Machine learning-based bridge cable damage detection under stochastic effects of corrosion and fire

Camera calibration is one of fundamental issues in computer vision and required for achieving accurate visual measurements. Least Squares Support Vector Machines (LS-SVM) are used to achieve the camera calibration. It doesn't need to confirm the intrinsic and extrinsic parameter of the camera. For a little more accurate calibration, acquired image is divided into two regions according to radial distortion of lens and Least Squares Support Vector Machines is applied to each region. A simple and flexible camera calibration using divided Least Squares Support Vector Machines (DLS-SVM) is proposed in this paper. Experiment results and comparison with BP neural network and Least Squares Support Vector Machines prove the validity of the proposed camera calibration.

Good water quality is important for normal production processes in industrial aquaculture. However, in situ or real-time monitoring is generally not available for many aquacultural systems due to relatively high monitoring costs. Therefore, it is necessary to predict water quality parameters in industrial aquaculture systems to obtain useful information for managing production activities. This study used back propagation neural network (BPNN), radial basis function neural network (RBFNN), support vector machine (SVM), and least squares support vector machine (LSSVM) to simulate and predict water quality parameters including dissolved oxygen (DO), pH, ammonium-nitrogen (NH3-N), nitrate nitrogen (NO3-N), and nitrite-nitrogen (NO2-N). Published data were used to compare the prediction accuracy of different methods. The correlation coefficients of BPNN, RBFNN, SVM, and LSSVM for predicting DO were 0.60, 0.99, 0.99, and 0.99, respectively. The correlation coefficients of BPNN, RBFNN, SVM, and LSSVM for predicting pH were 0.56, 0.84, 0.99, and 0.57. The correlation coefficients of BPNN, RBFNN, SVM, and LSSVM for predicting NH3-N were 0.28, 0.88, 0.99, and 0.25, respectively. The correlation coefficients of BPNN, RBFNN, SVM, and LSSVM for predicting NO3-N were 0.96, 0.87, 0.99, and 0.87, respectively. The correlation coefficients of BPNN, RBFNN, SVM, and LSSVM predicted NO2-N with correlation coefficients of 0.87, 0.08, 0.99, and 0.75, respectively. SVM obtained the most accurate and stable prediction results, and SVM was used for predicting the water quality parameters of industrial aquaculture systems with groundwater as the source water. The results showed that the SVM achieved the best prediction effect with accuracy of 99% for both published data and measured data from a typical industrial aquaculture system. The SVM model is recommended for simulating and predicting the water quality in industrial aquaculture systems.

To overcome the low positioning accuracy of piezoelectric actuators (PEAs) caused by the hysteresis non-linearity, a hysteresis compensation control method based on truncated least squares support vector machine(T-LSSVM) is proposed. Firstly, for the low-robustness of least squares support vector machine(LS-SVM), a novel truncation strategy is proposed and a robust truncated least squares support vector machine(T-LSSVM) for hysteresis modeling is established. Then, based on T-LSSVM, the hysteresis inverse model is established to achieve real-time compensation for the hysteresis nonlinearity in PEAs. Finally, based on the hysteresis inverse compensation method, the feedforward-feedback hysteresis compensation control for PEAs is established. To test the proposed control method, the PID feedback control is introduced as comparisons. Experimental results show that the proposed control method is of higher accuracy and better generalization, realizing real-time high-precision tracking control of PEAs.

Visible and near infrared (Vis/NIR) spectroscopy combined with a hybrid calibrations of partial least squares (PLS), BP neural network (BPNN) and least squares-support vector machine (LS-SVM) was investigated to determine the pH values of rice vinegars. Five varieties of rice vinegars and 300 samples were prepared. After some preprocessing, PLS was implemented for calibration as well as the extraction of principal components, which would be used as the inputs of BPNN and LS-SVM models. Finally, the BPNN and LS-SVM regression models were developed with a comparison of PLS. The correlation coefficient (r), root mean square error of prediction (RMSEP) and bias for prediction were 0.982, 0.042, and -0.012 by PLS, 0.992, 0.027, and 0.004 by BPNN, while 0.996, 0.018, and 0.005 by LS-SVM, respectively. The results indicated that Vis/NIR spectroscopy combined with chemometrics could be applied as a high precision way for the determination of pH of rice vinegars.

