Multiple Support Vector Machine Research Articles

Machine Learning Techniques for Fine Dead Fuel Load Estimation Using Multi-Source Remote Sensing Data

Fine dead fuel load is one of the most significant components of wildfires without which ignition would fail. Several studies have previously investigated 1-h fuel load using standard fuel parameters or site-specific fuel parameters estimated ad hoc for the landscape. On the one hand, these methods have a large margin of error, while on the other their production times and costs are high. In response to this gap, a set of models was developed combining multi-source remote sensing data, field data and machine learning techniques to quantitatively estimate fine dead fuel load and understand its determining factors. Therefore, the objectives of the study were to: (1) estimate 1-h fuel loads using remote sensing predictors and machine learning techniques; (2) evaluate the performance of each machine learning technique compared to traditional linear regression models; (3) assess the importance of each remote sensing predictor; and (4) map the 1-h fuel load in a pilot area of the Apulia region (southern Italy). In pursuit of the above, fine dead fuel load estimation was performed by the integration of field inventory data (251 plots), Synthetic Aperture Radar (SAR, Sentinel-1), optical (Sentinel-2), and Light Detection and Ranging (LIDAR) data applying three different algorithms: Multiple Linear regression (MLR), Random Forest (RF), and Support Vector Machine (SVM). Model performances were evaluated using Root Mean Squared Error (RMSE), Mean Squared Error (MSE), the coefficient of determination (R2) and Pearson’s correlation coefficient (r). The results showed that RF (RMSE: 0.09; MSE: 0.01; r: 0.71; R2: 0.50) had more predictive power compared to the other models, while SVM (RMSE: 0.10; MSE: 0.01; r: 0.63; R2: 0.39) and MLR (RMSE: 0.11; MSE: 0.01; r: 0.63; R2: 0.40) showed similar performances. LIDAR variables (Canopy Height Model and Canopy cover) were more important in fuel estimation than optical and radar variables. In fact, the results highlighted a positive relationship between 1-h fuel load and the presence of the tree component. Conversely, the geomorphological variables appeared to have lower predictive power. Overall, the 1-h fuel load map developed by the RF model can be a valuable tool to support decision making and can be used in regional wildfire risk management.

The Soil Nutrient Digital Mapping for Precision Agriculture Cases in the Trans-Ural Steppe Zone of Russia Using Topographic Attributes

Topographic features of territory have a significant impact on the spatial distribution of soil properties. This research is focused on digital soil mapping (DSM) of main agrochemical soil properties—values of soil organic carbon (SOC), nitrogen, potassium, calcium, magnesium, sodium, phosphorus, pH, and thickness of the humus-accumulative (AB) horizon of arable lands in the Trans-Ural steppe zone (Republic of Bashkortostan, Russia). The methods of multiple linear regression (MLR) and support vector machine (SVM) were used for the prediction of soil nutrients spatial distribution and variation. We used 17 topographic indices calculated using the SRTM (Shuttle Radar Topography Mission) digital elevation model. Results showed that SVM is the best method in predicting the spatial variation of all soil agrochemical properties with comparison to MLR. According to the coefficient of determination R2, the best predictive models were obtained for content of nitrogen (R2 = 0.74), SOC (R2 = 0.66), and potassium (R2 = 0.62). In our study, elevation, slope, and MMRTF (multiresolution ridge top flatness) index are the most important variables. The developed methodology can be used to study the spatial distribution of soil nutrients and large-scale mapping in similar landscapes.

A novel interval-valued fuzzy multiple twin support vector machine

Multiple twin support vector machine (MTSVM) which evaluates all the training data into a ``one-versus-rest'' structure is a multi-class classification algorithm. It has extensive applications in the multi-class classification problems. Like twin support vector machine (TSVM), MTSVM treats all sample points equally because it lacks the ability to judge the importance of different sample points. In order to improve the classification performance of MTSVM, a new method of adding interval-valued fuzzy membership degree to sample points is proposed. In this way, a novel interval-valued fuzzy multiple twin support vector machine (IVF-MTSVM) is established in this paper. Previous methods of adding fuzzy membership degree to sample points are totally based on their importance to the class, while the method in this paper emphasizes the importance of sample points to the classification model, and takes into account the importance to the class to some extent. This is a new perspective to establish fuzzy membership degree to sample points in support vector machines since it is different from the previous methods in thinking. Then the solution to IVF-MTSVM is derived. Experiments on UCI datasets show that this new method has certain advantages over other multi-class twin support vector machine methods in ``one-versus-rest'' structure and other fuzzy multiple twin support vector machine established by some previous methods. Finally, Friedman test and Benferroni-Dunn test are used to verify the statistical significance of this new method.

