24 results for Kasabov, N, Conference paper

WDNRBF: weighted data normalization for radial basic function type neural networks
Song, Q.; Kasabov, N (20090527T22:18:49Z)
Conference paper
Auckland University of TechnologyThis paper introduces an approach of Weighted Data Normalization (WDN) for Radial Basis Function (RBF) type of neural networks. It presents also applications for medical decision support systems. The WDN method optimizes the data normalization ranges for the input variables of the neural network. A steepest descent algorithm (BP) is used for the WDNRBF learning. The derived weights have the meaning of feature importance and can be used to select a minimum set of variables (features) that can optimize the performance of the RBF network model. The WDNRBF is illustrated on two case study prediction/identification problems. The first one is prediction of the MackeyGlass time series and the second one is a real medical decision support problem of estimating the level of renal functions in patients. The method can be applied to other distancebased, prototype learning neural network models.
View record details 
Gene trajectory clustering with a hybrid genetic algorithm and expectation maximization method
Chan, Z.; Kasabov, N (20090527T22:18:54Z)
Conference paper
Auckland University of TechnologyClustering time course gene expression data (gene trajectories) is an important step towards solving the complex problem of gene regulatory network (GRN) modeling and discovery as it significantly reduces the dimensionality of the gene space required for analysis. This paper introduces a novel method that hybridizes Genetic Algorithm (GA) and Expectation Maximization algorithms (EM) for clustering with the mixtures of Multiple Linear Regression models (MLRs). The proposed method is applied to cluster gene expression time course data into smaller number of classes based on their trajectory similarities. Its performance and application as a generic clustering method to other complex problems are discussed.
View record details 
Bioinformatics: a knowledge engineering approach
Kasabov, N (20090527T22:18:54Z)
Conference paper
Auckland University of TechnologyThe paper introduces the knowledge engineering (KE) approach for the modeling and the discovery of new knowledge in bioinformatics. This approach extends the machine learning approach with various rule extraction and other knowledge representation procedures. Examples of the KE approach, and especially of one of the recently developed techniques  evolving connectionist systems (ECOS), to challenging problems in bioinformatics are given, that include: DNA sequence analysis, microarray gene expression profiling, protein structure prediction, finding gene regulatory networks, medical prognostic systems, computational neurogenetic modeling.
View record details 
Transductive modeling with GA parameter optimization
Mohan, N.; Kasabov, N (20090527T22:18:53Z)
Conference paper
Auckland University of TechnologyIntroduction  While inductive modeling is used to develop a model (function) from data of the whole problem space and then to recall it on new data, transductive modeling is concerned with the creation of single model for every new input vector based on some closest vectors from the existing problem space. The model approximates the output value only for this input vector. However, deciding on the appropriate distance measure, on the number of nearest neighbors and on a minimum set of important features/variables is a challenge and is usually based on prior knowledge or exhaustive trial and test experiments. This paper proposes a Genetic Algorithm (GA) approach for optimizing these three factors. The method is tested on several datasets from UCI repository for classification tasks and results show that it outperforms conventional approaches. The drawback of this approach is the computational time complexity due to the presence of GA, which can be overcome using parallel computer systems due to the intrinsic parallel nature of the algorithm. © 2005 IEEE.
View record details 
Evolutionary Computation for Dynamic Parameter Optimisation of Evolving Connectionist Systems for Online Prediction of Time Series with Changing Dynamics
Kasabov, N; Song, Q.; Nishikawa, I. (20090527T22:18:48Z)
Conference paper
Auckland University of TechnologyThe paper describes a method of using evolutionary computation technique for parameter optimisation of evolving connectionist systems (ECOS) that operate in an online, lifelong learning mode. ECOS evolve their structure and functionality from an incoming stream of data in either a supervised, or/and in an unsupervised mode. The algorithm is illustrated on a case study of predicting a chaotic timeseries that changes its dynamics over time. With the online parameter optimisation of ECOS, a faster adaptation and a better prediction is achieved. The method is practically applicable for real time applications.
View record details 
Computational neurogenetic modelling: gene networks within neural networks
Kasabov, N; Benuskova, L.; Gomes Wysoski, S. (20090527T22:18:56Z)
Conference paper
Auckland University of TechnologyThis paper introduces a novel connectionist approach to neural network modelling that integrates dynamic gene networks within neurons with a neural network model. Interaction of genes in neurons affects the dynamics of the whole neural network. Through tuning the gene interaction network and the initial gene/protein expression values, different states of the neural network operation can be achieved. A generic computational neurogenetic model is introduced that implements this approach. It is illustrated by means of a simple neurogenetic model of a spiking neural network (SNN). Functioning of the SNN can be evaluated for instance by the field potentials, thus making it possible to attempt modelling the role of genes in different brain states such as epilepsy, schizophrenia, and other states, where EEG data is available to test the model predictions.
