Showing papers in "Neural Computing and Applications in 2011"

Comparison on Zhang neural dynamics and gradient-based neural dynamics for online solution of nonlinear time-varying equation

Abstract: Different from gradient-based neural dynamics, a special kind of recurrent neural dynamics has recently been proposed by Zhang et al for solving online time-varying problems Such a recurrent neural dynamics is designed based on an indefinite error-monitoring function instead of a usually norm- or square-based energy function In addition, Zhang neural dynamics (ZND) are depicted generally in implicit dynamics, whereas gradient-based neural dynamics (GND) are associated with explicit dynamics In this paper, we generalize the ZND design method to solving online nonlinear time-varying equations in the form of f (x, t) = 0 For comparative purposes, the GND model is also employed for such time-varying equations’ solving Computer-simulation results via power-sigmoid activation functions substantiate the theoretical analysis and efficacy of the ZND model for solving online nonlinear time-varying equations

A novel Hash algorithm construction based on chaotic neural network

Abstract: An algorithm for constructing a one-way novel Hash function based on two-layer chaotic neural network structure is proposed. The piecewise linear chaotic map (PWLCM) is utilized as transfer function, and the 4-dimensional and one-way coupled map lattices (4D OWCML) is employed as key generator of the chaotic neural network. Theoretical analysis and computer simulation indicate that the proposed algorithm presents several interesting features, such as high message and key sensitivity, good statistical properties, collision resistance and secure against meet-in-the-middle attacks, which can satisfy the performance requirements of Hash function.

Privacy preserving Back-propagation neural network learning over arbitrarily partitioned data

Abstract: Neural networks have been an active research area for decades. However, privacy bothers many when the training dataset for the neural networks is distributed between two parties, which is quite common nowadays. Existing cryptographic approaches such as secure scalar product protocol provide a secure way for neural network learning when the training dataset is vertically partitioned. In this paper, we present a privacy preserving algorithm for the neural network learning when the dataset is arbitrarily partitioned between the two parties. We show that our algorithm is very secure and leaks no knowledge (except the final weights learned by both parties) about other party’s data. We demonstrate the efficiency of our algorithm by experiments on real world data.

Modeling, control, and stability analysis for time-delay TLP systems using the fuzzy Lyapunov method

Abstract: In this study, we present a Takagi–Sugeno (T–S) fuzzy model for the modeling and stability analysis of oceanic structures. We design a nonlinear fuzzy controller based on a parallel distributed compensation (PDC) scheme and reformulate the controller design problem as a linear matrix inequalities (LMI) problem as derived from the fuzzy Lyapunov theory. The robustness design technique is adopted so as to overcome the modeling errors for nonlinear time-delay systems subject to external oceanic waves. The vibration of the oceanic structure, i.e., the mechanical motion caused by the force of the waves, is discussed analytically based on fuzzy logic theory and a mathematical framework. The end result is decay in the amplitude of the surge motion affecting the time-delay tension leg platform (TLP) system. The feedback gain of the fuzzy controller needed to stabilize the TLP system can be found using the Matlab LMI toolbox. This proposed method of fuzzy control is applicable to practical TLP systems. The simulation results show that not only can the proposed method stabilize the systems but that the controller design is also simplified. The effects of the amplitude damping of the surge motion on the structural response are obvious and work as expected due to the control force.

