检索结果-内蒙古大学图书馆

QuripfeNet: Quantum-Resistant IPFE-Based Neural Network

IEEE Transactions on Emerging Topics in Computing 2024年

作者： Han, KyungHyun Lee, Wai-Kong Karmakar, Angshuman Yi, Myung-Kyu Hwang, Seong Oun Gachon University Department of Computer Engineering Seongnam13120 Korea Republic of Universiti Tunku Abdul Rahman Faculty of Information and Communication Technology Malaysia Indian Institute of Technology Computer Science and Engineering Kanpur India

In order to protect the sensitive information in many applications involving neural networks,several privacy-preserving neural networks that operate on encrypted data have been developed. Unfortunately,existing encryption-based privacy-preserving neural networks are mainly built on classical cryptography primitives,which are not secure from the threat of quantum computing. In this paper,we propose the first quantum-resistant solution to protect neural network inferences based on an inner-product functional encryption scheme. The selected state-of-the-art functional encryption scheme based on lattice-based cryptography works with integer-type inputs,which is not directly compatible with neural network computations that operate in the floating point domain. We propose a polynomial-based secure convolution layer to allow a neural network to resolve this problem,along with a technique that reduces memory consumption. The proposed solution,named QuripfeNet,was applied in LeNet-5 and evaluated using the MNIST dataset. In a single-threaded implementation (CPU),QuripfeNet took 107.4 seconds for an inference to classify one image,achieving accuracy of 97.85%,which is very close to the unencrypted version. Additionally,the GPU-optimized QuripfeNet took 25.9 seconds to complete the same task,which is improved by 4.15 × compared to the CPU version. © 2013 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of ETSI GS QKD 014 Protocol in Multi-User Environment

Performance Analysis of ETSI GS QKD 014 Protocol in Multi-Us...

引用

International Symposium on INFOTEH-JAHORINA (INFOTEH)

作者： Amina Tankovic Emir Dervisevic Miroslav Voznak Miralem Mehic Enio Kaljic Department of Telecommunications Faculty of Electrical Engineering University of Sarajevo Sarajevo Bosnia and Herzegovina Department of Telecommunications Faculty of Electrical Engineering and Computer Science VSB - Technical University of Ostrava Ostrava Czechia

With the development of new technologies, next-generation mobile networks have brought new services with strict performance and security requirements. One promising solution that can ensure the highest possible level of security is quantum key distribution (QKD). This technology provides information-theoretical security using the principles of quantum physics. This paper presents an extended analysis of one implementation of the QKD key delivery protocol defined in the ETSI GS QKD 014 standard, considering a multi-user environment. We propose an empirically derived model of key delivery latency in such an environment based on regression analysis of experimental results. Using the proposed model, we estimate the limitations of the implemented solution in terms of maximum number of simultaneous users connected to one key management server, considering several applications in 5G/6G networks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancement of Neural Networks Model’s Predictions of Currencies Exchange Rates by Phase Space Reconstruction and Harris Hawks’ Optimization

引用

Computational Economics 2023年第2期63卷 835-860页

作者： Khan, Haider A. Ghorbani, Shahryar Shabani, Elham Band, Shahab S. Josef Korbel School of International Studies University of Denver Denver United States Department of Production Management Faculty of Management Sakarya University Serdivan Turkey Department of Agriculture Economics Faculty of Agriculture University of Tabriz Tabriz Iran Department of Computer Science and Information Engineering Future Technology Research Center National Yunlin University of Science and Technology Douliu Taiwan

Predictions of variations in exchange rates of other currencies to a vehicle currency such as the Dollar (USD) are vital in order to reduce the risks for international transactions. In this study, we use a heuristic algorithm of Harris Hawks’ optimization (HHO) along with phase space reconstructions (PSRs) coupled to the ANN (PSR-ANNHHO) to predict the daily data of GBP/USD and CAD/USD exchange rates. In this new hybrid model, unlike the previous ones, the input of the model is based on the two parameters of time delay and the embedding dimension. The HHO algorithm increases the performance of ANN, which has can model non-linear systems in a natural manner. The performance of the PSR-ANNHHO model can be compared with the ANN and the ANN hybridized with metaheuristic Algorithm of Innovative Gunner (AIG) model (ANN-AIG). The Modified Diebold–Mariano test indicates the statistical difference between the accuracy of the models. Based on the statistical measures and graphs, the PSR-ANNHHO model predicts exchange rates considerably better than stand-alone ANN and ANN-AIG model in each case. Hence, implementing PSR along with using the heuristic algorithms could increase the accuracy of the model. This model’s precise performance supports the case for it to be employed to predict future exchange rate variations, in order to decrease transactions risks in the global markets. © 2023, The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature.