Periodic surveys of asphalt pavement condition are very crucial in road maintenance. This work carries out a comparative study on the performance of machine learning approaches used for automatic pavement crack recognition. Six machine learning approaches, Naïve Bayesian Classifier (NBC), Classification Tree (CT), Backpropagation Artificial Neural Network (BPANN), Radial Basis Function Neural Network (RBFNN), Support Vector Machine (SVM), and Least Squares Support Vector Machine (LSSVM), have been employed. Additionally, Median Filter (MF), Steerable Filter (SF), and Projective Integral (PI) have been used to extract useful features from pavement images. In the feature extraction phase, performance comparison shows that the input pattern including the diagonal PIs enhances the classification performance significantly by creating more informative features. A simple moving average method is also employed to reduce the size of the feature set with positive effects on the model classification performance. Experimental results point out that LSSVM has achieved the highest classification accuracy rate. Therefore, this machine learning algorithm used with the feature extraction process proposed in this study can be a very promising tool to assist transportation agencies in the task of pavement condition survey.

It is well known that the performance of Least Squares Support Vector Machine (LSSVM) is guaranteed by k-fold cross-validation (k-CS) or other optimized approaches to choose an appropriate setting of a number of parameters including such as the regularization parameter (7) and the kernel parameter (σ) and so on. However, it is mentioned in a large number of research on k-CS that it need more computational time and large computational burden in the process of optimizing parameters for LSSVM. Moreover, the obtained parameters by CS method are fixed and it lead easily to a poor generalization capabilities in various application. In order to avoid k-CS and to implement parameters update online, this paper proposes a novel method which applied Unscented Kalman Filter (UKF) to dynamically implement parameter updating problem for LSSVM. To estimate LSSVM's parameters online, the state and measurement equations of UKF are first constructed by considering LSSVM's parameter choice as state variable and treating LSSVM model as the measurement equation, respectively. Then, the UKF approach is used to update the LSSVM parameters timely according to the last obtained instance. Applying the proposed method, LSSVM parameters are not any more fixed as tuned parameters on the training dataset, but are adjusted dynamically as new measurements arrived. Finally, the viability and superiority of the proposed method are verified by simulation.

In this paper, based on the Discrete Wavelet Transform (DWT) and Least Square Support Vector Machine (LSSVM), the torque observer for hybrid electric vehicles (HEV) is established. Data from the benchmarking test is employed as the training sample, and the DWT-LSSVM based multi-layer observer was trained to observe the torque distribution results of hybrid electric vehicles. The DWT -LSSVM based multi-layer observer can accurately offer the control results of the original vehicle and solve the problem that it is difficult to reproduce the control results of the original vehicle completely. The main work is as follows: first, a multi-layer observation model based on DWT-LSSVM is established. Multiple LSSVM modules are used to observe the input signals with different frequency that are decomposed by wavelet method, and wavelet reconstruction method is used to integrate the observation results of different input signals to obtain the final observation result of vehicle torque distribution. Secondly, the cross-validation method is used to optimize the parameters in LSSVM model to ensure the accuracy of model prediction. Thirdly, taking the test data of a four-wheel drive hybrid electric vehicle (4WD-HEV)as an example, the observation model proposed in this paper is compared with the simply LSSVM observation model. The results show that the observation results of the torque observation model based on DWT-LSSVM are better than those by the simply LSSVM observation model. The compare results justify the proposed method can improve the accuracy of torque observation.

Application of image texture for the sorting of tea categories using multi-spectral imaging technique and support vector machine

For an underwater Strapdown Inertial Navigation System/Doppler velocity log (SINS/DVL) integrated navigation system, the short-term failure of DVL may lead to the loss of reliable external velocity information from DVL, which will cause the SINS errors to accumulate. To circumvent this problem, this paper proposes a velocity predictor based on fuzzy multi-output least squares support vector machine (FMLS-SVM) to predict DVL measurements when DVL malfunctions occur. Firstly, the single-output least squares support vector machine (LS-SVM) model is extended to the multi-output LS-SVM model (MLS-SVM), and the self-adaptive fuzzy membership is introduced to fuzzify the input samples to overcome the over-fitting problem caused by the excessive sensitivity to the outlier points. Secondly, the fuzzy membership function is designed from the idea of the K nearest neighbor (KNN) algorithm. Finally, considering the influence of vehicle maneuver on the prediction model of DVL, the dynamic attitude angles are extended to the input samples of the prediction model to improve the adaptability of the DVL prediction model under large maneuver conditions. The performance of the method is verified by lake experiments. The comparison results show that the velocity predictor based on FMLS-SVM can correctly provide the estimated DVL measurements, effectively prolong the fault tolerance time of DVL faults, and improve the accuracy and reliability of the SINS/DVL integrated navigation system.

