A Fuzzy Bayesian Classifier with Learned Mahalanobis Distance

A comprehensive analysis of an automated system for epileptic seizure detection is explained in this work. When a seizure occurs, it is quite difficult to differentiate the non-stationary patterns from the discharges occurring in a rhythmic manner. The proposed approach deals with it efficiently by clustering it initially for the sake of feature extraction by using six different techniques categorized under two different methods, e.g., bio-inspired clustering and learning-based clustering. Learning-based clustering includes K-means clusters and Fuzzy C-means (FCM) clusters, while bio-inspired clusters include Cuckoo search clusters, Dragonfly clusters, Firefly clusters, and Modified Firefly clusters. Clustered values were then classified with 10 suitable classifiers, and after the performance comparison analysis of the EEG time series, the results proved that this methodology flow achieved a good performance index and a high classification accuracy. A comparatively higher classification accuracy of 99.48% was achieved when Cuckoo search clusters were utilized with linear support vector machines (SVM) for epilepsy detection. A high classification accuracy of 98.96% was obtained when K-means clusters were classified with a naive Bayesian classifier (NBC) and Linear SVM, and similar results were obtained when FCM clusters were classified with Decision Trees yielding the same values. The comparatively lowest classification accuracy, at 75.5%, was obtained when Dragonfly clusters were classified with the K-nearest neighbor (KNN) classifier, and the second lowest classification accuracy of 75.75% was obtained when Firefly clusters were classified with NBC.

In this paper, we propose a particle swarm optimization method incorporating quantum qubit operation to construct and optimize fuzzy rule-based classifiers. The proposed algorithm, denoted as QiQPSO, is inspired by the quantum computing principles. It employs quantum rotation gates to update the probability of each qubit with the corresponding quantum angle updating according to the update equation of the quantum-behaved particle swarm optimization (QPSO). After description of the principle of QiQPSO, we show how to apply QiQPSO to establish a fuzzy classifier through two procedures. The QiQPSO algorithm is first used to construct the initial fuzzy classification system based on the sample data and the grid method of partitioning the feature space, and then the fuzzy rule base of the initial fuzzy classifier is optimized further by QiQPSO in order to reduce the number of the fuzzy rules and thus improve its interpretability. In order to verify the effectiveness of the proposed method, QiQPSO is tested on various real-world classification problems. The experimental results show that the QiQPSO is able to effectively select feature variables and fuzzy rules of the fuzzy classifiers with high classification accuracies. The performance comparison with other methods also shows that the fuzzy classifier optimized by QiQPSO has higher interpretability as well as comparable or even better classification accuracies.

Care about automated documents classification has increased since the appearance of the digital documents and the wide diffusion of Internet. In the 1990's, the computer performance has greatly improved and has led to the methods of machine learning to establish automated classifiers. These methods have achieved good speed and classification's accuracy and researchers still investigate in this field to accomplish more accuracy and less time. Artificial immunologic systems have shown high performance in such as data clustering and anomaly detection which can be ascribed to the nature of the immunologic system in protecting the body. Some of the present methods and ways used in the training process of the document classification are time consuming and others have less accuracy rate concerned the classification of the related document as software engineering document classes For these reasons, this research deals with the study of Natural Immune System and using the dynamic process of the Innate Immune System work based on danger theory and Dendritic Cell (DC) technique in building Dendritic Cell Model (DCM) to classify Software Engineering documents as they comprise information related to developing the software systems, that makes it easy for the software engineer who works in maintenance. DCM has high classification's speed and accuracy besides easy and flexible use by designing interfaces that makes it easy for the user to deal with the system. In order to improve the quality and the efficiency of DCM method, it was compared to one of the best and well-known methods of classification referred to as, Naive Bayes(NB). After conducting several experiments on a various group of software engineering documents, evaluations results have shown that the accuracy of the innate immunologic method (DCM) has reached (DCM) (95%), whereas Naïve classification method has reached (90 %) with training and classification speed that doesn’t exceed one minutes. This shows the feasibility of using the algorithms of AIS systems in the field of information recovery and documents classification. This system was built and programmed in Java language and was implemented under an operating system environment Microsoft Windows7.

