Fuzzy Support Vector Machine Research Articles

RUE: A robust personalized cost assignment strategy for class imbalance cost-sensitive learning

Cost-sensitive learning is a popular paradigm to address class-imbalance learning (CIL) problem. Traditional cost-sensitive learning approaches always solve CIL problem by assigning a constant higher training error penalty for all minority instances than that of majority instances, but ignore the significance of location information. Therefore, several recent studies began to focus on the personalized cost assignment, i.e., designating different costs for different instances based on their location information. The emerging personalized cost-sensitive approaches always perform better than those traditional ones; however, the estimation for location information may be inaccurate as it is apt to be impacted by data density variation. To address this problem, we propose a novel location information estimation and cost assignment strategy called RUE. Unlike previous approaches, our proposed strategy explores location information by an indirect way: the error rate feed backed from a random undersampling ensemble. The strategy is robust towards data distribution, and is helpful for accurately estimating the significance of each instance regardless the complexity of data distribution. In context of Fuzzy Support Vector Machine (FSVM) and Weighted Extreme Learning Machine (WELM), the proposed cost assignment strategy is compared with several popular and state-of-the-art approaches, and the results show its effectiveness and superiority.

Slack-Factor-Based Fuzzy Support Vector Machine for Class Imbalance Problems

Class imbalance and noisy data widely exist in real-world problems, and the support vector machine (SVM) is hard to construct good classifiers on these data. Fuzzy SVMs (FSVMs), as variants of SVM, use a fuzzy membership function both to reflect the samples’ importance and to remove the impact of noises, and employ cost-sensitive technology to address the class imbalance. They can handle the noise and class imbalance problems in many cases; however, the fuzzy membership functions are often affected by the class imbalance data, leading to inaccurate measures for samples’ performance and affecting the performance of FSVMs. To solve this problem, we design a new fuzzy membership function and combine it with cost-sensitive learning to deal with the class imbalance problem with noisy data, named Slack-Factor-based FSVM (SFFSVM). In SFFSVM, the relative distances between samples and an estimated hyperplane, called slack factors, are used to define the fuzzy membership function. To eliminate the impact of class imbalance on the function and gain more accurate samples’ importance, we rectify the importance according to the positional relationship between the estimated hyperplane and the optimal hyperplane of the problem, and the slack factors of samples. Comprehensive experiments on artificial and real-world datasets demonstrate that SFFSVM outperforms other comparative methods on F1, MCC, and AUC-PR metrics.

Bar Image Identification Based on Laplacian Eigenmap and Fuzzy SVM

Bar code image recognition is a key technology in modern logistics management. An efficient identification system is built based on manifold learning and fuzzy SVM. By integrating the fractal image segmentation technology, it realizes high automatic classification and identification of bar code image. At first, the authors conduct the preprocessing of the collected code image, including three steps, tilt correction, image binarization based on globally dynamic threshold, and fractal segmentation technology. Then, a graph-based fuzzy support vector machine is proposed to realize the high accuracy classification and identification. Experimental results indicate that the accuracy of the proposed method is higher than other compared methods in both pure and noisy samples, reaching 96.6% and 94.5%. And no huge decrease exists when some noise is added to the pure dataset, and the percentage is only 2.1%, which is much lower than the drop of other methods. It shows that the proposed method can significantly promote the identification accuracy, the generalization, and robustness to noise.

Quantum Fuzzy Support Vector Machine for Binary Classification

In the objective world, how to deal with the complexity and uncertainty of big data efficiently and accurately has become the premise and key to machine learning. Fuzzy support vector machine (FSVM) not only deals with the classification problems for training samples with fuzzy information, but also assigns a fuzzy membership degree to each training sample, allowing different training samples to contribute differently in predicting an optimal hyperplane to separate two classes with maximum margin, reducing the effect of outliers and noise, Quantum computing has super parallel computing capabilities and holds the promise of faster algorithmic processing of data. However, FSVM and quantum computing are incapable of dealing with the complexity and uncertainty of big data in an efficient and accurate manner. This paper research and propose an efficient and accurate quantum fuzzy support vector machine (QFSVM) algorithm based on the fact that quantum computing can efficiently process large amounts of data and FSVM is easy to deal with the complexity and uncertainty problems. The central idea of the proposed algorithm is to use the quantum algorithm for solving linear systems of equations (HHL algorithm) and the least-squares method to solve the quadratic programming problem in the FSVM. The proposed algorithm can determine whether a sample belongs to the positive or negative class while also achieving a good generalization performance. Furthermore, this paper applies QFSVM to handwritten character recognition and demonstrates that QFSVM can be run on quantum computers, and achieve accurate classification of handwritten characters. When compared to FSVM, QFSVM’s computational complexity decreases exponentially with the number of training samples.