Development of QSAR models for prediction of fish bioconcentration factors using physicochemical properties and molecular descriptors with machine learning algorithms

Bioconcentration factors (BCFs) are indicators of the accumulation of chemical substances in organisms; they play an important role in the environmental risk assessment of various chemical substances. Experiments to obtain BCFs are expensive and time consuming; hence, it is desirable to predictively determine BCF during the early stage of chemical development. In this study, we developed a quantitative structure-activity relationship (QSAR) model using physicochemical properties, environmental fate endpoints, and molecular descriptors. Physicochemical properties and environmental fate endpoints were generated by OPERA, which is a QSAR software. Moreover, we calculated the molecular descriptors using Mordred. A gradient boosting decision tree model was developed as a machine learning model, and multiple linear regression and support vector machine models were developed for comparison. Our developed model showed that the coefficients of determination (R2) of the training and test sets were 0.923 and 0.863, respectively, which are higher than the predictions of the previous model and values calculated by OPERA. The results obtained from the present study suggest that an accurate QSAR model can be developed using the physicochemical properties, environmental fate endpoints, and molecular descriptors calculated from the chemical structure without actually conducting BCF experiments. The model could be one of the choice for the preliminary risk assessment without investing in a large number of BCF experiments during the early development stages of candidate chemicals.

Value of contrast-enhanced CT texture analysis in predicting IDH mutation status of intrahepatic cholangiocarcinoma

To explore the value of contrast-enhanced CT texture analysis in predicting isocitrate dehydrogenase (IDH) mutation status of intrahepatic cholangiocarcinomas (ICCs). Institutional review board approved this study. Contrast-enhanced CT images of 138 ICC patients (21 with IDH mutation and 117 without IDH mutation) were retrospectively reviewed. Texture analysis was performed for each lesion and compared between ICCs with and without IDH mutation. All textural features in each phase and combinations of textural features (p < 0.05) by Mann–Whitney U tests were separately used to train multiple support vector machine (SVM) classifiers. The classification generalizability and performance were evaluated using a tenfold cross-validation scheme. Among plain, arterial phase (AP), portal venous phase (VP), equilibrium phase (EP) and Sig classifiers, VP classifier showed the highest accuracy of 0.863 (sensitivity, 0.727; specificity, 0.885), with a mean area under the receiver operating characteristic curve of 0.813 in predicting IDH mutation in validation cohort. Texture features of CT images in portal venous phase could predict IDH mutation status of ICCs with SVM classifier preoperatively.

Quantifying Forest Fire and Post-Fire Vegetation Recovery in the Daxin’anling Area of Northeastern China Using Landsat Time-Series Data and Machine Learning

Many post-fire on-site factors, including fire severity, management strategies, topography, and local climate, are concerns for forest managers and recovery ecologists to formulate forest vegetation recovery plans in response to climate change. We used the Vegetation Change Tracker (VCT) algorithm to map forest disturbance in the Daxing’anling area, Northeastern China, from 1987 to 2016. A support vector machine (SVM) classifier and historical fire records were used to separate burned patches from disturbance patches obtained from VCT. Afterward, stepwise multiple linear regression (SMLR), SVM, and random forest (RF) were applied to assess the statistical relationships between vegetation recovery characteristics and various influential factors. The results indicated that the forest disturbance events obtained from VCT had high spatial accuracy, ranging from 70% to 86% for most years. The overall accuracy of the annual fire patches extracted from the proposed VCT-SVM algorithm was over 92%. The modeling accuracy of post-fire vegetation recovery was excellent, and the validation results confirmed that the RF algorithm provided better prediction accuracy than SVM and SMLR. In conclusion, topographic variables (e.g., elevation) and meteorological variables (e.g., the post-fire annual precipitation in the second year, the post-fire average relative humidity in the fifth year, and the post-fire extreme maximum temperature in the third year) jointly affect vegetation recovery in this cold temperate continental monsoon climate region.