关键词： Artificial neural network Exchange rate Harris hawks’ optimization Phase space reconstruction

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Three-Port Topology for Urban Charging Stations

A Hybrid Three-Port Topology for Urban Charging Stations

引用

Annual IEEE Conference on Applied Power Electronics Conference and Exposition (APEC)

作者： Mohammadreza Khodaparast Klidbari Naser Souri Zahra Sadat Habibolahi Hamid Montazeri Hedeshi Faculty of Electrical Engineering K. N. Toosi University of Technology Tehran Iran The Bradley Department of Electrical and Computer Engineering Virginia Tech United States Department of Electrical Engineering Iran University of Science and Technology Tehran Iran Faculty of Electrical and Computer Engineering University of Tabriz Tabriz Iran

ISBN: (数字)9798331516116

ISBN: (纸本)9798331516123

Electric vehicles are rapidly gaining popularity as a sustainable alternative to conventional gasoline. In urban areas, chargers with different ratings can accommodate the diverse needs of electric vehicles. However, the available multiport topologies have variable switching frequencies. This paper introduces a hybrid multiport isolated DC-DC converter for urban charging stations, incorporating fast and slow charging ports with a fixed switching frequency. It provides isolation and enables soft switching on the primary side of the converter without circulating current on its secondary side. The primary side does not need feedback, which reduces complexity. The second stage generates a wide output voltage range to charge the electric vehicle battery by employing a switch. In addition, the proposed topology offers reduced component count and simple control with fixed-frequency operation. This paper provides the concept and the operation modes. Experimental results are provided to validate its features. The prototype converter achieves 96% peak efficiency.

关键词： Switching frequency Soft switching Prototypes Switches DC-DC power converters Zero voltage switching Charging stations Electric vehicle charging Topology Complexity theory

来源：评论

学校读者我要写书评

暂无评论

LOA-RPL:Novel Energy-Efficient Routing Protocol for the Internet of Things Using Lion Optimization Algorithm to Maximize Network Lifetime

引用

computers, Materials & Continua 2021年第10期69卷 351-371页

作者： Sankar Sennan Somula Ramasubbareddy Anand Nayyar Yunyoung Nam Mohamed Abouhawwash Department of Computer Science Engineering Sona College of TechnologySalem636005India VNR Vignana Jyothi Institute of Engineering&Technology Hyderabad500090India Graduate School Duy Tan UniversityDa NangVietnam550000Vietnam Faculty of Information Technology Duy Tan UniversityDa NangVietnam550000Vietnam Department of Computer Science and Engineering Soonchunhyang UniversityAsan31538Korea Department of Mathematics Faculty of ScienceMansoura UniversityMansoura35516Egypt Department of Electrical and Computer Engineering Michigan State UniversityEast LansingMI48824USA

Energy conservation is a significant task in the Internet of Things(IoT)because IoT involves highly resource-constrained *** is an effective technique for saving energy by reducing duplicate *** a clustering protocol,the selection of a cluster head(CH)plays a key role in prolonging the lifetime of a ***,most cluster-based protocols,including routing protocols for low-power and lossy networks(RPLs),have used fuzzy logic and probabilistic approaches to select the CH ***,early battery depletion is produced near the *** overcome this issue,a lion optimization algorithm(LOA)for selecting CH in RPL is proposed in this ***-RPL comprises three processes:cluster formation,CH selection,and route establishment.A cluster is formed using the Euclidean *** selection is performed using *** establishment is implemented using residual energy *** extensive simulation is conducted in the network simulator ns-3 on various parameters,such as network lifetime,power consumption,packet delivery ratio(PDR),and *** performance of LOA-RPL is also compared with those of RPL,fuzzy rule-based energyefficient clustering and immune-inspired routing(FEEC-IIR),and the routing scheme for IoT that uses shuffled frog-leaping optimization algorithm(RISARPL).The performance evaluation metrics used in this study are network lifetime,power consumption,PDR,and *** proposed LOARPL increases network lifetime by 20%and PDR by 5%–10%compared with RPL,FEEC-IIR,and ***-RPL is also highly energy-efficient compared with other similar routing protocols.

关键词： Internet of things cluster head clustering protocol optimization algorithm lion optimization algorithm network lifetime routing protocol wireless sensor networks energy consumption low-power and lossy networks

来源：评论

学校读者我要写书评

暂无评论

Vibration characteristics of multilayer functionally graded microplates with variable thickness reinforced by graphene platelets resting on the viscoelastic medium under thermal effects