Depression or Major Depressive Disorder (MDD) is a psychiatric disorder. It is the major contributor to overall global burden of disease. Any deterioration in brain functioning is reflected in Electroencephalogram (EEG) signals. EEG signals are highly complex, nonstationary and nonlinear. So, it is very difficult to analyze visually and identify changes in the waveform in order to classify MDD and normal subjects. Thus, computerized quantitative EEG is used for the analysis of signals. Support Vector Machine (SVM) using band power feature reported an accuracy of 98.33% and using Kernel Eigen-Filter-Bank Common Spatial Patterns (KEFB-CSP) gave an accuracy of 91.67% [1, 2]. Logistic Regression (LR) using band power feature reported an accuracy of 98.33%, using 4 nonlinear features combination provided an accuracy of 90%, using wavelet transform provided an accuracy of 87.5% and using only alpha power gave an accuracy of 73.3% [1, 3, 4]. Naive Bayesian (NB) using band power feature provided an accuracy of 96.8% [1]. Artificial Neural Network using Relative Wavelet Energy (RWE) reported an accuracy of 98.11%, using power spectrum feature gave accuracy of 84% and using Lep–Ziv complexity accuracy of 60–80% was reported [5, 6, 7]. Linear Discriminant Analysis (LDA) reported an accuracy of 91.2% using SASI (Spectral Asymmetry Index) and DFA (Detrended Fluctuation Analysis) [8]. Decision Tree provided an accuracy of 80% using EEG band power as feature [9]. The study reveals that, in general, high classification accuracy is achieved by SVM, LR and ANN and highest classification accuracy of 98.33% is achieved by SVM. Highest accuracy is achieved by SVM because it is more robust and computationally more efficient due to maximal margin gap between separating hyper planes and kernel trick. The study gives some ideas which could be helpful for guiding and improving future researches. Since linear and nonlinear method for feature extraction are both equally efficient. So any of the linear/nonlinear feature can be used. For feature selection and reduction, Genetic Algorithm (GA), Principal Components Analysis (PCA) and Linear Discriminant Analysis (LDA) can be used. Since SVM, LR and ANN give high classification accuracy and any of them can be used or any hybrid technique like GA-SVM, GA-ANN can be used. This chapter compares various EEG signal analysis techniques, compares their accuracy and methodology used and finally recommends the most suitable technique based on the accuracy for detection of depression. The chapter also summarizes some of the key finding related to EEG features based on present state of art. These results could be helpful for guiding and improving the future research in this area.

Clustering documents enable the user to have a good overall view of the information contained in the documents. Most classical clustering algorithms assign each data to exactly one cluster, thus forming a crisp partition of the given data, but fuzzy clustering allows for degrees of membership, to which a data belongs to different clusters. In this system, documents are clustered by using fuzzy c-means (FCM) clustering algorithm. FCM clustering is one of well-know unsupervised clustering techniques. However FCM algorithm requires the user to pre-define the number of clusters and different values of clusters corresponds to different fuzzy partitions. So the validation of clustering result is needed. PBM index and F-measure are used for cluster validity.

Naive Bayes (NB) classifier is a simple and efficient classifier, but the independent assumption of its attribute limits the application of the actual data. This paper presents an approach called particle swarm optimization-naive Bayes (PSO-NB) which takes advantage of combination particle swarm optimization with naive Bayes for attribute selection to improve naive Bayes classifier. This method applies PSO firstly to search out an optimal subset of attributes reduction in the original attribute space, and then constructs a naive Bayes classifier on the gotten subset of the attributes reduction. Nineteen experimental results on UCI datasets distinctly show that compared with Cfs-BestFirst algorithm, NB algorithm, Decision Tree(C4.5) algorithm, K-neighbor(KNN) algorithm, the proposed algorithm has higher classification accuracy.

Non-Line-of-Sight (NLoS) propagation condition is a crucial factor affecting the precision of the localization in the Ultra-Wideband (UWB) Indoor Positioning System (IPS). Numerous supervised Machine Learning (ML) approaches have been applied for NLoS identification to improve the accuracy of the IPS. However, it is difficult for existing ML approaches to maintain a high classification accuracy when the database contains a small number of NLoS signals and a large number of Line-of-Sight (LoS) signals. The inaccurate localization of the target node caused by this small number of NLoS signals can still be problematic. To solve this issue, we propose feature-based Gaussian Distribution (GD) and Generalized Gaussian Distribution (GGD) NLoS detection algorithms. By employing our detection algorithm for the imbalanced dataset, a classification accuracy of $96.7\%$ and $98.0\%$ can be achieved. We also compared the proposed algorithm with the existing cutting-edge such as Support-Vector-Machine (SVM), Decision Tree (DT), Naive Bayes (NB), and Neural Network (NN), which can achieve an accuracy of $92.6\%$, $92.8\%$, $93.2\%$, and $95.5\%$, respectively. The results demonstrate that the GGD algorithm can achieve high classification accuracy with the imbalanced dataset. Finally, the proposed algorithm can also achieve a higher classification accuracy for different ratios of LoS and NLoS signals which proves the robustness and effectiveness of the proposed method.

