One efficient approach in classification is using a set of individual classifiers and then combining their outputs, usually knows as ensemble classification or multiple classifier system. In this paper, an ensemble classification system based on the random subspace approach is employed for diagnosis of endometriosis, in which individual classifiers of the ensemble system are trained with different feature subsets. Finally, for classifying an unknown test sample, classifiers’ outputs are fused using the majority voting combination rule.

Regarding to the limitations and benefits of remote sensing sensors، fusion of remote sensing data from multiple sensors is effective at land cover classification. All these data have different characteristics، e. g.، different spatial and spectral resolutions، different angle of view، and different abilities and disabilities. For many applications، the information provided by individual sensors is incomplete، inconsistent، or imprecise. Fusion of information from different sensors can produce a better understanding of the observed site، which is not possible with single sensor. Particularly، Light Detection And Ranging (LiDAR) provides accurate height information for objects on the earth، which makes LiDAR become more and more popular in terrain and land surveying. On the other hand، hyperspectral imaging is a relatively new technique in remote sensing that acquires hundreds of images corresponding to different spectral channels. The rich spectral information of HS data increases the capability to distinguish different physical materials، leading to the potential of a more accurate image classification. As hyperspectral and LIDAR data provide complementary information (spectral reflectance، and vertical structure، respectively)، a promising and challenging approach is to fuse these data in the information extraction procedure. This paper presents a multiple fuzzy classifier system (Multiple Classifier System or MCS) for fusions of hyperspectral and LiDAR data based on Decision Template (DT). After feature extraction on each data، the classification was performed by fuzzy K-Nearest Neighbor (KNN) on hyperspectral and LiDAR data separately. In a multiple fuzzy decision system، a set of decisions is first produced and then combined by a specific fusion method. The output of the fuzzy classifiers that provide the class belongingness of an input pattern to different classes is arranged in a matrix form defined as decision profile (DP) matrix. Then، a fuzzy decision fusion method (Decision Tempate) is utilized to fuse the results of fuzzy KNNs on hyperspectral and LiDAR data. In order to assess the fuzzy MCS proposed method، a crisp MCS based on (Support Vector Machine) SVM as crisp classifier and Naive Bayes (NB) as crisp classifier fusion method is applied on hyperspectral and LiDAR data. The experiments were executed on a hyperspectral image and a LiDAR derived Digital Surface Model (DSM); both with spatial resolution of 2. 5 m. The dataset have captured over the University of Houston campus and the neighbouring urban area by the NSF-funded Centre for Airborne Laser Mapping (NCALM). Also hyperspectral image has 144 spectral bands in 380 nm to 1050 nm region. Training and testing samples were selected from different areas of the images. They are spatially disjointed. Fuzzy MCS on hyperspectral and LiDAR data provide interesting conclusions on the effectiveness and potentialities of the joint use of these two data. Overall accuracies of fuzzy classifiers on LiDAR and hyperspectral data are %75 and %88 respectively. Fusion of these two fuzzy classifiers produced %96 as overall accuracy. Second scenario for joint use of hyperspectral and LiDAR data is fusion of these two data through a crisp decision fusion system. The results show that fuzzy classifier provided higher accuracies than crisp classification based on SVM for both data. In the presence of mixed coverage pixels in remote sensing data، crisp classifiers may produce errors while fuzzy classifiers are not affected by such errors and in principle can produce a classification that is more accurate than any crisp classifier. Also، fusion of ensemble of fuzzy classifiers based on Decision Template method produced more accuracy than fusion of crisp SVMs based on Bayesian Theory.

An emerging technique to improve classification performance is to build several different classifiers, and then to combine them, known as multiple classifier systems or ensemble classification systems. The design process of an ensemble system generally involves two steps: the collection of an ensemble of classifiers and the design of the combination rule. Researchers in various fields including pattern recognition, machine learning and statistics have examined the use of ensemble systems. Nabavi-Kerizi and Kabir provided a review of ensemble classification, where combining techniques have been mainly considered. However, the trend of recent papers in this active field shows that the ensemble systems have focused on different ways to design the ensemble of classifiers. In this paper, first we aim to establish a framework for different approaches. Based on this architecture, each approach has been introduced in details. Combination methods are then described in brief. At the end, active research areas in the field of ensemble learning are presented.

This paper presents a new framework based on modified EMD method for detection of single and multiple PQ issues. In modified EMD, DWT precedes traditional EMD process. This scheme makes EMD better by eliminating the mode mixing problem. This is a two step algorithm; in the first step, input PQ signal is decomposed in low and high frequency components using DWT. In the second stage, the low frequency component is further processed with EMD technique to get IMFs. Eight features are extracted from IMFs of low frequency component. Unlike low frequency component, features are directly extracted from the high frequency component. All these features form feature vector which is fed to PNN classifier for classification of PQ issues. For comparative analysis of performance of PNN, results are compared with SVM classifier. Moreover, performance of proposed methodology is also validated with noisy PQ signals. PNN has outperformed SVM for both noiseless and noisy PQ signals.

Introduction: Classification and prediction are two most important applications of statistical methods in the field of medicine. According to this note that the classical classification are provided due to the clinical symptom and do not involve the use of specialized information and knowledge. Therefore, using a classifier that can combine all this information, is necessary. The aim of this study was to design a decision support system for classification of thyroid disorder using fuzzy if and then classifier. Materials and Methods: The data consisted of 310 patients, including 105 healthy people, 150 hypothyroidisms and 55 hyperthyroidisms, who referred to Shahid Beheshti Hospital and Imam Khomeini Clinic of Hamadan (Iran) in order to investigate the status of their thyroid disease. In this fuzzy system variable including age and BMI, as well as laboratory tests such as TSH, T4, and T3, the score of hyperthyroid and hypothyroid symptoms used as input and the output variable includes individual health status. The max-min Mamdani inference system along with center of gravity deffizifier have been used in the fuzzy toolbox of MATLAB software. Results: The fuzzy rule-based classification model had a great performance for predicting thyroid disorder in the both test and train sets. Conclusion: Fuzzy rules-based classifier by using overlapping sets, had a high potential for managing the uncertainty associated with medical diagnosis. Also, by enabling the use of linguistic variables in the decision making process and design, the interpretation of the results has improved for doctors who are not familiar with modeling concepts.

