FedAdaSS: Federated Learning with Adaptive Parameter Server Selection Based on Elastic Cloud Resources

The rapid expansion of artificial intelligence(AI)applications has raised significant concerns about user privacy,prompting the development of privacy-preserving machine learning(ML)paradigms such as federated learning(FL).FL enables the distributed training of ML models,keeping data on local devices and thus addressing the privacy concerns of users.However,challenges arise from the heterogeneous nature of mobile client devices,partial engagement of training,and non-independent identically distributed(non-IID)data distribution,leading to performance degradation and optimization objective bias in FL training.With the development of 5G/6G networks and the integration of cloud computing edge computing resources,globally distributed cloud computing resources can be effectively utilized to optimize the FL process.Through the specific parameters of the server through the selection mechanism,it does not increase the monetary cost and reduces the network latency overhead,but also balances the objectives of communication optimization and low engagement mitigation that cannot be achieved simultaneously in a single-server framework of existing works.In this paper,we propose the FedAdaSS algorithm,an adaptive parameter server selection mechanism designed to optimize the training efficiency in each round of FL training by selecting the most appropriate server as the parameter server.Our approach leverages the flexibility of cloud resource computing power,and allows organizers to strategically select servers for data broadcasting and aggregation,thus improving training performance while maintaining cost efficiency.The FedAdaSS algorithm estimates the utility of client systems and servers and incorporates an adaptive random reshuffling strategy that selects the optimal server in each round of the training process.Theoretical analysis confirms the convergence of FedAdaSS under strong convexity and L-smooth assumptions,and comparative experiments within the FLSim framework demonstrate a reduction in training round-to-accuracy by 12%–20%compared to the Federated Averaging(FedAvg)with random reshuffling method under unique server.Furthermore,FedAdaSS effectively mitigates performance loss caused by low client engagement,reducing the loss indicator by 50%.

Machine tool selection based on fuzzy evaluation and optimization of cutting parameters

The paper analyzes the factors influencing machine tool selection. By using fuzzy mathematics theory, we establish a theorietical model for optimal machine tool selection considering geometric features, clamping size, machining range, machining precision and surface roughness. By means of fuzzy comprehensive evaluation method, the membership degree of machine tool selection and the largest comprehensive evaluation index are determined. Then the reasonably automatic selection of machine tool is realized in the generative computer aided process planning （CAPP） system. Finally, the finite element model based on ABAQUS is established and the cutting process of machine tool is simulated. According to the theoretical and empirical cutting parameters and the curve of surface residual stress, the optimal cutting parameters can be determined.

Congruent Feature Selection Method to Improve the Efficacy of Machine Learning-Based Classification in Medical Image Processing

Machine learning(ML)is increasingly applied for medical image processing with appropriate learning paradigms.These applications include analyzing images of various organs,such as the brain,lung,eye,etc.,to identify specific flaws/diseases for diagnosis.The primary concern of ML applications is the precise selection of flexible image features for pattern detection and region classification.Most of the extracted image features are irrelevant and lead to an increase in computation time.Therefore,this article uses an analytical learning paradigm to design a Congruent Feature Selection Method to select the most relevant image features.This process trains the learning paradigm using similarity and correlation-based features over different textural intensities and pixel distributions.The similarity between the pixels over the various distribution patterns with high indexes is recommended for disease diagnosis.Later,the correlation based on intensity and distribution is analyzed to improve the feature selection congruency.Therefore,the more congruent pixels are sorted in the descending order of the selection,which identifies better regions than the distribution.Now,the learning paradigm is trained using intensity and region-based similarity to maximize the chances of selection.Therefore,the probability of feature selection,regardless of the textures and medical image patterns,is improved.This process enhances the performance of ML applications for different medical image processing.The proposed method improves the accuracy,precision,and training rate by 13.19%,10.69%,and 11.06%,respectively,compared to other models for the selected dataset.The mean error and selection time is also reduced by 12.56%and 13.56%,respectively,compared to the same models and dataset.