Support vector regression with reduced training sets for air temperature prediction: a comparison with artificial neural networks

Abstract: Sudden changes in weather, in particular extreme temperatures, can result in increased energy expenditures, depleted agricultural resources, and even loss of life. However, these ill effects can be reduced with accurate air temperature predictions that provide adequate advance warning. Support vector regression (SVR) was applied to meteorological data collected across the state of Georgia in order to produce short-term air temperature predictions. A method was proposed for reducing the number of training patterns of massively large data sets that does not require lengthy pre-processing of the data. This method was demonstrated on two large data sets: one containing 300,000 cold-weather training patterns collected during the winter months and one containing 1.25 million training patterns collected throughout the year. These patterns were used to produce predictions from 1 to 12 h ahead. The mean absolute error (MAE) for the evaluation set of winter-only patterns ranged from 0.514°C for the 1-h prediction horizon to 2.303°C for the 12-h prediction horizon. For the evaluation set of year-round patterns, the MAE ranged from 0.513°C for the 1-h prediction horizon to 1.922°C for the 12-h prediction horizon. These results were competitive with previously developed artificial neural network (ANN) models that were trained on the full data sets. For the winter-only evaluation data, the SVR models were slightly more accurate than the ANN models for all twelve of the prediction horizons. For the year-round evaluation data, the SVR models were slightly more accurate than the ANN models for three of the twelve prediction horizons.

Comparison of new activation functions in neural network for forecasting financial time series

Abstract: In artificial neural networks (ANNs), the activation function most used in practice are the logistic sigmoid function and the hyperbolic tangent function. The activation functions used in ANNs have been said to play an important role in the convergence of the learning algorithms. In this paper, we evaluate the use of different activation functions and suggest the use of three new simple functions, complementary log-log, probit and log-log, as activation functions in order to improve the performance of neural networks. Financial time series were used to evaluate the performance of ANNs models using these new activation functions and to compare their performance with some activation functions existing in the literature. This evaluation is performed through two learning algorithms: conjugate gradient backpropagation with Fletcher–Reeves updates and Levenberg–Marquardt.

Bounded robust control of nonlinear systems using neural network–based HJB solution

Abstract: In this paper, a Hamilton–Jacobi–Bellman (HJB) equation–based optimal control algorithm for robust controller design is proposed for nonlinear systems The HJB equation is formulated using a suitable nonquadratic term in the performance functional to tackle constraints on the control input Utilizing the direct method of Lyapunov stability, the controller is shown to be optimal with respect to a cost functional, which includes penalty on the control effort and the maximum bound on system uncertainty The bounded controller requires the knowledge of the upper bound of system uncertainty In the proposed algorithm, neural network is used to approximate the solution of HJB equation using least squares method Proposed algorithm has been applied on the nonlinear system with matched and unmatched type system uncertainties and uncertainties in the input matrix Necessary theoretical and simulation results are presented to validate proposed algorithm

Metaheuristics for the feedforward artificial neural network (ANN) architecture optimization problem

Abstract: This article deals with evolutionary artificial neural network (ANN) and aims to propose a systematic and automated way to find out a proper network architecture To this, we adapt four metaheuristics to resolve the problem posed by the pursuit of optimum feedforward ANN architecture and introduced a new criteria to measure the ANN performance based on combination of training and generalization error Also, it is proposed a new method for estimating the computational complexity of the ANN architecture based on the number of neurons and epochs needed to train the network We implemented this approach in software and tested it for the problem of identification and estimation of pollution sources and for three separate benchmark data sets from UCI repository The results show the proposed computational approach gives better performance than a human specialist, while offering many advantages over similar approaches found in the literature

GA-based decoupled adaptive FSMC for nonlinear systems by a singular perturbation scheme

Abstract: Generally, the difficulty with multivariable system control is how to overcome the coupling effects for each degree of freedom. The computational burden and dynamic uncertainty of multivariable systems makes the model-based decoupling approach hard to implement in a real-time control system. In this study, an intelligent adaptive controller is proposed to handle these behaviors. The structure of these model-free new controllers is based on fuzzy systems for which the initial parameter vector values are found based on the genetic algorithm. One modified adaptive law is derived based on Lyapunov stability theory to control the system for tracking a user-defined reference model. The requirement of the Kalman–Yacubovich lemma is fulfilled. In addition, a non-square multivariable system can be decoupled into several isolated reduced-order square multivariable subsystems by using the singular perturbation scheme for different time-scale stability analysis. The adjustable parameters for the intelligent system can be initialized using a genetic algorithm. Novel online parameter tuning algorithms are developed based on the Lyapunov stability theory. A boundary-layer function is introduced into these updating laws to cover parameter and modeling errors and to guarantee that the state errors converge into a specified error bound. Finally, a numerical simulation is carried out to demonstrate the control methodology that can rapidly and efficiently control nonlinear multivariable systems.

