technique combines different observations (graph structure and nodal attributes) of the same source (attributed graph) in a complementary way while also reducing the intrinsic bias in the learned representations. Experimental results on dynamic graphs show that the proposed online strategy can improve the group fairness measures for node classification together with comparable/better utility to the baselines. © 2023 IEEE.

关键词： dynamic graphs factorization-based node representation fair dynamic embeddings Fairness

来源：评论

学校读者我要写书评

暂无评论

Compensating for Size Effect in Shear Wave Elastography Using Deep Neural Networks 23

Compensating for Size Effect in Shear Wave Elastography Usin...

引用

23rd International Conference on Control, Automation and Systems, ICCAS 2023

作者： Lee, Seungyeop Hwang, Jae Youn Eun, Yongsoon Dgist Department of Electrical Engineering and Computer Science Daegu42988 Korea Republic of

ISBN: (纸本)9788993215274

In ultrasound shear wave elastography (USWE), the elasticity of a small lesion is underestimated due to the wave reflection inside the lesion. This paper proposes using a deep neural network to compensate for the size effect without explicit size information. The deep neural network corrects the underestimation of the elastic modulus. The dataset for the training process consists of 4000 images with lesions of random sizes and elastic moduli, obtained from the k-Wave MATLAB Toolbox. A mean absolute error (MAE) is calculated between the ground truth and the image generated by the generator network for 500 test datasets with the unitary elasticity background. The maximum value of MAE is 0.0082, indicating that the generator network generates images that are similar to the ground truth in size and modulus. When the unitary elasticity background is replaced by the image of the breast phantom, the neural network proves to be effective in size effect compensation. © 2023 ICROS.

关键词： Elasticity

来源：评论

学校读者我要写书评

暂无评论

Enhanced U-Net and PSO-Optimized ANFIS for Classifying Fish Diseases in Underwater Images

引用

International Journal of Fuzzy Systems 2024年第8期26卷 2518-2535页

作者： Khabusi, Simon Peter Huang, Yo-Ping Lee, Mong-Fong Tsai, Meng-Chun Department of Electrical Engineering National Taipei University of Technology Taipei10608 Taiwan Department of Electrical Engineering National Penghu University of Science and Technology Penghu88046 Taiwan Department of Computer Science and Information Engineering National Taipei University New Taipei City23741 Taiwan Department of Information and Communication Engineering Chaoyang University of Technology Taichung41349 Taiwan Department of Aquaculture National Penghu University of Science and Technology Penghu88046 Taiwan General Competency Center National Penghu University of Science and Technology Penghu88046 Taiwan

Fish diseases are among the major limiting factors to increase global aquaculture production. They lead to increased fish mortality, low breeding and growth rates, and low meat quality. The success of aquaculture is heavily dependent on the timely identification of disease. Therefore, we propose a fuzzy U-Net model to automatically identify fish disease from underwater images. U-Net is enhanced with multi-head channel and spatial attention and used to segment infected fish regions from fish disease images. Color pixel intensity features are then extracted from the localized regions, a form of guided feature extraction. Fuzzy C-means clustering is then used to find the cluster centroids and data distribution within the clusters, for the design of fuzzy membership functions. Moreover, the number of clusters are determined by silhouette score. Adaptive neuro-fuzzy inference system (ANFIS) is then trained, tested, and cross-validated for fish disease identification. The model parameters are optimized using particle swarm optimization (PSO) algorithm and compared with gradient-based methods. For image segmentation, the enhanced U-Net achieved a mean intersection over union (IoU) of 86.29%, mean pixel accuracy of 90.94%, mean precision of 93.58%, and mean recall value of 89.94% on 42 test images. Subsequently, ANFIS with PSO achieved overall superior performance on fish disease identification over gradient-based methods, with accuracy of 99.31%, precision of 99.00%, recall of 99.00%, and F1-score of 99.00%. The high-performance results of the optimized ANFIS confirm the robustness and efficacy of the proposed method to automatically identify fish diseases in aquaculture. © The Author(s) under exclusive licence to Taiwan Fuzzy Systems Association 2024.

