Credit scoring by fuzzy support vector machines with a novel membership function

Shi, Jian; Xu, Benlian Article Credit scoring by fuzzy support vector machines with a novel membership function Journal of Risk and Financial Management Provided in Cooperation with: MDPI – Multidisciplinary Digital Publishing Institute, Basel Suggested Citation: Shi, Jian; Xu, Benlian (2016) : Credit scoring by fuzzy support vector machines with a novel membership function, Journal of Risk and Financial Management, ISSN 1911-8074, MDPI, Basel, Vol. 9, Iss. 4, pp. 1-10, https://doi.org/10.3390/jrfm9040013 This Version is available at: https://hdl.handle.net/10419/178580 Standard-Nutzungsbedingungen: Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Zwecken und zum Privatgebrauch gespeichert und kopiert werden. Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich machen, vertreiben oder anderweitig nutzen. Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, gelten abweichend von diesen Nutzungsbedingungen die in der dort genannten Lizenz gewährten Nutzungsrechte. Terms of use: Documents in EconStor may be saved and copied for your personal and scholarly purposes. You are not to copy documents for public or commercial purposes, to exhibit the documents publicly, to make them publicly available on the internet, or to distribute or otherwise use the documents in public. If the documents have been made available under an Open Content Licence (especially Creative Commons Licences), you may exercise further usage rights as specified in the indicated licence. https://creativecommons.org/licenses/by/4.0/ Journal of Risk and Financial Management Article Credit Scoring by Fuzzy Support Vector Machines with a Novel Membership Function Jian Shi and Benlian Xu * School of Electrical & Automatic Engineering, Changshu Institute of Technology, Changshu 215500, China; [email protected] *Correspondence: [email protected] Academic Editor: Jingzhi Huang Received: 28 June 2016; Accepted: 26 October 2016; Published: 7 November 2016 Abstract: Due to the recent financial crisis and European debt crisis, credit risk evaluation has become an increasingly important issue for financial institutions. Reliable credit scoring models are crucial for commercial banks to evaluate the financial performance of clients and have been widely studied in the fields of statistics and machine learning. In this paper a novel fuzzy support vector machine (SVM) credit scoring model is proposed for credit risk analysis, in which fuzzy membership is adopted to indicate different contribution of each input point to the learning of SVM classification hyperplane. Considering the methodological consistency, support vector data description (SVDD) is introduced to construct the fuzzy membership function and to reduce the effect of outliers and noises. The SVDD-based fuzzy SVM model is tested against the traditional fuzzy SVM on two real-world datasets and the research results confirm the effectiveness of the presented method. Keywords: fuzzy support vector machine; support vector data description; credit scoring 1. Introduction During the recent financial crisis, many financial institutions endured great losses from customers’ defaults on loans such as the subprime mortgage crisis in the USA. However, credit-granting institutions cannot simply refuse all applicants to avoid credit risk as the competition in the growing credit market has become fierce. Effective credit scoring has become one of the primary techniques for gaining competitive advantages in credit market which can help financial institutions to increase credit volume without excessively increasing their exposure to default. Credit scoring models are developed to discriminate applicants as either accepted or rejected with respect to the customers’ application form and credit report, which is built on the basis of past applicants’ characteristics [ 1 – 3 ]. Since even a fraction of improvement in accuracy of credit scoring might translate into noteworthy future savings, numerous data mining and statistical techniques have been proposed to derive a satisfied credit scoring model over the past decades. Generally, these methods can be classified to statistics approaches (e.g., discriminant analysis and logistic regression), and machine learning approaches (e.g., artificial neural network and support vector machine). Though traditional statistical methods are relatively simple and explainable, their discriminating ability is still an argumentative problem due to the nonlinear relationship between default probability and credit patterns. Additionally, statistical methods must assume posterior probability models while machine learning approaches commonly operate without this limitation. Regarding recent credit scoring techniques, artificial neural network [ 4 , 5 ] has been criticized for its poor performance when incorporating irrelevant attributes or small data sets, while support vector machine, motivated by statistical learning theory [ 6 , 7 ], is particularly well suited for coping with a large number of explanatory attributes or sparse data sets [ 8 – 11 ]. Baesens et al. studied the performance of various state-of-the-art classification algorithms on eight real-life credit scoring J. Risk Financial Manag. 