Imbalanced classification using support vector machine ensemble

Abstract: Imbalanced data sets often have detrimental effects on the performance of a conventional support vector machine (SVM). To solve this problem, we adopt both strategies of modifying the data distribution and adjusting the classifier. Both minority and majority classes are resampled to increase the generalization ability. For minority class, an one-class support vector machine model combined with synthetic minority oversampling technique is used to oversample the support vector instances. For majority class, we propose a new method to decompose the majority class into clusters and remove two clusters using a distance measure to lessen the effect of outliers. The remaining clusters are used to build an SVM ensemble with the oversampled minority patterns, the SVM ensemble can achieve better performance by considering potentially suboptimal solutions. Experimental results on benchmark data sets are provided to illustrate the effectiveness of the proposed method.

A neural network proxy cache replacement strategy and its implementation in the Squid proxy server

Abstract: As the Internet has become a more central aspect for information technology, so have concerns with supplying enough bandwidth and serving web requests to end users in an appropriate time frame. Web caching was introduced in the 1990s to help decrease network traffic, lessen user perceived lag, and reduce loads on origin servers by storing copies of web objects on servers closer to end users as opposed to forwarding all requests to the origin servers. Since web caches have limited space, web caches must effectively decide which objects are worth caching or replacing for other objects. This problem is known as cache replacement. We used neural networks to solve this problem and proposed the Neural Network Proxy Cache Replacement (NNPCR) method. The goal of this research is to implement NNPCR in a real environment like Squid proxy server. In order to do so, we propose an improved strategy of NNPCR referred to as NNPCR-2. We show how the improved model can be trained with up to twelve times more data and gain a 5–10% increase in Correct Classification Ratio (CCR) than NNPCR. We implemented NNPCR-2 in Squid proxy server and compared it with four other cache replacement strategies. In this paper, we use 84 times more data than NNPCR was tested against and present exhaustive test results for NNPCR-2 with different trace files and neural network structures. Our results demonstrate that NNPCR-2 made important, balanced decisions in relation to the hit rate and byte hit rate; the two performance metrics most commonly used to measure the performance of web proxy caches.

Fuzzy wavelet neural network based on fuzzy clustering and gradient techniques for time series prediction

Abstract: This paper presents the development of fuzzy wavelet neural network system for time series prediction that combines the advantages of fuzzy systems and wavelet neural network The structure of fuzzy wavelet neural network (FWNN) is proposed, and its learning algorithm is derived The proposed network is constructed on the base of a set of TSK fuzzy rules that includes a wavelet function in the consequent part of each rule A fuzzy c-means clustering algorithm is implemented to generate the rules, that is the structure of FWNN prediction model, automatically, and the gradient-learning algorithm is used for parameter identification The use of fuzzy c-means clustering algorithm with the gradient algorithm allows to improve convergence of learning algorithm FWNN is used for modeling and prediction of complex time series and prediction of foreign-exchange rates Exchange rates are dynamic process that changes every day and have high-order nonlinearity The statistical data for the last 2 years are used for the development of FWNN prediction model Effectiveness of the proposed system is evaluated with the results obtained from the simulation of FWNN-based systems and with the comparative simulation results of previous related models

Vibration signal analysis for electrical fault detection of induction machine using neural networks

