Least Squares Support Vector Machine Method Research Articles

Prediction of the effluent chemical oxygen demand and volatile fatty acids for anaerobic treatment based on different feature selections machine-learning methods from lab-scale to pilot-scale

The effluent chemical oxygen demand (COD) and volatile fatty acids (VFA) are important indicators for measuring wastewater anaerobic treatment systems. Through lab and pilot experiments on the anaerobic treatment process of high-salt wastewater, combined with different prediction requirements, the feature variables are classified. The effluent-COD and VFA prediction models of five different Machine-learning methods (i.e., back propagation neural network (BPNN), Genetic algorithm optimizes BPNN(GA-BP), support vector machine (SVM), Least squares support vector machine (LSSVM), and random forest (RF)) were established. The modeling results on different dataset (i.e., lab dataset, pilot dataset and mixed dataset) showed that the SVM and LSSVM methods based on statistical learning had the best model prediction performance in lab and pilot datasets, and the RF method performed well in mixed dataset. Furthermore, the genetic algorithm was adopted to optimize the RF model. After optimization of mixed dataset, the effluent-COD prediction (i.e., R2 = 0.966, RMSE/MAE are 61.227/48.584 mg/L) and VFA prediction (i.e., R2 = 0.639, RMSE/MAE are 26.838/21.831 mg/L) have been improved compared with the original RF model (i.e., R2 = 0.918, RMSE/MAE are 86.232/65.03 mg/L of effluent-COD, and R2 = 0.539, RMSE/MAE are 35.489/26.726 mg/L of VFA). This research can provide a reference for the prediction of the anaerobic treatment of actual large-scale industrial wastewater.

Fault diagnosis of anti-friction bearings based on Bi-dimensional ensemble local mean decomposition and optimized dynamic least square support vector machine

In order to ensure the normal operation of rotating equipment, it is very important to quickly and efficiently diagnose the faults of anti-friction bearings. Hereto, fault diagnosis of anti-friction bearings based on Bi-dimensional ensemble local mean decomposition and optimized dynamic least square support vector machine (LSSVM) is presented in this paper. Bi-dimensional ensemble local mean decomposition, an extension of ensemble local mean decomposition from one-dimensional signal processing to Bi-dimensional signal processing, is used to extract the features of anti-friction bearings. Moreover, an optimized dynamic LSSVM is used to fault diagnosis of anti-friction bearings. The experimental results show that Bi-dimensional ensemble local mean decomposition is superior to Bi-dimensional local mean decomposition, optimized dynamic LSSVM is superior to traditional LSSVM, and the proposed Bi-dimensional ensemble local mean decomposition and optimized dynamic LSSVM method is effective for fault diagnosis of anti-friction bearings.

Combined kernel with parameter optimization for least squares support vector machine postdistorter in visible light communications

The nonlinearity and memory effects induced by light-emitting diode distort the transmitted signal, which significantly limits the performance of visible light communication (VLC) system. With the characteristics of low computational complexity, fast convergence speed, and strong generalization ability, least squares support vector machine (LSSVM) is investigated in this paper and employed to alleviate the nonlinear effect. Since the performance of LSSVM is largely determined by the type of the adopted kernel functions, we utilize Gaussian and Laplace functions and propose a new combined kernel, which can increase the reproducing kernel Hilbert space and thus enhance the global expressive power compared with conventionally used Gaussian kernel. To further improve the performance, a hybrid parameter optimization algorithm is exploited to optimize the proposed kernel, based on genetic algorithm and particle swarm optimization. The property of the proposed postdistortion method is verified by numerical simulations, and better performance is obtained in VLC systems compared with the Gaussian-kernel LSSVM and conventional memory polynomial method.

Fast and nondestructive discrimination of fresh tea leaves at different altitudes based on near infrared spectroscopy and various chemometrics methods

Near infrared spectroscopy (NIRS) combined with various chemometrics methods was tried to identify the fresh tea leaves at different altitudes quickly and nondestructively. Three kinds of samples were collected, then scanning NIRS, conducting spectral preprocessing to remove noise information, using backward interval partial least squares to screen characteristic spectral intervals, going on principal component analysis, respectively. Finally, least squares support vector machine method (LS-SVM) was applied to establish NIRS models, whose robustness was tested by prediction set samples. The best pretreated method was the combination of multivariate scattering correction and the first derivative. Six characteristic spectral intervals were screened, and the corresponding spectral wavenumbers were 4821.2-5091.2 cm-1, 5368.9-5638.8 cm-1, 6190.4-6460.4 cm-1, 7011.9-7281.9 cm-1, 8924.9-9191.1 cm-1 and 9734.9-10000 cm-1. The cumulative contribution rate of the first three principal components was 99.92%. The root mean square error of the cross validation and the determination coefficient of the calibration set model were 0.027 and 0.973, respectively. The root mean square error and the determination coefficient of the prediction set model were 0.034 and 0.968, respectively. The discrimination accuracy in prediction set was 100%. The results showed NIRS combined with LS-SVM can realize fast and nondestructive discrimination of fresh tea leaves at different altitudes.

