This paper presents the results of Persian handwritten word recognition based on MIXTURE of EXPERTS technique. In the basic form of ME the problem space is automatically divided into several subspaces for the EXPERTS, and the outputs of EXPERTS are combined by a gating network. In our proposed model, we used MIXTURE of EXPERTS Multi Layered Perceptrons with Momentum term in the classification Phase. Applying this term makes three effects in our system: a) increase convergence rate, b) obtain the optimum performance in our system, c) and escape from the local minima on the error surface. We produce three different MIXTURE of EXPERTS structure. Experimental result for proposed method show an error rate reduction of 6.42% compare to the MIXTURE of MLPs EXPERTS. Comparison with some of the most related methods indicates that the proposed model yields excellent recognition rate in handwritten word recognition.

Forecasting in financial markets has always been of intereste for researchers and investors. In particular, forecasting the market indexes is of major importance. Index forecasting methods in financial markets have been developed along with the development of time series models. In this paper a specific model for forecasting Tehran exchange price index was proposed based on MIXTURE of EXPERTS. The results confirmed the high performance of the proposed model in modeling and forecasting Tehran exchange price index time series.

This paper proposed a new method for face recognition with principal component analysis in the feature extraction phase, and devised a modified version of MIXTURE of EXPERTS in which each expert is an MLP, instead of linear networks in order to improve the performance of the expert networks, and consequently the whole network performance; Therewith, we use a Momentum term in training the MLP EXPERTS, which speeds up the adjustment of weight greatly. We explore three different MIXTURE of EXPERTS constructing a neural network. Our proposed model, achieved a correct recognition rate on Yale and ORL datasets. Comparisons with other algorithms demonstrate that our method performs better in terms of higher recognition rate, with smaller number of epochs in human face recognition.

EEG is one of the most important and common sources for study of brain function and neurological disorders. Automated systems are under study for many years to detect EEG changes. Because of the importance of making correct decision, we are looking for better classification methods for EEG signals. In this paper a smart compound system is used for classifying EEG signals to different groups. Since in each classification the system accuracy of making decision is very important, in this study we look for some methods to improve the accuracy of EEG signals classification. In this paper the use of MIXTURE of EXPERTS for improving the EEG signals classification of normal subjects and patients with epilepsy is shown and the classification accuracy is evaluated. Decision making was performed in two stages: 1) feature extractions with different methods of eigenvector and 2) Classification using the classifier trained by extracted features. This smart system inputs are formed from composites features that are selected appropriate with network structure. In this study tree methods based on eigenvectors (Minimum Norm, MUSIC, Pisarenko) are chosen for the estimation of Power Spectral Density (PSD). After the implementation of ME and train it on composite features, we propose that this technique can reach high classification accuracy. Hence, EEG signals classification of epilepsy patients in different situations and control subjects is available. In this study, MIXTURE of EXPERTS structure was used for EEG signals classification. Proper performance of Neural Network depends on the size of train and test data. Combination of multiple Neural Networks even without using the probable structure in obtaining weights in classification problem can produce high accuracy in less time, which is important and valuable in the classification point of view.

Sudden Cardiac Death (SCD) is caused by loss of heart function which ultimately stops heart from pumping blood throughout the body and therefore, claims the patient’s life within few minutes. Once detected, sudden cardiac deaths could substantially decrease through applying medical procedures or instrumentations such as defibrillators. Nonetheless, effective approaches to SCD prediction, based on which doctors can make informed decisions, are yet to be discovered. This research aims to propose a novel approach to local feature selection with the assistance of the most accurate methodologies, which have formerly been developed in previous works of this team, for extracting features from nonlinear, time-frequency and classic processes. Furthermore, taking into consideration the existence of different features from different areas, the MIXTURE of EXPERTS is put forward as a means of classification. The suggested methods enable us to select features that differ from one another in each minute before the incidence through the agency of optimal feature selection in each one-minute period of the signal. Not only will this facilitate increasing the prediction time from 4 minutes to 12 with a high level of accuracy, but it also will provide us with an opportunity to interpret clinical signs considering the plurality of features in each minute. Additionally, applying the MIXTURE of EXPERTS classification proceeds to ensure a precise decision-making on the output of different areas processes. The results indicate to the superiority of the proposed method to those mentioned in similar studies.