Structural Modal Parameter Recognition and Related Damage Identification Methods under Environmental Excitations: A Review

Modal parameters can accurately characterize the structural dynamic properties and assess the physical state of the structure.Therefore,it is particularly significant to identify the structural modal parameters according to the monitoring data information in the structural health monitoring(SHM)system,so as to provide a scientific basis for structural damage identification and dynamic model modification.In view of this,this paper reviews methods for identifying structural modal parameters under environmental excitation and briefly describes how to identify structural damages based on the derived modal parameters.The paper primarily introduces data-driven modal parameter recognition methods(e.g.,time-domain,frequency-domain,and time-frequency-domain methods,etc.),briefly describes damage identification methods based on the variations of modal parameters(e.g.,natural frequency,modal shapes,and curvature modal shapes,etc.)and modal validation methods(e.g.,Stability Diagram and Modal Assurance Criterion,etc.).The current status of the application of artificial intelligence(AI)methods in the direction of modal parameter recognition and damage identification is further discussed.Based on the pre-vious analysis,the main development trends of structural modal parameter recognition and damage identification methods are given to provide scientific references for the optimized design and functional upgrading of SHM systems.

Effects of processing parameters on fabrication defects,microstructure and mechanical properties of additive manufactured Mg–Nd–Zn–Zr alloy by selective laser melting process

Mg–3Nd–0.2Zn–0.4Zr(NZ30K,wt.%)alloy is a new kind of high-performance metallic biomaterial.The combination of the NZ30K Magnesium(Mg)alloy and selective laser melting(SLM)process seems to be an ideal solution to produce porous Mg degradable implants.However,the microstructure evolution and mechanical properties of the SLMed NZ30K Mg alloy were not yet studied systematically.Therefore,the fabrication defects,microstructure,and mechanical properties of the SLMed NZ30K alloy under different processing parameters were investigated.The results show that there are two types of fabrication defects in the SLMed NZ30K alloy,gas pores and unfused defects.With the increase of the laser energy density,the porosity sharply decreases to the minimum first and then slightly increases.The minimum porosity is 0.49±0.18%.While the microstructure varies from the large grains with lamellar structure inside under low laser energy density,to the large grains with lamellar structure inside&the equiaxed grains&the columnar grains under middle laser energy density,and further to the fine equiaxed grains&the columnar grains under high laser energy density.The lamellar structure in the large grain is a newly observed microstructure for the NZ30K Mg alloy.Higher laser energy density leads to finer grains,which enhance all the yield strength(YS),ultimate tensile strength(UTS)and elongation,and the best comprehensive mechanical properties obtained are YS of 266±2.1 MPa,UTS of 296±5.2 MPa,with an elongation of 4.9±0.68%.The SLMed NZ30K Mg alloy with a bimodal-grained structure consisting of fine equiaxed grains and coarser columnar grains has better elongation and a yield drop phenomenon.

Role of processing parameters on relative density,microstructure and mechanical properties of selective laser melted titanium alloy

The relationships between the selective laser melting(SLM)processing parameters including laser power,scanning speed and hatch space,the relative density,the microstructure,and resulting mechanical properties of Ti-6Al-2Zr-1Mo-1V alloy were investigated in this work.The result shows that laser power acts a dominant role in determining the relative density in comparison with scanning speed and hatch space.The optimal SLM process window for fabricating relative density>99%samples is located in the energy density range of 34.72 J·mm^(-3)to 52.08 J·mm^(-3),where the laser power range is between 125 W and 175 W.An upward trend is found in the micro-hardness as the energy density is increased.The optimum SLM processing parameters of Ti-6Al-2Zr-1Mo-1V alloy are:laser power of 150 W,scanning speed of 1,600 mm·s^(-1),hatch space of 0.08 mm,and layer thickness of 0.03 mm.The highest ultimate tensile strength,yield strength,and ductility under the optimum processing parameter are achieved,which are 1,205 MPa,1,099 MPa,and 8%,respectively.The results of this study can be used to guide SLM production Ti-6Al-2Zr-1Mo-1V alloy parts.