Modeling and Control of Electromagnetic Coil System Using Model Order Reduction-Based LSSVM Method*

Magnetic micro/nanorobot (MM) is promising for in-body therapy due to its advantage of untethered controllability. Since the motion of MMs can be directly manipulated by the magnetic field (MF) created by electromagnetic coil systems, it is essential to study the MF generation control methods. In this study, iron core-based solenoids are employed in an electromagnetic coil system that can produce a stronger MF than regular coil systems. However, the coil system presents hysteretic nonlinearity due to the iron core's coercivity, which degrades closed-loop control performances. To tackle this challenge, an effective hysteresis compensation method is developed to linearize the solenoid system. Specifically, the least squares support vector machine (LSSVM) is adopted to model the hysteretic behavior of the solenoid system, and the discrete empirical interpolation method (DEIM) is applied to reduce the complexity of the model for improving the calculation efficiency. Based on the LSSVM and DEIM approaches, a highly efficient LSSVM-DEIM hysteresis compensator is developed. In order to generate precise dynamic MF effectively, the LSSVM-DEIM hysteresis compensator is combined with prevalent feedback controllers to form composite control schemes. Experiments show that the control system with the LSSVM-DEIM hysteresis compensator can produce a more accurate MF compared with that of the benchmark control methods.

Identification of adulterated milk based on auto-correlation spectra

A qualitative analysis of melamine-adulterated milk was proposed based on two-trace two-dimensional (2T2D) auto-correlation spectra. The concentration of melamine was used as external perturbation, and 40 adulterated samples of each brand with different concentrations of melamine (0.01 g/L to 1 g/L) were configured. Four brands of milk were used to configure experimental samples, including Guangming brand, Mengniu brand, Sanyuan brand and Wandashan brand. Spectroscopic data of pure milk and melamine-adulterated milk were measured by infrared (IR) (80–4000 cm−1) spectrophotometer. 2T2D auto-correlation spectral technology combined with least squares support vector machine (LS-SVM) method was used for qualitative analysis. The two strongest auto-correlation peaks in the auto-correlation spectra were selected for modeling. For Guangming brand, the intensities of auto-correlation at two wave numbers 2898 cm−1 and 2972 cm−1 were selected as independent variables. For Mengniu brand, the intensities of auto-correlation at two wave numbers 2852 cm−1 and 2920 cm−1 were selected. For Sanyuan brand, the intensities of auto-correlation at two wave numbers 2900 cm−1 and 2974 cm−1 were selected. For Wandashan brand, the intensities of auto-correlation at two wave numbers 2900 cm−1 and 2974 cm−1 were selected. For four brands fused together, the intensities of auto-correlation at two wave numbers 2900 cm−1 and 2974 cm−1 were selected. For each brand, the accuracy of qualitative analysis was 100 %. For four brands fused together, the accuracy of qualitative analysis was 99.05 %. In this way, it greatly reduced the amount of data to be processed. This study showed that 2T2D auto-correlation spectral technology combined with LS-SVM method was perfect for the discrimination of melamine-adulterated milk.

Identification of Banana Types with the Least-Squares Support Vector Machine

The classification of banana species is still done manually by banana farmers. This identification process has the disadvantage that it requires more manpower to sort, the level of perception of the type of fruit produced can be different because humans can experience fatigue, are not always consistent, and human judgments are also subjective. Thus, a tool is needed that can identify the type of banana fruit precisely and accurately. One of them is by creating a computer-based system using the statistical feature extraction method of digital images. By performing color feature extraction using Color Moments (RGBHSVYCbCr), then texture extraction using Gray-Level Co-occurence Matrix (GLCM), and using the Least-Squares Support Vector Machine (LS-SVM) method for classification of banana species. LS-SVM is a modification of SVM, which is used to improve classification performance. In the SVM algorithm, there is quadratic programming that is used to obtain the optimal solution in determining the Lagrange function; from the Lagrange function, it will be used in calculating the value of the weight and bias parameters. Quadratic programming is not efficient when applied to higher spatial dimensions because the computation will be very complex and very long. LS-SVM is better than standard SVM in terms of the calculation process, faster convergence, and higher precision. At the end of the experiment, the LS-SVM method succeeded in detecting the type of banana with a test accuracy value of 90%.