Surface Recognition via Force-Sensory Walking-Pattern Classification for Biped Robot

Real-time surface recognition has become a critical factor for ensuring safe walking of intelligent biped robots in a complex human living environment. This work aims at enabling wide cost-efficient implementation of sensing solutions for surface recognition via walking-pattern classification by restricting the necessary hardware to a cost-economic microprocessor and a single type of force sensors. For experimental analysis, we explored the walking-pattern classification performance using a framework which combines a support vector machine (SVM) and four time-domain feature descriptors, i.e., mean of amplitude (MA), integral of absolute value (IAV), variance (VAR), and root mean square (RMS). During the online pattern classification, the dynamical force-sensory-data stream was extracted using a real-time overlapped-window-based method. Multiple binary SVM classifiers were applied for solving the multi-class classification problem, due to the reasonably high accuracy and the relatively small complexity for hardware implementation, allowing simultaneous strength exploitation of above four individual feature descriptors with a one-versus-one (OVO) strategy. The experimental results, obtained with 250 samples/surface, verified 93.8% mean average precision, 93.7% average accuracy and recall rates of 98.8%, 91.6%, 82.0%, 98.0%, 98.0% for smooth wood, rough foam, smooth foam, thick carpet, and thin carpet, respectively. Only the dynamical force-sensing data were employed for a 10-fold cross validation, which enabled the high processing speed of 0.73 ms/stride. The developed cost-efficient and accurate surface-recognition system can be useful for ensuring safe in-door locomotion for the biped robot and can help the robot to better understand the human living environment by increasing its sensing diversity.

Data-Driven Subsynchronous Oscillation Identification Using Field Synchrophasor Measurements

With the increasing development of renewable energy and high-voltage direct current (HVDC) transmission technology, the integration of power electronics-interfaced components has caused sub-&#x002F;super-synchronous inter-harmonics into power signals, yielding the subsynchronous oscillations (SSOs). Online monitoring and identification of SSOs are crucial to the secure and stable operation of power systems. This paper proposes a data driven SSOs identification method using realistic phasor measurement unit (PMU) data. Three features are extracted via the analysis of a large number of historical PMU data, which can reflect the SSO features and the interference level. An SSOs identification method is proposed through a multiple-support vector machine (SVM) model. It allows us to adaptively select the proper classifier among the multiple-SVM models according to the interference level estimated by the extracted features. This significantly improves the identification accuracy under both low and high interference inputs of a practical power grid. An automatic update function based on incremental learning is also developed to enhance the model performance when the SSO data are subject to new features. Experimental results using field-measured PMU data validate the advantages of the proposed method over other alternatives.

Ensemble of Multiple Kernel SVM Classifiers for Detection of Online Spam Reviews

The Social web contains enormous content, in which higher range of online users believe the Online Reviews for their decision making before any online purchase or using services. The online reviews written are all not true. Some of the Reviews are Spam for many reasons. Data Mining Classification provides good solution to find the Review as Spam or Ham. SVM(Support Vector Machines) classifier is the most frequently used classifier. There are proven record of achieving high performance through SVM Classifier during classification of all kinds of data especially text data for binary classification. Ensemble of Multiple Kernels such as SVM-Polynomial, SVM-Linear, SVM-Sigmoid, SVM-RBF(Radial Basis Function) of SVM improves the classifiers performance in a significant way.