Parameter selection of support vector machine for function approximation based on chaos optimization

The support vector machine （SVM） is a novel machine learning method, which has the ability to approximate nonlinear functions with arbitrary accuracy. Setting parameters well is very crucial for SVM learning results and generalization ability, and now there is no systematic, general method for parameter selection. In this article, the SVM parameter selection for function approximation is regarded as a compound optimization problem and a mutative scale chaos optimization algorithm is employed to search for optimal paraxneter values. The chaos optimization algorithm is an effective way for global optimal and the mutative scale chaos algorithm could improve the search efficiency and accuracy. Several simulation examples show the sensitivity of the SVM parameters and demonstrate the superiority of this proposed method for nonlinear function approximation.

Sufficient variable selection of high dimensional nonparametric nonlinear systems based on Fourier spectrum of density-weighted derivative

The variable selection of high dimensional nonparametric nonlinear systems aims to select the contributing variables or to eliminate the redundant variables.For a high dimensional nonparametric nonlinear system,however,identifying whether a variable contributes or not is not easy.Therefore,based on the Fourier spectrum of densityweighted derivative,one novel variable selection approach is developed,which does not suffer from the dimensionality curse and improves the identification accuracy.Furthermore,a necessary and sufficient condition for testing a variable whether it contributes or not is provided.The proposed approach does not require strong assumptions on the distribution,such as elliptical distribution.The simulation study verifies the effectiveness of the novel variable selection algorithm.

On Performance Characteristics of a Nonparametric Subset Selection Procedure with a Small Randomized Block Experimental Design

This article addresses the issue of computing the constant required to implement a specific nonparametric subset selection procedure based on ranks of data arising in a statistical randomized block experimental design. A model of three populations and two blocks is used to compute the probability distribution of the relevant statistic, the maximum of the population rank sums minus the rank sum of the “best” population. Calculations are done for populations following a normal distribution, and for populations following a bi-uniform distribution. The least favorable configuration in these cases is shown to arise when all three populations follow identical distributions. The bi-uniform distribution leads to an asymptotic counterexample to the conjecture that the least favorable configuration, i.e., that configuration minimizing the probability of a correct selection, occurs when all populations are identically distributed. These results are consistent with other large-scale simulation studies. All relevant computational R-codes are provided in appendices.

Parameters selection in gene selection using Gaussian kernel support vector machines by genetic algorithm

In microarray-based cancer classification, gene selection is an important issue owing to the large number of variables and small number of samples as well as its non-linearity. It is difficult to get satisfying results by using conventional linear sta- tistical methods. Recursive feature elimination based on support vector machine (SVM RFE) is an effective algorithm for gene selection and cancer classification, which are integrated into a consistent framework. In this paper, we propose a new method to select parameters of the aforementioned algorithm implemented with Gaussian kernel SVMs as better alternatives to the common practice of selecting the apparently best parameters by using a genetic algorithm to search for a couple of optimal parameter. Fast implementation issues for this method are also discussed for pragmatic reasons. The proposed method was tested on two repre- sentative hereditary breast cancer and acute leukaemia datasets. The experimental results indicate that the proposed method per- forms well in selecting genes and achieves high classification accuracies with these genes.

Selection of the Linear Regression Model According to the Parameter Estimation

In this paper, based on the theory of parameter estimation, we give a selection method and, in a sense of a good character of the parameter estimation, we think that it is very reasonable. Moreover, we offer a calculation method of selection statistic and an applied example.