Modeling and forecasting of ionosphere TEC using least squares SVM in central Europe

We propose a new method for spatio-temporal modeling of ionosphere total electron content (TEC) using least squares support vector machine (LS-SVM). In the SVM model, dual programming is used to solve the system of equations. Therefore, large-scale problem solving with the SVM greatly increases computation time and decreases accuracy. To overcome these limitations, a LS-SVM method is proposed. This method uses simple linear equations to solve the system of equations. As a result, the complexity of the computational algorithm is reduced. In addition, the convergence speed and accuracy of the results increase. To evaluate the new method, observations of 30 GNSS stations in the central Europe are used. The observations are for 80 days from 2014, with different solar (F10.7) and geomagnetic activity (KP and DST) indices. The results of the LS-SVM model at three control stations are compared with the vertical TEC (VTEC) of the GPS and also with the VTEC of the SVM, NeQuick and global ionosphere map (GIM) models. On all days considered, the averaged RMSE of the LS-SVM, SVM, GIM and NeQuick models at the control stations are calculated as 2.45, 3.13, 4.61 and 7.48 TECU, respectively. In precise point positioning (PPP) analysis and at the high geomagnetic activity, the maximum RMSE of LS-SVM, SVM, GIM and NeQuick models are computed 52.34, 63.22, 70.21 and 79.55 mm, respectively. During periods of low geomagnetic activity, the RMSE of the LS-SVM model is lower than the other models. Seasonal error analysis of all 4 models shows that the LS-SVM model has less error in different seasons compared to the other models. The results also show that the proposed model has a higher speed and accuracy than the SVM, GIM and NeQuick. Therefore, it can be considered a regional model of the ionosphere in the European region.

RBF Sliding Mode Control Method for an Upper Limb Rehabilitation Exoskeleton Based on Intent Recognition

Aiming at the lack of active willingness of patients to participate in the current upper limb exoskeleton rehabilitation training control methods, this study proposed a radial basis function (RBF) sliding mode impedance control method based on surface electromyography (sEMG) to identify the movement intention of upper limb rehabilitation. The proposed control method realizes the process of active and passive rehabilitation training according to the wearer’s movement intention. This study first established a joint angle prediction model based on sEMG for the problem of poor human–machine coupling and used the least-squares support vector machine method (LSSVM) to complete the upper limb joint angle prediction. In addition, in view of the problem of poor compliance in the rehabilitation training process, an adaptive sliding mode controller based on the RBF network approximation system model was proposed. In the process of active training, an impedance model was added based on the position loop control, which could dynamically adjust the motion trajectory according to the interaction force. The experiment results showed that the impedance control method based on the RBF could effectively reduce the interaction force between the human and machine to improve the compliance of the exoskeleton manipulator and achieve the purpose of stabilizing the impedance characteristics of the system.

Improved firefly algorithm–extended Kalman filter–least-square support-vector machine voltage sag monitoring and classification method based on edge computing

Aiming at the hardware reusability, multi-service carrying capacity, and computing resource limitations of edge devices, a light-weight voltage sag monitoring and classification method based on improved firefly algorithm optimization, extended Kalman filter, and least-square support-vector machine is proposed. The strategy of linearly decreasing inertia weight is introduced to optimize the state error of the extended Kalman filter algorithm and the measurement noise covariance matrix to achieve accurate monitoring of voltage sags. Extract characteristic quantities such as average value, duration of sag, minimum sag dispersion characteristics, number of sag phases, and flow direction of disturbance energy. As a model training data set, the least-square support-vector machine method optimized based on the improved firefly algorithm is used to create a multi-level classification model of voltage sag source to realize the classification of voltage sag sources. This method fully considers the influence of the limited resources of edge computing equipment on the algorithm, and effectively improves the use of computing resources by improving the optimization algorithm. Simulation and experimental results show that this method is suitable for edge computing equipment to monitor and distinguish voltage sags.

