Twin support vector machine: theory, algorithm and applications

Prediction and the influencing factor study of colorectal cancer hospitalization costs in China based on machine learning-random forest and support vector regression: a retrospective study

Aims

As people's standard of living improves, the incidence of colorectal cancer is increasing, and colorectal cancer hospitalization costs are relatively high. Therefore, predicting the cost of hospitalization for colorectal cancer patients can provide guidance for controlling healthcare costs and for the development of related policies.

Methods

This study used the first page of medical record data on colorectal cancer inpatient cases of a tertiary first-class hospital in Shenzhen from 2018 to 2022. The impacting factors of hospitalization costs for colorectal cancer were analyzed. Random forest and support vector regression models were used to establish predictive models of the cost of hospitalization for colorectal cancer patients and to compare and evaluate.

Results

In colorectal cancer inpatients, major procedures, length of stay, level of procedure, Charlson comorbidity index, age, and medical payment method were the important influencing factors. In terms of the test set, the R2 of the Random forest model was 0.833, the R2 of the Support vector regression model was 0.824; the root mean square error (RMSE) of the Random forest model was 0.029, and the RMSE of the Support vector regression model was 0.032. In the Random Forest model, the weight of the major procedure was the highest (0.286).

Conclusion

Major procedures and length of stay have the greatest impacts on hospital costs for colorectal cancer patients. The random forest model is a better method to predict the hospitalization costs for colorectal cancer patients than the support vector regression.

Origin identification of Cornus officinalis based on PCA-SVM combined model

Infrared spectroscopy can quickly and non-destructively extract analytical information from samples. It can be applied to the authenticity identification of various Chinese herbal medicines, the prediction of the mixing amount of defective products, and the analysis of the origin. In this paper, the spectral information of Cornus officinalis from 11 origins was used as the research object, and the origin identification model of Cornus officinalis based on mid-infrared spectroscopy was established. First, principal component analysis was used to extract the absorbance data of Cornus officinalis in the wavenumber range of 551~3998 cm-1. The extracted principal components contain more than 99.8% of the information of the original data. Second, the extracted principal component information was used as input, and the origin category was used as output, and the origin identification model was trained with the help of support vector machine. In this paper, this combined model is called PCA-SVM combined model. Finally, the generalization ability of the PCA-SVM model is evaluated through an external test set. The three indicators of Accuracy, F1-Score, and Kappa coefficient are used to compare this model with other commonly used classification models such as naive Bayes model, decision trees, linear discriminant analysis, radial basis function neural network and partial least square discriminant analysis. The results show that PCA-SVM model is superior to other commonly used models in accuracy, F1 score and Kappa coefficient. In addition, compared with the SVM model with full spectrum data, the PCA-SVM model not only reduces the redundant variables in the model, but also has higher accuracy. Using this model to identify the origin of Cornus officinalis, the accuracy rate is 84.8%.

J, Victoire A. Variational mode decomposition combined fuzzy—Twin support vector machine model with deep learning for solar photovoltaic power forecasting

A novel Variational Mode Decomposition (VMD) combined Fuzzy-Twin Support Vector Machine Model with deep learning mechanism is devised in this research study to forecast the solar Photovoltaic (PV) output power in day ahead basis. The raw data from the solar PV farms are highly fluctuating and to extract the useful stable components VMD is employed. A novel Fuzzy–Twin Support Vector Machine (FTSVM) model developed acts as the forecasting model for predicting the solar PV output power for the considered solar farms. The twin support vector machine (SVM) model formulates two separating hyperplanes for predicting the output power and in this research study a fuzzy based membership function identifies most suitable two SVM prediction hyperplanes handling the uncertainties of solar farm data. For the developed, new VMD-FTSVM prediction technique, their optimal parameters for the training process are evaluated with the classic Ant Lion Optimizer (ALO) algorithm. The solar PV output power is predicted using the novel VMD-FTSVM model and during the process multi-kernel functions are utilized to devise the two fuzzy based hyperplanes that accurately performs the prediction operation. Deep learning (DL) based training of the FTSVM model is adopted so that the deep auto-encoder and decoder module enhances the accuracy rate. The proposed combined forecasting model, VMD-ALO-DLFTSVM is validated for superiority based on a two 250MW PV solar farm in India. Results prove that the proposed model outperforms the existing model in terms of the performance metrics evaluated and the forecasted PV Power.

