Search

Parallel Support Vector Machine (SVM) based on big data has achieved some results in data mining, but due to the complexity of the data itself and a large amount of noisy data, its execution efficiency and classification accuracy in the big data environment are very low. In order to eliminate noise, a noise reduction method based on Noise Cleaning (NC) strategy was proposed, and redundant training samples in big data environments were deleted; Introduce an improved Artificial Fish Swarm Algorithm (IAFSA) to obtain the final Parallel SVM algorithm using mutual information and artificial fish swarm algorithm based on MapReduce (MIAFSA-PSVM) classification model. The results indicate that when compared to CMI-PSVM, the execution time of MIAFSA-PSVM algorithm is higher on the NDC dataset with the largest data size, The SVM parameter optimization algorithm based on MapReduce and cuckoo search (CSSVM-MR) and the particle swarm optimization based parallel support vector machine ensemble algorithm (PSO-PSVM) decreased by 40.1%, 79.3%, and 51.7%, respectively. This indicates that GIESVM-MR and MIAFSA-PSVM have strong adaptability to big data environments and high classification accuracy. [ABSTRACT FROM AUTHOR]

Intelligent Transportation Systems have become integral to daily life, with VANETs (vehicular ad-hoc networks) playing the pivotal role. VANETs, the subsets of MANETs, employ vehicles as nodes to establish intelligent transport systems. However, due to critical applications such as military use, these networks are susceptible to attacks. With features like high mobility, dynamic network topology, and coverage issues, security breaches are a concern. This necessitates a secure routing algorithm to mitigate attacks and ensure message delivery. In our study, we utilize the UNSW-NB15 intrusion detection dataset to develop training and testing models. Our proposed novel intrusion detection system employs a feature selection algorithm that prioritizes significant arriving traffic attributes. This algorithm enhances abnormal activity detection while minimizing associated features. To achieve this, we modify the Conditional Random Field algorithm with fuzzy-based rules, resulting in a more efficient selection of influential and contributing features for detecting attacks such as DoS, Worms, Fuzzers, and Shellcode. Through appropriate feature selection using the modified Conditional Random Field and Support Vector Machine classification system in our experiments, we demonstrate a notable increase in security by reducing the false positive rate. Additionally, our approach excels in detecting accuracy of Fuzzers (98.86%), DoS (98.80%), Worms (34.45%), and Shellcode (89.308%), ultimately enhancing network performance. These findings underscore the effectiveness of our proposed method in enhancing intrusion detection and overall network efficiency. [ABSTRACT FROM AUTHOR]

Explainable Machine Learning brings expandability, interpretability, and accountability to Data Mining Algorithms. Existing explanation frameworks focus on explaining the decision process of a single model in a static dataset. However, in data stream mining changes in data distribution over time, called concept drift, may require updating the learning models to reflect the current data environment. It is therefore important to go beyond static models and understand what has changed among the learning models before and after a concept drift. We propose a Data Stream Explanability framework (DSE) that works together with a typical data stream mining framework where support vector machine models are used. DSE aims to help non-expert users understand model dynamics in a concept drifting data stream. DSE visualizes differences between SVM models before and after concept drift, to produce explanations on why the new model fits the data better. A survey was carried out between expert and non-expert users on the effectiveness of the framework. Although results showed non-expert users on average responded with less understanding of the issue compared to expert users, the difference is not statistically significant. This indicates that DSE successfully brings the explanability of model change to non-expert users. [ABSTRACT FROM AUTHOR]

Support Vector Machine (SVM) is a machine learning with excellent classification performance, which has been widely used in various fields such as data mining, text classification, face recognition and etc. However, when data volume scales to a certain level, the computational time becomes too long and the efficiency becomes low. To address this issue, we propose a parallel balanced SVM algorithm based on Spark, named PB-SVM, which is optimized on the basis of the traditional Cascade SVM algorithm. PB-SVM contains three parts, i.e., Clustering Equal Division, Balancing Shuffle and Iteration Termination, which solves the problems of data skew of Cascade SVM and the large difference between local support vector and global support vector. We implement PB-SVM in AliCloud Spark distributed cluster with five kinds of public datasets. Our experimental results show that in the two-classification test on the dataset covtype, compared with MLlib-SVM and Cascade SVM on Spark, PB-SVM improves efficiency by 38.9% and 75.4%, and the accuracy is improved by 7.16% and 8.38%. Moreover, in the multi-classification test, compared with Cascade SVM on Spark on the dataset covtype, PB-SVM improves efficiency and accuracy by 94.8% and 18.26% respectively. [ABSTRACT FROM AUTHOR]