Reservoir Parameters Estimation with Some Log Curves of Qiongdongnan Basin Based on LS-SVM Method

Reservoir porosity and permeability are considered as very important parameters in characterizing oil and gas reservoirs. Traditional methods for porosity and permeability prediction are well log and core data analysis to get some regression empirical formulas. However, because of strong non-linear relationship between well log data and core data such as porosity and permeability, usual statistical regression methods are not completely able to provide meaningful estimate results. It is very difficult to measure fine scale porosity and permeability parameters of the reservoir. In this paper, the least square support vector machine (LS-SVM) method is applied to the parameters estimation with well log and core data of Qiongdongnan basin reservoirs. With the log and core exploration data of Qiongdongnan basin, the approach and prediction models of porosity and permeability are constructed and applied. There are several type of log data for the determination of porosity and permeability. These parameters are related with the selected log data. However, a precise analysis and determine of parameters require a combinatorial selection method for different type data. Some curves such as RHOB,CALI,POTA,THOR,GR are selected from all obtained logging curves of a Qiongdongnan basin well to predict porosity. At last we give some permeability prediction results based on LS-SVM method. High precision practice results illustrate the efficiency of LS-SVM method for practical reservoir parameter estimation problems.

Optimization and comparison of models for core temperature prediction of mother rabbits using infrared thermography

Core temperature is a measurement used to evaluate and diagnose the health status of mother rabbits. The preferred method is to use an indwelling probe to measure the rectal temperature. This procedure can be stressful to rabbits, are time and labor-consuming. The objective of this paper was to develop the fastest, accurate and non-invasive method to measure the rectal temperature of mother rabbits using Infrared thermography (IRT) and machine learning (ML). Two hundred lactating mother rabbits (LR) and two hundred non-lactating mother rabbits (NLR) of the YPLU breed were used in the experiment and IRT data, rectal temperature and ambient temperature were recorded. The results showed that there was a significant correlation between the maximum infrared temperature of eyes (EMIT) and ears (RMIT) and rectal temperature (p < 0.05) and a significant correlation between the EMIT, RMIT and the ambient temperature (p < 0.01) in two kinds of mother rabbits. Least squares support vector machine (LS-SVM), Gaussian process (GP), and partial least squares (PLS) machine learning methods were used to establish models of mother rabbits’ core temperature. Using the over-sampling method to process the training set, three models of LS-SVM, GP, and PLS with improved generalization performance were obtained. The RMSE for the test set by LS-SVM, GP, and PLS methods were 0.13℃, 0.12℃ and 0.07℃ and the R2 were 0.94, 0.96 and 0.98, respectively. Compared with the results obtained from two other regressions, LS-SVM and GP, the PLS method exhibited the best performance. The prediction error of the test set is <0.2℃, which can better predict the core temperature of the mother rabbits.

Incipient Chiller Fault Diagnosis Using an Optimized Least Squares Support Vector Machine With Gravitational Search Algorithm

Operational faults in centrifugal chillers will lead to high energy consumption, poor indoor thermal comfort, and low operational safety, and thus it is of significance to detect and diagnose the anomalies timely and effectively, especially for those at their incipient stages. The least squares support vector machine (LSSVM) has been regarded as an effective algorithm for multiclass classification. One of the most difficult issues in LSSVM is parameter tuning. Therefore, this paper reports a development of a gravitational search algorithm (GSA) optimized LSSVM method for incipient fault diagnosis in centrifugal chillers. Considering the inadequacies of conventional principle component analysis (PCA) algorithm for nonlinear data transformation, kernel principle component analysis (KPCA) was firstly employed to reduce the dimensionality of the original input data. Secondly, an optimized “one against one” multi-class LSSVM classifier was developed and its penalty constant and kernel bandwidth were tuned by GSA. Based on the fault samples of seven typical faults at their incipient stages in chillers from ASHRAE RP 1043, the proposed GSA optimized LSSVM fault diagnostic model was trained and validated. For the purpose of demonstrating the priority of the proposed fault diagnosis method, the obtained results were compared to that of using the LSSVM classifier optimized by another two algorithms, namely, the conventional cross-validation method and particle swarm optimizer. Results showed that the best fault diagnosis performance could be achieved using the proposed GSA-LSSVM classifier. The overall average fault diagnosis accuracy for the least severity faults was reported over 95%.