Abstract: Fault detection is desirable for increasing machinery availability, reducing consequential damage, and improving operational efficiency. Many of these faulty situations in three-phase induction motors originate from an electrical source. Vibration signal analysis is found to be sensitive to electrical faults. However, conventional methods require detailed information on motor design characteristics and cannot be applied effectively to vibration diagnosis because of their nonadaptability and the random nature of the vibration signals. This paper presents the development of an online electrical fault detection system that uses neural network modeling of induction motor in vibration spectra. The short-time Fourier transform is used to process the quasi-steady vibration signals for continuous spectra so that the neural network model can be trained. The electrical faults are detected from changes in the expectation of modeling errors. Experimental observations show that a robust and automatic electrical fault detection system is produced whose effectiveness is demonstrated while minimizing the triggering of false alarms due to power supply imbalance.

Hierarchical optimization of personalized experiences for e-Learning systems through evolutionary models

Abstract: Recent researches in e-Learning area highlight the need to define novel and advanced support mechanism for commercial and academic organizations in order to enhance the skills of employees and students and, consequently, to increase the overall competitiveness in the new economy world. This is due to the unbelievable velocity and volatility of modern knowledge that require novel learning methods which are able to offer additional support features as efficiency, task relevance and personalization. This paper tries to deal with these features by proposing an adaptive e-Learning framework based on Computational Intelligence methodologies by supporting e-Learning systems’ designers in two different aspects: (1) they represent the most suitable solution, able to support learning content and activities, personalized to specific needs and influenced by specific preferences of the learner and (2) they assist designers with computationally efficient methods to develop “in time” e-Learning environments. Our work attempts to achieve both results by exploiting an ontological representation of learning environment and a hierarchical memetic approach of optimization. In detail, our approach takes advantage of a collection of ontological models and processes for adapting an e-Learning system to the learner expectations by efficiently solving a well-defined optimization problem, through a hierarchical multi-cores memetic approach.

An incremental online semi-supervised active learning algorithm based on self-organizing incremental neural network

Abstract: An incremental online semi-supervised active learning algorithm, which is based on a self-organizing incremental neural network (SOINN), is proposed. This paper describes improvement of the two-layer SOINN to a single-layer SOINN to represent the topological structure of input data and to separate the generated nodes into different groups and subclusters. We then actively label some teacher nodes and use such teacher nodes to label all unlabeled nodes. The proposed method can learn from both labeled and unlabeled samples. It can query the labels of some important samples rather than selecting the labeled samples randomly. It requires neither prior knowledge, such as the number of nodes, nor the number of classes. It can automatically learn the number of nodes and teacher vectors required for a current task. Moreover, it can realize online incremental learning. Experiments using artificial data and real-world data show that the proposed method performs effectively and efficiently.

Affine-based registration of CT and MR modality images of human brain using multiresolution approaches: comparative study on genetic algorithm and particle swarm optimization

Abstract: We present a non-linear 2-D/2-D affine registration technique for MR and CT modality images of section of human brain. Automatic registration is achieved by maximization of a similarity metric, which is the correlation function of two images. The proposed method has been implemented by choosing a realistic, practical transformation and optimization techniques. Correlation-based similarity metric should be maximal when two images are perfectly aligned. Since similarity metric is a non-convex function and contains many local optima, choice of search strategy for optimization is important in registration problem. Many optimization schemes are existing, most of which are local and require a starting point. In present study we have implemented genetic algorithm and particle swarm optimization technique to overcome this problem. A comparative study shows the superiority and robustness of swarm methodology over genetic approach.

Neural network training based on FPGA with floating point number format and it’s performance

Abstract: In this paper, two-layered feed forward artificial neural network’s (ANN) training by back propagation and its implementation on FPGA (field programmable gate array) using floating point number format with different bit lengths are remarked based on EX-OR problem. In the study, being suitable with the parallel data-processing specification on ANN’s nature, it is especially ensured to realize ANN training operations parallel over FPGA. On the training, Virtex2vp30 chip of Xilinx FPGA family is used. The network created on FPGA is coded by using VHDL. By comparing the results to available literature, the technique developed here proved to consume less space for the subjected ANN training which has the same structure and bit length, it is shown to have better performance.

