Differentially Private Support Vector Machines with Knowledge Aggregation

With the widespread data collection and processing,privacy-preserving machine learning has become increasingly important in addressing privacy risks related to individuals.Support vector machine(SVM)is one of the most elementary learning models of machine learning.Privacy issues surrounding SVM classifier training have attracted increasing attention.In this paper,we investigate Differential Privacy-compliant Federated Machine Learning with Dimensionality Reduction,called FedDPDR-DPML,which greatly improves data utility while providing strong privacy guarantees.Considering in distributed learning scenarios,multiple participants usually hold unbalanced or small amounts of data.Therefore,FedDPDR-DPML enables multiple participants to collaboratively learn a global model based on weighted model averaging and knowledge aggregation and then the server distributes the global model to each participant to improve local data utility.Aiming at high-dimensional data,we adopt differential privacy in both the principal component analysis(PCA)-based dimensionality reduction phase and SVM classifiers training phase,which improves model accuracy while achieving strict differential privacy protection.Besides,we train Differential privacy(DP)-compliant SVM classifiers by adding noise to the objective function itself,thus leading to better data utility.Extensive experiments on three high-dimensional datasets demonstrate that FedDPDR-DPML can achieve high accuracy while ensuring strong privacy protection.

Resting-state functional magnetic resonance imaging and support vector machines for the diagnosis of major depressive disorder in adolescents

BACKGROUND Research has found that the amygdala plays a significant role in underlying pathology of major depressive disorder(MDD).However,few studies have explored machine learning-assisted diagnostic biomarkers based on amygdala functional connectivity(FC).AIM To investigate the analysis of neuroimaging biomarkers as a streamlined approach for the diagnosis of MDD in adolescents.METHODS Forty-four adolescents diagnosed with MDD and 43 healthy controls were enrolled in the study.Using resting-state functional magnetic resonance imaging,the FC was compared between the adolescents with MDD and the healthy controls,with the bilateral amygdala serving as the seed point,followed by statistical analysis of the results.The support vector machine(SVM)method was then applied to classify functional connections in various brain regions and to evaluate the neurophysiological characteristics associated with MDD.RESULTS Compared to the controls and using the bilateral amygdala as the region of interest,patients with MDD showed significantly lower FC values in the left inferior temporal gyrus,bilateral calcarine,right lingual gyrus,and left superior occipital gyrus.However,there was an increase in the FC value in Vermis-10.The SVM analysis revealed that the reduction in the FC value in the right lingual gyrus could effectively differentiate patients with MDD from healthy controls,achieving a diagnostic accuracy of 83.91%,sensitivity of 79.55%,specificity of 88.37%,and an area under the curve of 67.65%.CONCLUSION The results showed that an abnormal FC value in the right lingual gyrus was effective as a neuroimaging biomarker to distinguish patients with MDD from healthy controls.

Support vector machines approach to mean particle size of rock fragmentation due to bench blasting prediction

Aiming at the problems of the traditional method of assessing distribution of particle size in bench blasting, a support vector machines （SVMs） regression methodology was used to predict the mean particle size （X50） resulting from rock blast fragmentation in various mines based on the statistical learning theory. The data base consisted of blast design parameters, explosive parameters, modulus of elasticity and in-situ block size. The seven input independent variables used for the SVMs model for the prediction of X50 of rock blast fragmentation were the ratio of bench height to drilled burden （H/B）, ratio of spacing to burden （S/B）, ratio of burden to hole diameter （B/D）, ratio of stemming to burden （T/B）, powder factor （Pf）, modulus of elasticity （E） and in-situ block size （XB）. After using the 90 sets of the measured data in various mines and rock formations in the world for training and testing, the model was applied to 12 another blast data for validation of the trained support vector regression （SVR） model. The prediction results of SVR were compared with those of artificial neural network （ANN）, multivariate regression analysis （MVRA） models, conventional Kuznetsov method and the measured X50 values. The proposed method shows promising results and the prediction accuracy of SVMs model is acceptable.

Support vector machines for emotion recognition in Chinese speech

Support vector machines (SVMs) are utilized for emotion recognition in Chinese speech in this paper. Both binary class discrimination and the multi class discrimination are discussed. It proves that the emotional features construct a nonlinear problem in the input space, and SVMs based on nonlinear mapping can solve it more effectively than other linear methods. Multi class classification based on SVMs with a soft decision function is constructed to classify the four emotion situations. Compared with principal component analysis (PCA) method and modified PCA method, SVMs perform the best result in multi class discrimination by using nonlinear kernel mapping.