Measurement and analysis of regional flood disaster resilience based on a support vector regression model refined by the selfish herd optimizer with elite opposition-based learning

Flood disasters are sudden, frequent, uncertain and highly hazardous natural disasters. The precise identification of the spatiotemporal evolution characteristics, key driving factors and influencing mechanisms of resilience has become a hot spot in disaster risk reduction research. Therefore, the cumulative information contribution rate-Pearson correlation coefficient (CICR- PCC) model is used in this paper to construct a flood disaster resilience index system by quantitative methods, and a support vector regression model refined by the selfish herd optimizer with elite opposition-based learning (EO-SHO-SVR) is built to improve the accuracy of flood disaster resilience evaluation. On this basis, the EO-SHO-SVR model is used to analyze the spatiotemporal evolution of flood disaster resilience in the Jiansanjiang branch of China Beidahuang Agricultural Reclamation Group Co., Ltd. over the past 22 years. In addition, to verify the comprehensive performance of the EO-SHO-SVR model, support vector regression (SVR), imperial competition algorithm-improved support vector regression (ICA-SVR), and unimproved selfish herd optimizer support vector regression (SHO-SVR) models were selected for comparative analysis. The results show that during the study period, the resilience levels reached a plateau of high levels from 1997 to 2018 after experiencing a state of steady low levels followed by increased volatility. Among the investigated factors, land-average flood prevention investment, GDP per capita, agricultural machinery power per unit of arable land, water conservancy project investment as a percentage of GDP, and rainfall are the main driving factors that cause spatiotemporal differences in flood disaster resilience in the study area. Spatially, the resilience levels in the Jiansanjiang branch are ordered as northern farms > southern farms > central farms, and the comprehensive index of resilience shows an increasing trend from west to east. In the model comparison, the EO-SHO-SVR model has outstanding advantages in fitting performance, reliability, rationality and stability, which fully demonstrates that the EO-SHO-SVR model is highly advanced and practical in the measurement of flood disaster resilience. These research results can provide a more accurate evaluation model of regional flood disaster resilience. In addition, they can also provide valuable information for regional flood resilience improvement and flood risk avoidance.

Capped L2,p-norm metric based robust least squares twin support vector machine for pattern classification

Least squares twin support vector machine (LSTSVM) is an effective and efficient learning algorithm for pattern classification. However, the distance in LSTSVM is measured by squared L₂-norm metric that may magnify the influence of outliers. In this paper, a novel robust least squares twin support vector machine framework is proposed for binary classification, termed as CL_2,p-LSTSVM, which utilizes capped L_2,p-norm distance metric to reduce the influence of noise and outliers. The goal of CL_2,p-LSTSVM is to minimize the capped L_2,p-norm intra-class distance dispersion, and eliminate the influence of outliers during training process, where the value of the metric is controlled by the capped parameter, which can ensure better robustness. The proposed metric includes and extends the traditional metrics by setting appropriate values of p and capped parameter. This strategy not only retains the advantages of LSTSVM, but also improves the robustness in solving a binary classification problem with outliers. However, the nonconvexity of metric makes it difficult to optimize. We design an effective iterative algorithm to solve the CL_2,p-LSTSVM. In each iteration, two systems of linear equations are solved. Simultaneously, we present some insightful analyses on the computational complexity and convergence of algorithm. Moreover, we extend the CL_2,p-LSTSVM to nonlinear classifier and semi-supervised classification. Experiments are conducted on artificial datasets, UCI benchmark datasets, and image datasets to evaluate our method. Under different noise settings and different evaluation criteria, the experiment results show that the CL_2,p-LSTSVM has better robustness than state-of-the-art approaches in most cases, which demonstrates the feasibility and effectiveness of the proposed method.