2016,9, 13; doi:10.3390/jrfm9040013 www.mdpi.com/journal/jrfm J. Risk Financial Manag. 2016,9, 13 2 of 10 data sets [ 12 ]. Thomas et al. tested 17 consumer credit modeling methods and report that SVM ranks the highest in term of classification accuracy [ 13 ]. Huang et al. constructed hybrid SVM-based credit scoring models with three strategies for feature selection and model parameter setting [ 14 ]. Martens et al. extracted rules from the trained SVM to obtain both accurate and comprehensible credit scoring models [ 15 ]. Niklis et al. developed linear and nonlinear support vector machines risk assessment and classification models, as well as additive SVM model that well suited the requirements of credit rating systems, which provided very competitive results [ 16 ]. Harris introduced the use of the clustered support vector machine for credit scorecard development and addresses some of the limitations associated with traditional nonlinear support vector machine based methods [ 17 ]. Cheng and Li proposed a rating model based on a support vector machine with monotonicity constraints derived from the prior knowledge of financial experts which helps correct the loss of monotonicity in data occurring during the collecting process [18]. However, in many real word credit scoring problems, some input training points are corrupted by noise, and some applicants may be assigned to the wrong side by accident. These points are all outliers, which do not completely belong to one class, but with different memberships in the two classes. In this case, standard SVM training algorithm will make the classification boundary to severely deviate from the optimal hyperplane as SVM is very sensitive to outliers. Lin and Wang introduced the concept of fuzzy SVM, which applies a fuzzy membership value to each input point according to its relative importance in the classification and reformulates the SVM such that allows different input point to make different contributions to the learning of decision surface [ 19 ]. Fuzzy SVM can be used as a remedy for unwanted over fitting caused by treating every data sample equally [ 20 – 22 ], however, the effects of the membership values when training fuzzy SVM is an interesting issue in the context of credit scoring modeling [ 23 ]. In this study, considering the methodological consistency, a novel support vector date description based fuzzy membership function is proposed to reduce the effects of outliers and improves the classification accuracy and generalization, and the effects of the membership values in fuzzy SVM is investigated and compared to those of SVM. This paper is organized as follows. Section 2recalls the background on SVM and fuzzy SVM, and reports two typical linear and nonlinear fuzzy membership functions. Section 3highlights the main novelty of this work. The main aspects of the SVDD-based membership function are detailed. Section 4collects the experimental results on two real world credit datasets. Finally, Section 5draws the conclusion remarks. 2. SVM and Fuzzy SVM 2.1. Standard Support Vector Machines In this section, the basic concept of SVM for classification problems is presented. Consider a two-class problem with a set of lsample points: (x 1 ,y 1 ), ..., (x l ,y l ). Each x i has a class label y i∈ { − 1,1} which denotes two classes separately. When the sample points are rigidly linear separable, SVM classifier tries to search for a hyperplane with the largest margin to separate them by solving the following quadratic program: min 1 2||w||2 subject to yi(wTxi+b)≥1i=1, 2, ..., l (1) where wis the weight vector and b is the bias term. For linear non-separable separable case, non-negative slack variables ξi are introduced to measure the amount of violation of the constraints in Equation (1). The QP problem turns to: J. Risk Financial Manag. 