关键词： Fuzzy inference

来源：评论

学校读者我要写书评

暂无评论

3D Joist Perception, Detection, and Climbing for Hexapod Robot

3D Joist Perception, Detection, and Climbing for Hexapod Rob...

引用

IS and T International Symposium on Electronic Imaging: Intelligent Robotics and Industrial Applications using computer Vision, IRIACV 2023

作者： Li, Yibin Zakhor, Avideh Department of Electrical Engineering and Computer Science University of California Berkeley United States

Avoiding obstacles is challenging for autonomous robotic systems. In this work, we examine obstacle avoidance for legged hexapods, as it relates to climbing over randomly placed wooden joists. Our main motivation is to enable robots to navigate inside tight attic spaces of single-family residential homes in the U.S., which typically contain rows of 4, 6, or 8 inch tall joists placed 16 inches apart from each other. We formulate the task as a 3D joist detection problem, and propose a detect-plan-act pipeline using a simultaneous localization and mapping (SLAM) algorithm to generate a pointcloud and a grid map to expose high obstacles such as joists. A line detector is applied on the grid map to extract parameters of the joist, such as height, orientation, and distance;based on this information the hexapod plans a sequence of leg movements to either climb over the joist or move sideways if the joist is too high. We show that our perception and path planning modules work well on the real-world joists with different heights and orientations. © 2023, Society for Imaging science and Technology.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Challenges in Evaluating Quality of Service in Modern Power Grids 15

Challenges in Evaluating Quality of Service in Modern Power ...

引用

15th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2023

作者： Hilde, Amushembe Sastry, Musti KS Namibia University of Science and Technology Department of Electrical and Computer Engineering Windhoek Namibia

ISBN: (纸本)9798350324433

The quality of service in modern power grids depends on various factors, including outage duration, number of affected consumers, supply adequacy, resolving customer grievances, and network availability. Typically, regional distribution companies manage their respective networks independently in a de-centralized Electricity Supply Industry (ESI). Outage data and reliability indices are generally used to assess the overall service quality. For this, data needs to be collected from different regions support the centralized computational models for determining the reliability indices. However, currently there is no known standard data collection process or a centralized software solution to determine the reliability indices for different regions. To address this problem, this paper focuses on understanding various operational challenges in data collection and supply quality evaluation. Then, it points to the need of classifying outages based on their causes, and then suggests appropriate data models and computational methodologies, with a framework for evaluating and reporting reliability indices. A novel dashboard for reporting various reliability indices from different regions is also presented. © 2023 IEEE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Security and Privacy Challenges in SDN-Enabled IoT Systems: Causes, Proposed Solutions,and Future Directions

引用

computers, Materials & Continua 2024年第8期80卷 2511-2533页

作者： Ahmad Rahdari Ahmad Jalili Mehdi Esnaashari Mehdi Gheisari Alisa A.Vorobeva Zhaoxi Fang Panjun Sun Viktoriia M.Korzhuk Ilya Popov Zongda Wu Hamid Tahaei Institute of Artificial Intelligence Shaoxing UniversityShaoxing312000China Department of Computer Engineering Gonbad Kavous UniversityGonbad-e Kavus49717-99151Iran Faculty of Computer Engineering K.N.Toosi University of TechnologyTehran196976-4499Iran Department of Computer Science and Engineering Saveetha School of EngineeringSaveetha Institute of Medical and Technical SciencesChennai602105India Secure Information Technologies Department National Research University ITMOSt.Petersburg197101Russia School of Electrical and Computer Engineering Shiraz UniversityShiraz71946–84334Iran Department of Computer Science and Engineering Islamic Azad UniversityDamavand***Iran Department of R&D Shenzhen BKD Co.Ltd.Shenzhen518000China