Big Data is a popular research area where a vast amount of data is created, replicated, and consumed by society. The quality of the data used directly influences big data knowledge discovery. The existence of noise is the most prevalent problem influencing data quality. The following techniques were developed to reduce noise in data with a distributed setting: Homogenous Ensemble for Big Data (HME-BD) and Heterogeneous Ensemble for Big Data (HTE-BD). In this article, the performance of HTE-BD is improved further by developing Enhanced HTE-BD (EHTE-BD), which combines Logistic Regression based Support Vector Machine (LR-SVM) in conjunction with RF, LR, and KNN to reduce noisy data. Furthermore, the Multi-Objective Evolutionary Fuzzy Method for Subgroup Discovery throughout Big Data (MEFASDBD) was used to resolve the multi-objective optimization challenge, and the Non-Dominated Sorting Genetic Algorithm-II (NSGA-II) was utilized to handle the rising dimensionality issue through subgroup discovery. To address the NSGA-II's slow convergence rate, an Improved Multi-Objective Meta-Heuristic Fuzzy approach for discovering subgroups in big data is described, that contains a meta-heuristic method for subgroup discovery known as the Multi-Objective Differential Search Algorithm (MODSA). It selects the most relevant subgroups from vast amounts of data, reducing the data's dimensionality. The Fuzzy Deep Neural Network (FDNN) classifier assesses the main subgroups. By removing noisy data and selecting the most relevant subgroups, the performance of FDNN in classifying vast amounts of data is improved. [ABSTRACT FROM AUTHOR]

Knowledge extraction, data mining, e-learning or web applications platforms use heterogeneous and distributed data. The proliferation of these multifaceted platforms faces many challenges such as high scalability, the coexistence of complex similarity metrics, and the requirement of data quality evaluation. In this study, an extended complete formal taxonomy and some algorithms that utilize in achieving the detection and correction of contextual data quality anomalies were developed and implemented on structured data. Our methods were effective in detecting and correcting more data anomalies than existing taxonomy techniques, and also highlighted the demerit of Support Vector Machine (SVM). These proposed techniques, therefore, will be of relevance in detection and correction of errors in large contextual data (Big data). [ABSTRACT FROM AUTHOR]

Although Machine Learning (ML) is widely used to examine hidden patterns in complex databases and learn from them to predict future events in many fields, utilization of it for predicting the outcome of occupational accidents is relatively sparse. This study utilized diversified ML algorithms; Multinomial Logistic Regression (MLR), Support Vector Machines (SVM), Single C5.0 Tree (C5), Stochastic Gradient Boosting (SGB), and Neural Network (NN) in classifying the severity of occupational accidents in binary (Fatal/NonFatal) and multi-class (Fatal/Major/Minor) outcomes. Comparison of the performance of models showed Balanced Accuracy to be the best for SVM and SGB methods in 2-Class and SGB in 3-Class. Algorithms performed better at predicting fatal accidents compared to major and minor accidents. Results obtained revealed that, ML unveils factors contributing to severity to better address the corrective actions. Furthermore, taking action related to even some of the most significant factors in complex accidents database with many attributes can prevent majority of severe accidents. Interpretation of most significant factors identified for accident prediction suggest the following corrective measures: taking fall prevention actions, prioritizing workplace inspections based on the number of employees, and supplementing safety actions according to worker's age and experience. [ABSTRACT FROM AUTHOR]

Quality prediction plays an essential role in the business outcome of the product. Due to the business interest of the concept, it has extensively been studied in the last few years. Advancement in machine learning (ML) techniques and with the advent of robust and sophisticated ML algorithms, it is required to analyze the factors influencing the success of the movies. This paper presents a hybrid features prediction model based on pre-released and social media data features using multiple ML techniques to predict the quality of the pre-released movies for effective business resource planning. This study aims to integrate pre-released and social media data features to form a hybrid features-based movie quality prediction (MQP) model. The proposed model comprises of two different experimental models; (i) predict movies quality using the original set of features and (ii) develop a subset of features based on principle component analysis technique to predict movies success class. This work employ and implement different ML-based classification models, such as Decision Tree (DT), Support Vector Machines with the linear and quadratic kernel (L-SVM and Q-SVM), Logistic Regression (LR), Bagged Tree (BT) and Boosted Tree (BOT), to predict the quality of the movies. Different performance measures are utilized to evaluate the performance of the proposed ML-based classification models, such as Accuracy (AC), Precision (PR), Recall (RE), and F-Measure (FM). The experimental results reveal that BT and BOT classifiers performed accurately and produced high accuracy compared to other classifiers, such as DT, LR, LSVM, and Q-SVM. The BT and BOT classifiers achieved an accuracy of 90.1% and 89.7%, which shows an efficiency of the proposed MQP model compared to other state-of-art- techniques. The proposed work is also compared with existing prediction models, and experimental results indicate that the proposed MQP model performed slightly better compared to other models. The experimental results will help the movies industry to formulate business resources effectively, such as investment, number of screens, and release date planning, etc. [ABSTRACT FROM AUTHOR]

OBJECTIVE: With Sina Weibo data as the background, support vector machine (SVM) and k-nearest neighbor (KNN) method are used to predict and analyze the user's micro-blog emotion and related behavior in social network, hoping to obtain rich potential business value. METHODS: First, the API interface of Sina Weibo is utilized to obtain the information of users in Sina Weibo; then, the Excel software is utilized to sort and analyze the extracted data to extract the features of micro- blogs posted by users. Second, SVM and KNN algorithms are utilized to calculate the weighted average and propose a hybrid multi-classifier-based Mixed Classifier Emotion Prediction Model (MCEPM). Finally, through the evaluation criteria, including precision (P), recall rate (R), and harmonic average (F1), the specific experimental results of SVM and KNN weight coefficients are compared with the prediction results of MCEPM. RESULTS: The prediction effect of MCEPM is associated with the weight coefficients of SVM and KNN. If the weight coefficients of SVM and KNN are 0.6 and 0.4, the prediction effect of MCEPM will be optimal. Comprehensive analysis shows that the MCEPM model can balance the prediction results of the positive and negative samples of the two classifiers. CONCLUSION: MCEPM model is superior to other algorithms in micro-blog emotion prediction, which can help enterprises analyze users' product inclination and provide accurate customer service requirements for enterprises. [ABSTRACT FROM AUTHOR]