2016,9, 13 3 of 10 min 1 2||w||2+Cl ∑ i=1 ξi subject to yi(wTxi+b)≥1−ξii=1, 2, ..., l ξi≥0i=1, 2, ..., l (2) where Cis a regularized constant determining the tradeoff between margin maximization and classification violation. In many cases, it’s difficult to obtain a suitable hyperplane in the original input space by such a linear classifier, thus a nonlinear mapping ϕ (x) that satisfies Mercer’s condition can be introduced to map the input variable x i into a higher dimensional feature space. To solve the QP problem, the kernel function K(x i ,x j ) = ϕ (x i ) ·ϕ (x j ) is introduced to compute the dot product of the data points in feature space, and the shape of the mapping ϕ is unnecessary to know. Then the optimal problem turns to the following dual form by constructing a Lagrangian: min 1 2 l ∑ i=1 l ∑ j=1 αiαjyiyjK(xi,xj)− l ∑ i=1 αi subject to l ∑ i=1 yiαi=0 0 ≤αi≤C i =1, 2, ..., l (3) where αare the non-negative Lagrange multipliers related to the constraints in Equation (2). Some commonly used kernel functions are polynomial, sigmoid and radial basis function (RBF). RBF kernel is employed in this study because of its superiority, which is experimentally demonstrated by Gestel et al. [24]. 2.2. Fuzzy Support Vector Machines In credit scoring modeling, the applicants may not be exactly assigned to creditworthy or default ones. In other words, there is a fuzzy membership associated with each applicant, which can be regarded as the attitude of the corresponding applicants toward one class in the classification. Lin and Wang proposed the theory of fuzzy support vector machine based on standard SVM [ 19 ]. Suppose a set of labeled sample points with associated fuzzy membership: (x 1 ,y 1 ,s 1 ), ..., (x l ,y l ,s l ). Each x i has a class label yi∈{−1,1} and a fuzzy membership which satisfies 0 < si≤1. Since the fuzzy membership s i is the attitude of the corresponding point toward one class and the parameter ξi is a measure of the constraints violation, the term s iξi can be treated as a measure of constraints violation with different weights. Then the quadratic problem can be described as: min 1 2||w||2+Cl ∑ i=1 siξi subject to yi(wTϕ(xi) + b)≥1−ξii=1, 2, ..., l ξi≥0i=1, 2, ..., l (4) By constructing a Lagrangian, the quadratic programs can be solved in their dual space just as that for standard SVM: min 1 2 l ∑ i=1 l ∑ j=1 αiαjyiyjK(xi,xj)− l ∑ i=1 αi subject to l ∑ i=1 yiαi=0 0 ≤αi≤siC i =1, 2, ..., l (5) With different value of s i , the tradeoff between the maximization of margin and the amount of constraints violation can be controlled. It is noted that a smaller s i makes the corresponding point x i less important in the training, thus choosing appropriate fuzzy memberships in a given problem is J. Risk Financial Manag. 2016,9, 13 4 of 10 of pivotal importance for FSVM. Lin proposed a model by setting a linear fuzzy membership as a function of the distance between each data point and its corresponding class center [ 19 ]. For the above training sample sequence: (x 1 ,y 1 ,s 1 ), ..., (x l ,y l ,s l ), denote x+ the mean of class with label +1 and x− the mean of class −1. The radius of class +1 is as follows: r+=max|x+−xi|where yi=1 (6) and the radius of class −1 is: r−=max|x−−xi|where yi=−1 (7) The fuzzy membership of each sample is si=(1− |x+−xi|/(r++δ)where yi=1 1− |x−−xi|/(r−+δ)where yi=−1(8) with δ> 0 to avoid the case si= 0. The method performs well as the fuzzy membership is a function of the mean and radius of each class, and the effect of outlier can be reduced as it contributes little to the final decision plane. However, the algorithm is carried out in the original input space rather than the feature space, Tang further proposed a nonlinear membership function defined in the feature space with mapping function ϕ (x) on the basis of the above method [ 25 ]. Define ϕ+ and ϕ− as the centers of the two classes by taking average on the points mapped to the feature space: ϕ+=1 n+∑ yi=1 ϕ(xi),ϕ−=1 n−∑ yi=−1 ϕ(xi)(9) where n+and n−are the numbers of samples in two classes. The radius is defined similarly to those of Lin: r+=max|ϕ+−ϕ(xi)|where yi=1 r−=max|ϕ−−ϕ(xi)|where yi=−1(10) Then the square of distance is calculated in the feature space: d2 i+=||ϕ−−ϕ(xi)||2=K(xi,xi)−2 n+∑ yj=1 K(xj,xi) + 1 n2 + ∑ i ∑ yj=1 K(xi,xj) d2 i−=||ϕ+−ϕ(xi)||2=K(xi,xi)−2 n+∑ yj=1 K(xj,xi) + 1 n2 + ∑ i ∑ yj=1 K(xi,xj)(11) Finally the fuzzy membership of each sample is calculated as: si=   1−qd2 i+/(r2 ++δ)where yi=1 1−qd2 i−/(r2 −+δ)where yi=−1(12) with δ> 0 to avoid the case si= 0. The nonlinear version of FSVM outperforms the linear one as it could more accurately represent the contribution of each sample to the decision surface in the feature space. Both algorithm define the center and radius by taking average and maxim on sample points, however, they could be defined in a more explicable way. J. Risk Financial Manag. 