Granular multiple kernel learning for identifying RNA-binding protein residues via integrating sequence and structure information

RNA-binding proteins play an important role in the biological process. However, the traditional experiment technology to predict RNA-binding residues is time-consuming and expensive, so the development of an effective computational approach can provide a strategy to solve this issue. In recent years, most of the computational approaches are constructed on protein sequence information, but the protein structure has not been considered. In this paper, we use a novel computational model of RNA-binding residues prediction, using protein sequence and structure information. Our hybrid features are encoded by local sequence and structure feature extraction models. Our predictor is built by employing the Granular Multiple Kernel Support Vector Machine with Repetitive Under-sampling (GMKSVM-RU). In order to evaluate our method, we use fivefold cross-validation on the RBP129, our method achieves better experimental performance with MCC of 0.3367 and accuracy of 88.84%. In order to further evaluate our model, an independent data set (RBP60) is employed, and our method achieves MCC of 0.3921 and accuracy of 87.52%. Above results demonstrate that integrating sequence and structure information is beneficial to improve the prediction ability of RNA-binding residues.

Analysis of prediction algorithm for forest land spatial evolution trend in rural planning

This study is to find the factors that affect the spatial change of forest land and purposefully predict the evolution trend of forest land space, so as to facilitate the rural planning work. The rural forest land situation in Zhangjiakou City of Hebei Province is analyzed, and the future evolution and development of forest space are predicted through analysis of correlation between the forest land influencing factors and the forest land productivity. Meanwhile, the multiple linear regression (MLR) prediction algorithm and support vector machine (SVM) are compared to obtain a more accurate prediction algorithm, which provides a strong basis for rural planning. The research results show that the annual rainfall and rainfall erosion have poor correlation with the spatial evolution of forest land relatively; while the average annual temperature is negatively correlated with annual rainfall and the rainfall erosivity. In addition, the soil erosion and terrain undulation of forest land have higher correlations with the rainfall erosivity due to abundant rainfall. The steeper the slope, the less human interference. What’s more, the prediction value of SVM is closer to the actual value with smaller absolute error, so it is more accurate than MLR. Therefore, research on the prediction algorithm provides new ideas for enriching the prediction algorithms of the spatial evolution trend, and is of great significance for improving the forest resource reserve capacity and meeting more forest resource demand in China. In addition, it can optimize the natural environmental quality, so it can be applied to rural planning and construction.

Learning Common Time-Frequency-Spatial Patterns for Motor Imagery Classification.

The common spatial patterns (CSP) algorithm is the most popular spatial filtering method applied to extract electroencephalogram (EEG) features for motor imagery (MI) based brain-computer interface (BCI) systems. The effectiveness of the CSP algorithm depends on optimal selection of the frequency band and time window from the EEG. Many algorithms have been designed to optimize frequency band selection for CSP, while few algorithms seek to optimize the time window. This study proposes a novel framework, termed common time-frequency-spatial patterns (CTFSP), to extract sparse CSP features from multi-band filtered EEG data in multiple time windows. Specifically, the whole MI period is first segmented into multiple subseries using a sliding time window approach. Then, sparse CSP features are extracted from multiple frequency bands in each time window. Finally, multiple support vector machine (SVM) classifiers with the Radial Basis Function (RBF) kernel are trained to identify the MI tasks and the voting result of these classifiers determines the final output of the BCI. This study applies the proposed CTFSP algorithm to three public EEG datasets (BCI competition III dataset IVa, BCI competition III dataset IIIa, and BCI competition IV dataset 1) to validate its effectiveness, compared against several other state-of-the-art methods. The experimental results demonstrate that the proposed algorithm is a promising candidate for improving the performance of MI-BCI systems.

Prediction of ionic conductivity of imidazolium-based ionic liquids at different temperatures using multiple linear regression and support vector machine algorithms

The conductivity of various imidazolium-based ILs has been predictedviaQSPR approach using MLR and SVM regression coupled with stepwise model-building. This will aid the screening of suitable ILs with desired conductivity for specific applications.

Research on Key Algorithms of the Lung CAD System Based on Cascade Feature and Hybrid Swarm Intelligence Optimization for MKL-SVM.