In recent years the used of personalization in service provisioning applications has been very popular. However, effective personalization cannot be achieved without accurate user profiles. A number of classification algorithms have been used to classify user related information to create accurate user profiles. In this study four different classification algorithms which are; naive Bayesian (NB), Bayesian networks (BN), lazy learning of Bayesian rules (LBR) and instance-based learner (IB1) are compared using a set of user profile data. According to our simulation results NB and IB1 classifiers have the highest classification accuracy with the lowest error rate. The obtained simulation results have been evaluated against the existing works of support vector machines (SVMs), decision trees (DTs) and neural networks (NNs).

We propose the use of a Fuzzy Naive Bayes classifier with a MAP rule as a decision making module for the RoboCup Soccer Simulation 3D domain. The Naive Bayes classifier has proven to be effective in a wide range of applications, in spite of the fact that the conditional independence assumption is not met in most cases. In the Naive Bayes classifier, each variable has a finite number of values, but in the RoboCup domain, we must deal with continuous variables. To overcome this issue, we use a fuzzy extension known as the Fuzzy Naive Bayes classifier that generalizes the meaning of an attribute so it does not have exactly one value, but a set of values to a certain degree of truth. We implemented this classifier in a 3D team so an agent could obtain the probabilities of success of the possible action courses given a situation in the field and decide the best action to execute. Specifically, we use the pass evaluation skill as a test bed. The classifier is trained in a scenario where there is one passer, one teammate and one opponent that tries to intercept the ball. We show the performance of the classifier in a test scenario with four opponents and three teammates. After a brief introduction, we present the specific characteristics of our training and test scenarios. Finally, results of our experiments are shown.KeywordsBayesian NetworkEmotion RecognitionFuzzy VariableTest ScenarioConditional Independence AssumptionThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

High accuracy remote sensed image classification technology is a long-term and continuous pursuit goal of remote sensing applications. In order to evaluate single classification algorithm accuracy, take Landsat TM image as data source, Northwest Yunnan as study area, seven types of land cover classification like Maximum Likelihood Classification has been tested, the results show that: (1)the overall classification accuracy of Maximum Likelihood Classification(MLC), Artificial Neural Network Classification(ANN), Minimum Distance Classification(MinDC) is higher, which is 82.81% and 82.26% and 66.41% respectively; the overall classification accuracy of Parallel Hexahedron Classification(Para), Spectral Information Divergence Classification(SID), Spectral Angle Classification(SAM) is low, which is 37.29%, 38.37, 53.73%, respectively. (2) from each category classification accuracy: although the overall accuracy of the Para is the lowest, it is much higher on grasslands, wetlands, forests, airport land, which is 89.59%, 94.14%, and 89.04%, respectively; the SAM, SID are good at forests classification with higher overall classification accuracy, which is 89.8% and 87.98%, respectively. Although the overall classification accuracy of ANN is very high, the classification accuracy of road, rural residential land and airport land is very low, which is 10.59%, 11% and 11.59% respectively. Other classification methods have their advantages and disadvantages. These results show that, under the same conditions, the same images with different classification methods to classify, there will be a classifier to some features has higher classification accuracy, a classifier to other objects has high classification accuracy, and therefore, we may select multi sub-classifier integration to improve the classification accuracy. © (2015) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.

In fuzzy C-means (FCM) clustering, each data point belongs to a cluster to a degree specified by a membership grade. FCM partitions a collection of vectors in c fuzzy groups and finds a cluster center in each group such that the dissimilarity measure is minimized. This paper presents a training algorithm for the radial basis function (RBF) network using symmetry-based Fuzzy C-means (SFCM) clustering method which is the modified version of FCM clustering method based on point symmetry distance measure. The training algorithm which uses SFCM clustering method to train the network has a number of advantages such as faster training time, more accurate predictions and reduced network architecture compared to the standard RBF networks. The proposed training algorithm has been implemented in the RBF networks created by the newrb function of MATLAB which uses gradient based iterative method as learning strategy, therefore the new network will undergo a hybrid learning process. The networks called Symmetry-based Fuzzy C-means Clustering–Radial Basis Function Network (SFCM/RBF) has been tested against the standard RBF network and the networks called standard Fuzzy C-means Clustering (FCM)-RBF network (FCM/RBF) in forecasting. The experimental models has been tested on three real world application problems, particularly in Air pollutant problem, Biochemical Oxygen Demand (BOD) problem, and Phytoplankton problem. Keywords: Fuzzy c-means clustering; SFCM; Radial basis function network; point symmetry distance; forecasting.