2016,9, 13 5 of 10 3. Fuzzy SVM with SVDD Membership Function Methodological consistency has been a major design principle and is expected to improve the comprehensibility of the modeling paradigm, which, in turn, may avail dispersion in practical applications [ 26 ]. Support Vector Data Description (SVDD) is inspired by the support vector machine classifier, which searches for a spherically shaped boundary around a dataset to detect novel data or outliers [ 27 , 28 ]. In this section, a SVDD member function is proposed for FSVM, which is defined in the feature space as well. Similar to the SVM hyperplane approach with largest margin between two classes, SVDD estimates a hypersphere with the minimum volume to find an enclosed boundary containing almost all target objects, instead of using a hyperplane in SVM. Assume a hypersphere with center aand radius R, the cost function is defined as below: min R2+C l ∑ i=1 ξi subject to ||(ϕ(xi)−a)||2≤R2+ξi,ξi≥0i=1, 2, ..., l (13) where ξi are slack variables, and the parameter Ccontrols the trade-off between the volume and the violation. The above optimal hypersphere problem can be solved by constructing the Lagrangian, which results in: max l ∑ i=1 αiK(xi,xi)− l ∑ i=1 l ∑ j=1 αiαjK(xi,xj) subject to ∑ i=1 αi=1, 0 ≤αi≤C i =1, 2, ..., l (14) The training samples with nonzero αi are support vectors and are used to describe the hypersphere boundary. Denote a+and a−as the centers of class +1 and class −1 in the feature space respectively. According to K-T condition, the center of the each class can be calculated as: a+=∑ yi=1 αixi,a−=∑ yi=−1 αixi(15) The radius of class +1 is then defined by r+=max|a+−ϕ(xi)|where yi=1 (16) and the radius of class −1 by r−=max|a−−ϕ(xi)|where yi=−1 (17) The square of the distance between any sample x i with class label y i = 1 and the class center a+ in the feature space can be calculated as: d2 i+=K(xi,xi)−2∑ yj=1 α+ jK(xj,xi) + ∑ i ∑ yj=1 α+ iα+ jK(xi,xj)(18) The square of the distance between the sample of class −1 and its corresponding class center a− is derived similarly: d2 i−=K(xi,xi)−2∑ yj=−1 α− jK(xj,xi) + ∑ i ∑ yj=−1 α− iα− jK(xi,xj)(19) J. Risk Financial Manag. 2016,9, 13 6 of 10 By definition , the radius r+ is the distance from the center a+ of the hypersphere of class +1 to any of its support vectors on the boundary, and r−is the corresponding radius of class −1. r+=dsv+,r−=dsv−(20) Then the fuzzy membership siof each input sample xican be defined as follows: si=   1−qd2 i+/(r2 ++δ)where yi=1 1−qd2 i−/(r2 −+δ)where yi=−1(21) where δ > 0 is a small constant used to avoid the case s i = 0. In this paper, δ is set to 1 × 10 −3 for all three models. Once the coefficients s i are derived, fuzzy SVM for classification can be modeled according to Equation (4) in Section 2. The fuzzy memberships are calculated in the feature space with a more explainable center and radius. As the class center and radius are defined in the minimum SVDD hypersphere including all the class targets, the fuzzy membership are more explicit and interpretable in the feature space compared to those average and maxim algorithm. In addition, the above formulas are similar to that of Jiang’s, and are expected to reduce the effect of outliers as well. 4. Experimental Results and Discussion In this section, two real-world credit datasets, the Australian and German credit data sets, are adopted to evaluate the performance of the proposed SVDD-FSVM method. Experimental results are compared with those of linear and nonlinear fuzzy SVMs. Australian credit data set, with 307 instances of accepted customers and 383 instances of rejected customers, contains 14 attributes, where six are continuous attributes and eight are categorical attributes. For confidentiality reasons, all attribute names and values have been changed to meaningless symbols. The German credit dataset is more unbalanced, consisting of 700 examples of creditworthy applicants and 300 examples of default applicants, with 24 numeric features describing 19 attributes. The attributes of each applicant are depicted in Table 1, with 4 attributes changed to dummy variables. Both data sets are made public from the UCI Repository of Machine Learning Databases, and are generally adopted as benchmarks to compare the performance of various classification models. Table 1. Input variables of German data set. Original Attributes Input Variables Variable Type Attribute Description A1 V1 