Efficient secure federated learning aggregation framework based on homomorphic encryption by Shengxing YU, Zhong CHEN

“…In order to solve the problems of data security and communication overhead in federated learning, an efficient and secure federated aggregation framework based on homomorphic encryption was proposed.In the process of federated learning, the privacy and security issues of user data need to be solved urgently.However, the computational cost and communication overhead caused by the encryption scheme would affect the training efficiency.Firstly, in the case of protecting data security and ensuring training efficiency, the Top-K gradient selection method was used to screen model gradients, reducing the number of gradients that need to be uploaded.A candidate quantization protocol suitable for multi-edge terminals and a secure candidate index merging algorithm were proposed to further reduce communication overhead and accelerate homomorphic encryption calculations.Secondly, since model parameters of each layer of neural networks had characteristics of the Gaussian distribution, the selected model gradients were clipped and quantized, and the gradient unsigned quantization protocol was adopted to speed up the homomorphic encryption calculation.Finally, the experimental results show that in the federated learning scenario, the proposed framework can protect data privacy, and has high accuracy and efficient performance.…”
Get full text

16QAM Blind Equalization via Maximum Entropy Density Approximation Technique and Nonlinear Lagrange Multipliers by R. Mauda, M. Pinchas

“…Recently a new blind equalization method was proposed for the 16QAM constellation input inspired by the maximum entropy density approximation technique with improved equalization performance compared to the maximum entropy approach, Godard’s algorithm, and others. In addition, an approximated expression for the minimum mean square error (MSE) was obtained. …”
Get full text

Robust Planning for Hydrogen-Based Multienergy System Considering P2HH and Seasonal Hydrogen Storage by Shufan Wang, Dong Yang, Linglu Zhang, Lingzhi Chenmei

“…Since renewable energy is rapidly growing in the active distribution networks, the integrated energy system coupled with energy storage is a promising way to address the intermittent issues of renewable sources. …”
Get full text

One Iteration method in Numerical solution of Endemic Models with arbitrarily distributed periods of infection for long time by Bahman Babayar-Razlighi

“…Organization of the given algorithm is such that the problem is solved by a numerical iteration on union of short time intervals, and the process forward interval by interval. …”
Get full text

Enhancement Ear-based Biometric System Using a Modified AdaBoost Method by Abdulkareem Merhej Radhi, Subhi Aswad Mohammed

“…           The primary objective of this paper is to improve a biometric authentication and classification model using the ear as a distinct part of the face since it is unchanged with time and unaffected by facial expressions. …”
Get full text

Adaptive Asymmetric Real Laplace Wavelet Filtering and Its Application on Rolling Bearing Early Fault Diagnosis by Shuting Wan, Bo Peng

“…To overcome this issue, the present paper comes up with a rolling bearing fault-diagnosing approach based on adaptive asymmetric real Laplace wavelet (ARLW) filtering, which is on the strength of water cycle optimization algorithm (WCA). Firstly, ARLW is introduced to filter the initial vibration signal since its waveform has the same asymmetric structure as the fault impact. …”
Get full text

Studying Three Abstract Artists Based on a Multiplex Network Knowledge Representation by Luis Fernando Gutiérrez, Roberto Zarama, Juan Alejandro Valdivia

“…We used the recently proposed MultiRank algorithm to suggest possible explanations of the dynamic of some artistic styles. …”
Get full text

Sentiment Analysis Twitter Bahasa Indonesia Berbasis WORD2VEC Menggunakan Deep Convolutional Neural Network by Hans Juwiantho, Esther Irawati Setiawan, Joan Santoso, Mauridhi Hery Purnomo

“…The results of experiments that have been carried out with the Deep Convolutional Neural Network algorithm have the best accuracy value of 76.40%. …”
Get full text

Estimation of the Time of Occurrence of the Maximum Electrical Demand by Selecting the Optimal Classification Model and Making Use of Unbalanced Data by César Aristóteles Yajure, Valesca M. Fuenzalida Sánchez

“…To predict the time of maximum demand, supervised machine learning algorithms were used: random forests, K nearest neighbors, support vector machine, and logistic regression. …”
Get full text