Feature selection and lung nodule recognition are the core modules of the lung computer-aided detection (Lung CAD) system. To improve the performance of the Lung CAD system, algorithmic research is carried out for the above two parts, respectively. First, in view of the poor interpretability of deep features and the incomplete expression of clinically defined handcrafted features, a feature cascade method is proposed to obtain richer feature information of nodules as the final input of the classifier. Second, to better map the global characteristics of samples, the multiple kernel learning support vector machine (MKL-SVM) algorithm with a linear convex combination of polynomial kernel and sigmoid kernel is proposed. Furthermore, this paper applied the methods for speed contraction factor and roulette strategy, and a mixture of simulated annealing (SA) and particle swarm optimization (PSO) is used for global optimization, so as to solve the problem that the PSO is easy to lose particle diversity and fall into the local optimal solution as well as improve the model's training speed. Therefore, the MKL-SVM algorithm is presented in this paper, which is based on swarm intelligence optimization is proposed for lung nodule recognition. Finally, the algorithm construction experiments are conducted on the cooperative hospital dataset and compared with 8 advanced algorithms on the public dataset LUNA16. The experimental results show that the proposed algorithms can improve the accuracy of lung nodule recognition and reduce the missed detection of nodules.

A SVM-based framework for fault detection in high-speed trains

High-Speed Trains (HSTs) demand high reliability, maintainability and availability of their installed equipment. The braking system, in particular, is a safety-critical system in HSTs. Accurately and efficiently detecting any ongoing faults in such a system is very important to ensure safety, facilitate maintenance and reduce downtime of HSTs. Data-driven approaches have become very popular for fault detection with the implemented built-in monitoring systems and the artificial intelligence. Due to the high reliability of the HSTs, most of the monitoring data are on the normal conditions and only a small part concerns the faulty conditions. Such imbalanced data may reduce the fault detection rate of a data-driven model. Along with the between-class imbalance problem, the fusion of various continuous and discrete signals is also an obstacle in building an efficient fault detection model. In this paper, the weighted-feature strategy and the cost-sensitive learning are integrated effectively in a multi-kernel support vector machine model, to solve the problems brought by between-class imbalance and heterogeneous signals. The experiments on real datasets concerning faults in braking systems of a HST and fourteen public imbalanced datasets are carried out to verify the effectiveness and generalizability of the proposed method. With respect to both F-measure and G-mean, the proposed method outperforms the benchmark methods in the experiments, showing the potential of the combination of weighted feature strategy, multiple kernel learning and support vector machine in fault detection.

MBSVR: Multiple birth support vector regression

Although the learning speed in twin support vector regression (TWSVR) is four times that in support vector regression (SVR), the computing time and fitting precision of TWSVR are limited. This paper develops multiple birth support vector regression (MBSVR), motivated by the multiple birth support vector machine (MBSVM) formulation. MBSVR constructs the final regressor from K hyperplanes, each of which is obtained by solving a small quadratic programming problem (QPP) with the associated constraints, in which all points in each of the corresponding class should be as far away as possible from its corresponding hyperplane. Since MBSVM can be seen as an extension of the twin support vector machine (TWSVM) and its computing time is less than that of TWSVM, the proposed MBSVR is also faster than TWSVR, especially when the number of classes K is large. To verify the performance of the proposed MBSVR, it is compared with TWSVR, TSVR (another form of twin support vector regression) and SVR on several synthetic datasets and UCI datasets.

In-season weather data provide reliable yield estimates of maize and soybean in the US central Corn Belt

Weather conditions regulate the growth and yield of crops, especially in rain-fed agricultural systems. This study evaluated the use and relative importance of readily available weather data to develop yield estimation models for maize and soybean in the US central Corn Belt. Total rainfall (Rain), average air temperature (Tavg), and the difference between maximum and minimum air temperature (Tdiff) at weekly, biweekly, and monthly timescales from May to August were used to estimate county-level maize and soybean grain yields for Iowa, Illinois, Indiana, and Minnesota. Step-wise multiple linear regression (MLR), general additive (GAM), and support vector machine (SVM) models were trained with Rain, Tavg, and with/without Tdiff. For the total study area and at individual state level, SVM outperformed other models at all temporal levels for both maize and soybean. For maize, Tavg and Tdiff during July and August, and Rain during June and July, were relatively more important whereas for soybean, Tavg in June and Tdiff and Rain during August were more important. The SVM model with weekly Rain and Tavg estimated the overall maize yield with a root mean square error (RMSE) of 591 kg ha−1 (4.9% nRMSE) and soybean yield with a RMSE of 205 kg ha−1 (5.5% nRMSE). Inclusion of Tdiff in the model considerably improved yield estimation for both crops; however, the magnitude of improvement varied with the model and temporal level of weather data. This study shows the relative importance of weather variables and reliable yield estimation of maize and soybean from readily available weather data to develop a decision support tool in the US central Corn Belt.