qualitative Status of existing checking account A2 V2 numerical Duration in month A3 V3 qualitative Credit history A4 V4,V5 dummy Purpose (V4: new car, V5: used car) A5 V6 numerical Credit amount A6 V7 qualitative Savings account/bonds A7 V8 qualitative Present employment since A8 V9 qualitative Personal status and sex A9 V10,V11 dummy Other debtors/guarantors (V10: none, V11: co-applicant) A10 V12 numerical Present residence since A11 V13 qualitative Property A12 V14 numerical Age in years A13 V15 qualitative Other installment plans A14 V16,V17 dummy Housing (V16: rent, V17: own) A15 V18 numerical Number of existing credits at this bank A16 V19,V20,V21 dummy Job (V19: unemployed/unskilled (non-resident), V20: unskilled (resident), V21: skilled employee/official) A17 V22 numerical Number of people being liable to provide maintenance for A18 V23 qualitative Telephone A19 V24 qualitative foreign worker J. Risk Financial Manag. 2016,9, 13 7 of 10 The input variables are normalized with respect to their maximum values and the fuzzy membership of each input instance is then derived by the SVDD operation. To visualize the SVDD hypersphere, the variables are projected to the two dimensional plane by principal component analysis, which is a popular multivariate statistic tool aiming to handle high dimensional, noisy, and correlated data by defining a reduced set of latent variables (referred to as principal components) [ 29 ]. The boundaries of class +1 and class –1 of Australian dataset for the first fold partition are pictured in Figure 1and those of German dataset are pictured in Figure 2. Both hyperspheres are calculated with a confidence limit of 98%. Though the two principal components contain over 90% of the information (measured by variance) of the original data in both sets, the figures show that the rejected applicants and accepted applicants can hardly be distinguished by a simple boundary in two dimensional plane. J. Risk Financial Manag. 2016, 4, x FOR PEER REVIEW 7 of 10 analysis, which is a popular multivariate statistic tool aiming to handle high dimensional, noisy, and correlated data by defining a reduced set of latent variables (referred to as principal components) [29]. The boundaries of class +1 and class –1 of Australian dataset for the first fold partition are pictured in Figure 1 and those of German dataset are pictured in Figure 2. Both hyperspheres are calculated with a confidence limit of 98%. Though the two principal components contain over 90% of the information (measured by variance) of the original data in both sets, the figures show that the rejected applicants and accepted applicants can hardly be distinguished by a simple boundary in two dimensional plane. Figure 1. Principal components plot of SVDD for Australia data set. For comparison purpose, the detailed performance of SVDD-FSVM is tested against linear FSVM and nonlinear FSVM. This study assessed the three credit scoring methods in terms of accuracy and other major assessment metrics such as sensitivity and specificity. Denote the number of default clients classified as accepted ones by DA and classified as rejected ones by DR. Let the number of creditworthy clients classified as accepted ones be CA and classified as rejected ones be CR. Then these evaluation criteria measuring the efficiency of the classification are defined as: CA Sensitivity CA CR DR Specificity DR DA CA DR Accuracy CA CR DA DR       (22) Figure 1. Principal components plot of SVDD for Australia data set. For comparison purpose, the detailed performance of SVDD-FSVM is tested against linear FSVM and nonlinear FSVM. This study assessed the three credit scoring methods in terms of accuracy and other major assessment metrics such as sensitivity and specificity. Denote the number of default clients classified as accepted ones by DA and classified as rejected ones by DR. Let the number of creditworthy clients classified as accepted ones be CA and classified as rejected ones be CR. Then these evaluation criteria measuring the efficiency of the classification are defined as: Sensitivity =CA CA+CR Speci f icity =DR DR+DA Accuracy =CA+DR CA+CR+DA+DR (22) J. Risk Financial Manag. 