Class imbalance is often a problem in various real-world datasets, where one class contains a small number of data and the other contains a large number of data. It is notably difficult to develop an effective model using traditional data mining and machine learning algorithms without using data preprocessing techniques to balance the dataset. Oversampling is often used as a pretreatment method for imbalanced datasets. Specifically, synthetic oversampling techniques focus on balancing the number of training instances between the majority class and the minority class by generating extra artificial minority class instances. However, the current oversampling techniques simply consider the imbalance of quantity and pay no attention to whether the distribution is balanced or not. Therefore, this paper proposes an entropy difference and kernel-based SMOTE (EDKS) which considers the imbalance degree of dataset from distribution by entropy difference and overcomes the limitation of SMOTE for nonlinear problems by oversampling in the feature space of support vector machine classifier. First, the EDKS method maps the input data into a feature space to increase the separability of the data. Then EDKS calculates the entropy difference in kernel space, determines the majority class and minority class, and finds the sparse regions in the minority class. Moreover, the proposed method balances the data distribution by synthesizing new instances and evaluating its retention capability. Our algorithm can effectively distinguish those datasets with the same imbalance ratio but different distribution. The experimental study evaluates and compares the performance of our method against state-of-the-art algorithms, and then demonstrates that the proposed approach is competitive with the state-of-art algorithms on multiple benchmark imbalanced datasets. [ABSTRACT FROM AUTHOR]

The selection of big data attributes plays a positive role in the development of the network. At present, the attribute selection for big data is completed by detecting the attribute of data, which can not guarantee the accuracy of the selection. In this paper, a big data attribute selection method based on support vector machine (SVM) is proposed for distributed network fault diagnosis database. The method is used to mine big data in the distributed network fault diagnosis database, and calculate its attribute weights according to which complete attribute classification, so as to complete the selection if big data attributes. Experiments show that the proposed method improves the efficiency of big data attribute selection, and has certain practical value. [ABSTRACT FROM AUTHOR]

Green buildings have many advantages that traditional buildings do not possess, but there are still problems such as insufficient promotion and application. One of the important reasons is the lack of pertinent evaluation of green buildings. The current assessment of the economic benefits of green building design is still at a qualitative stage, and there is a lack of quantitative assessment methods and models. Based on this, this study establishes a green building design evaluation index system including cost and economic benefits. In the cost estimation, a nonlinear evaluation model based on data mining is designed to ensure a better estimation accuracy and credibility. In the evaluation of economic benefits, an incremental benefit evaluation model based on fuzzy mathematics is designed to evaluate its comprehensive economic benefits in a quantitative way. The results of data simulation show that the least squares support vector machine has achieved a good balance between the estimation time and accuracy. The comprehensive evaluation model proposed in this paper has strong operability and good evaluation effect, which is of great significance to promote the development of green building design. [ABSTRACT FROM AUTHOR]

Technological innovation in manufacturing industry is a kind of R&D activity that produces new technologies, including input and output of technological innovation. In this paper, the authors analyze the lean production and technological innovation in manufacturing industry based on SVM algorithms and data mining technology. Data mining can discover novel, effective, potential and ultimately understandable data patterns from a deeper level, and encode the data to predict the development trend of enterprises. The machine learning support vector machine method is used to analyze and model the collected data. At the same time, we constructed a decision tree using random forest, and explained the significance of the training algorithm through the visualization results. The simulation results show that learning growth dimension and market dimension have the greatest impact on business model innovation. In the context of TEC, business model innovation must pay attention to market grasp and customer demand oriented, so as to improve the competitiveness of manufacturing enterprises. [ABSTRACT FROM AUTHOR]

Competitive sports require athletes to operate in real time, and there are many uncertainties. At present, there are few applications of artificial intelligence in the prediction of competitive sports, and the relevant literature about fitness motivation is rare. Based on this, this study is based on the machine learning algorithm and uses the support vector machine to build the competitive sports model and fitness motivation evaluation. At the same time, this study combines the actual situation to construct a corresponding factor analysis model for racing sports, and this factor analysis is a combination of data mining and machine learning. Only by adopting appropriate measures can students' motivation of physical fitness be effectively fostered and stimulated, their active participation in physical exercise and lifelong fitness habits be fostered. On the basis of traditional SVM method, PCA-SVM model is constructed to further improve the prediction accuracy and validity of fitness motivation. In this paper, the principal components of eight kinds of operation behavior are extracted; fitness motivation is not only the direct reason for college students to participate in fitness exercise, but also the motive force of fitness behavior. Grid Search algorithm is selected to optimize the parameters of SVM. The recognition rate of Grid Search-SVM is 94.79%, and satisfactory results are obtained. [ABSTRACT FROM AUTHOR]