Deep learning and multimodal target recognition of complex and ambiguous words in automated English learning system

On the basis of convolution neural network, deep learning algorithm can make the convolution layer convolute the input image to complete the hierarchical expression of feature information, which makes pattern recognition more simple and accurate. Now, in the theory of multimodal discourse analysis, the nonverbal features in communication are studied as a symbol system similar to language. In this paper, the author analyzes the deep learning complexity and multimodal target recognition application in English education system. Multimodal teaching gradually has its practical significance in the process of rich teaching resources. The large-scale application of multimedia technology in college English classroom is conducive to the construction of a real language environment. The simulation results show that the multi-layer and one-dimensional convolution structure of the product neural network can effectively complete many natural language problems, including the tagging of lexical and semantic roles, and thus effectively improve the accuracy of natural language processing. Multimodal teaching mode helps to memorize vocabulary images more deeply. 84% of students think that multi-modal teaching mode is closer to life. Meanwhile, multimedia teaching display is more acceptable. College English teachers should renew their teaching concepts and adapt themselves to the new teaching mode.

Detecting Ordinal Subcascades

Ordinal classifier cascades are constrained by a hypothesised order of the semantic class labels of a dataset. This order determines the overall structure of the decision regions in feature space. Assuming the correct order on these class labels will allow a high generalisation performance, while an incorrect one will lead to diminished results. In this way ordinal classifier systems can facilitate explorative data analysis allowing to screen for potential candidate orders of the class labels. Previously, we have shown that screening is possible for total orders of all class labels. However, as datasets might comprise samples of ordinal as well as non-ordinal classes, the assumption of a total ordering might be not appropriate. An analysis of subsets of classes is required to detect such hidden ordinal substructures. In this work, we devise a novel screening procedure for exhaustive evaluations of all order permutations of all subsets of classes by bounding the number of enumerations we have to examine. Experiments with multi-class data from diverse applications revealed ordinal substructures that generate new and support known relations.

Detection and Classification of Advanced Persistent Threats and Attacks Using the Support Vector Machine

Traditional network attack and hacking models are constantly evolving to keep pace with the rapid development of network technology. Advanced persistent threat (APT), usually organized by a hacker group, is a complex and targeted attack method. A long period of strategic planning and information search usually precedes an attack on a specific goal. Focus is on a targeted object and customized specific methods are used to launch the attack and obtain confidential information. This study offers an attack detection system that enables early discovery of the APT attack. The system uses the NSL-KDD database for attack detection and verification. The main method uses principal component analysis (PCA) for feature sampling and the enhancement of detection efficiency. The advantages and disadvantages of using the classifiers are then compared to detect the dataset, the classifier supports the vector machine, naive Bayes classification, the decision tree and neural networks. Results of the experiments show the support vector machine (SVM) to have the highest recognition rate, reaching 97.22% (for the trained subdata A). The purpose of this study was to establish an APT early warning model mechanism, that could be used to reduce the impact and influence of APT attacks.

Classification of Heart Sounds Based on the Wavelet Fractal and Twin Support Vector Machine

Heart is an important organ of human beings. As more and more heart diseases are caused by people’s living pressure or habits, the diagnosis and treatment of heart diseases also require technical improvement. In order to assist the heart diseases diagnosis, the heart sound signal is used to carry a large amount of cardiac state information, so that the heart sound signal processing can achieve the purpose of heart diseases diagnosis and treatment. In order to quickly and accurately judge the heart sound signal, the classification method based on Wavelet Fractal and twin support vector machine (TWSVM) is proposed in this paper. Firstly, the original heart sound signal is decomposed by wavelet transform, and the wavelet decomposition coefficients of the signal are extracted. Then the two-norm eigenvectors of the heart sound signal are obtained by solving the two-norm values of the decomposition coefficients. In order to express the feature information more abundantly, the energy entropy of the decomposed wavelet coefficients is calculated, and then the energy entropy characteristics of the signal are obtained. In addition, based on the fractal dimension, the complexity of the signal is quantitatively described. The box dimension of the heart sound signal is solved by the binary box dimension method. So its fractal dimension characteristics can be obtained. The above eigenvectors are synthesized as the eigenvectors of the heart sound signal. Finally, the twin support vector machine (TWSVM) is applied to classify the heart sound signals. The proposed algorithm is verified on the PhysioNet/CinC Challenge 2016 heart sound database. The experimental results show that this proposed algorithm based on twin support vector machine (TWSVM) is superior to the algorithm based on support vector machine (SVM) in classification accuracy and speed. The proposed algorithm achieves the best results with classification accuracy 90.4%, sensitivity 94.6%, specificity 85.5% and F1 Score 95.2%.