Data validation and missing data reconstruction using self-organizing map for water treatment

Abstract: Applications in the water treatment domain generally rely on complex sensors located at remote sites. The processing of the corresponding measurements for generating higher-level information such as optimization of coagulation dosing must therefore account for possible sensor failures and imperfect input data. In this paper, self-organizing map (SOM)-based methods are applied to multiparameter data validation and missing data reconstruction in a drinking water treatment. The SOM is a special kind of artificial neural networks that can be used for analysis and visualization of large high-dimensional data sets. It performs both in a nonlinear mapping from a high-dimensional data space to a low-dimensional space aiming to preserve the most important topological and metric relationships of the original data elements and, thus, inherently clusters the data. Combining the SOM results with those obtained by a fuzzy technique that uses marginal adequacy concept to identify the functional states (normal or abnormal), the SOM performances of validation and reconstruction process are tested successfully on the experimental data stemming from a coagulation process involved in drinking water treatment.

Adaptive Lyapunov-based neural network sensorless control of permanent magnet synchronous machines

Abstract: In this paper, an adaptive neural network sensorless control scheme is introduced for permanent magnet synchronous machines (PMSMs). The control strategy consists of an adaptive speed controller that capitalizes on the machine’s inverse model to achieve accurate tracking, two artificial neural networks (ANNs) for currents control, and an ANN-based observer for speed estimation to overcome the drawback associated with the use of mechanical sensors while the rotor position is obtained by the estimated rotor speed direct integration to reduce the effect of the system noise. A Lyapunov stability-based ANN learning technique is also proposed to insure the ANNs’ convergence and stability. Unlike other sensorless control strategies, no a priori offline training, weights initialization, voltage transducer, or mechanical parameters knowledge is required. Results for different situations highlight the performance of the proposed controller in transient, steady-state, and standstill conditions.

Credit rating modelling by kernel-based approaches with supervised and semi-supervised learning

Abstract: This paper presents the modelling possibilities of kernel-based approaches to a complex real-world problem, i.e. corporate and municipal credit rating classification. Based on a model design that includes data pre-processing, the labelling of individual parameter vectors using expert knowledge, the design of various support vector machines with supervised learning as well as kernel-based approaches with semi-supervised learning, this modelling is undertaken in order to classify objects into rating classes. The results show that the rating classes assigned to bond issuers can be classified with high classification accuracy using a limited subset of input variables. This holds true for kernel-based approaches with both supervised and semi-supervised learning.

Stability analysis for delayed genetic regulatory networks with reaction--diffusion terms

Abstract: This paper deals with the problem of asymptotic stability for delayed genetic regulatory networks with reaction--diffusion terms. For three types of boundary conditions, delay-dependent criteria are established by the Lyapunov--Krasovskii functional approach, respectively. The obtained results are expressed in terms of linear matrix inequalities. Numerical examples illustrating the effectiveness of the proposed approach are provided.

Parallel Hash function construction based on chaotic maps with changeable parameters

Abstract: A parallel Hash algorithm construction based on chaotic maps with changeable parameters is proposed and analyzed in this paper. The two main characteristics of the proposed algorithm are parallel processing mode and message expansion. The algorithm translates the expanded message blocks into the corresponding ASCII code values as the iteration times, iterates the chaotic asymmetric tent map and then the chaotic piecewise linear map, continuously, with changeable parameters dynamically obtained from the position index of the corresponding message blocks, to generate decimal fractions, then rounds the decimal fractions to integers, and finally cascades these integers to construct intermediate Hash value. Final Hash value with the length of 128-bit is generated by logical XOR operation of intermediate Hash values. Theoretical analysis and computer simulation indicate that the proposed algorithm satisfies the performance requirements of a secure Hash function.