Naive Bayesian classifier (NBC) is a simple and effective classification model. However, the fact that the assumption of independence is often violated in reality makes it perform poorly on some datasets. In our pre-research, we attempt to improve the NBC model based on the strategy of the fuzzy feature selection. The main idea of the improvement strategy is to adjust the features' contribution to classification through the feature important factor (FIF) which describes the importance of the features. This strategy overcomes deficiencies caused by the assumption of independence. Based on the pre-research, we optimize the strategy of fuzzy feature selection with the establishment of the dual NBC model in order to improve the NBC model more. Through the experimental analysis on the UCI datasets, the strategy of the fuzzy feature selection on the dual NBC model is proved effective.

Multiple SVR based on ensemble learning could be enhanced from the viewpoint of the performance, but the performance of modeling closely depends on the initial condition of the partitioning method and they are easily affected by noise and outliers. In this study, a multi-linear fuzzy support vector regression (MFSVR) robust to noise is proposed with the aid of the composite kernel function and $\varepsilon $ -fuzzy c-means (FCM) clustering based on insensitive data information. Here insensitive data information stands for the interval data information of “$\varepsilon $ ” which stands for insensitive loss parameter used in the $\varepsilon $ - insensitive loss function. The objective of this study is to reduce the effect of noise and to alleviate the overfitting problem through the synergistic effect of the following methods: First, $\varepsilon $ -FCM clustering based on insensitive data information is used for considering more impact on decision boundary and reducing the effect of noise. Second, the composite kernel based on multiple linear kernel expression is proposed for implementing multi-linear decision boundary to alleviate overfitting problem. In more detail, each training data point is assigned with corresponding membership degrees in the $\varepsilon $ -FCM clustering. Some data which are potentially to be noise or outlier are assigned with lower membership degrees and given small contribution (compensation) considered in composite kernel function. Then, the composite kernel function for multiple local SVRs is constructed according to the distribution characteristics of $\varepsilon $ -FCM clustering. The proposed MFSVR is tested with both synthetic and UCI data sets in order to verify the effectiveness as well as efficient performance improvement. Experimental results demonstrate that the proposed method shows the better performance when compared to other some methods studied so far.

In the field of data processing and analysis, the dataset may be a large set of features that restrict data usability and applicability, and thus the dimensions of data sets need to be reduced. Feature selection is the process of removing as much of the redundant and irrelevant features as possible from the original dataset to improve the mining process efficiency. This paper presented a study to evaluate and compare the effect of filter and wrapper methods as feature selection approaches in terms of classification accuracy and time complexity. The Naive Bayes Classifier and three classification datasets from the UCI repository are utilizing in the classification procedure. To investigate the effect of feature selection methods, they are applied to the different characteristics datasets to obtain the selected feature vectors which are then classified according to each dataset category. The datasets used in this paper are the Iris, Ionosphere, and Ovarian Cancer dataset. Experimental results indicate that the filter and wrapper methods provide approximately equal classification accuracy where the average accuracy value of the Ionosphere and Ovarian Cancer dataset is 0.78 and 0.91 for the same selected feature vectors respectively. For Iris dataset, the filter method outperforms the wrapper method by achieving the same accuracy value using only half number of selected features. The results also show that the filter method surpasses when considering the execution time.

Naive Bayesian model has good classification accuracy and efficiency, which makes it show good performance in many fields, especially in data mining and artificial intelligence. However, the traditional Naive Bayesian classification model ignores the attributes’ independence, resulting in the reduction of classification accuracy. For this reason, an improved model based on attribute fusion and weighting(AWNBC) is proposed, in which data fusion is realized by Spearman coefficient and weighting is realized by average confidence and ReliefF coefficient. The experiment classifies the selected data in UCI database. The result of experiments show that the improved classification model has good classification accuracy and efficiency.