Fuzzy support vector machine for classification of time series data: A simulation study

Support vector machine (SVM) has become one of most developed methods for classification, focusing on cross-sectional analysis. However, classification of time series data is an important issue in statistics and data mining. Classification of time series data using SVMs that focus on cross-sectional data leads to improper classification, and hence, the SVM needs to be extended for handling time series dataset. As with cross-section data, the problem of imbalanced data is also common in time series data. Fuzzy method has been proven to be capable of overcoming the case of imbalanced data. In this paper, we developed a Fuzzy Support Vector Machine (FSVM) model to classify time series data with imbalanced class. The proposed method puts the fuzzy membership function on the constraint function. Through simulation studies, this research aims to assess the performance of the developed FSVM in classifying time series data. Based on the classification accuracy criteria, we prove that the proposed FSVM method outperforms the standard SVM method for the classification of multiclass time series data.

Mathematical Modeling of Multiscale Network Traffic Combination Prediction Based on Fuzzy Support Vector Machine

In the process of multiscale network traffic prediction using a single model, the results are often single, resulting in a decline in the accuracy of multiscale network traffic prediction. In order to solve this problem effectively, a mathematical modeling method of multiscale network traffic combination prediction based on fuzzy SVM is proposed. Firstly, according to the multiscale network approximation signal, the multiscale network traffic feature function is constructed to complete the multiscale network traffic feature extraction. Secondly, according to the feature extraction results, the fuzzy membership function is introduced into the SVM, and the fuzzy SVM is used to classify the multiscale network traffic. Finally, based on the traffic classification results, the combination prediction of multiscale network traffic is completed by combining the grey Verhulst prediction model with the GNN model. The experimental results show that the prediction accuracy of this method for multiscale network traffic is higher, and the prediction accuracy can always maintain above 95%, and the MSE and MAE values are relatively low.

Risk assessment method of e-commerce transaction based on fuzzy support vector machine

Risk assessment method of e-commerce transaction based on fuzzy support vector machine

A kernel-free fuzzy support vector machine with Universum

<p style='text-indent:20px;'>Support vector machines with Universum are attractive for dealing with classification problems by incorporating prior information. In this paper, a quadratic function based kernel-free support vector machine with Universum is proposed for binary classification. To deal with noise and outliers, two fuzzy membership functions considering both information entropy and distance information are constructed for labeled and Universum data, respectively. The fuzzy membership function for Universum is also adopted for further selecting Universum data to improve the robustness. The proposed model corresponds to an efficiently solved convex quadratic programming. In the meanwhile, by avoiding the issue of choosing kernel functions, the proposed model saves more computational time when compared with other Universum-based support vector machines. Finally, some numerical tests are implemented on several data sets to validate the classification effectiveness of the proposed method. The numerical results illustrate the competitive performance when compared with some state-of-the-art support vector machines. Applications on two credit rating data sets are also conducted to distinguish the classification performance of the proposed method.</p>

A MODIFIED FUZZY SUPPORT VECTOR MACHINE CLASSIFICATION-BASED APPROACH FOR EMOTIONAL RECOGNITION USING PHYSIOLOGICAL SIGNALS

Emotional state recognition has become an essential topic for human–robot interaction researches that diverted and covers a wide range of topics. By specifying emotional expressions, robots can identify the significant variables of human behavior and apply them to communicate in a very human-like fashion and develop interaction possibilities. The multimodality and spontaneity nature of human emotions make them hard to be recognized by robots. Each modality has its advantages and limitations, which, along with the unstructured behavior of spontaneous facial expressions, make several challenges for the proposed approaches in the literature. The most important of these approaches is based on a combination of explicit feature extraction methods and manual modality. This paper proposes a modified fuzzy support vector machine (FSVM) classification-based approach for emotional recognition using physiological signals. The main contribution of this study includes applying various data extraction indices and proper kernels for the FSVM classification method and evaluating the signal's richness in experimental tests. The developed emotional recognition method is also compared with conventional SVM and other existing state-of-the-art emotional recognition algorithms. The comparison results show an improved accuracy of the developed method over other approaches.