Software-Defined Networking(SDN)represents a significant paradigm shift in network architecture,separating network logic from the underlying forwarding devices to enhance flexibility and centralize ***-rently,the Internet of Things(IoT)connects numerous devices to the Internet,enabling autonomous interactions with minimal human ***,implementing and managing an SDN-IoT system is inherently complex,particularly for those with limited resources,as the dynamic and distributed nature of IoT infrastructures creates security and privacy challenges during SDN *** findings of this study underscore the primary security and privacy challenges across application,control,and data planes.A comprehensive review evaluates the root causes of these challenges and the defense techniques employed in prior works to establish sufficient secrecy and privacy *** investigations have explored cutting-edge methods,such as leveraging blockchain for transaction recording to enhance security and privacy,along with applying machine learning and deep learning approaches to identify and mitigate the impacts of Denial of Service(DoS)and Distributed DoS(DDoS)***,the analysis indicates that encryption and hashing techniques are prevalent in the data plane,whereas access control and certificate authorization are prominently considered in the control plane,and authentication is commonly employed within the application ***,this paper outlines future directions,offering insights into potential strategies and technological advancements aimed at fostering a more secure and privacy-conscious SDN-based IoT ecosystem.

关键词： Security privacy-preserving software-defined network internet of things

来源：评论

学校读者我要写书评

暂无评论

Investigation on radiated emissions of electric aircraft at airports

Investigation on radiated emissions of electric aircraft at ...

引用

2023 International Symposium on Electromagnetic Compatibility - EMC Europe, EMC Europe 2023

作者： Yan, Jiexiong Johansson, Jonny Ekman, Jonas Nilsson, Andreas Wisten, Ake Luleå University of Technology Department of Computer Science Electrical and Space Engineering Sweden

ISBN: (纸本)9798350324006

Electric aircraft are gaining popularity due to their zero-carbon emission, low noise level and low operational cost. Current study regarding electric aircraft centers on safety as well as battery durability and little light has been shed on electromagnetic compatibility (EMC). Electric aircraft, together with their charging stations, are complex systems and their existence at an airport might pose the risk for interference of other electric equipment, for example, communication systems. This paper presents preliminary measurements on electromagnetic emissions from an electric aircraft and its charging station at an airport. Radiated emission measurements were performed from 30 MHz to 1 GHz and the results suggest that the aircraft emits energy mainly below 200 MHz during the charging process and that the general radiation level at the test site challenges the limits for class B equipment in EN 55032. However, the electric aircraft and the charging station do not seem to have influence on the communication systems at the test site. The results could serve as a guidance in terms of charging station installations at airports and the establishment of EMC related regulations about electric aircraft. © 2023 IEEE.

关键词： Electromagnetic compatibility

来源：评论

学校读者我要写书评

暂无评论

Pareto Front Shape-Agnostic Pareto Set Learning in Multi-Objective Optimization

Pareto Front Shape-Agnostic Pareto Set Learning in Multi-Obj...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Ye, Rongguang Chen, Longcan Kou, Wei-Bin Zhang, Jinyuan Ishibuchi, Hisao Southern University of Science and Technology Department of Computer Science and Engineering Shenzhen518055 China The University of Hong Kong Department of Electrical and Electronic Engineering 999077 Hong Kong

ISBN: (纸本)9781665410205

Pareto set learning (PSL) is an emerging approach for acquiring the complete Pareto set of a multi-objective optimization problem. Existing methods primarily rely on the mapping of preference vectors in the objective space to Pareto optimal solutions in the decision space. However, the sampling of preference vectors theoretically requires prior knowledge of the Pareto front shape to ensure high performance of the PSL methods. Designing a sampling strategy of preference vectors is difficult since the Pareto front shape cannot be known in advance. To make Pareto set learning work effectively in any Pareto front shape, we propose a Pareto front shape-agnostic Pareto _Set Learning (GPSL) that does not require the prior information about the Pareto front. The fundamental concept behind GPSL is to treat the learning of the Pareto set as a distribution transformation problem. Specifically, GPSL can transform an arbitrary distribution into the Pareto set distribution. We demonstrate that training a neural network by maximizing hypervolume enables the process of distribution transformation. Our proposed method can handle any shape of the Pareto front and learn the Pareto set without requiring prior knowledge. Experimental results show the high performance of our proposed method on diverse test problems compared with recent Pareto set learning algorithms. © 2024 IEEE.

关键词： Contrastive 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：