Fault Diagnosis of Wind Turbine Generator System Based on PMI-LSSVM

Considering the multi-source wind power information such as wind speed, rotation speed, spindle horizontal and vertical vibration, a fault diagnosis method of wind turbine generator system based on partial mutual information (PMI) and least squares support vector machine (LSSVM) was proposed. A large amount of data containing fault status, such as blade fault, converter fault, generator fault, pitch bearing fault and yaw system fault, was analyzed. The PMI method was used to screen the characteristic parameters of the operation state of the wind turbine to identify the fault of the unit. The characteristic parameters of the wind turbine in various states were trained by LSSVM method to establish the mapping relationship between the parameter vectors of different characteristics and the fault types, so as to achieve the purpose of fault diagnosis. Besides, the different fault history data of wind turbine was used to test the fault model performance. The results compared with artificial neural network (ANN) method showed that the proposed method had good fault recognition ability and fast operation speed, which was suitable for fault diagnosis of multibrid technology wind turbine generator system, and can meet the requirements of online fault diagnosis.

Using Optical Coherence Tomography and Intravascular Ultrasound Imaging to Quantify Coronary Plaque Cap Stress/Strain and Progression: A Follow-Up Study Using 3D Thin-Layer Models.

Accurate plaque cap thickness quantification and cap stress/strain calculations are of fundamental importance for vulnerable plaque research. To overcome uncertainties due to intravascular ultrasound (IVUS) resolution limitation, IVUS and optical coherence tomography (OCT) coronary plaque image data were combined together to obtain accurate and reliable cap thickness data, stress/strain calculations, and reliable plaque progression predictions. IVUS, OCT, and angiography baseline and follow-up data were collected from nine patients (mean age: 69; m: 5) at Cardiovascular Research Foundation with informed consent obtained. IVUS and OCT slices were coregistered and merged to form IVUS + OCT (IO) slices. A total of 114 matched slices (IVUS and OCT, baseline and follow-up) were obtained, and 3D thin-layer models were constructed to obtain stress and strain values. A generalized linear mixed model (GLMM) and least squares support vector machine (LSSVM) method were used to predict cap thickness change using nine morphological and mechanical risk factors. Prediction accuracies by all combinations (511) of those predictors with both IVUS and IO data were compared to identify optimal predictor(s) with their best accuracies. For the nine patients, the average of minimum cap thickness from IVUS was 0.17 mm, which was 26.08% lower than that from IO data (average = 0.23 mm). Patient variations of the individual errors ranged from ‒58.11 to 20.37%. For maximum cap stress between IO and IVUS, patient variations of the individual errors ranged from ‒30.40 to 46.17%. Patient variations of the individual errors of maximum cap strain values ranged from ‒19.90 to 17.65%. For the GLMM method, the optimal combination predictor using IO data had AUC (area under the ROC curve) = 0.926 and highest accuracy = 90.8%, vs. AUC = 0.783 and accuracy = 74.6% using IVUS data. For the LSSVM method, the best combination predictor using IO data had AUC = 0.838 and accuracy = 75.7%, vs. AUC = 0.780 and accuracy = 69.6% using IVUS data. This preliminary study demonstrated improved plaque cap progression prediction accuracy using accurate cap thickness data from IO slices and the differences in cap thickness, stress/strain values, and prediction results between IVUS and IO data. Large-scale studies are needed to verify our findings.

A new intelligent fault diagnosis and prognosis method for wind turbine doubly-fed induction generator

Condition Monitoring and fault-prognosis approaches are typical methods to reduce the energy production cost and Wind Turbine downtime. In this paper, a new CM combinatory system and fault prognosis are proposed based on an adaptive threshold, feature-level fusion, and new degradation indicator and the CM operation is based on a new index Symptom of Degeneration crossing of an adaptive threshold. Also, a new adaptive threshold is proposed based on the fuzzy rules and WT operation point. Fault prognosis is conducted with the Least-Squares Support-Vector Machine method, and Particle Swarm Optimization is employed for the optimum selecting of the wavelet Kernel function and the SVM parameters. The proposed technique is compared with other methods and the simulation results illustrate the PSO-LS-SVM superiorities. The effectiveness of the proposed prognostic structure is evaluated using a WT test-rig prototype. The experimental results demonstrate that the Condition-Based Maintenance is improved by the proposed structure and the RUL is predicted before serious damage occurrences.