Channel Estimation for Switch-Based Millimeter-Wave Communications via Atomic Norm by Tao Ma, Xiangning Fan, Xiaohuan Wu

“…We then propose an efficient algorithm to solve this problem based on Wirtinger projection. …”
Get full text

Experimental Demonstration of a Cubic-Receiver-Based MIMO Visible Light Communication System by Ling Wei, Hongming Zhang, Jian Song

“…Besides, the system can support user mobility in real time, since it does not require the receiver adjustment and alignment.…”
Get full text

The Support Vector Regression with L1 Norm: Application to Weather Radar Data in Adjusting Rainfall Errors by Asım Egemen Yılmaz, Arzu Ozkaya

“…The paper depicts the methodological base of the algorithm that covers additive and multiplicative corrections and the results of practical implementations considering the locations of gauge measurements. …”
Get full text

SPOTting Model Parameters Using a Ready-Made Python Package. by Tobias Houska, Philipp Kraft, Alejandro Chamorro-Chavez, Lutz Breuer

“…They further show the benefit of having one package at hand that includes number of well performing parameter search methods, since not every case study can be solved sufficiently with every algorithm or every objective function.…”
Get full text

A Novel Mechanism for Fire Detection in Subway Transportation Systems Based on Wireless Sensor Networks by Zhen-Jiang Zhang, Jun-Song Fu, Hua-Pei Chiang, Yueh-Min Huang

“…Fusion of data decreases the amount of useful information since the distribution of data is not considered. …”
Get full text

Satellite Geodesy Captures Offset Magma Supply Associated With Lava Lake Appearance at Masaya Volcano, Nicaragua by K. J. Stephens, C. Wauthier

“…The center of inflation is located in the NW part of the caldera, north of the active Santiago vent which has hosted a new lava lake since 11 December 2015. Simultaneous inversions of those Interferometric Synthetic Aperture Radar data sets using a neighbourhood algorithm demonstrate that a spherical magma reservoir explains the geodetic data, with a horizontal location ∼3 km north of the active Santiago vent and a depth‐to‐center ∼3 km. …”
Get full text

Optimizing the Joint Replenishment and Delivery Scheduling Problem under Fuzzy Environment Using Inverse Weight Fuzzy Nonlinear Programming Method by Yu-Rong Zeng, Lin Wang, Xian-Hao Xu, Qing-Liang Fu

“…Thirdly, the fuzzy simulation approach and differential evolution algorithm (DE) are utilized to solve this problem. …”
Get full text

Effectiveness of the Spatial Domain Techniques in Digital Image Steganography by Rosshini Selvamani, Yusliza Yusoff

“…The purpose of this research is to determine the best and most effective algorithm among the three competitive spatial domain algorithms, which are Least Significant Bit (LSB), Optimum Pixel Adjustment Procedure (OPAP), and Pixel Value Differencing (PVD) which in regard demonstrated the efficacy of spatial domain algorithms. …”
Get full text

A Survey of Localization in Wireless Sensor Network by Long Cheng, Chengdong Wu, Yunzhou Zhang, Hao Wu, Mengxin Li, Carsten Maple

“…Then we investigate the node self-localization methods. Since the widespread adoption of the wireless sensor network, the localization methods are different in various applications. …”
Get full text

LX-mixers for QAOA: Optimal mixers restricted to subspaces and the stabilizer formalism by Franz G. Fuchs, Ruben Pariente Bassa

“…Overall, we hope that this new perspective can lead to further insight into the development of quantum algorithms.…”
Get full text

Post-Quantum Homomorphic Encryption: A Case for Code-Based Alternatives by Siddhartha Siddhiprada Bhoi, Arathi Arakala, Amy Beth Corman, Asha Rao

“…Homomorphic Encryption (HE) allows secure and privacy-protected computation on encrypted data without the need to decrypt it. Since Shor’s algorithm rendered prime factorisation and discrete logarithm-based ciphers insecure with quantum computations, researchers have been working on building post-quantum homomorphic encryption (PQHE) algorithms. …”
Get full text