Prediction of lysine HMGylation sites using multiple feature extraction and fuzzy support vector machine

Protein 3-hydroxyl-3-methylglutarylation (HMGylation) is newly discovered lysine acylation modification in mitochondrion. The accurate identification of HMGylation sites is the premise and key to further explore the molecular mechanisms of HMGylation. In this study, a novel bioinformatics tool named HMGPred is developed to predict HMGylation sites. Multiple effective features, including amino acid composition, amino acid factors, binary encoding, and the composition of k-spaced amino acid pairs, are integrated to encode HMGylation sites. And F-score feature ranking with incremental feature selection was used to eliminate redundant features. Moreover, a fuzzy support vector machine algorithm is used to effectively reduce the influence of noise problem by assigning different samples to different fuzzy membership degrees. As illustrated by 10-fold cross-validation, HMGPred achieves a satisfactory performance with an area under receiver operating characteristic curve of 0.9110. Feature analysis indicates that some k-spaced amino acid pair features, such as ‘KxxxT’ and ‘DxxxE’, play a critical role in the prediction of HMGylation sites. The results of prediction and analysis might be helpful for investigating the mechanisms of HMGylation. For the convenience of experimental researchers, HMGPred is implemented as a web server at http://123.206.31.171/HMGPred/.

Relative Density-Based Intuitionistic Fuzzy SVM for Class Imbalance Learning

The support vector machine (SVM) has been combined with the intuitionistic fuzzy set to suppress the negative impact of noises and outliers in classification. However, it has some inherent defects, resulting in the inaccurate prior distribution estimation for datasets, especially the imbalanced datasets with non-normally distributed data, further reducing the performance of the classification model for imbalance learning. To solve these problems, we propose a novel relative density-based intuitionistic fuzzy support vector machine (RIFSVM) algorithm for imbalanced learning in the presence of noise and outliers. In our proposed algorithm, the relative density, which is estimated by adopting the k-nearest-neighbor distances, is used to calculate the intuitionistic fuzzy numbers. The fuzzy values of the majority class instances are designed by multiplying the score function of the intuitionistic fuzzy number by the imbalance ratio, and the fuzzy values of minority class instances are assigned the intuitionistic fuzzy membership degree. With the help of the strong capture ability of the relative density to prior information and the strong recognition ability of the intuitionistic fuzzy score function to noises and outliers, the proposed RIFSVM not only reduces the influence of class imbalance but also suppresses the impact of noises and outliers, and further improves the classification performance. Experiments on the synthetic and public imbalanced datasets show that our approach has better performance in terms of G-Means, F-Measures, and AUC than the other class imbalance classification algorithms.

Speech Emotion Recognition Based on Fuzzy Support Vector Machine

Speech Emotion Recognition Based on Fuzzy Support Vector Machine

Hybrid Biometric Based Person Identification Using Machine Learning

When compared to the more traditional methods of authentication, biometric systems offer a much higher level of protection for a wide range of uses (like pin, passwords etc.). Various sectors of modern society can find use for biometric systems. Among these are authentication for computers, attendance tracking for businesses, financial transactions, safeguarding private information, securing access to buildings, and ensuring the safety of travellers at airports. Identifying and verifying individuals via their unique physical and behavioural characteristics is the primary function of the biometric system. Importance of biometric systems in modern society is analysed in this paper. Single-trait biometric user recognition is currently used, but it does not offer sufficient security for critical programmes. Multimodal biometric systems are used to get around these issues. Physical and behavioural characteristics, like fingerprints and DNA, signatures and fingerprints, etc., are all part of a multimodal biometric system's arsenal for authenticating users. In addition to the hard biometric features already mentioned (skin colour, age, height, hair colour, eye colour, gender, etc.), the use of a person's soft biometric traits is becoming increasingly common. While soft biometrics can be used to boost the efficiency of biometric systems that focus on other characteristics, they are not without their own set of drawbacks, such as a lack of permanence and distinctive behaviour. User authentication, security, and performance are all boosted by the work presented in this paper using Machine learning (F-SVM -Fuzzy-Support Vector Machine) model.

