Least Squares Support Vector Machine Research Articles

Study on finishing inner wall of Co[sbnd]Cr alloy cardiovascular stent tube via novel atomized CBN/metal spherical magnetic abrasive powders

In this study, in order to solve the problem that the inner wall of the cardiovascular stent is difficult to polish, the magnetic abrasive finishing (MAF) method is used to finish the inner wall of the CoCr alloy tube that is used for the manufacture of the cardiovascular stent. The surface defects such as wrinkles, cracks and pits generated in the production process are removed, and the internal surface roughness is decreased to obtain better surface quality. Firstly, aiming at the problem of poor performance of traditional magnetic abrasive powders (MAPs), “gas-solid two-phase double-stage atomization and rapid solidification” is proposed and a novel atomized CBN/metal spherical MAPs with different sizes are successfully prepared. This MAP is used for MAF of the inner wall of CoCr alloy cardiovascular stent. Secondly, the slotted magnetic pole is designed according to the numerical simulation, and the MAF setup for the inner wall of ultra-fine and ultra-long tubes is developed. Finally, the orthogonal experiment is carried out with surface roughness as the evaluation index. Through the analysis of range theory, the order of the apparent degree of each process parameter on surface roughness is as follows: tube rotational speed > feed speed of magnetic pole > MAPs filling quantity > MAP particle size. According to the result, a model of surface roughness prediction based on whale optimization algorithm (WOA) and least squares support vector machine (LSSVM) is constructed. The interaction between tube rotational speed and other process parameters is analyzed based on the model fitting results, and the process parameters are optimized. The result show that MAF technology can effectively remove the defects of the inner wall of the CoCr alloy cardiovascular stent tube and accurately predict the surface roughness. After MAF under the optimized process parameters, the surface roughness Ra decreases from 0.485 μm to 0.092 μm.

Machine-learning predictions of solubility and residual trapping indexes of carbon dioxide from global geological storage sites

Ongoing anthropogenic carbon dioxide (CO2) emissions to the atmosphere cause severe air pollution that leads to complex changes in the climate, which pose threats to human life and ecosystems more generally. Geological CO2 storage (GCS) offers a promising solution to overcome this critical environmental issue by removing some of the CO2 emissions. The performance of GCS projects depends directly on the solubility and residual trapping efficiency of CO2 in a saline aquifer. This study models the solubility trapping index (STI) and residual trapping index (RTI) of CO2 in saline aquifers by applying four robust machine learning (ML) and deep learning (DL) algorithms. Extreme learning machine (ELM), least square support vector machine (LSSVM), general regression neural network (GRNN), and convolutional neural network (CNN) are applied to 6811 compiled simulation records from published studies to provide accurate STI and RTI predictions. Employing different statistical error metrics coupled with supplementary evaluations, involving score and robustness analyses, the prediction accuracy of the models proposed is comparatively assessed. The findings of the study revealed that the LSSVM model delivers the lowest RMSE values: 0.0043 (STI) and 0.0105 (RTI) with few outlying predictions. Presenting the highest STI and RTI prediction scores the LSSVM is distinguished as the most credible model among all the four models studied. The models consider eight input variables, of which the time elapsed and injection rate displays the strongest correlations with STI and RTI, respectively. The results suggest that the proposed LSSVM model is best suited for monitoring CO2 sequestration efficiency from the data variables considered. Applying such models avoids time-consuming complex simulations and offers the potential to generate fast and reliable assessments of GCS project feasibility. Accurate modeling of CO2 storage trapping indexes guarantees successful geological CO2 storage operation, which is, in fact, the cornerstone of properly controlling and managing environmentally polluting gases.

Detection of Defective Features in Cerasus Humilis Fruit Based on Hyperspectral Imaging Technology