Artificial neural network to predict the effect of heat treatments on Vickers microhardness of low-carbon Nb microalloyed steels

Abstract: In the present study, an artificial neural networks-based model (ANNs) was developed to predict the Vickers microhardness of low-carbon Nb microalloyed steels Fourteen parameters affecting the Vickers microhardness were considered as inputs, including the austenitizing temperature, cooling rate, initial austenite grain size, different chemical compositions and Nb in solution The network was then trained to predict the Vickers microhardness amounts as outputs A Multilayer feed-forward back-propagation network was developed and trained using experimental data form literatures Five low-carbon Nb microalloyed steels and one low-carbon steel without Nb were investigated The effects of austenitizing temperature (900–1,100°C) and subsequent cooling rate (015–227°C/s) and initial austenite grain size (5–130 μm) on the Vickers microhardness of steels were modeled by ANNs as well The predicted values are in very good agreement with the measured ones, indicating that the developed model is very accurate and has the great ability for predicting the Vickers microhardness

Model reduction and optimization of reactive batch distillation based on the adaptive neuro-fuzzy inference system and differential evolution

Abstract: This paper considers the application of the adaptive neuro-fuzzy inference system (ANFIS) instead of the highly nonlinear model of a reactive batch distillation column for optimization. The architecture has been developed for fuzzy modeling that learns information from a data set, in order to compute the membership function and rule base in accordance with the given input–output data. In this work, the differential evolution algorithm has been employed for optimization of operation policy of reactive batch distillation for producing ethyl acetate. In optimization, minimal batch time and high purity of product are considered, and reflux ratio and final batch time are taken as decision parameters. The results show that the reduced model (ANFIS) is able to properly create a robust model of the reactive batch distillation, and CPU use is reduced to 1/18,000 of that of a real mathematical model. The highest yield and mole fraction of ethyl acetate were achieved through the use of the obtained optimization policy.

n -Fold obstinate filters in BL -algebras

Abstract: In this paper, we introduced the notion of n-fold obstinate filter in BL-algebras and we stated and proved some theorems, which determine the relationship between this notion and other types of n-fold filters in a BL-algebra. We proved that if F is a 1-fold obstinate filter, then A/F is a Boolean algebra. Several characterizations of n-fold fantastic filters are given, and we show that A is a n-fold fantastic BL-algebra if A is a MV-algebra (n ≥ 1) and A is a 1-fold positive implicative BL-algebra if A is a Boolean algebra. Finally, we construct some algorithms for studying the structure of the finite BL-algebras and n-fold filters in finite BL-algebras.

Functional modeling of astrocytes in epilepsy: a feedback system perspective

Abstract: Astrocytes, a subtype of glial cells, in the brain provide structural and metabolic supports to the nervous system. They are also active partners in synaptic transmission and neuronal activities. In the present study, a biologically plausible thalamocortical neural population model (TCM) originally proposed by Suffczynski et al. (Neuroscience 126(2):467–484, 2004) is extended by integrating the functional role of astrocytes in the regulation of synaptic transmission. Therefore, the original TCM is modified to consider neuron-astrocyte interactions. Using the modified model, it is demonstrated that the healthy astrocytes are capable to compensate the variation of cortical excitatory input by increasing their firing frequency. In this way, they can preserve the attractor corresponding to the normal activity. Furthermore, the performance of the pathological astrocytes is also investigated. It is hypothesized that one of the plausible causes of seizures is the malfunction of astrocytes in the regulatory feedback loop. That is, pathologic astrocytes are not any more able to regulate and/or compensate the excessive increase of the cortical input. Therefore, pathologic astrocytes lead to the emergence of paroxysmal attractor. Results demonstrate that disruption of the homeostatic or signaling function of astrocytes can initiate the synchronous firing of neurons, suggesting that astrocytes might be one of the potential targets for the treatment of epilepsy.