In this work, an efficient scheme has been proposed for the computer-aided detection of the wide-spread disease diabetes. This scheme involves certain data mining techniques for the purpose of detecting the chances of diabetes by looking into a patient's medical record. This work attempts to classify the nature of diabetes (Type-I and Type-II) as well. It also tries to determine the level of risk associated presently with the affected patient. Four different algorithms namely decision tree, Naive Bayes, support vector machine (SVM), and Adaboost-M1 have been used for the purpose of labeling the records as either diabetic or non-diabetic. A comparison strategy is then followed to adopt the best scheme among these through the voting expert. The proposed work gives satisfactory diagnosis result when compared to the ground-truth data. Overall accuracy rate of 95% is achieved through k-fold cross-validation (k = 10) method. Comparison of the proposed work with other state-of-the-art schemes has also been performed that favors the said work. [ABSTRACT FROM AUTHOR]

Feature selection is a common solution to microarray analysis. Previous approaches either select features based on classical statistical tests that can be tuned up with a classifier, or using regularization penalties incorporated in the cost function. Here we propose to use a feature ranking and weighting scheme instead, which combines statistical techniques with a weighted k -NN classifier using a modified forward selection procedure. We demonstrate that classification accuracy of our proposal outperforms existing methods on a range of public microarray gene expression datasets. The proposed method is also compared to state-of-the-art feature selection algorithms by means of the Friedman test. Although a bunch of feature selection techniques has been used for genomic data, the experimental results show the classification superiority of our method on most of the present gene expression datasets. [ABSTRACT FROM AUTHOR]

This paper is aimed to solve uncertainty in financial data mining by using fuzzy support vector machine (FSVM), and prior wavelet denoising and subsequent error adjustment based on generalized autoregressive conditional heteroskedasticity (GARCH) model are also supplemented respectively. The hybrid information capturing methodology proposed above can thus be supposed to address complex nonlinear dynamics behind the noise of financial data. To this end, a key approach to ascertain membership values for financial sample data is introduced in order to build the FSVM in terms of statistical characteristics of the financial data from the prior wavelet denoising stage. Moreover, the GARCH model is also employed in the final step so that the test errors from the preliminary test based on FSVM are deeply analyzed to capture missed price volatility information which are often neglected by existing approaches involving the traditional SVM models. The methodology proposed is thus enabled to sufficiently tackle the styled facts, such as nonlinearity, instability, strong noise, skewed distribution, and so on, because two factors of influencing price volatility, that is, the market factor and the time series factor, are all accounted for, and its prediction outperformance appears in empirical analysis of S&P 500 index. [ABSTRACT FROM AUTHOR]

The probabilistic linguistic terms set (PLTS) can reflect different importance degrees or weights of all possible linguistic terms (LTs) given by the experts for a specific object. The PROMETHEE II method is an important ranking method which can comprise preferences as well as indifferences, and it has a unique characteristic that can provide different types of preference functions. Based on the advantages of the PLTS and the PROMETHEE II method, in this paper, we extend the PROMETHEE II method to process the probabilistic linguistic information (PLI), and propose the PL-PROMETHEE II method with an improved possibility degree formula which can avoid the weaknesses from the original formula. Then concerning the multi-attribute decision making (MADM) problems with totally unknown weight information, the maximum deviation method is used to get the objective weight vector of the attributes, and net flows of the alternatives from the PROMETHEE II method are used to rank the alternatives. Finally, a numerical example is given to illustrate the feasibility of the proposed method. [ABSTRACT FROM AUTHOR]

In this paper an exploratory classification, so called open set problem, is investigated. Open set recognition assumes there is incomplete knowledge of the world at training time, and unknown classes can be submitted to an algorithm during testing. For this problem we elaborated a theoretical model, Double Probability Model (DPM), based on likelihoods of a classifier.We developed it with double smoothing solution in order to solve technical difficulties avoiding zero values in the predictions. We applied the GMM based Fisher vector for the mathematical representation of the images and the C-SVC with RBF kernel for the classification. The last contributions of the paper are new goodness indicators for classification in open set problem, the new type of accuracies. The experimental results present that our Double Probability Model helps with classification, the accuracy increases by using our proposed model. We compared our method to a state-of-the-art open set recognition solution and the results showed that DPM outperforms existing techniques. [ABSTRACT FROM AUTHOR]

Extreme learning machine (ELM) has demonstrated great potential in machine learning and data mining. Smoothing strategy is an important technology for continuous optimizations. In this work, we apply a smoothing technique to replace the hinge loss function by an accurate smooth approximation. This will allow us to solve ELM as an unconstrained minimization problem directly. We term this reformulated problem as smooth ELM (SELM). A Newton-Armijo algorithm is used to solve the proposed SELM, and the resulting algorithm converges globally and quadratically. The proposed SELM with fast running speed has less decision variables and can better deal with nonlinear problems than the existing smooth support vector machine. Numerical experiments on various types of datasets including two-class datasets and multi-class datasets demonstrate that the speed of SELM is much faster than that of the existing ELM models. And compared with other popular algorithms of support vector machine and ELM, the proposed SELM achieves better or similar generalization. These demonstrate the effectiveness and fast speed of the algorithm. [ABSTRACT FROM AUTHOR]