Detection of skin defects in Cerasus humilis fruit is a critical process to guarantee its quality and price. This study presents a valid method for the detection of defective features in Cerasus humilis fruits based on hyperspectral imaging. A total of 420 sample images were acquired that included three types of natural defects and undamaged samples. After acquiring hyperspectral images of Cerasus humilis fruits, the spectral data were extracted from the region of interest (ROI). Five spectral preprocessing methods were used to preprocess the original spectral data, including Savitsky–Golay (S-G), standard normal variate (SNV), multiplicative scatter correction (MSC), baseline correction (BC), and de-trending (De-T). Regression coefficient (RC), successive projections algorithm (SPA), and competitive adaptive reweighed sampling (CARS) were conducted to select optimal sensitive wavelengths (SWs); as a result, 11 SWs, 17 SWs, and 13 SWs were selected, respectively. Then, the least squares-support vector machine (LS-SVM) discrimination model was established using the selected SWs. The results showed that the discriminate accuracy of the CARS-LS-SVM method was 91.43%. Based on the characteristics of image information, images corresponding to eight sensitive wavebands (950, 994, 1071, 1263, 1336, 1457, 1542, and 1628 nm) selected by CARS were subjected to principal component analysis (PCA). Then, an effective approach for detecting the defective features was exploited based on the imfill function, canny operator, region growing algorithm, bwareaopen function, and the images of PCA. The location and area of defect feature of 105 Cerasus humilis fruits could be recognized; the detect precision was 88.57%. This investigation demonstrated that hyperspectral imaging combined with an image processing technique could achieve the rapid identification of undamaged samples and natural defects in Cerasus humilis fruit. This provides a theoretical basis for the development of Cerasus humilis fruit grading and sorting equipment.

Stock Price Prediction of Walmart Based on Combination of SVM and LS-SVM Models

One of the most significant operations in the finance sector is stock trading. The stock market is an essential part in the economy of a country and serves as the indicators of the situation of a country’s economy as the stock prices go up or down. Therefore, stock price prediction, the behavior of attempting to predict the potential worth of a corporation or any financial instruments successfully, will maximize investor’s gain, enhance market’s confidence, and help government policymakers to make economic decisions. In order to forecast the price of a stock, a machine learning approach is constructed in this study. The suggested algorithm includes random forest, support vector machine (SVM), and least square support vector machine (LS-SVM). In particular, the random forest is employed to select the most important features from the technical indicators calculated for stock price prediction. The SVM and the LS-SVM models are employed to predict the daily stock prices. Besides, R-Squared (R²), mean squared error (MSE) and mean absolute error (MAE) are used for model evaluation. According to the results, both SVM and LS-SVM models can predict stock price well, but both algorithms are not suitable for large datasets, and overfitting problem exists. These results shed light on guiding further exploration of stock price predictions.

Improved Barnacle Mating Optimizer-Based Least Square Support Vector Machine to Predict COVID-19 Confirmed Cases with Total Vaccination

Abstract Every country must have an accurate and efficient forecasting model to avoid and manage the epidemic. This paper suggests an upgrade to one of the evolutionary algorithms inspired by nature, the Barnacle Mating Optimizer (BMO). First, the exploration phase of the original BMO is enhanced by enforcing and replacing the sperm cast equation through Levy flight. Then, the Least Square Support Vector Machine (LSSVM) is partnered with the improved BMO (IBMO). This hybrid approach, IBMO-LSSVM, has been deployed effectively for time-series forecasting to enhance the RBF kernel-based LSSVM model since vaccination started against COVID-19 in Malaysia. In comparison to other well-known algorithms, our outcomes are superior. In addition, the IBMO is assessed on 19 conventional benchmarks and the IEEE Congress of Evolutionary Computation Benchmark Test Functions (CECC06, 2019 Competition). In most cases, IBMO outputs are better than comparison algorithms. However, in other circumstances, the outcomes are comparable.

Quantitative Detection of Tank Floor Defects by Pseudo-Color Imaging of Three-Dimensional Magnetic Flux Leakage Signals

Highly integrated three-dimensional magnetic sensors have just been developed and have been used in some fields, such as angle measurement of moving objects. The sensor used in this paper is a three-dimensional magnetic sensor with three Hall probes highly integrated inside; 15 sensors are used to design the sensor array and then measure the magnetic field leakage of the steel plate; the three-dimensional component characteristics of the magnetic field leakage are used to determine the defect area. Pseudo-color imaging is the most widely used in the imaging field. In this paper, color imaging is used to process magnetic field data. Compared with analyzing the three-dimensional magnetic field information obtained directly, this paper converts the magnetic field information into color image information through pseudo-color imaging and then obtains the color moment characteristic values of the color image in the defect area. Moreover, the least-square support-vector machine and particle swarm optimization (PSO-LSSVM) algorithm are used to quantitatively identify the defects. The results show that the three-dimensional component of the magnetic field leakage can effectively determine the area range of defects, and it is feasible to use the color image characteristic value of the three-dimensional magnetic field leakage signal to identify defects quantitatively. Compared with a single component, the three-dimensional component can effectively improve the identification rate of defects.

Discrimination of Free-Range and Caged Eggs by Chemometrics Analysis of the Elemental Profiles of Eggshell.