Research of neural network algorithm based on factor analysis and cluster analysis

Abstract: Aiming at the large sample with high feature dimension, this paper proposes a back-propagation (BP) neural network algorithm based on factor analysis (FA) and cluster analysis (CA), which is combined with the principles of FA and CA, and the architecture of BP neural network. The new algorithm reduces the feature dimensionality of the initial data through FA to simplify the network architecture; then divides the samples into different sub-categories through CA, trains the network so as to improve the adaptability of the network. In application, it is first to classify the new samples, then using the corresponding network to predict. By an experiment, the new algorithm is significantly improved at the aspect of its prediction precision. In order to test and verify the validity of the new algorithm, we compare it with BP algorithms based on FA and CA.

Self-organizing map artificial neural network application in multidimensional soil data analysis

Abstract: Because of the complex nonlinear relationships between soil variables and their multivariable aspects, classical analytic, deterministic, or linear statistical methods are unreliable and cause difficulty to present or visualize the results. Using intelligent techniques, which have ability to analyze the multidimensional soil data with an intricate visualization technique, is crucial for nutrient and water management in soil, consequently, for sustainable agriculture and groundwater management. In this study, first, the Kohonen self-organizing feature maps (KSOFM) neural network was applied to analyze the effects of soil physical properties on soil chemical/hydraulic processes, and to diagnose the inter-relationships of the multivariable soil data in vadose zone. The inter-relationships among the soil variables were extracted and interpreted using the pattern analysis visualized in component planes. Then K-means clustering algorithm was used to determine the optimal number of clusters by using the Silhouette clustering validity index, resulting in six clusters or groups for soil variables. In conclusion, the KSOFM technique is an effective tool for analyzing and diagnosing the dynamics in soil and extracting information from the multidimensional soil data. These results suggest that this technique has a potential to monitor and diagnose not only soil physical/chemical/hydraulic processes, but also soil morphological and microbiological processes.

Gene selection using independent variable group analysis for tumor classification

Abstract: Microarrays are capable of detecting the expression levels of thousands of genes simultaneously. So, gene expression data from DNA microarray are characterized by many measured variables (genes) on only a few samples. One important application of gene expression data is to classify the samples. In statistical terms, the very large number of predictors or variables compared to small number of samples makes most of classical “class prediction” methods unemployable. Generally, this problem can be avoided by selecting only the relevant features or extracting new features containing the maximal information about the class label from the original data. In this paper, a new method for gene selection based on independent variable group analysis is proposed. In this method, we first used t-statistics method to select a part of genes from the original data. Then, we selected the key genes from the selected genes for tumor classification using IVGA. Finally, we used SVM to classify tumors based on the key genes selected using IVGA. To validate the efficiency, the proposed method is applied to classify three different DNA microarray data sets. The prediction results show that our method is efficient and feasible.

Clustering of entropy topography in epileptic electroencephalography

Abstract: Epileptic seizures have been considered sudden and unpredictable events for centuries. A seizure seems to occur when a massive group of neurons in the cerebral cortex begins to discharge in a highly organized rhythmic pattern, then it develops according to some poorly described dynamics. As proved by the results reported by different research groups, seizures appear not completely random and unpredictable events. Thus, it is reasonable to wonder when, where and why the epileptogenic processes start up in the brain and how they result in a seizure. In order to detect these phenomena from the very beginning (hopefully minutes before the seizure itself), we introduced a technique, based on entropy topography, that studies the synchronization of the electric activity of neuronal sources in the brain. We tested it over 3 EEG data set from patients affected by partial epilepsy and 25 EEG recordings from patients affected by generalized seizures as well as over 40 recordings from healthy subjects. Entropy showed a very steady spatial distribution and appeared linked to the brain zone where seizures originated. A self-organizing map-based spatial clustering of entropy topography showed that the critical electrodes shared the same cluster long time before the seizure onset. The healthy subjects showed a more random behaviour.