Ignition Pattern Analysis for Automotive Engine Trouble Diagnosis Using Wavelet Packet Transform and Support Vector Machines

Engine spark ignition is an important source for diagnosis of engine faults.Based on the waveform of the ignition pattern,a mechanic can guess what may be the potential malfunctioning parts of an engine with his/her experience and handbooks.However,this manual diagnostic method is imprecise because many spark ignition patterns are very similar.Therefore,a diagnosis needs many trials to identify the malfunctioning parts.Meanwhile the mechanic needs to disassemble and assemble the engine parts for verification.To tackle this problem,an intelligent diagnosis system was established based on ignition patterns.First,the captured patterns were normalized and compressed.Then wavelet packet transform（WPT） was employed to extract the representative features of the ignition patterns.Finally,a classification system was constructed by using multi-class support vector machines（SVM） and the extracted features.The classification system can intelligently classify the most likely engine fault so as to reduce the number of diagnosis trials.Experimental results show that SVM produces higher diagnosis accuracy than the traditional multilayer feedforward neural network.This is the first trial on the combination of WPT and SVM to analyze ignition patterns and diagnose automotive engines.

The Application of Support Vector Machines to Gas Turbine Performance Diagnosis

SVMs（support vector machines） is a new artificial intelligence methodology derived from Vapnik＇s statistical learning theory, which has better generalization than artificial neural network. A Csupport vector classifiers Based Fault Diagnostic Model （CBFDM） which gives the 3 most possible fault causes is constructed in this paper. Five fold cross validation is chosen as the method of model selection for CBFDM. The simulated data are generated from PW4000-94 engine influence coefficient matrix at cruise, and the results show that the diagnostic accuracy of CBFDM is over 93 % even when the standard deviation of noise is 3 times larger than the normal. This model can also be used for other diagnostic problems.

System Identification Modeling of Ship Manoeuvring Motion in 4 Degrees of Freedom Based on Support Vector Machines

Based on support vector machines, three modeling methods, i.e., white-box modeling, grey-box modeling and black-box modeling of ship manoeuvring motion in 4 degrees of freedom are investigated. With the whole-ship mathematical model for ship manoeuvring motion, in which the hydrodynamic coefficients are obtained from roll planar motion mechanism test, some zigzag tests and turning circle manoeuvres are simulated. In the white-box modeling and grey-box modeling, the training data taken every 5 s from the simulated 20°/20° zigzag test are used, while in the black-box modeling, the training data taken every 5 s from the simulated 15°/15°, 20°/20° zigzag tests and 15°, 25° turning manoeuvres are used; and the trained support vector machines are used to predict the whole 20°/20° zigzag test. Comparisons between the simulated and predicted 20°/20° zigzag tests show good predictive ability of the proposed methods. Besides, all mathematical models obtained by the proposed modeling methods are used to predict the 10°/10° zigzag test and 35° turning circle manoeuvre, and the predicted results are compared with those of simulation tests to demonstrate the good generalization performance of the mathematical models. Finally, the proposed modeling methods are analyzed and compared with each other in aspects of application conditions, prediction accuracy and computation speed. The appropriate modeling method can be chosen according to the intended use of the mathematical models and the available data needed for system identification.

Weather Prediction With Multiclass Support Vector Machines in the Fault Detection of Photovoltaic System

Since the efficiency of photovoltaic(PV) power is closely related to the weather,many PV enterprises install weather instruments to monitor the working state of the PV power system.With the development of the soft measurement technology,the instrumental method seems obsolete and involves high cost.This paper proposes a novel method for predicting the types of weather based on the PV power data and partial meteorological data.By this method,the weather types are deduced by data analysis,instead of weather instrument A better fault detection is obtained by using the support vector machines(SVM) and comparing the predicted and the actual weather.The model of the weather prediction is established by a direct SVM for training multiclass predictors.Although SVM is suitable for classification,the classified results depend on the type of the kernel,the parameters of the kernel,and the soft margin coefficient,which are difficult to choose.In this paper,these parameters are optimized by particle swarm optimization(PSO) algorithm in anticipation of good prediction results can be achieved.Prediction results show that this method is feasible and effective.