Within the field of data mining and machine learning, the K-Nearest Neighbor algorithm is a classic algorithm which simply yet elegantly classifies data based upon its similarity to other data. While it follows that the accuracy increases as more data are provided, handling large sets of data is difficult to process serially. It is therefore ideal to perform these tasks in parallel or distributed mode. In this paper, we proposed a framework for distributed nearest neighbor classification. A custom K-Nearest Neighbor algorithm was developed using Hadoop, an environment for developing and deploying applications in parallel on a cluster. The algorithm was implemented on a cluster then tested for accuracy and time of execution. It was observed that the accuracy depends on the provided k-value and on the data set, which is to be expected for the K-Nearest Neighbor process. The time of execution was found to increase logarithmically as the file size, and thus the amount of data the algorithm must parse, increases exponentially. [ABSTRACT FROM AUTHOR]

Decision tree is a simple and effective method and it can be supplemented with ensemble methods to improve its performance. Random Forest and Rotation Forest are two approaches which are perceived as “classic” at present. They can build more accurate and diverse classifiers than Bagging and Boosting by introducing the diversities namely randomly chosen a subset of features or rotated feature space. However, the splitting criteria used for constructing each tree in Random Forest and Rotation Forest are Gini index and information gain ratio respectively, which are skew-sensitive. When learning from highly imbalanced datasets, class imbalance impedes their ability to learn the minority class concept. Hellinger distance decision tree (HDDT) was proposed by Chawla, which is skew-insensitive. Especially, bagged unpruned HDDT has proven to be an effective way to deal with highly imbalanced problem. Nevertheless, the bootstrap sampling used in Bagging can lead to ensembles of low diversity compared to Random Forest and Rotation Forest. In order to combine the skew-insensitivity of HDDT and the diversities of Random Forest and Rotation Forest, we use Hellinger distance as the splitting criterion for building each tree in Random Forest and Rotation Forest respectively. An experimental framework is performed across a wide range of highly imbalanced datasets to investigate the effectiveness of Hellinger distance, information gain ratio and Gini index which are used as the splitting criteria in ensembles of decision trees including Bagging, Boosting, Random Forest and Rotation Forest. In addition, Balanced Random Forest is also included in the experiment since it is designed to tackle class imbalance problem. The experimental results, which contrasted through nonparametric statistical tests, demonstrate that using Hellinger distance as the splitting criterion to build individual decision tree in forest can improve the performances of Random Forest and Rotation Forest for highly imbalanced classification. [ABSTRACT FROM AUTHOR]

Feature selection is an important machine learning topic, especially in high dimensional applications, such as cancer prediction with microarray data. This work addresses the issue of high dimensionality of feature selection for linear and kernel-based Support Vector Machines (SVMs) considering second-order cone programming formulations. These formulations provide a robust and efficient framework for classification, while an adequate feature selection process avoids errors in the estimation of means and covariances. Our approach is based on a sequential backward elimination which uses different linear and kernel-based contribution measures to determine the feature relevance. Experimental results with microarray datasets demonstrate the effectiveness in terms of predictive performance and construction of a low-dimensional data representation. [ABSTRACT FROM AUTHOR]

Group probability classifier learning is an emerging and promising learning technique, especially in privacy-preserving data mining. It is used to train a classifier from a group probability dataset, where the class labels of each sample are unknown while the probabilities of each class in the given data groups of the whole dataset are available. The existing work is mainly based on the inverse calibration (IC) strategy to obtain the estimated labels for data in the group probability dataset and then make use of classical classification algorithms such as support vector machine (SVM) model to train the desired classifier. A critical challenge of the exiting IC-based methods lies in the difficulty of designing an ideal IC function for label estimation and the methods are sensitive to the adopted IC function. In order to overcome this shortcoming, a novel probability transductive classifier that does not involve IC in the learning procedure is proposed, where the probability values are directly used as the output of the training data for the model training. Particularly, on the training data with the output being continuous real values, the existing classical regression model can be easily adopted to model the group probability classification problem. For a future testing data, the model output of the obtained group probability classification model can present the probability that the testing data belong to the positive class. With a given threshold, the final class label of the testing data can be obtained for the classification task. The experimental results on synthetic datasets and real UCI datasets show that the proposed method is more effective than the existing methods. [ABSTRACT FROM AUTHOR]

An empirical framework for customer churn prediction modeling is presented in this work. This task represents a very interesting business analytics challenge, given its highly class imbalanced nature, and the presence of noisy variables that adversely affect the prediction capabilities of classification models. In this work, two SVM-based techniques are compared: Support Vector Data Description (SVDD), and standard two-class SVMs. The proposed methodology involves the comparison of these two methods under different conditions of class imbalance and using different subsets of variables. Feature ranking is performed via the Fisher Score Criterion, while the class imbalance problem is dealt with through resampling techniques, namely random undersampling and SMOTE oversampling. Experiments on four customer churn prediction datasets show the advantages of SVDD: it outperforms standard SVM in terms of predictive performance, demonstrating the importance of techniques that take the class imbalance problem into account. [ABSTRACT FROM AUTHOR]