In the present article, an improved Learning Classifier System (LCS) is proposed to control the balance of a moving unmanned bicycle. A significant characteristic of learning classifier systems is that they can learn through a set of system actions in the real world (similar to intelligent creatures) while no dynamic model of the system is needed. Contrary to studies reported in the literature where action domain of the controller is discrete and accordingly such controller cannot be used in real world applications, in the present study efficacy of the classifier system is enhanced by definition of continuous domain for the outputs, and then is used to control the balance of unmanned bicycle. A scheme based upon fuzzy membership functions is proposed which makes it possible for the domain of actions to be continuous. The proposed LCS features a dynamic reward assignment mechanism which is invented to cope with the bicycle’s delayed response due to its mass inertias. This allows the rapid calculation of the reward and hence enables the controller to be used in such real time applications as the balance control of unmanned vehicles. A standard 2 degree of freedom (2-DOF) bicycle model is employed to demonstrate the efficiency of the enhanced LCS. Simulation results show that the proposed classifier system outperforms traditional classifier system as well as some of the more common balance-control strategies reported in the literature.

Background: Multiple Sclerosis (MS) is the most frequent non-traumatic neurological disease capable of causing disability in young adults. Detection of MS lesions with Magnetic Resonance Imaging (MRI) is the most common technique. However, manual interpretation of vast amounts of data is often tedious and error-prone. Furthermore, changes in lesions are often subtle and extremely unrepresentative. Objectives: To develop an automated non-subjective method for the detection and quantification of MS lesions. Materials & Methods: This paper focuses on the automatic detection and classification of MS lesions in brain MRI images. Two datasets, one simulated and the other one recorded in hospital, are utilized in this work. A novel hybrid algorithm combining image processing and machine learning techniques is implemented. To this end, first, intricate morphological patterns are extracted from MRI images via texture analysis. Then, statistical textures-based features are extracted. Afterward, two supervised machine learning algorithms, i. e., the Hidden Markov Model (HMM) and Adaptive Neuro-Fuzzy Inference System (ANFIS) are employed within a hybrid platform. The hybrid system makes decisions based on ensemble learning. The stacking technique is used to apply predictions from both models o train a perceptron as a decisive model. Results: Experimental results on both datasets indicate that the proposed hybrid method outperforms HMM and ANFIS classifiers with reducing false positives. Furthermore, the performance of the proposed method compared with the state-of-the-art methods, was approved. Conclusion: Remarkable results of the proposed method motivate advanced detection systems employing other MRI sequences and their combination.

Optical and polarimetric synthetic aperture radar (PolSAR) earth observations offer valuable sources of information for agricultural applications and crop mapping. Various spectral features، vegetation indices and textural indicators can be extracted from optical data. These features contain information about the reflectance and spatial arrangement of crop types. By contrast، PolSAR data provide quad-polarization backscattering observations and target decompositions، which give information about the structural properties and scattering mechanisms of different crop types. Combining these two sources of information can present a complementary data set with a significant number of spectral، textural، and polarimetric features for crop mapping and monitoring. Moreover، a temporal combination of both observations may lead to obtaining more reliable results compared to the use of single-time observations. However، there are several challenges in cropland classification using this large amount of information. The first challenge is the possibility correlation among some optical features or radar features which leads to redundant features. Moreover، some optical or radar features may have a low relevancy with some or all crop types. These two challenges cause to increase complexity and computational load of classification. In addition، when the ratio of number of samples to the number of features is very low، the curse of dimensionality may be occur. Another challenge of classification is the imbalanced distribution among various crop types، the so called imbalanced data. Various classifier have been presented for cropland classification from optical and radar data. Among these classifiers، the multiple classifier systems (MCS) especially the random forest (RF). The main aim of this paper is an alternative to RF which is able to solve these two challenges، the curse of dimensionality and the imbalanced data، simultaneously. The proposed MCSs have other modifications in feature selection and fusion steps of RF. These two methods called as balanced filter forest (BFF) and cost-sensitive filter forest (CFF). The study area of this paper was the southwest district of Winnipeg، Manitoba، Canada، which is covered by various annual crops. The data used in this paper were bi-temporal optical and radar images acquired by RapidEye satellites and the UAVSAR system. RapidEye is a spaceborne satellite، which has five spectral channels: blue (B)، green (G)، red (R)، NIR and RE. In this paper، two optical images were collected on 5 and 14 July 2012. Both these images were orthorectified on the local North American 1983 datum (NAD-83) with a spatial resolution of about 5 m. The UAVSAR sensor is an airborne SAR sensor، which operates in the L-band frequency in full polarization mode (i. e.، HH، HV، VH and VV). The radar images used in this paper were simultaneously acquired with the optical images. They were orthorectified on the World Geodetic System 1984 datum (WGS-84) with an SRTM3 digital elevation model. They were also multilooked by 2 pixels in azimuth and 3 pixels in range directions. Moreover، the de-speckling process، using a 5 × 5 boxcar filter، was applied to the data in order to alleviate the speckle effect. The spatial resolution of these images was then approximately 15 m. The results indicated that the proposed methods could increase the overall accuracy to 10% and the speediness to 6 times more than the classical RF method.