Robust intelligent topology for estimation of heat capacity of biochar pyrolysis residues

Biochar is recognized as a promising spectrum for thermal science applications considering environmental protection. In this study, different artificial intelligence (AI) techniques are employed to determine the heat capacity of biochar derived from pyrolysis of different biomass sources as a function of pyrolysis temperature, post-treatments process, and temperature. Relatively substantial experimental measurements are employed for adjusting the hyper-parameters of the considered AI methodologies. Accurate measurement using seven statistical criteria confirmed that the least-squares support vector machine (LS-SVM) with the Gaussian-type kernel is the best paradigm for the considered task. Statistical analysis shows an excellent capacity of the developed LS-SVM approach for estimation of heat capacity of biochar, i.e., mean square error (MSE) of 6.82, absolute average relative deviation (AARD) of 0.15%, and regression coefficient (R2) of one. Furthermore, the LS-SVM method accuracy is more than 700 times better than the developed empirical correlation in literature.

Least Squares Support Vector Machine Regression Based on Sparse Samples and Mixture Kernel Learning

Least squares support vector machine (LSSVM) is a machine learning algorithm based on statistical theory. Itsadvantages include robustness and calculation simplicity, and it has good performance in the data processingof small samples. The LSSVM model lacks sparsity and is unable to handle large-scale data problem, this articleproposes an LSSVM method based on mixture kernel learning and sparse samples. This algorithm reduces theinitial training set to a sub-dataset using a sparse selection strategy. It converts the single kernel function in theLSSVM model into a mixed kernel function and optimizes its parameters. The reduced sub-dataset is used fortraining LSSVM. Finally, a group of datasets in the UCI Machine Learning Repository were used to verify theeffectiveness of the proposed algorithm, which is applied to real-world power load data to achieve better fittingand improve the prediction accuracy.

Parametric and non-parametric methods for monitoring nonlinear fuzzy profiles

In many statistical process control (SPC) applications, the quality of a process or product is represented by a relationship or the so-called quality profile, between a quality characteristic and one or more explanatory variables. The process quality characteristics are sometimes measured with a reasonable degree of approximation. Often, especially when qualitative assessments arise, evaluation of quality characteristics is carried out ambiguously or using linguistic qualifiers. The fuzzy sets theory has proved to be a well-established approach for dealing with uncertainty due to the approximate measurement, ambiguity in subjective evaluations, or vagueness in linguistic variables. Our main purpose was to present and compare four methods of monitoring nonlinear fuzzy profiles, for which different nonlinear fuzzy regression modeling approaches are considered. The first two methods are “a data-driven fuzzy rule-based” and “an extended least square support vector machine (LS-SVM),” for which the profile is characterized without considering a predefined mathematical relationship. However, for the other two methods, a specific form of the profile was needed. The third method, namely “a modified fuzzy regression model,” was initially invented for linear models. Besides, the fourth method employs “the fuzzy least square method” based on linearizing transformation. The exponentially weighted moving average (EWMA) control statistic was used to derive the control statistic to be plotted on the univariate as well as multivariate control charts. An extensive simulation study was conducted to compare the performance of the methods, and the average run length (ARL) criterion was considered to assess the detect-ability of control charts against various out-of-control conditions. Our comparison results indicated that the multivariate EWMA (MEWMA) chart based on the LS-SVM method outperforms the rest in detecting process shifts with smaller values of ARL when the process undergoes out-of-control conditions.

A study on ship collision conflict prediction in the Taiwan Strait using the EMD-based LSSVM method.

Ship collision accidents are the primary threat to traffic safety in the sea. Collision accidents can cause casualties and environmental pollution. The collision risk is a major indicator for navigators and surveillance operators to judge the collision danger between meeting ships. The number of collision accidents per unit time in a certain water area can be considered to describe the regional collision risk However, historical ship collision accidents have contingencies, small sample sizes and weak regularities; hence, ship collision conflicts can be used as a substitute for ship collision accidents in characterizing the maritime traffic safety situation and have become an important part of methods that quantitatively study the traffic safety problem and its countermeasures. In this work, an EMD-QPSO-LSSVM approach, which is a hybrid of empirical mode decomposition (EMD) and quantum-behaved particle swarm optimization (QPSO) optimized least squares support vector machine (LSSVM) model, is proposed to forecast ship collision conflicts. First, original ship collision conflict time series are decomposed into a collection of intrinsic mode functions (IMFs) and a residue with EMD. Second, both the IMF components and residue are applied to establish the corresponding LSSVM models, where the key parameters of the LSSVM are optimized by QPSO algorithm. Then, each subseries is predicted with the corresponding LSSVM. Finally, the prediction values of the original ship collision conflict datasets are calculated by the sum of the forecasting values of each subseries. The prediction results of the proposed method is compared with GM, Lasso regression method, EMD-ENN, and the predicted results indicate that the proposed method is efficient and can be used for the ship collision conflict prediction.