Data Mining (DM) researchers often focus on the development and testing of models for a single decision (e.g., direct mailing, churn detection, etc.). In practice, however, multiple decisions have often to be made simultaneously which are not independent and the best global solution is often not the combination of the best individual solutions. This problem can be addressed by searching for the overall best solution by using optimization methods based on the predictions made by the DM models. We describe one case study were this approach was used to optimize the layout of a retail store in order to maximize predicted sales. A metaheuristic is used to search different hypothesis of space allocations for multiple product categories, guided by the predictions made by regression models that estimate the sales for each category based on the assigned space. We test three metaheuristics and three regression algorithms on this task. Results show that the Particle Swam Optimization method guided by the models obtained with Random Forests and Support Vector Machines models obtain good results. We also provide insights about the relationship between the correctness of the regression models and the metaheuristics performance. [ABSTRACT FROM AUTHOR]

One of the major developments in machine learning in the past decade is the ensemble method, which finds highly accurate classifier by combining many moderately accurate component classifiers. In this research work, new ensemble classification methods are proposed with homogeneous ensemble classifier using bagging and heterogeneous ensemble classifier using arcing and their performances are analyzed in terms of accuracy. A Classifier ensemble is designed using Radial Basis Function (RBF) and Support Vector Machine (SVM) as base classifiers. The feasibility and the benefits of the proposed approaches are demonstrated by the means of standard datasets of direct marketing. The main originality of the proposed approach is based on three main parts: preprocessing phase, classification phase and combining phase. A wide range of comparative experiments are conducted for standard datasets of direct marketing. The performance of the proposed homogeneous and heterogeneous ensemble classifiers are compared to the performance of other standard homogeneous and heterogeneous ensemble methods. The standard homogeneous ensemble methods include Error correcting output codes, dagging and heterogeneous ensemble methods include majority voting, stacking. The proposed ensemble methods provide significant improvement of accuracy compared to individual classifiers and the proposed bagged RBF and SVM performs significantly better than ECOC and Dagging and the proposed hybrid RBF-SVM performs significantly better than voting and stacking. Also heterogeneous models exhibit better results than homogeneous models for standard datasets of direct marketing. [ABSTRACT FROM AUTHOR]

BACKGROUND: The size of medical datasets is usually very large, which directly affects the computational cost of the data mining process. Instance selection is a data preprocessing step in the knowledge discovery process, which can be employed to reduce storage requirements while also maintaining the mining quality. This process aims to filter out outliers (or noisy data) from a given (training) dataset. However, when the dataset is very large in size, more time is required to accomplish the instance selection task. OBJECTIVE: In this paper, we introduce an efficient data preprocessing approach (EDP), which is composed of two steps. The first step is based on training a model over a small amount of training data after preforming instance selection. The model is then used to identify the rest of the large amount of training data. METHODS: Experiments are conducted based on two medical datasets for breast cancer and protein homology prediction problems that contain over 100000 data samples. In addition, three well-known instance selection algorithms are used, IB3, DROP3, and genetic algorithms. On the other hand, three popular classification techniques are used to construct the learning models for comparison, namely the CART decision tree, k-nearest neighbor (k-NN), and support vector machine (SVM). RESULTS: The results show that our proposed approach not only reduces the computational cost by nearly a factor of two or three over three other state-of-the-art algorithms, but also maintains the final classification accuracy. CONCLUSIONS: To perform instance selection over large scale medical datasets, it requires a large computational cost to directly execute existing instance selection algorithms. Our proposed EDP approach solves this problem by training a learning model to recognize good and noisy data. To consider both computational complexity and final classification accuracy, the proposed EDP has been demonstrated its efficiency and effectiveness in the large scale instance selection problem. [ABSTRACT FROM AUTHOR]

BACKGROUND: Now-a-days, some new classes of diseases have come into existences which are known as lifestyle diseases. The main reasons behind these diseases are changes in the lifestyle of people such as alcohol drinking, smoking, food habits etc. After going through the various lifestyle diseases, it has been found that the fertility rates (sperm quantity) in men has considerably been decreasing in last two decades. Lifestyle factors as well as environmental factors are mainly responsible for the change in the semen quality. OBJECTIVE: The objective of this paper is to identify the lifestyle and environmental features that affects the seminal quality and also fertility rate in man using data mining methods. METHOD: The five artificial intelligence techniques such as Multilayer perceptron (MLP), Decision Tree (DT), Navie Bayes (Kernel), Support vector machine+Particle swarm optimization (SVM+PSO) and Support vector machine (SVM) have been applied on fertility dataset to evaluate the seminal quality and also to predict the person is either normal or having altered fertility rate. While the eight feature selection techniques such as support vector machine (SVM), neural network (NN), evolutionary logistic regression (LR), support vector machine plus particle swarm optimization (SVM+PSO), principle component analysis (PCA), chi-square test, correlation and T-test methods have been used to identify more relevant features which affect the seminal quality. These techniques are applied on fertility dataset which contains 100 instances with nine attribute with two classes. RESULTS: The experimental result shows that SVM+PSO provides higher accuracy and area under curve (AUC) rate (94% & 0.932) among multi-layer perceptron (MLP) (92% & 0.728), Support Vector Machines (91% & 0.758), Navie Bayes (Kernel) (89% & 0.850) and Decision Tree (89% & 0.735) for some of the seminal parameters. This paper also focuses on the feature selection process i.e. how to select the features which are more important for prediction of fertility rate. In this paper, eight feature selection methods are applied on fertility dataset to find out a set of good features. The investigational results shows that childish diseases (0.079) and high fever features (0.057) has less impact on fertility rate while age (0.8685), season (0.843), surgical intervention (0.7683), alcohol consumption (0.5992), smoking habit (0.575), number of hours spent on setting (0.4366) and accident (0.5973) features have more impact. It is also observed that feature selection methods increase the accuracy of above mentioned techniques (multilayer perceptron 92%, support vector machine 91%, SVM+PSO 94%, Navie Bayes (Kernel) 89% and decision tree 89%) as compared to without feature selection methods (multilayer perceptron 86%, support vector machine 86%, SVM+PSO 85%, Navie Bayes (Kernel) 83% and decision tree 84%) which shows the applicability of feature selection methods in prediction. CONCLUSION: This paper lightens the application of artificial techniques in medical domain. From this paper, it can be concluded that data mining methods can be used to predict a person with or without disease based on environmental and lifestyle parameters/features rather than undergoing various medical test. In this paper, five data mining techniques are used to predict the fertility rate and among which SVM+PSO provide more accurate results than support vector machine and decision tree. [ABSTRACT FROM AUTHOR]