Comparison of Block Design Nonparametric Subset Selection Rules Based on Alternative Scoring Rules

This article compares the size of selected subsets using nonparametric subset selection rules with two different scoring rules for the observations. The scoring rules are based on the expected values of order statistics of the uniform distribution (yielding rank values) and of the normal distribution (yielding normal score values). The comparison is made using state motor vehicle traffic fatality rates, published in a 2016 article, with fifty-one states (including DC as a state) and over a nineteen-year period (1994 through 2012). The earlier study considered four block design selection rules—two for choosing a subset to contain the “best” population (i.e., state with lowest mean fatality rate) and two for the “worst” population (i.e., highest mean rate) with a probability of correct selection chosen to be 0.90. Two selection rules based on normal scores resulted in selected subset sizes substantially smaller than corresponding rules based on ranks (7 vs. 16 and 3 vs. 12). For two other selection rules, the subsets chosen were very close in size (within one). A comparison is also made using state homicide rates, published in a 2022 article, with fifty states and covering eight years. The results are qualitatively the same as those obtained with the motor vehicle traffic fatality rates.

Piezoelectric transducer parameter selection for exciting a single mode from multiple modes of Lamb waves

Excitation and propagation of Lamb waves by using rectangular and circular piezoelectric transducers surface- bonded to an isotropic plate are investigated in this work. Analytical stain wave solutions are derived for the two transducer shapes, giving the responses of these transducers in Lamb wave fields. The analytical study is supported by a numericM simulation using the finite element method. Symmetric and antisymmetric components in the wave propagation responses are inspected in detail with respect to test parameters such as the transducer geometry, the length and the excitation frequency. By placing only one piezoelectric transducer on the top or the bottom surface of the plate and weakening the strength of one mode while enhancing the strength of the other modes to find the centre frequency, with which the peak wave amplitude ratio between the SO and A0 modes is maximum, a single mode excitation from the multiple modes of the Lamb waves can be achieved approximately. Experimental data are presented to show the validity of the analyses. The results are used to optimize the Lamb wave detection system.

Parameter selection and model research on remote sensing evaluation for nearshore water quality

Using remote sensing technology for water quality evaluation is an inevitable trend in marine environmental monitoring. However, fewer categories of water quality parameters can be monitored by remote sensing technology than the 35 specified in GB3097-1997 Marine Water Quality Standard. Therefore, we considered which parameters must be selected by remote sensing and how to model for water quality evaluation using the finite parameters. In this paper, focused on Leizhou Peninsula nearshore waters, we found N, P, COD, PH and DO to be the dominant parameters of water quality by analyzing measured data. Then, mathematical statistics was used to determine that the relationship among the five parameters was COD〉DO〉P〉N〉pH. Finally, five-parameter, fourparameter and three-parameter water quality evaluation models were established and compared. The results showed that COD, DO, P and N were the necessary parameters for remote sensing evaluation of the Leizhou Peninsula nearshore water quality, and the optimal comprehensive water quality evaluation model was the four- parameter model. This work may serve as a reference for monitoring the quality of other marine waters by remote sensing.

TV/L2-based image denoisingalgorithm with automaticparameter selection

In order to improve the adaptiveness of TV/L2-based image denoising algorithm in differ- ent signal-to-noise ratio （SNR） environments, an iterative denoising method with automatic parame- ter selection is proposed. Based upon the close connection between optimization function of denois- ing problem and regularization parameter, an updating model is built to select the regularized param- eter. Both the parameter and the objective function are dynamically updated in alternating minimiza- tion iterations, consequently, it can make the algorithm work in different SNR environments. Mean- while, a strategy for choosing the initial regularization parameter is presented. Considering Morozov discrepancy principle, a convex function with respect to the regularization parameter is modeled. Via the optimization method, it is easy and fast to find the convergence value of parameter, which is suitable for the iterative image denoising algorithm. Comparing with several state-of-the-art algo- rithms, many experiments confirm that the denoising algorithm with the proposed parameter selec- tion is highly effective to evaluate peak signal-to-noise ratio （PSNR） and structural similarity

Scaling parameters selection principle for the scaled unscented Kalman filter

The paper deals with the state estimation of the widely used scaled unscented Kalman filter（UKF）. In particular, the stress is laid on the scaling parameters selection principle for the scaled UKF. Several problems caused by recommended constant scaling parameters are highlighted. On the basis of the analyses, an effective scaled UKF is proposed with self-adaptive scaling parameters,which is easy to understand and implement in engineering. Two typical strong nonlinear examples are given and their simulation results show the effectiveness of the proposed principle and algorithm.