引用

International Journal of Thermofluids 2024年 22卷

作者： Lawongkerd, Jintara Roodgar Saffari, Peyman Jearsiripongkul, Thira Thongchom, Chanachai Ismail, Sikiru Oluwarotimi Saffari, Pouyan Roodgar Keawsawasvong, Suraparb Department of Civil Engineering Thammasat School of Engineering Faculty of Engineering Thammasat University Pathumthani12120 Thailand Department of Mechanical Engineering Thammasat School of Engineering Faculty of Engineering Thammasat University Pathumthani12120 Thailand Research Unit in Structural and Foundation Engineering Department of Civil Engineering Faculty of Engineering Thammasat School of Engineering Thammasat University Pathumthani12120 Thailand Department of Engineering School of Physics Engineering and Computer Science University of Hertfordshire England HatfieldAL10 9AB United Kingdom Research Unit in Sciences and Innovative Technologies for Civil Engineering Infrastructures Department of Civil Engineering Faculty of Engineering Thammasat School of Engineering Thammasat University Pathumthani12120 Thailand

Due to their improved mechanical properties and adaptability, microplates with tailored variable thickness profiles are becoming essential parts of advanced micro- and nanoelectromechanical systems (MEMS and NEMS). This study conducts a thorough analytical analysis of the vibration properties of thermally loaded, multilayer functionally graded graphene platelet-reinforced composite (FG-GPLRC) microplates of linearly or parabolically varying thickness resting on viscoelastic medium under different boundary conditions. The Halpin–Tsai micromechanical model and the law of mixtures are employed to calculate the effective material characteristics for various reinforcement distributions in the microplate. These distributions encompass uniformly symmetric and asymmetric arrangements. The study utilized the first-order shear deformation theory (FSDT) in conjunction with the modified strain gradient theory (MSGT) and Hamilton's principle to generate the dynamic governing equations for the structure, accounting for size-dependent effects. The resulting equations are afterwards solved using the utilization of the Galerkin technique. This enables the evaluation of the proposed solution's correctness and precision. The impact of various factors on vibration behavior is investigated through numerical analysis. These factors encompass length scale parameters, temperature fluctuations, temperature distribution profiles, boundary conditions, the distribution pattern of the GPL, taper constants in both unidirectional and bidirectional scenarios, the weight fraction of the GPL. © 2024

关键词： Multilayers

来源：评论

学校读者我要写书评

暂无评论

A Multi-Stage Security Solution for Medical Color Images in Healthcare Applications

引用

computer Systems science & engineering 2023年第9期46卷 3599-3618页

作者： Walid El-Shafai Fatma Khallaf El-Sayed M.El-Rabaie Fathi E.Abd El-Samie Iman Almomani Security Engineering Lab Computer Science DepartmentPrince Sultan UniversityRiyadh11586Saudi Arabia Department of Electronics and Electrical Communications Engineering Faculty of Electronic EngineeringMenoufia UniversityMenouf32952Egypt Department of Electrical Engineering Faculty of EngineeringAhram Canadian UniversityGizaEgypt Computer Science Department King Abdullah II School of Information TechnologyThe University of JordanJordan11942Jordan

This paper presents a robust multi-stage security solution based on fusion,encryption,and watermarking processes to transmit color healthcare images,*** presented solution depends on the features of discrete cosine transform(DCT),lifting wavelet transform(LWT),and singular value decomposition(SVD).The primary objective of this proposed solution is to ensure robustness for the color medical watermarked images against transmission *** watermark embedding,the host color medical image is transformed into four sub-bands by employing three stages of *** resulting low-frequency sub-band is then transformed by employing three stages of DCT followed by SVD ***,a fusion process is used for combining different watermarks into a single watermark *** single fused image is then ciphered using Deoxyribose Nucleic Acid(DNA)encryption to strengthen the ***,the DNA-ciphered fused watermark is embedded in the host medical image by applying the suggested watermarking technique to obtain the watermarked *** main contribution of this work is embedding multiple watermarks to prevent identity *** the presence of different multimedia attacks,several simulation tests on different colormedical images have been *** results prove that the proposed security solution achieves a decent imperceptibility quality with high Peak Signal-to-Noise Ratio(PSNR)values and high correlation between the extracted and original watermark ***,the watermark image extraction process succeeds in achieving high efficiency in the presence of attacks compared with related works.

关键词： Medical images DNA encryption digital image watermarking fusion healthcare applications

来源：评论

学校读者我要写书评

暂无评论

28-m W Fully Embedded AI Techniques with On-site Learning for Low-Power Handy Tactile Sensing System

28-m W Fully Embedded AI Techniques with On-site Learning fo...