Aiming at the problem that the Least Squares Support Vector Machines(LSSVM) was sensitive to noises or outliers, fuzzy idea was used to the Least Squares Support Vector Machines.The Fuzzy Least Squares Support Vector Machines(FLSSVM) was proposed and was applied to the Landslide Deformation Prediction. Experimental results show that this method can improve the accuracy of prediction and be effectively applied to landslide deformation prediction.

The Least Squares Support Vector Machine (LS-SVM) is a modified SVM with a ridge regression cost function and equality constraints. It has been successfully applied in many classification problems. But, the common issue for LS-SVM is that it lacks sparseness, which is a serious drawback in its applications. To tackle this problem, a fast approach is proposed in this paper for developing sparse LS-SVM. First, a new regression solution is proposed for the LS-SVM which optimizes the same objective function for the conventional solution. Based on this, a new subset selection method is then adopted to realize the sparse approximation. Simulation results on different benchmark datasets i.e. Checkerboard, two Gaussian datasets, show that the proposed solution can achieve better objective value than conventional LS-SVM, and the proposed approach can achieve a more sparse LS-SVM than the conventional LS-SVM while provide comparable predictive classification accuracy. Additionally, the computational complexity is significantly decreased.

This paper uses a radial basis function (RBF) neural network for star identification. A feature vector consisting of distance and angle cosine values is constructed as a library of recognition feature stars and input to the neural network. Then, the network’s output is the number of the corresponding primary star. Comparing the training efficiency and robustness of the grid algorithm with the BP neural network and radial basis function neural network for star identification, the experimental results show that the radial basis function neural network has a strong anti-interference ability against noise and pseudo-star interference. The following conclusions are drawn from the simulation tests: the sample recognition rate of radial basis function neural network algorithm can reach 96% for star position and star addition noise; when the proportion of pseudo-star reaches 20%, the sample recognition rate of radial basis function neural network algorithm is still higher than grid algorithm and BP neural network, which indicates that the radial basis function neural network algorithm has the solid anti-interference ability to both noise and pseudo-star. Therefore, the radial basis function neural network algorithm based on star Identification has specific application prospects.

Icing condition prediction of wind turbine blade by using artificial neural network based on modal frequency

In the practical implementation of control of electromyography (sEMG) driven devices, algorithms should recognize the human’s motion from sEMG with fast speed and high accuracy. This study proposes two feature engineering (FE) techniques, namely, feature-vector resampling and time-lag techniques, to improve the accuracy and speed of least square support vector machine (LSSVM) for wrist palmar angle estimation from sEMG feature. The root mean square error and correlation coefficients of LSSVM with FE are 9.50 2.32 degree and 0.971 0.018 respectively. The average training time and average execution time of LSSVM with FE in processing 12600 sEMG points are 0.016 s and 0.053 s respectively. To evaluate the proposed algorithm, its estimation results are compared with those of three other methods, namely, LSSVM, radial basis function (RBF) neural network, and RBF with FE. Experimental results verify that introduction of time-lag into feature vector can greatly improve the estimation accuracy of both RBF and LSSVM; meanwhile the application of feature-vector resampling technique can significantly increase the training and execution speed of RBF neural network and LSSVM. Among different algorithms applied in this study, LSSVM with FE techniques performed best in terms of training and execution speed, as well as estimation accuracy.

Many kinds of classification method are able to diagnose a patient who suffered Hepatitis disease. One of classification methods that can be used was Least Squares Support Vector Machines (LSSVM). There are two parameters that very influence to improve the classification accuracy on LSSVM, they are kernel parameter and regularization parameter. Determining the optimal parameters must be considered to obtain a high classification accuracy on LSSVM. This paper proposed an optimization method based on Improved Ant Colony Algorithm (IACA) in determining the optimal parameters of LSSVM for diagnosing Hepatitis disease. IACA create a storage solution to keep the whole route of the ants. The solutions that have been stored were the value of the parameter LSSVM. There are three main stages in this study. Firstly, the dimension of Hepatitis dataset will be reduced by Local Fisher Discriminant Analysis (LFDA). Secondly, search the optimal parameter LSSVM with IACA optimization using the data training, And the last, classify the data testing using optimal parameters of LSSVM. Experimental results have demonstrated that the proposed method produces high accuracy value (93.7%) for the 80-20% training-testing partition.