As one of the foods commonly eaten all over the world, eggs have attracted more and more attention for their quality and price. A method based on elemental profiles and chemometrics to discriminate between free-range and caged eggs was established. Free-range (n1 = 127) and caged (n2 = 122) eggs were collected from different producing areas in China. The content of 16 elements (Zn, Pb, Cd, Co, Ni, Fe, Mn, Cr, Mg, Cu, Se, Ca, Al, Sr, Na, and K) in the eggshell was determined using a inductively coupled plasma atomic emission spectrometer (ICP-AES). Outlier diagnosis is performed by robust Stahel-Donoho estimation (SDE) and the Kennard and Stone (K-S) algorithm for training and test set partitioning. Partial least squares discriminant analysis (PLS-DA) and least squares support vector machine (LS-SVM) were used for classification of the two types of eggs. As a result, Cd, Mn, Mg, Se, and K make an important contribution to the classification of free-range and caged eggs. By combining column-wise and row-wise rescaling of the elemental data, the sensitivity, specificity, and accuracy were 91.9%, 91.1%, and 92.7% for PLS-DA, while the results of LS-SVM were 95.3%, 95.6%, and 95.1%, respectively. The result indicates that chemometrics analysis of the elemental profiles of eggshells could provide a useful and effective method to discriminate between free-range and caged eggs.

Accurate method for sleep stages classification using discriminated features and single EEG channel

Sleep classification can be time-consuming and challenging for professionals since electroencephalograms (EEGs) need to be segmented, evaluated, and manually annotated. This study aims to investigate the possibility of automating the classification of sleep stages to speed up the identification of sleep problems and assist medical professionals. In this study, Wavelet Transform (WT) and Residue Decomposition (RD) are proposed for feature extraction. First, the input signals are subjected to the Wavelet Transform of depth five with Daubechies order four (WTDB4) every 30 s at a frequency of 100 Hz. The Standard Deviation (SD), Sample Entropy (SE), and Zero Crossing Rate (ZCR) are then extracted from selected wavelet components. Following that, for each sub-band, the mean residue value and Median Absolute Deviation (MAD) of this value are determined. In addition, the Least Square Support Vector Machine (LSSVM) classifier is used to classify EEG signals obtained from the Sleep EDF single-channel database (Fpz-Cz). Also, the superiority of the LS-SVM performance over other classifiers such as Decision Tree (DT), Ensemble (Ens), Bagging (Bag), Random Subspace (RS), Random Forest (RF), Stacking (St), and Artificial Neural Networks (ANN) is demonstrated. Additionally, since single-channel EEGs are only used to categorize, the hardware implementation costs are low. Compared to other methods, numerical computer simulations show good classification results with the proposed method.

Application of machine learning techniques to build digital twins for long train dynamics simulations

The paper shows the feasibility of building closed-form and fast-to-evaluate surrogate models via supervised kernel-based machine learning regressions behaving as digital twins for computationally expensive multibody simulations. The aforementioned surrogate models are adopted to predict the railway vehicle dynamics safety indexes defined in the international standards, depending on the wheel-rail forces, directly from the results of longitudinal train dynamics simulations. The digital twin models are trained with the outputs of Simpack multibody simulations of a reference freight wagon, to which the in-train forces calculated by an in-house MATLAB longitudinal train dynamics simulator are applied. Two machine learning techniques are considered: the support vector machine and the least-squares support vector machine regressions. Both techniques ensure a good accuracy even with a limited number of training samples. The derivation of the surrogate models can strongly enhance the modelling capabilities of common longitudinal train dynamics simulators, that cannot evaluate the wheel-rail contact forces. At the same time, the method shown in the paper allows to strongly reduce the total computational times, as the evaluation of the closed-form surrogate models allows to effectively estimate the safety indexes with no need for computationally demanding multibody simulations.

Ultra-short-term wind power prediction based on double decomposition and LSSVM

To reduce the influence of the random fluctuation on wind power prediction, a new ultra-short-term wind power prediction model, based on wavelet decomposition (WD), variational mode decomposition (VMD), and least-squares support vector machine (LSSVM), is proposed in this paper. The method is based on the double decomposition and LSSVM, where the wind power sequence is decomposed by WD into low- and high-frequency components, which are further decomposed by VMD to obtain many modal components with tendency and periodicity. Multiple LSSVM prediction models are then established with historical wind power data and weather data as the inputs to obtain the predicted values of the multiple modal components. The final predicted values of wind power are achieved by data fusion of outputs of these LSSVM models. The experimental results show that the MAPE (mean absolute percentage error) of the combined prediction model is 4.66%, which is the best compared with nine benchmark models. This demonstrates the high performance of the proposed WD-VMD-LSSVM model for short-term prediction of wind power.