Genetic parameters and response to selection for body weight in turbot(Scophthalmus maximus, Linnaeus)

Genetic parameters and response to selection were estimated for harvest body weight in turbot. The data consisted of 10 952 individuals of 508 full-sib families from three generations（G0, G1, and G2）. The heritability estimates for G0, G1, and G2 were 0.11±0.08, 0.18±0.09, and 0.17±0.07, respectively. Over three generations, the heritability estimate was 0.19±0.04. Maternal and common environmental effects were 0.10±0.04, 0.14±0.04, and0.13±0.03 within each generation and 0.12±0.01 across generations. The selection differential in growth was 18.24 g in G0 and 21.19 g in G1 corresponding to an average of 19.72 g per generation. The genetic gains were also calculated, they were 22.06 g in G1 and 11.93 g in G2, corresponding to 6.36% and 3.52% body weight. The total genetic gain after two generations was 10.10% body weight, which indicated that the selective breeding program for the body weight trait in turbot was successful.

Parameter selection of support vector regression based on hybrid optimization algorithm and its application

Choosing optimal parameters for support vector regression （SVR） is an important step in SVR. design, which strongly affects the pefformance of SVR. In this paper, based on the analysis of influence of SVR parameters on generalization error, a new approach with two steps is proposed for selecting SVR parameters, First the kernel function and SVM parameters are optimized roughly through genetic algorithm, then the kernel parameter is finely adjusted by local linear search, This approach has been successfully applied to the prediction model of the sulfur content in hot metal. The experiment results show that the proposed approach can yield better generalization performance of SVR than other methods,

Mathematical basis,correlativity and selection of seismicity parameters

Using the analytic expression of seismicity parameters, the dependency and correlativity between the statisticalparameters and seismic frequency or seismic intensity are discussed. The statistical parameters are divided into twokinds. One kind is the regional seismicity parameter, 17 parameters are analyzed in this paper. The other kind isthe seismicity distribution parameter. They are the distribution parameters of time, space and magnitude. The existent base and rationality of distribution parameters depend on the application of distribution model. We analyzeand draw an analogy between the natural probability, Poisson, Weibull distributions and multi-f racial analyticformula in time, space and magnitude. And some examples are given in this paper. The P value and H value of aftershock sequence attenuation, the U value and F value of eanhquake swarm sequence and the entropy of information are discussed preliminarily. Another method about analyzing relationships among time-series curves aregiven. The resemblance relativity degree R,.,, and the relativity degree G,.,, of relative change slope can be usedas the determining values. At last, some preliminary ideas about sifting and using for seismicity parameters are advanced in this paper.

Fault Diagnosis Based on Fuzzy Support Vector Machine with Parameter Tuning and Feature Selection

This study describes a classification methodology based on support vector machines(SVMs),which offer superior classification performance for fault diagnosis in chemical process engineering.The method incorporates an efficient parameter tuning procedure(based on minimization of radius/margin bound for SVM's leave-one-out errors)into a multi-class classification strategy using a fuzzy decision factor,which is named fuzzy support vector machine(FSVM).The datasets generated from the Tennessee Eastman process(TEP)simulator were used to evaluate the clas-sification performance.To decrease the negative influence of the auto-correlated and irrelevant variables,a key vari-able identification procedure using recursive feature elimination,based on the SVM is implemented,with time lags incorporated,before every classifier is trained,and the number of relatively important variables to every classifier is basically determined by 10-fold cross-validation.Performance comparisons are implemented among several kinds of multi-class decision machines,by which the effectiveness of the proposed approach is proved.