View record details 
Inductive vs transductive inference, global vs local models: SVM, TSVM, and SVMT for gene expression classification problems
Pang, S.; Kasabov, N (20090527T22:18:57Z)
Conference paper
Auckland University of TechnologyThis paper compares inductive, versus transductive modeling, and also global, versus local models with the use of SVM for gene expression classification problems. SVM are used in their three variants  inductive SVM, transductive SVM (TSVM), and SVM tree (SVMT) the last two techniques being recently introduced by the authors. The problem of gene expression classification is used for illustration and four benchmark data sets are used to compare the different SVM methods. The TSVM outperforms the inductive SVM models applied on a small to medium variable (gene) set and a small to medium sample set, while SVMT is superior when the problem is defined with a large data set, or  a large set of variables (e.g. 7,000 genes, with little or no variable preselection).
View record details 
Neural Systems for solving the inverse problem of recovering the Primary Signal Waveform in potential transformers
Kasabov, N; Venkov, G.; Minchev, S. (20090527T22:18:57Z)
Conference paper
Auckland University of TechnologyThe inverse problem of recovering the potential transformer primary signal waveform using secondary signal waveform and information about the secondary load is solved here via two inverse neural network models. The first model uses two recurrent neural networks trained in an offline mode. The second model is designed with the use a Dynamic Evolving NeuralFuzzy Interface System (DENFIS) and suited for online application and integration into existing protection algorithms as a parallel module. It has the ability of learning and adjusting its structure in an online mode to reflect changes in the environment. The model is suited for real time applications and improvement of protection relay operation. The two models perform better than any existing and published models so far and are useful not only for the reconstruction of the primary signal, but for predicting the signal waveform for some time steps ahead and thus for estimating the drifts in the incoming signals and events.
View record details 
Discovering rules of adaptation and interaction: from molecules and gene interaction to brain functions
Kasabov, N (20090527T22:18:51Z)
Conference paper
View record details
Auckland University of Technology 
An adaptive model of person identification combining speech and image information
Zhang, D.; Ghobakhlou, A.; Kasabov, N (20090527T22:18:54Z)
Conference paper
Auckland University of TechnologyThe paper introduces a combination of adaptive neural network systems and statistical method for integrating speech and face image information for person identification. The method allows for the development of models of persons and their ongoing adjustment based on new speech and face images. The method is illustrated with a modeling and classification of different persons, when speech and face images are presented in an incremental way. In this model, there are two sub  networks, one for face image and one for speaker recognition. A higherlevel layer is applied to make a final decision. In the speaker recognition subnetwork, a textdependant model is built using Evolving Connectionist Systems (ECOS) [1]. In the face image recognition subnetwork, composite profile technique is applied for face image feature extraction and Zero Instruction Set Computing (ZISC) [2] technology is used to build the neural network. In the higherlevel conceptual subsystem, final recognition decision is made using statistical method. The experiments show that ECOS and ZISC are appropriate techniques for the creation of evolving models for the task of speaker and face recognition individually. It is also shown that the integration of the speech and image information using statistical method improves the person identification rate. © 2004 IEEE.
View record details 
A versatile quantuminspired evolutionary algorithm
Platel, M.; Sehliebs, S.; Kasabov, N (20090527T22:18:54Z)
Conference paper
Auckland University of TechnologyThis study points out some weaknesses of existing QuantumInspired Evolutionary Algorithms (QEA) and explains in particular how hitchhiking phenomenons can slow down the discovery of optimal solutions and encourage premature convergence. A new algorithm, called Versatile Quantuminspired Evolutionary Algorithm (vQEA), is proposed. With vQEA, the attractors moving the population through the search space are replaced at every generation without considering their fitness. The new algorithm is much more reactive. It always adapts the search toward the last promising solution found thus leading to a smoother and more efficient exploration. In this paper, vQEA is tested and compared to a Classical Genetic Algorithm CGA and to a QEA on several benchmark problems. Experiments have shown that vQEA performs better than both CGA and QEA in terms of speed and accuracy. It is a highly scalable algorithm as well. Finally, the properties of the vQEA are discussed and compared to Estimation of Distribution Algorithms (EDA). © 2007 IEEE.
View record details 
An incremental principal component analysis for chunk data
Ozawa, S.; Pang, S.; Kasabov, N (20090527T22:18:48Z)
Conference paper
Auckland University of TechnologyThis paper presents a new algorithm of dynamic feature selection by extending the algorithm of Incremental Principal Component Analysis (IPCA), which has been originally proposed by Hall and Martin. In the proposed IPCA, a chunk of training samples can be processed at a time to update the eigenspace of a classification model without keeping all the training samples given so far. Under the assumption that L of training samples are given in a chunk, first we derive a new eigenproblem whose solution gives us a rotation matrix of eigenaxes, then we introduce a new algorithm of augmenting eigenaxes based on the accumulation ratio. We also derive the onepass incremental update formula for the accumulation ratio. The experiments are carried out to verify if the proposed IPCA works well. Our experimental results demonstrate that it works well independent of the size of data chunk, and that the eigenvectors for major components are obtained without serious approximation errors at the final learning stage. In addition, it is shown that the proposed IPCA can maintain the designated accumulation ratio by augmenting new eigenaxes properly. This property enables a learning system to construct an informative eigenspace with minimum dimensionality. © 2006 IEEE.