Temperature prediction control based on least squares support vector machines

A prediction control algorithm is presented based on least squares support vector machines (LS-SVM) model for a class of complex systems with strong nonlinearity. The nonlinear off-line model of the controlled plant is built by LS-SVM with radial basis function (RBF) kernel. In the process of system running, the off-line model is linearized at each sampling instant, and the generalized prediction control (GPC) algorithm is employed to implement the prediction control for the controlled plant. The obtained algorithm is applied to a boiler temperature control system with complicated nonlinearity and large time delay. The results of the experiment verify the effectiveness and merit of the algorithm.

Study of tide prediction method influenced by nonperiodic factors based on support vector machines

Harmonic analysis, the traditional tidal forecasting method, cannot take into account the impact of noncyclical factors, and is also based on the BP neural network tidal prediction model which is easily limited by the amount of data. According to the movement of celestial bodies, and considering the insufficient tidal characteristics of historical data which are impacted by the nonperiodic weather, a tidal prediction method is designed based on support vector machine （SVM） to carry out the simulation experiment by using tidal data from Xiamen Tide Gauge, Luchaogang Tide Gauge and Weifang Tide Gauge individually. And the results show that the model satisfactorily carries out the tide prediction which is influenced by noncyclical factors. At the same time, it also proves that the proposed prediction method, which when compared with harmonic analysis method and the BP neural network method, has faster modeling speed, higher prediction precision and stronger generalization ability.

Classification of power quality combined disturbances based on phase space reconstruction and support vector machines

Power Quality (PQ) combined disturbances become common along with ubiquity of voltage flickers and harmonics. This paper presents a novel approach to classify the different patterns of PQ combined disturbances. The classification system consists of two parts, namely the feature extraction and the automatic recognition. In the feature extraction stage, Phase Space Reconstruction (PSR), a time series analysis tool, is utilized to construct disturbance signal trajectories. For these trajectories, several indices are proposed to form the feature vectors. Support Vector Machines (SVMs) are then implemented to recognize the different patterns and to evaluate the efficiencies. The types of disturbances discussed include a combination of short-term dis-turbances (voltage sags, swells) and long-term disturbances (flickers, harmonics), as well as their homologous single ones. The feasibilities of the proposed approach are verified by simulation with thousands of PQ events. Comparison studies based on Wavelet Transform (WT) and Artificial Neural Network (ANN) are also reported to show its advantages.

Robustly stable model predictive control based on parallel support vector machines with linear kernel

Robustly stable multi-step-ahead model predictive control (MPC) based on parallel support vector machines (SVMs) with linear kernel was proposed. First, an analytical solution of optimal control laws of parallel SVMs based MPC was derived, and then the necessary and sufficient stability condition for MPC closed loop was given according to SVM model, and finally a method of judging the discrepancy between SVM model and the actual plant was presented, and consequently the constraint sets, which can guarantee that the stability condition is still robust for model/plant mismatch within some given bounds, were obtained by applying small-gain theorem. Simulation experiments show the proposed stability condition and robust constraint sets can provide a convenient way of adjusting controller parameters to ensure a closed-loop with larger stable margin.

New predictive control algorithms based on Least Squares Support Vector Machines

Used for industrial process with different degree of nonlinearity, the two predictive control algorithms presented in this paper are based on Least Squares Support Vector Machines (LS-SVM) model. For the weakly nonlinear system, the system model is built by using LS-SVM with linear kernel function, and then the obtained linear LS-SVM model is transformed into linear input-output relation of the controlled system. However, for the strongly nonlinear system, the off-line model of the controlled system is built by using LS-SVM with Radial Basis Function (RBF) kernel. The obtained nonlinear LS-SVM model is linearized at each sampling instant of system running, after which the on-line linear input-output model of the system is built. Based on the obtained linear input-output model, the Generalized Predictive Control (GPC) algorithm is employed to implement predictive control for the controlled plant in both algorithms. The simulation results after the presented algorithms were implemented in two different industrial processes model; respectively revealed the effectiveness and merit of both algorithms.

Fast Training of Support Vector Machines Using Error-Center-Based Optimization

This paper presents a new algorithm for Support Vector Machine (SVM) training, which trains a machine based on the cluster centers of errors caused by the current machine. Experiments with various training sets show that the computation time of this new algorithm scales almost linear with training set size and thus may be applied to much larger training sets, in comparison to standard quadratic programming (QP) techniques.

