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%.

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.

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.

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.

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.

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.

Novel Method for Selection of Regularization Parameter in the Near-field Acoustic Holography

Because of the ill-posedness of the near-field acoustic holography（NAH）,the regularization method is required to stabilize the computational process of NAH.The regularization effect is related to how to select the parameter correctly and effectively.However the L-curve method commonly used for the selection of regularization parameters has the disadvantages of wrong selection and incorrect selection,which influences the application of NAH.For the purpose of solving the problems existed in the L-curve method,the （？）-curve method is introduced into the field of NAH,and the performance applied to NAH directly is analyzed on the basis of equivalent source method-based NAH.However,it is found out via investigations that the（？）-curve method in NAH also has the problem of wrong selection and is unable to choose the regularization parameter correctly.In order to select the parameter correctly and effectively,a novel method for selecting regularization parameters is proposed based on the original（？）-curve method,which can be called improved （？）-curve method.In the proposed method the regularization parameters are discretized linearly between the largest singular value and the smallest singular value,and the solution norm and the residual norm corresponding to these regularization parameters are also described in a linear coordinate instead of in a lg-lg coordinate,which are the two main differences compared with the L-curve and with the original（？）-curve method.In linear coordinate and using the linearly discretized regularization parameters,the solution norm is a monotonically decreasing function of the residual norm as the increase of the regularization parameter,moreover the curve is convex everywhere.So the regularization parameters can be selected correctly and effectively based on the improved（？）-curve method.Then a numerical simulation is done with a simply supported plate to verify the validity of the proposed method.Experiments with two actual sources,a clamped plate and the double speakers,are carried out to do a further demonstration.The simulation result as well as the experimental result shows that the improved（？）-curve method is efficacious and has some advantages over the L-curve method and the original（？）-curve method.The proposed novel method is able to avoid the problem of wrong selection and to select the regularization parameter correctly even if the curve is smooth.

Parameter selection in time series prediction based on nu-support vector regression

The theory of nu-support vector regression (Nu-SVR) is employed in modeling time series variationfor prediction. In order to avoid prediction performance degradation caused by improper parameters, themethod of parallel multidimensional step search (PMSS) is proposed for users to select best parameters intraining support vector machine to get a prediction model. A series of tests are performed to evaluate themodeling mechanism and prediction results indicate that Nu-SVR models can reflect the variation tendencyof time series with low prediction error on both familiar and unfamiliar data. Statistical analysis is alsoemployed to verify the optimization performance of PMSS algorithm and comparative results indicate thattraining error can take the minimum over the interval around planar data point corresponding to selectedparameters. Moreover, the introduction of parallelization can remarkably speed up the optimizing procedure.

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.

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.

Adaptive Parameter Selection for Total Variation Image Deconvolution

In this paper,we propose a discrepancy rule-based method to automatically choose the regularization parameters for total variation image restoration problems. The regularization parameters are adjusted dynamically in each iteration.Numerical results are shown to illustrate the performance of the proposed method.

Improved Particle Swarm Optimization for Selection of Shield Tunneling Parameter Values

This article proposes an exponential adjustment inertia weight immune particle swarm optimization(EAIW-IPSO)to enhance the accuracy and reliability regarding the selection of shield tunneling parameter values.According to the iteration changes and the range of inertia weight in particle swarm optimization algorithm(PSO),the inertia weight is adjusted by the form of exponential function.Meanwhile,the self-regulation mechanism of the immune system is combined with the PSO.12 benchmark functions and the realistic cases of shield tunneling parameter value selection are utilized to demonstrate the feasibility and accuracy of the proposed EAIW-IPSO algorithm.Comparison with other improved PSO indicates that EAIW-IPSO has better performance to solve unimodal and multimodal optimization problems.When solving the selection of shield tunneling parameter values,EAIW-IPSO can provide more accurate and reliable references for the realistic engineering.

A recognition method of vibration parameter image based on improved immune negative selection algorithm for rotating machinery

To overcome the limitations of traditional monitoring methods, based on vibration parameter image of rotating machinery, this paper presents an abnormality online monitoring method suitable for rotating machinery using the negative selection mechanism of biology immune system. This method uses techniques of biology clone and learning mechanism to improve the negative selection algorithm to generate detectors possessing different monitoring radius, covers the abnormality space effectively, and avoids such problems as the low efficiency of generating detectors, etc. The result of an example applying the presented monitoring method shows that this method can solve the difficulty of obtaining fault samples preferably and extract the turbine state character effectively, it also can detect abnormality by causing various fault of the turbine and obtain the degree of abnormality accurately. The exact monitoring precision of abnormality indicates that this method is feasible and has better on-line quality, accuracy and robustness.

Parameter Selection and Performance Analysis of Mobile Terminal Models Based on Unity3D

Mobile platform is now widely seen as a promising multimedia service with a favorable user group and market prospect. To study the influence of mobile terminal models on the quality of scene roaming, a parameter setting platform of mobile terminal models is established to select the parameter selection and performance index on different mobile platforms in this paper. This test platform is established based on model optimality principle, analyzing the performance curve of mobile terminals in different scene models and then deducing the external parameter of model establishment. Simulation results prove that the established test platform is able to analyze the parameter and performance matching list of a mobile terminal model.

Theoretical Basis in Regression Model Based Selection of the Most Cost Effective Parameters of Hard Rock Surface Mining

What determines selection of the most cost effective parameters of hard rock surface mining is consideration of all alternative variants of mine design and the conflicting effect of their parameters on cost. Consideration could be realized based on the mathematical model of the cumulative influence of rockmass and mine design variables on the overall cost per ton of the hard rock drilled, blasted, hauled and primary crushed. Available works on the topic mostly dwelt on four processes of hard rock surface mining separately. This paper dwells on the theoretical part of a research proposed to enhance effectiveness in the selection of the parameters of hard rock surface mining design based on the regression model of overall cost per tonne of the rock mined fit on the determinant variations of rockmass and mine design. The regression model could be developed based on the statistical data generated by many of the hard rock surface mines operating in variable conditions of rockmass and mine design worldwide. Also, a regression model based general algorithm has been formulated for the development of software and computer aided selection of the most cost effective parameters of hard rock surface mining.

THEORETICAL ANALYSIS AND PRACTICE ON THE SELECTION OF KEY PARAMETERS FOR HORIZONTAL BIAS BURNER

The air flow ratio and the pulverized coal mass flux ratio between the rich and lean sides are the key parameters of horizontal bias burner. In order to realize high combustion efficiency, excellent stability of ignition, low NO x emission and safe operation, six principal demands are presented on the selection of key parameters. An analytical model is established on the basis of the demands, the fundamentals of combustion and the operation results. An improved horizontal bias burner is also presented and applied. The experiment and numerical simulation results show the improved horizontal bias burner can realize proper key parameters, lower NO x emission, high combustion efficiency and excellent performance of part load operation without oil support. It also can reduce the circumfluence and low velocity zone existing at the downstream sections of vanes, and avoid the burnout of the lean primary air nozzle and the jam in the lean primary air channel. The operation and test results verify the reasonableness and feasibility of the analytical model.