Archimedes Optimization Algorithm with Deep Learning-Based Prostate Cancer Classification on Magnetic Resonance Imaging

Prostate cancer (PCa) is becoming one of the most frequently occurring cancers among men and causes an even greater number of deaths. Due to the complexity of tumor masses, radiologists find it difficult to identify PCa accurately. Over the years, several PCa-detecting methods have been formulated, but these methods cannot identify cancer efficiently. Artificial Intelligence (AI) has both information technologies that simulate natural or biological phenomena and human intelligence in addressing issues. AI technologies have been broadly implemented in the healthcare domain, including 3D printing, disease diagnosis, health monitoring, hospital scheduling, clinical decision support, classification and prediction, and medical data analysis. These applications significantly boost the cost-effectiveness and accuracy of healthcare services. This article introduces an Archimedes Optimization Algorithm with Deep Learning-based Prostate Cancer Classification (AOADLB-P2C) model on MRI images. The presented AOADLB-P2C model examines MRI images for the identification of PCa. To accomplish this, the AOADLB-P2C model performs pre-processing in two stages: adaptive median filtering (AMF)-based noise removal and contrast enhancement. Additionally, the presented AOADLB-P2C model extracts features via a densely connected network (DenseNet-161) model with a root-mean-square propagation (RMSProp) optimizer. Finally, the presented AOADLB-P2C model classifies PCa using the AOA with a least-squares support vector machine (LS-SVM) method. The simulation values of the presented AOADLB-P2C model are tested using a benchmark MRI dataset. The comparative experimental results demonstrate the improvements of the AOADLB-P2C model over other recent approaches.

Response mechanism and rapid detection of phenotypic information in rice root under heavy metal stress

The root is an important organ affecting cadmium accumulation in grains, but there is no comprehensive research involving rice root phenotype under cadmium stress yet. To assess the effect of cadmium on root phenotypes, this paper investigated the response mechanism of phenotypic information including cadmium accumulation, adversity physiology, morphological parameters, and microstructure characteristics, and explored rapid detection methods of cadmium accumulation and adversity physiology. We found that cadmium had the effect of "low-promotion and high-inhibition" on root phenotypes. In addition, the rapid detection of cadmium (Cd), soluble protein (SP), and malondialdehyde (MDA) were achieved based on spectroscopic technology and chemometrics, where the optimal prediction model was least squares support vector machine (LS-SVM) based on the full spectrum (Rp=0.9958) for Cd, competitive adaptive reweighted sampling-extreme learning machine (CARS-ELM) (Rp=0.9161) for SP and CARS-ELM (Rp=0.9021) for MDA, all with Rp higher than 0.9. Surprisingly, it took only about 3 min, which was more than 90% reduction in detection time compared with laboratory analysis, demonstrating the excellent ability of spectroscopy for root phenotype detection. These results reveal response mechanism to heavy metal and provide rapid detection method for phenotypic information, which can substantially contribute to crop heavy metal control and food safety supervision.

A new empirical model for accurate investigation of rheological behavior of MWCNT/oxide nanoparticles-engine oil hybrid nano-lubricants

One of the most fundamental properties of nanofluids is their viscosity. To determine the viscosity of these fluids, many models based on experimental or theoretical studies have been developed. However, the bulk of these models either offer outcomes that are inaccurate or are restricted to a certain operating condition. As a result, determining the viscosity of nanofluids is a difficult undertaking. In this work, a novel model based on Least Squares Support Vector Machines (LSSVM) was provided to predict the viscosity of hybrid nano-lubricants of MWCNT-metal oxide nanoparticles/engine oil. Metal oxide nanoparticles including Al2O3, ZnO, SiO2, TiO2, CuO, and MgO, and engine oils including 5W50, 10W40, 20W50, SAE40, and SAE50 were considered in the studied hybrid nano-lubricants. The reliability of the proposed model was determined by comparing its outputs to experimental data obtained at various temperatures, nanoparticles’ concentrations, shear rates, and solid volume fractions. Additionally, the LSSVM model's coefficient of determination for all data was found to be 0.99649, demonstrating its high accuracy. Moreover, using the Monte-Carlo technique, the sensitivity analysis of the input variables on the output was computed which showed that the most sensitive variables for this model are shear rate, lubricant density, and nanoparticles volume fraction. This work highlights the requirement for a trustworthy approach to determine the viscosity of hybrid nano-lubricants and suggests one.