Prediction of chaotic systems with multidimensional recurrent least squares support vector machines

In this paper, we propose a multidimensional version of recurrent least squares support vector machines （MDRLS- SVM） to solve the problem about the prediction of chaotic system. To acquire better prediction performance, the high-dimensional space, which provides more information on the system than the scalar time series, is first reconstructed utilizing Takens＇s embedding theorem. Then the MDRLS-SVM instead of traditional RLS-SVM is used in the high- dimensional space, and the prediction performance can be improved from the point of view of reconstructed embedding phase space. In addition, the MDRLS-SVM algorithm is analysed in the context of noise, and we also find that the MDRLS-SVM has lower sensitivity to noise than the RLS-SVM.

Sparse representation based on projection method in online least squares support vector machines

A sparse approximation algorithm based on projection is presented in this paper in order to overcome the limitation of the non-sparsity of least squares support vector machines （LS-SVM）. The new inputs are projected into the subspace spanned by previous basis vectors （BV） and those inputs whose squared distance from the subspace is higher than a threshold are added in the BV set, while others are rejected. This consequently results in the sparse approximation. In addition, a recursive approach to deleting an exiting vector in the BV set is proposed. Then the online LS-SVM, sparse approximation and BV removal are combined to produce the sparse online LS-SVM algorithm that can control the size of memory irrespective of the processed data size. The suggested algorithm is applied in the online modeling of a pH neutralizing process and the isomerization plant of a refinery, respectively. The detailed comparison of computing time and precision is also given between the suggested algorithm and the nonsparse one. The results show that the proposed algorithm greatly improves the sparsity just with little cost of precision.

A Method of Identifying Electromagnetic Radiation Sources by Using Support Vector Machines

Electromagnetic Radiation Source Identification(ERSI) is a key technology that is widely used in military and radiation management and in electromagnetic interference diagnostics.The discriminative capability of machine learning methods has recently been used for facilitating ERSI.This paper presents a new approach to improve ERSI by adopting support vector machines,which are proven to be effective tools in pattern classification and regression,on the basis of the spatial distribution of electromagnetic radiation sources.Spatial information is converted from 3D cubes to 1D vectors with subscripts as inputs in order to simplify the model.The model is trained with 187 500 data sets in order to enable it to identify the types of radiation source types with an accuracy of up to 99.9%.The influence of parameters(e.g.,penalty parameter,reflection and noise from the ambient environment,and the scaling method for the input data) are discussed.The proposed method has good performance in noisy and reverberant environment.It has an identification accuracy of 82.15% when the signal-to-noise ratio is 20 dB.The proposed method has better accuracy in a noisy environment than artificial neural networks.Given that each Electromagnetic(EM) source has unique spatial characteristics,this method can be used for EM source identification and EM interference diagnostics.

Chaotic time series prediction using fuzzy sigmoid kernel-based support vector machines

Support vector machines （SVM） have been widely used in chaotic time series predictions in recent years. In order to enhance the prediction efficiency of this method and implement it in hardware, the sigmoid kernel in SVM is drawn in a more natural way by using the fuzzy logic method proposed in this paper. This method provides easy hardware implementation and straightforward interpretability. Experiments on two typical chaotic time series predictions have been carried out and the obtained results show that the average CPU time can be reduced significantly at the cost of a small decrease in prediction accuracy, which is favourable for the hardware implementation for chaotic time series prediction.

A Multiple Model Approach to Modeling Based on Fuzzy Support Vector Machines

A new multiple models(MM) approach was proposed to model complex industrial process by using Fuzzy Support Vector Machines(F -SVMs). By applying the proposed approach to a pH neutralization titration experiment, F -SVMs MM not only provides satisfactory approximation and generalization property, but also achieves superior performance to USOCPN multiple modeling method and single modeling method based on standard SVMs.

Modelling of modern automotive petrol engine performance using Support Vector Machines

Modern automotive petrol engine performance is significantly affected by effective tune-up. Current practice of engine tune-up relies on the experience of the automotive engineer, and tune-up is usually done by trial-and-error method and then the vehicle engine is run on the dynamometer to show the actual engine performance. Obviously the current practice involves a large amount of time and money, and then may even fail to tune up the engine optimally because a formal performance model of the engine has not been determined yet. With an emerging technique, Support Vector Machines (SVM), the approximate per- formance model of a petrol vehicle engine can be determined by training the sample engine performance data acquired from the dynamometer. The number of dynamometer tests for an engine tune-up can therefore be reduced because the estimated engine performance model can replace the dynamometer tests to a certain extent. In this paper, the construction, validation and accuracy of the model are discussed. The study showed that the predicted results agree well with the actual test results. To illustrate the significance of the SVM methodology, the results were also compared with that regressed using multilayer feedforward neural networks.