Affinity based fuzzy kernel ridge regression classifier for binary class imbalance learning

The class imbalance learning (CIL) problem indicates when one class have very low proportions of samples (minority class) compared to the other class (majority class). Even though kernel ridge regression (KRR) shows high generalization ability at a considerably quicker learning speed than conventional machine learning algorithms, it fails to achieve an excellent result for CIL problems. To address this inherent limitation of KRR, a novel affinity-based fuzzy KRR (AFKRR) is proposed for dealing with the binary CIL problem. In AFKRR, an affinity-based fuzzy membership value is linked to each training sample. The affinity of the majority class datapoint is measured using the support vector data description (SVDD) trained by the majority class datapoints. The classification ability of the proposed AFKRR is calculated using the area under the receiver optimal characteristics curve (AUC), F-measure and Geometric mean. AFKRR’s performance is compared with the support vector machine (SVM), affinity and class probability-based fuzzy SVM (ACFSVM), entropy-based fuzzy SVM (EFSVM), improved density weighted least squares SVM (IDLSSVM-CIL), KRR and intuitionistic fuzzy KRR (IFKRR) models on a few real-world as well as a few artificial imbalanced datasets. Experimental outcomes reveal the usability and efficacy of the proposed AFKRR model.

Innovative Evaluation Method of Government Physical Education Training Quality Based on Fuzzy Mathematics

Current sports training quality evaluation methods cannot accurately detect the integrity of training data, resulting in low accuracy of training quality evaluation. Considering the function of the government in providing public sports services and the role of the government in coordinating the sports training of all parties, this paper puts forward an innovative evaluation method of government physical education training quality based on fuzzy mathematics. First of all, the real-time data on sports training sensor signal is obtained by using SiCN (Silicon Carbonitride) sensor, and the real-time detection circuit and data amplification module are designed. Based on the core hardware for instant data detection of sports training sensor signal, a fuzzy support vector machine model is established to detect the integrity of government sports innovation training data, reconstruct the track of sports training action, and thus construct an innovative evaluation model of government sports training quality based on heredity and support vector machine. Experimental results show that compared with existing methods, the proposed method has higher accuracy in data integrity detection, better reconstruction effect in sports training action, with evaluation results reaching more than 90 points.

A Collision Reduction Adaptive Data Rate Algorithm Based on the FSVM for a Low-Cost LoRa Gateway

LoRa (Long Range), a wireless communication technology for low power wide area networks (LPWANs), enables a wide range of IoT applications and inter-device communication, due to its openness and flexible network deployment. In the actual deployment and operation of LoRa networks, the static link transmission scheme does not make full use of the channel resources in the time-varying channel environment, resulting in a poor network performance. In this paper, we propose a more effective adaptive data rate (ADR) algorithm for low-cost gateways, we firstly analyze the impact of the different hardware parameters (RSSI, SNR) on the link quality and classify the link quality using the fuzzy support vector machine (FSVM). Secondly, we establish an end device (ED) throughput model and energy consumption model and design different adaptive rate algorithms, according to the different link quality considering both the link-level performance and the MAC layer performance. The proposed algorithm uses machine learning to classify the link quality, which can accurately classify the link quality using a small amount of data, compared to other adaptive rate algorithms, and the link parameter adaptation algorithm can maximize the throughput while ensuring the link stability, by considering the link-level performance and the MAC layer performance, compared to other algorithms. The results show that it outperforms the standard LoRaWAN ADR algorithm in both the single ED and the multi ED scenarios, in terms of the packets reception rate (PRR) and the network throughput. Compared to the LoRaWAN ADR in 32 multi-ED scenarios, the proposed algorithm improves the throughput by 34.12% and packets the reception rate by 26%, significantly improving the network throughput and the packets reception rate.