Wireless Body Area Network for Preventing Self-Inoculation Transmission of Respiratory Viral Diseases.

This paper proposes an idea of Wireless Body Area Networks (WBANs) based on Bluetooth Low-Energy (BLE) standards to recognize and alarm a gesture of touching the face, and in effect, to prevent self-inoculation of respiratory viral diseases, such as COVID-19 or influenza A, B, or C. The proposed network comprises wireless modules placed in bracelets and a necklace. It relies on the received signal strength indicator (RSSI) measurements between the bracelet and necklace modules. The measured signal is cleared of noise using the exponential moving average (EMA). Next, we use a classification algorithm based on a Least-Squares Support Vector Machine (LSSVM) in order to detect facial touches. When the results of the classification indicate that the hand is moving toward the face, an alarm is sent through the neck module and the vibrator embedded in the wrist module is switched on. Based on the performed tests, it can be concluded that the proposed solution is characterized by high accuracy and reliability. It should be useful, especially for individuals who are regularly exposed to the risk of respiratory infections.

Spectroscopic studies on thermal degradation and quantitative prediction on acid value of edible oil during frying by Raman spectroscopy

The health risks posed by harmful substances resulting from the thermal degradation of frying oils are of great concern. Characteristic peak intensity ratios (PIRs) screened from Raman spectra were used to characterize the thermal degradation. High correlation coefficients between PIRs and acid values (AVs) of 0.972 (linear fitting), 0.984 (logarithmic function fitting), and 0.954 (linear fitting) for fried soybean oil, canola oil, and palm oil, were obtained at the PIRs of I1267/I1749, I1267/I1659, and I1267/I1749, respectively. The highly correlated PIRs common to the three oils were determined by Pearson’s correlation coefficient combined with heat maps. To accommodate both linear and nonlinear features, a global model for predicting AVs of multi-varieties frying oils was constructed using a least-squares support vector machine algorithm, and the results performed well with a root mean square error of prediction of 0.016 and a ratio of prediction to deviation of 11.351. The whole results demonstrate that Raman spectroscopy could characterize the thermal degradation and has excellent quantitative analysis ability for food control based on AV in frying oils, thus providing a new approach to quality control of frying oils.

Nondestructive detection of water status and distribution in corn kernels during hot air drying using multispectral imaging.

The characteristics of corn kernels are strongly connected with the content of three statuses of water: bound water, immobilized water, and free water. Monitoring different water contents is very important to optimize the drying process, improve corn quality, and reduce energy consumption. The feasibility of nondestructive detection of water status and its distribution in corn kernels during the hot-air drying process using multispectral imaging was investigated. The chemometric methods used to develop prediction models were back propagation neural network, least-squares support vector machine, and partial least squares. The back propagation neural network achieved the best prediction performance for total and free water contents, with correlation coefficient of prediction (Rp ) of 0.9717 and 0.9782 respectively, root-mean-square error of prediction (RMSEP) of 4.48% and 2.54% respectively, and ratio of prediction to deviation (RPD) of 4.87 and 4.29 respectively. And partial least squares was better for the prediction of immobilized and bound water contents, with Rp of 0.9612 and 0.9798 respectively, RMSEP of 0.57% and 0.06% respectively, and RPD of 4.78 and 4.42 respectively. It could be concluded that multispectral imaging combined with chemometric methods would be a promising technique for rapid and nondestructive detection of water status and its distribution in corn kernels. © 2023 Society of Chemical Industry.

Slope stability prediction based on adaptive CE factor quantum behaved particle swarm optimization-least-square support vector machine

Since the prediction of slope stability is affected by the combination of geological and engineering factors with uncertainties such as randomness, vagueness and variability, the traditional qualitative and quantitative analysis cannot match the recent requirements to judge them accurately. In this study, we expect that the adaptive CE factor quantum behaved particle swarm optimization (ACE-QPSO) and least-square support vector machine (LSSVM) can improve the prediction accuracy of slope stability. To ensure the global search capability of the algorithm, we introduced three classical benchmark functions to test the performance of ACE-QPSO, quantum behaved particle swarm optimization (QPSO), and the adaptive dynamic inertia weight particle swarm optimization (IPSO). The results show that the ACE-QPSO algorithm has a better global search capability. In order to evaluate the stability of the slope, we followed the actual project and research literature and selected the unit weight, slope angle, height, internal cohesion, internal friction angle and pore water pressure as the main indicators. To determine whether the algorithm is scientifically and practically feasible for slope deformation prediction, the ACE-QPSO-, QPSO-, IPSO-LSSVM and single least-square support vector machine algorithms were trained and tested based on a real case of slope project with six index factors as the input layer of the LSSVM model and the safety factor as the output layer of the model. The results show that the ACE-QPSO-LSSVM algorithm has a better model fit (R2=0.8030), minor prediction error (mean absolute error=0.0825, mean square error=0.0110) and faster convergence (second iteration), which support that the ACE-QPSO-LSSVM algorithm emthod is more feasible and efficient in predicting slope stability.