2016, 4, x FOR PEER REVIEW 8 of 10 Figure 2. Principal components plot of SVDD for German data set. In this study, the credit dataset is randomly partitioned into identical training and test sets using 5-fold cross validation and a grid search is employed to find the optimal parameters [30]. The average comparison results on German and Australian dataset are shown in Tables 2 and 3 respectively. Table 2. Performance on the Australian test data set. Methods Sensitivity (%) Specificity (%) Accuracy (%) SVDD-FSVM 87.53 86.84 87.25 Nonlinear FSVM 89.87 85.13 87.10 Linear FSVM 86.95 86.48 86.67 Table 3. Performance on the German test data set. Methods Sensitivity (%) Specificity (%) Accuracy (%) SVDD-FSVM 89.59 48.60 77.30 Nonlinear FSVM 92.15 41.75 77.00 Linear FSVM 95.18 23.42 73.60 The result listed in Table 2 indicates that the SVDD-FSVM outperformed the other two FSVMs on Australia data set, with overall accuracy of 87.25, comparing with those of 87.10 and 86.67 obtained from the corresponding nonlinear and linear FSVM models, respectively. Though the sensitivity, specificities and accuracy of German dataset in Table 3 are relatively lower than those of Australia data set as the German data structure is considered more unbalanced than the Australian data set, SVDD-FSVM still yields the best results among all the three approaches, with the specificity especially improved, which is considered more important than the sensitivity for the credit risk control of financial institutes. 5. Conclusions This paper has presented methods for using fuzzy support vector machines to establish credit scoring models. Comparing with standard SVM, fuzzy SVM imposes a fuzzy membership to each input point such that different input points can make different contributions to the learning of decision surface, which enhances the SVM in reducing the effect of outliers and noises in data points Figure 2. Principal components plot of SVDD for German data set. J. Risk Financial Manag. 2016,9, 13 8 of 10 In this study, the credit dataset is randomly partitioned into identical training and test sets using 5-fold cross validation and a grid search is employed to find the optimal parameters [ 30 ]. The average comparison results on German and Australian dataset are shown in Tables 2and 3respectively. Table 2. Performance on the Australian test data set. Methods Sensitivity (%) Specificity (%) Accuracy (%) SVDD-FSVM 87.53 86.84 87.25 Nonlinear FSVM 89.87 85.13 87.10 Linear FSVM 86.95 86.48 86.67 Table 3. Performance on the German test data set. Methods Sensitivity (%) Specificity (%) Accuracy (%) SVDD-FSVM 89.59 48.60 77.30 Nonlinear FSVM 92.15 41.75 77.00 Linear FSVM 95.18 23.42 73.60 The result listed in Table 2indicates that the SVDD-FSVM outperformed the other two FSVMs on Australia data set, with overall accuracy of 87.25, comparing with those of 87.10 and 86.67 obtained from the corresponding nonlinear and linear FSVM models, respectively. Though the sensitivity, specificities and accuracy of German dataset in Table 3are relatively lower than those of Australia data set as the German data structure is considered more unbalanced than the Australian data set, SVDD-FSVM still yields the best results among all the three approaches, with the specificity especially improved, which is considered more important than the sensitivity for the credit risk control of financial institutes. 5. Conclusions This paper has presented methods for using fuzzy support vector machines to establish credit scoring models. Comparing with standard SVM, fuzzy SVM imposes a fuzzy membership to each input point such that different input points can make different contributions to the learning of decision surface, which enhances the SVM in reducing the effect of outliers and noises in data points with unmodeled characteristics. As choosing a proper fuzzy membership function is quite important to solving classification problem with FSVM, the SVDD version of fuzzy membership is proposed for methodological consistency consideration, which is a function of the distance between each input point and its corresponding SVDD hypersphere center. The SVDD-FSVM credit scoring model overall yields the best performance among all the three models when appropriately trained on two real-world credit data sets. The results indicate that the proposed method provides classification accuracy and reliability, and is supposed to have promising potential for practical use. Acknowledgments: This work is supported by national natural science foundation of China (No. 61273312, No. 61673075), the natural science fundamental research program of higher education colleges in Jiangsu province (No. 14KJD510001), Suzhou municipal science and technology plan project (No. SYG201548) and the project of talent peak of six industries (No. DZXX-013). Author Contributions: Benlian Xu conceived and designed the experiments; Jian Shi performed the experiments, analyzed the data and wrote the paper. Conflicts of Interest: The authors declare no conflict of interest.