BACKGROUND: Diagnosing different types of liver diseases clinically is a quite hectic process because patients have to undergo large numbers of independent laboratory tests. On the basis of results and analysis of laboratory test, different liver diseases are classified. Hence to simplify this complex process, we have developed a Rule Base Classification Model (RBCM) to predict different types of liver diseases. The proposed model is the combination of rules and different data mining techniques.OBJECTIVE: The objective of this paper is to propose a rule based classification model with machine learning techniques for the prediction of different types of Liver diseases.METHOD: A dataset was developed with twelve attributes that include the records of 583 patients in which 441 patients were male and rests were female. Support Vector Machine (SVM), Rule Induction (RI), Decision Tree (DT), Naive Bayes (NB) and Artificial Neural Network (ANN) data mining techniques with K-cross fold technique are used with the proposed model for the prediction of liver diseases. The performance of these data mining techniques are evaluated with accuracy, sensitivity, specificity and kappa parameters as well as statistical techniques (ANOVA and Chi square test) are used to analyze the liver disease dataset and independence of attributes.RESULT: Out of 583 patients, 416 patients are liver diseases affected and rests of 167 patients are healthy. The proposed model with decision tree (DT) technique provides the better result among all techniques (RI, SVM, ANN and NB) with all parameters (Accuracy 98.46%, Sensitivity 95.7%, Specificity 95.28% and Kappa 0.983) while the SVM exhibits poor performance (Accuracy 82.33%, Sensitivity 68.03%, Specificity 91.28% and Kappa 0.801). It is also found that the best performance of the model without rules (RI, Accuracy 82.68%, Sensitivity 86.34%, Specificity 90.51% and Kappa 0.619) is almost similar to the worst performance of the rule based classification model (SVM, Accuracy 82.33%, Sensitivity 68.03%, Specificity 91.28% and Kappa 0.801 and the accuracy of chi square test is 76.67%.CONCLUSION: This study demonstrates that there is a significant difference between the proposed rules based classification model and the model without rules for the liver diseases prediction and the rule based classification model with decision tree (DT) technique provides most accurate result. This model can be used as a valuable tool for medical decision making. [ABSTRACT FROM AUTHOR]

In the context of classification most efforts have been devoted to deriving accurate prediction models from a set of examples whose class is supposed to be known with certainty. However, there are situations where class labels are affected by an intrinsic vagueness, as in ranking customers for marketing campaigns or credit approval. In this paper we propose a new two-phase fuzzy classification method aimed at generating accurate classification rules when labels are uncertain. In the first phase, an ensemble method is applied in order to derive the value of the class membership function for each example in the dataset. In the second phase, an optimal classification model is obtained by solving a fuzzy variant of discrete support vector machines. Computational tests performed on benchmark and real world marketing and credit risk datasets show the effectiveness of the proposed method when it is compared to alternative classification techniques. Furthermore, the tests reveal that the new fuzzy discrete SVM model is a robust regularization method capable of generating stable classification rules, reducing the variance of the error and smoothing out the noise due to outliers. [ABSTRACT FROM AUTHOR]

Pre-processing plays a vital role in classification tasks, particularly when complex features are involved, and this demands a highly intelligent method. In bioinformatics, where datasets are categorised as having complex features, the need for pre-processing is unavoidable. In this paper, we propose a framework for selecting the discriminatory features from protein sequences prior to classification by integrating the filter and wrapper approaches. Several state-of-the-art multivariate filters were explored in the first phase to remove the unwanted features that contributed to noise, while particle swarm optimisation (PSO) with support vector machine (SVM) was adopted in the wrapper phase to produce the most optimal features. Several PSO variants were investigated in the wrapper phase to compare the most suitable PSO variants for the problem domain. The results of both phases were analysed based on classification accuracy, number of selected features, modelling time and area under the curve on the main dataset and, five benchmark machine learning datasets of similar complexity. The higher classification accuracy of the proposed framework was highly reliable with an improvement over the filter phase and the use of full features despite using smaller features. [ABSTRACT FROM AUTHOR]