Construction of Cross-Border e-Commerce Financial Risk Analysis System Based on Support Vector Machine

The rapid changes in the economic situation and the complex market environment make the cross-border e-commerce industry, as an important part of the market economy, face many challenges and risks in the development process. The particularity of its transaction and the imperfect tax mechanism have virtually increased the financial management risk. The research constructs the financial risk analysis model with the help of the support vector machine (SVM) and fuzzy theory. Through algorithm test and empirical research, it is found that the average accuracy of the optimized SVM on the selected data set is more than 90%, and after parameter optimization, the change of model fitness tends to be stable with the increase of iteration times, which greatly improves the search ability of sample data, and the accuracy of financial data classification with high risk is 46.8%. In the empirical research, the model established by fuzzy SVM can effectively eliminate the irrelevant index data, and the prediction accuracy of investment risk and operation risk has reached 80% or more. In the prediction of financing risk and tax risk, its accuracy has been improved by 12.4% compared to that before use.

Deep learning approach for Touchless Palmprint Recognition based on Alexnet and Fuzzy Support Vector Machine

Due to stable and discriminative features, palmprint-based biometrics has been gaining popularity in recent years. Most of the traditional palmprint recognition systems are designed with a group of hand-crafted features that ignores some additional features. For tackling the problem described above, a Convolution Neural Network (CNN) model inspired by Alex-net that learns the features from the ROI images and classifies using a fuzzy support vector machine is proposed. The output of the CNN is fed as input to the fuzzy Support vector machine. The CNN's receptive field aids in extracting the most discriminative features from the palmprint images, and Fuzzy SVM results in a robust classification. The experiments are conducted on popular contactless datasets such as IITD, POLYU2, Tongji, and CASIA databases. Results demonstrate our approach outperformers several state-of-art techniques for palmprint recognition. Using this approach, we obtain 99.98% testing accuracy for the Tongji dataset and 99.76 % for the POLYU-II datasets.

Fuzzy support vector machine with graph for classifying imbalanced datasets

Since support vector machine (SVM) considers all the training samples equally, it suffers from the problems of noise/outliers and class imbalance. Although many fuzzy support vector machines (FSVMs) have been proposed to suppress the effect of noise/outliers and class imbalance, most of them ignore the impact of the curse of dimensionality on the discriminative performance of fuzzy membership function and do not give the fuzzy membership function corresponding to the kernel space, which seriously reduces the performance of FSVM. To solve these problems, we propose the fuzzy support vector machine with graph (GraphFSVM) in this paper. Specifically, we first design a graph-based fuzzy membership function to accurately assess the importance of samples in original feature space and prove that the function can mine discriminative information between samples in high-dimensional data. Additionally, since the data distribution in kernel space is different from those in the original feature space, a method is provided to calculate the fuzzy membership function in the kernel space. Finally, the GraphFSVM model analyzes samples of each class independently, this suppresses the effect of class imbalance. Following the above principles, we design the graph-based fuzzy support vector machine and propose a detailed optimization method. Experimental results on UCI, gene expression, and image datasets show that the GraphFSVM has better generalization and robustness than other state-of-the-art methods.

Multi-objective Metaheuristics with Intelligent Deep Learning Model for Pancreatic Tumor Diagnosis

Pancreatic tumor is the deadliest disease which needs earlier identification to reduce the mortality rate. With this motivation, this study introduces a Multi-Objective Metaheuristics with Intelligent Deep Learning Model for Pancreatic Tumor Diagnosis (MOM-IDL) model. The proposed MOM-IDL technique encompasses an adaptive Weiner filter based pre-processing technique to enhance the image quality and get rid of the noise. In addition, multi-level thresholding based segmentation using Kapur’s entropy is employed where the threshold values are optimally chosen by the barnacles mating optimizer (BMO). Besides, densely connected network (DenseNet-169) is employed as a feature extractor and fuzzy support vector machine (FSVM) is utilized as a classifier. For improving the classification performance, the BMO technique was implemented for fine-tuning the parameters of the FSVM model. The design of MOBMO algorithm for threshold selection and parameter optimization processes shows the novelty of the work. A wide range of simulations take place on the benchmark dataset and the experimental results highlighted the enhanced performance of the MOM-IDL technique over the recent state of art techniques.