This paper presents a new classification framework for Iranian license plate character recognition. In this framework, a set of robust features are calculated from license plate characters based on directional projections, kirsch edge detector and local means. The characters are then classified using MIXTURE of EXPERTS which use the multilayer Perceptrons (MLPs) as expert and gating networks. The proposed recognition algorithm is evaluated on a database of Iranian license plate characters consisting of 14256 binary images, and the recognition rate of 99.42% is achieved. The proposed algorithm yields better performance of the Iranian license plate character recognition in comparison with conventional methods which use a single MLP neural network.

Background: Macular disorders, such as diabetic macular edema (DME) and age-related macular degeneration (AMD) are among the major ocular diseases. Having one of these diseases can lead to vision impairments or even permanent blindness in a not-so-long time span. So, the early diagnosis of these diseases are the main goals for researchers in the field. Methods: This study is designed in order to present a comparative analysis on the recent convolutional MIXTURE of EXPERTS (CMoE) models for distinguishing normal macular OCT from DME and AMD. For this purpose, we considered three recent CMoE models called MIXTURE ensemble of convolutional neural networks (ME-CNN), Multiscale Convolutional MIXTURE of EXPERTS (MCME), and Wavelet-based Convolutional MIXTURE of EXPERTS (WCME) models. For this research study, the models were evaluated on a database of three different macular OCT sets. Two first OCT sets were acquired by Heidelberg imaging systems consisting of 148 and 45 subjects respectively and set3 was constituted of 384 Bioptigen OCT acquisitions. To provide better performance insight into the CMoE ensembles, we extensively analyzed the models based on the 5-fold cross-validation method and various classification measures such as precision and average area under the ROC curve (AUC). Results: Experimental evaluations showed that the MCME and WCME outperformed the ME-CNN model and presented overall precisions of 98. 14% and 96. 06% for aligned OCTs respectively. For non-aligned retinal OCTs, these values were 93. 95% and 95. 56%. Conclusion: Based on the comparative analysis, although the MCME model outperformed the other CMoE models in the analysis of aligned retinal OCTs, the WCME offers a robust model for diagnosis of non-aligned retinal OCTs. This allows having a fast and robust computer-aided system in macular OCT imaging which does not rely on the routine computerized processes such as denoising, segmentation of retinal layers, and also retinal layers alignment.

Ensemble learning is an effective machine learning method that improves the classification performance. In this method, the outputs of multiple classifiers are combined so that the better results can be attained. As different classifiers may offer complementary information about the classification, combining classifiers, in an efficient way, can achieve better results than any single classifier. Combining multiple classifiers is only effective if the individual classifiers are accurate and diverse. In this paper, we propose a two-stage method for classifiers combination. In the first stage, by MIXTURE of expert’s strategy we produce different classifiers and in the second stage by using particle swarm optimization (PSO), we find the optimal weights for linear combination of them. Experimental results on different data sets show that proposed method outperforms the independent training and MIXTURE of expert’s methods.

Negative Correlation Learning (NCL) and MIXTURE of EXPERTS (ME), two popular combining methods, each employ different special error functions for the simultaneous training of NN EXPERTS to produce negatively correlated NN EXPERTS. In this paper, we review the properties of the NCL and ME methods, discussing their advantages and disadvantages. Characterization of both methods showed that they have different but complementary features, so if a hybrid system can be designed to include features of both NCL and ME, it may be better than each of its basis approaches. In this study, an approach is proposed to combine the features of both methods, i.e., MIXTURE of Negatively Correlated EXPERTS (MNCE). In this approach, the capability of a control parameter for NCL is incorporated in the error function of ME, which enables the training algorithm of ME to establish better balance in bias-variance-covariance trade-offs. The proposed hybrid ensemble methods, MNCE, are compared with their constituent methods, ME and NCL, in solving several benchmark problems. The experimental results show that our proposed method preserve the advantages and alleviate the disadvantages of their basis approaches, offering significantly improved performance over the original methods.