ChemModLab, written by the ECCR @ NCSU consortium under NIH support, is a toolbox for fitting and assessing quantitative structure-activity relationships (QSARs). Its elements are: a cheminformatic front end used to supply molecular descriptors for use in modeling; a set of methods for fitting models; and methods for validating the resulting model. Compounds may be input as structures from which standard descriptors will be calculated using the freely available cheminformatic front end PowerMV; PowerMV also supports compound visualization. In addition, the user can directly input their own choices of descriptors, so the capability for comparing descriptors is effectively unlimited. The statistical methodologies comprise a comprehensive collection of approaches whose validity and utility have been accepted by experts in the fields. As far as possible, these tools are implemented in open-source software linked into the flexible R platform, giving the user the capability of applying many different QSAR modeling methods in a seamless way. As promising new QSAR methodologies emerge from the statistical and data-mining communities, they will be incorporated in the laboratory. The web site also incorporates links to public-domain data sets that can be used as test cases for proposed new modeling methods. The capabilities of ChemModLab are illustrated using a variety of biological responses, with different modeling methodologies being applied to each. These show clear differences in quality of the fitted QSAR model, and in computational requirements. The laboratory is web-based, and use is free. Researchers with new assay data, a new descriptor set, or a new modeling method may readily build QSAR models and benchmark their results against other findings. Users may also examine the diversity of the molecules identified by a QSAR model. Moreover, users have the choice of placing their data sets in a public area to facilitate communication with other researchers; or can keep them hidden to preserve confidentiality. [ABSTRACT FROM AUTHOR]

Genetic researches have gradually become an area which is intensively studied on in recent years. The reason of that is the fact that a lot of diseases and features are transferred to the other generations by genes. These transfers are generally at the base of diseases. The evaluation of the input which is reached as the result of the researches is also accepted as a separate field. The aim of this study is to develop a model which enables the best classification of the patients by DNA microarray expression inputs. For this purpose, the classification which is based on Unsupervised Learning has mainly been used, by bringing together various methods. The Independent Components Analysis is used for dimension reduction, Kohonen Map Method is used for clustering and Random Forest Method is used for classification purposes. The model which is formed by combining these methods and very popular classification method Support Vector Machines (SVMs) has been studied and their classification performance is compared by True Classification Rate (TCR) on two real publicity data sets. The highest value that TCR can take on is one. The aim is to close this value to one. By the help of the model proposed in this study, we expect a reduction in the cost of these researches and aim to prevent wrong diagnoses as much as possible. [ABSTRACT FROM AUTHOR]

Excessive lose of customer account is becoming a major headache for VIP E-Mail hosting companies. Analysis of what kind of customer is more prone to lose and finding the appropriate measures to sustain those customers has become urgent needs. Recently, classification models based on mathematical programming have been widely used in business intelligence. The purpose of this paper is to propose several multiple criteria programming methods for classification and apply these methods to VIP E-Mail behavior classification. We first introduce a model for a generalized multiple criteria programming based classification method, specifically four particular forms, and then we use a cross-validation method to test the stability and accuracy of multiple criteria programming methods on VIP E-Mail accounts. Finally, we compare our models with Support Vector Machine (SVM). The results show that the classification models based on mathematical programming are satisfactorily accurate and stable on a VIP E-Mail dataset. Therefore, it can be concluded that applying the proposed method on VIP E-Mail behavior analysis can provide stable and credible results. [ABSTRACT FROM AUTHOR]

The selection of a proper auditor is driven by several factors. Here, we use three data mining classification techniques to predict the auditor choice. The methods used are Decision Trees, Neural Networks and Support Vector Machines. The developed models are compared in term of their performances. The wrapper feature selection technique is used for the Decision Tree model. Two models reveal that the level of debt is a factor that influences the auditor choice decision. This study has implications for auditors, investors, company decision makers and researchers. [ABSTRACT FROM AUTHOR]

Confocal Scanning Laser Tomography (CSLT) techniques capture high-quality images of the optic disc (the retinal region where the optic nerve exits the eye) that are used in the diagnosis and monitoring of glaucoma. We present a hybrid framework, combining image processing and data mining methods, to support the interpretation of CSLT optic nerve images. Our framework features (a) Zernike moment methods to derive shape information from optic disc images; (b) classification of optic disc images, based on shape information, to distinguish between healthy and glaucomatous optic discs. We apply Multi Layer Perceptrons, Support Vector Machines and Bayesian Networks for feature sub-set selection and image classification; and (c) clustering of optic disc images, based on shape information, using Self-Organizing Maps to visualize sub-types of glaucomatous optic disc damage. Our framework offers an automated and objective analysis of optic nerve images that can potentially support both diagnosis and monitoring of glaucoma. [ABSTRACT FROM AUTHOR]

The availability of modern imaging techniques such as Confocal Scanning Laser Tomography (CSLT) for capturing high-quality optic nerve images offer the potential for developing automatic and objective methods for diagnosing glaucoma. We present a hybrid approach that features the analysis of CSLT images using moment methods to derive abstract image defining features. The features are then used to train classifers for automatically distinguishing CSLT images of normal and glaucoma patient. As a first, in this paper, we present investigations in feature subset selction methods for reducing the relatively large input space produced by the moment methods. We use neural networks and support vector machines to determine a sub-set of moments that offer high classification accuracy. We demonstratee the efficacy of our methods to discriminate between healthy and glaucomatous optic disks based on shape information automatically derived from optic disk topography and reflectance images. [ABSTRACT FROM AUTHOR]