引用

2022 International Symposium on VLSI Design, Automation and Test, VLSI-DAT 2022

作者： Yano, Yuji Iwamoto, Hisashi Yoshimura, Takuma Nishida, Yoshihiro Mori, Tatsuya Komoku, Kiyotaka Takao, Hidekuni Arimoto, Kazutami Poco-apoco Networks Development Department Osaka Japan Kagawa University Faculty of Engineering and Design Takamatsu Japan FaMT Himeji Development Department Japan Okayama Prefectural University Faculty of Computer Science and Systems Engineering Sojya Japan

ISBN: (纸本)9781665409216

We have been studying an edge-AI learning-and-inference techniques for low-power handy battery operating tactile sensing system. It works in an event-driven of normally off power supply mechanism. The power consumption during classify operation at 10 inference per second is approximately 28m W. The proposed system adopts on-site embedded learning for the low power consumption and the high recognition accuracy, which is effective to operate in variety of environments. On-site learning function improves the recognition accuracy to classify the six kinds of paper from 50% to 91 % though humans can hardly identify them. © 2022 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Unseen Named Entity Recognition for Thai Language

Unseen Named Entity Recognition for Thai Language

引用

International SoC Design Conference, ISOCC

作者： Watcharet Kuntichod Wilaiporn Lee Akara Prayote Department of Computer and Information Science Faculty of Applied Science King Mongkut's University of Technology North Bangkok Bangkok Thailand Department of Electrical and Computer Engineering Faculty of Engineering King Mongkut’s University of Technology North Bangkok Bangkok Thailand

ISBN: (数字)9798350377088

ISBN: (纸本)9798350377095

Most common challenges in Named-entity recognition (NER) require suitable and annotated datasets, tailored to the specific domain of the documents under analysis, for example, legal, medical, and financial documents each require distinct datasets. Reliable identification of named entities within the training set is crucial. Annotations is a vital role in building an effective mechanism. However, creating training sets demands significant human effort, contributing to the high costs associated with NER. High quality training materials are indispensable for evolving machine-learning algorithms, underscoring the importance of dependable training data. Thus, the primary challenge lies in acquiring and managing data rather than in the algorithms themselves. To overcome most common situations of finding new unseen names, this paper proposes a mechanism to detect a new undiscovered name in Thai language based on sentence contexts. The method uses BI-LSTM model to learn sentence structures and predict a new unseen name from its context. Our framework comprises two main tasks. The first one is word entity extraction. The second task is using the model to identify unrecognized named entities. Evaluation of the proposed method is described with a successful rate of accuracy in discovering newly identified entities. This contributes to the expansion of entity recognition capabilities in Thai language processing

关键词： Training Accuracy Text analysis Training data Named entity recognition Machine learning Predictive models Prediction algorithms Reliability Stress

来源：评论

学校读者我要写书评

暂无评论

Numerical Simulation of Full-Scale Square Concrete Filled Steel Tubular (CFST) Columns Under Seismic Loading

Numerical Simulation of Full-Scale Square Concrete Filled St...

引用

International Conference on Modern Mechanics and Applications, ICOMMA 2020

作者： Phan, Hao D. Lin, Ker-Chun Phan, Hieu T. Faculty of Civil Engineering The University of Danang – University of Science and Technology Danang Viet Nam Department of Civil and Construction Engineering National Taiwan University of Science and Technology Taipei Taiwan National Center for Research on Earthquake Engineering Taipei Taiwan Department of Computer Science and Software Engineering Miami University OxfordOH United States

ISBN: (纸本)9789811632389

This paper presents numerical investigations on the seismic behavior of full-scale square concrete filled steel tubular (CFST) columns. The main objective is to understand the seismic behavior and evaluate the seismic performance of these composite columns under high levels of axial compression. Finite element analysis (FEA) models in ABAQUS software were used to simulate a series of columns subjected to axial compression and cyclic lateral loading. The CFST columns were modeled using eight-node reduced integration brick elements (C3D8R) for the infilled concrete with confinement effect, and four-node reduced integration shell elements (S4R) for the steel tube with consideration of steel-concrete interaction and steel wall’s buckling. The feasibility of the FEA models has been validated by published experimental results. The validated FEA model was further extended to conduct parametric studies with various parameters including width-to-thickness ratio (B/t), concrete strength, and axial compression level. The numerical analysis results reveal that with the same B/t and constituent materials, the higher the axial compression was, the lower the shear strength and the deformation capacity were. Also, the higher axial compression led to earlier local buckling of the steel tube, especially, in the case of the thinner steel wall (B/t of 41.7). The thicker steel wall (B/t of 20.8) resulted in higher strength and larger deformation capacity of the column. Increasing concrete material strength significantly improved the column’s shear strength for both thinner and thicker steel walls, but it led to significant development in deformation for the column having thicker steel walls. This study also reveals that only the square CFST columns with B/t of 20.8 using medium material strengths satisfy the seismic performance demand for the building columns in high seismic zones (ultimate interstory drift ratio (IDRu) not less than 3% radian) under high axial compression (up to 55% of

关键词： Concrete confinement effect Finite element analysis (FEA) model High axial compression Local buckling Seismic performance Square CFST columns Width-to-thickness ratio (B/t)

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：