Research on transformer fault diagnosis based on ISOMAP and IChOA‐LSSVM

AbstractOil‐immersed transformers play an important role in the stable operation of power systems. In order to improve the accuracy of transformer fault diagnosis, a transformer fault diagnosis method based on Isomap and IChOA‐LSSVM is proposed. Firstly, Isomap is used to reduce the dimensionality of the 14‐dimensional transformer fault characteristics data to eliminate redundant data between variables. In addition, IChOA is proposed to optimise the Least Squares Support Vector Machine (LSSVM) parameters and establish an optimal diagnosis model based on LSSVM. For ChOA, three improvement methods are proposed. Circle mapping is used instead of the original population initialisation to improve population diversity. In addition, the location weighting strategy with proportional weights and the Gaussian Corsi variation strategy is proposed to improve the optimization accuracy and efficiency of ChOA. The improved ChOA is compared with the original ChOA, PSO and GWO algorithms by five benchmark test functions. Finally, the improved Chimpanzee Optimisation algorithm was used to find the parameters of the LSSVM to obtain the fault diagnosis model combining Isomap and IChOA‐LSSVM. The model is compared with PSO‐LSSVM, ChOA‐LSSVM and GWO‐LSSVM. The diagnostic accuracy is 90.83%, 81.67%, 83.33% and 80%, respectively. The results demonstrate that the proposed method can effectively improve the performance of transformer fault diagnosis.

An Intelligent Advanced Classification Method for Tunnel-Surrounding Rock Mass Based on the Particle Swarm Optimization Least Squares Support Vector Machine

The fast and accurate classification of surrounding rock mass is the basis for tunnel design and construction and has significant value in engineering applications. Therefore, this paper proposes a method for classifying and predicting surrounding rock mass based on particle swarm optimization (PSO)–least squares support vector machine (LSSVM). The premise of the research is that the data acquired from digital drilling technology are divided into a training group and a test group; the training group continuously optimizes the algorithm for the particle swarm optimization least squares support vector machine, and then the test group is used for verification. Moreover, the fast searching abilities of the particle swarm significantly accelerate the computational power and computational accuracy of the least squares support vector machine, making it a high-speed analog search tool. Taking the Jiaozhou Bay undersea tunnel in China as an example, a comparison of the evaluation results of PSO-LSSVM and QGA-RBF (quantum genetic algorithm-radical basis function neural network) is undertaken. The results show that PSO-LSSVM matches well with the field-measured surrounding rock grade. Applying the method in an engineering context proves that it has good self-learning abilities, even when the sample size is small and the prediction accuracy is high; as such, it meets the engineering requirements. The technique has the advantages of small sample prediction, pattern recognition, and nonlinear prediction.

Landslide Displacement Prediction of Shuping Landslide Combining PSO and LSSVM Model

Predicting the deformation of landslides is significant for landslide early warning. Taking the Shuping landslide in the Three Gorges Reservoir area (TGRA) as a case, the displacement is decomposed into two components by a time series model (TSM). The least squares support vector machine (LSSVM) model optimized by particle swarm optimization (PSO) is selected to predict the landslide displacement prediction based on rainfall and reservoir water level (RWL). Five parameters, including rainfall over the previous month, rainfall over the previous two months, RWL, change in RWL over the previous month and period displacement over the previous half year, are selected as the input variables. The relationships between the five parameters and the landslide displacement are revealed by grey correlation analysis. The PSO-LSSVM model is used to predict the periodic term displacement (PTD), and the least squares method is applied to predict the trend term displacement (TTD). With the same input variables, the back propagation (BP) model and the PSO-SVM model are also developed for comparative analysis. In the PSO-LSSVM model, the R2 of three monitoring stations is larger than 0.98, and the MAE values and the RMSE values are the smallest among the three models. The outcomes demonstrate that the PSO-LSSVM model has a high accuracy in predicting landslide displacement.