A Novel Incipient Fault Diagnosis Method for Analog Circuits Based on GMKL-SVM and Wavelet Fusion Features

To enhance the reliability of analog circuits in complex electrical systems, a novel incipient fault diagnosis method is presented in this article. The wavelet packet feature quantities, which consist of the energy, fluctuation coefficient, skewness, and margin factor, are obtained via multiscale time-frequency analysis with wavelet packet transform (WPT). Then, generalized discriminant analysis (GDA) is employed to realize the fusion of wavelet packet feature quantities because it can handle the data nonlinearity and eliminate redundant information. Furthermore, the generalized multiple kernel learning support vector machine (GMKL-SVM), which has the advantages of a strong generalization ability and high accuracy, is developed to identify the incipient fault classes of analog circuits. Moreover, a new particle swarm intelligent optimization algorithm, the sine cosine algorithm (SCA), is adopted to optimize key parameters of GMKL-SVM because of its high convergence speed and strong global optimization ability. The method is fully evaluated with the Sallen-Key bandpass filter circuit, the four-op-amp biquad high-pass filter circuit, and the leapfrog filter circuit. The experimental results demonstrate that the proposed incipient fault diagnosis method for analog circuits can produce higher diagnosis accuracy than other typical incipient fault diagnosis methods.

Local Similarity-Based Fuzzy Multiple Kernel One-Class Support Vector Machine

One-class support vector machine (OCSVM) is one of the most popular algorithms in the one-class classification problem, but it has one obvious disadvantage: it is sensitive to noise. In order to solve this problem, the fuzzy membership degree is introduced into OCSVM, which makes the samples with different importance have different influences on the determination of classification hyperplane and enhances the robustness. In this paper, a new calculation method of membership degree is proposed and introduced into the fuzzy multiple kernel OCSVM (FMKOCSVM). The combined kernel is used to measure the local similarity between samples, and then, the importance of samples is determined based on the local similarity between training samples, so as to determine the membership degree and reduce the impact of noise. The proposed membership requires only positive data in the calculation process, which is consistent with the training set of OCSVM. In this method, the noise has a smaller membership value, which can reduce the negative impact of noise on the classification boundary. Simultaneously, this method of calculating membership has a higher efficiency. The experimental results show that FMKOCSVM based on proposed local similarity membership is efficient and more robust to outliers than the ordinary multiple kernel OCSVMs.

Quantitative Analysis and Discrimination of Partially Fermented Teas from Different Origins Using Visible/Near-Infrared Spectroscopy Coupled with Chemometrics.

Partially fermented tea such as oolong tea is a popular drink worldwide. Preventing fraud in partially fermented tea has become imperative to protect producers and consumers from possible economic losses. Visible/near-infrared (VIS/NIR) spectroscopy integrated with stepwise multiple linear regression (SMLR) and support vector machine (SVM) methods were used for origin discrimination of partially fermented tea from Vietnam, China, and different production areas in Taiwan using the full visible NIR wavelength range (400–2498 nm). The SMLR and SVM models achieved satisfactory results. Models using data from chemical constituents’ specific wavelength ranges exhibited a high correlation with the spectra of teas, and the SMLR analyses improved discrimination of the types and origins when performing SVM analyses. The SVM models’ identification accuracies regarding different production areas in Taiwan were effectively enhanced using a combination of the data within specific wavelength ranges of several constituents. The accuracy rates were 100% for the discrimination of types, origins, and production areas of tea in the calibration and prediction sets using the optimal SVM models integrated with the specific wavelength ranges of the constituents in tea. NIR could be an effective tool for rapid, nondestructive, and accurate inspection of types, origins, and production areas of teas.