View record details 
Computational neurogenetic modeling: a methodology to study gene interactions underlying neural oscillations
Benuskova, L.; Wysoski, S.; Kasabov, N (20090527T22:18:49Z)
Conference paper
Auckland University of TechnologyWe present new results from Computational Neurogenetic Modeling to aid discoveries of complex gene interactions underlying oscillations in neural systems. Interactions of genes in neurons affect the dynamics of the whole neural network model through neuronal parameters, which change their values as a function of gene expression. Through optimization of the gene interaction network, initial gene/protein expression values and neuronal parameters, particular target states of the neural network operation can be achieved, and statistics about gene interaction matrix can be extracted. In such a way it is possible to model the role of genes and their interactions in different brain states and conditions. Experiments with human EEG data are presented as an illustration of this methodology and also, as a source for the discovery of unknown interactions between genes in relation to their impact on brain activity. © 2006 IEEE.
View record details 
Evolving connectionist systems based role allocation of robots for soccer playing
Huang, L.; Song, Q.; Kasabov, N (20090527T22:18:50Z)
Conference paper
Auckland University of TechnologyFor a group of robots (multiagents) to complete a task, it is important for each of them to play a certain role changing with the environment of the task. One typical example is robotic soccer in which a team of mobile robots perform soccer playing behaviors. Traditionally, a robot's role is determined by a closedform function of a robot's postures relative to the target which usually cannot accurately describe real situations. In this paper, the robot role allocation problem is converted to the one of pattern classification. Evolving classification function (ECF), a special evolving connectionist systems (ECOS), is used to identify the suitable role of a robot from the data collected from the robot system in real time. The software and hardware platforms are established for data collection, learning and verification for this approach. The effectiveness of the approach are verified by the experimental studies. ©2005 IEEE.
View record details 
Online evolving fuzzy clustering
Ravi, V.; Srinivas, E.; Kasabov, N (20090527T22:18:50Z)
Conference paper
Auckland University of TechnologyIn this paper, a novel online evolving fuzzy clustering method that extends the evolving clustering method (ECM) of Kasabov and Song (2002) is presented, called EFCM. Since it is an online algorithm, the fuzzy membership matrix of the data is updated whenever the existing cluster expands, or a new cluster is formed. EFCM does not need the numbers of the clusters to be predefined. The algorithm is tested on several benchmark data sets, such as Iris, Wine, Glass, EColi, Yeast and Italian Olive oils. EFCM results in the least objective function value compared to the ECM and Fuzzy CMeans. It is significantly faster (by several orders of magnitude) than any of the offline batchmode clustering algorithms. A methodology is also proposed for using theXieBeni cluster validity measure to optimize the number of clusters. © 2007 IEEE.
View record details 
TWNFC  Transductive neuralfuzzy classifier with weighted data normalization and its application in medicine
Ma, T.; Song, Q.; Marshall, M.; Kasabov, N (20090527T22:18:51Z)
Conference paper
Auckland University of TechnologyThis paper introduces a novel fuzzy model  transductive neuralfuzzy classifier with weighted data normalization (TWNFC), While inductive approaches are concerned with the development of a model to approximate data in the whole problem space (induction), and consecutively  using this model to calculate the output value(s) for a new input vector (deduction), in transductive systems a local model is developed for every new input vector, based on some closest data to this vector from the training data set. The weighted data normalization method (WDN) optimizes the data normalization ranges for the input variables of a system. A steepest descent algorithm is used for training the TWNFC model The TWNFC is illustrated on a case study: a real medical decision support problem of estimating the survival of haemodialysis patients. This personalized modeling can also be applied to other distancebased, prototype learning neural network or fuzzy inference models. © 2005 IEEE.
View record details 
A twostage methodology for gene regulatory network extraction from timecourse gene expression data
Chan, Z.; Kasabov, N; Collins, L. (20090527T22:18:50Z)
Conference paper
Auckland University of TechnologyThe discovery of gene regulatory networks (GRN) from timecourse gene expression data (gene trajectory data) is useful for (1) identifying important genes in relation to a disease or a biological function; (2) gaining an understanding on the dynamic interaction between genes; (3) predicting gene expression values at future time points and accordingly, (4) predicting drug effect over time. In this paper, we propose a twostage methodology that is implemented in the software "Gene Network Explorer (GNetXP)" for extracting GRNs from gene trajectory data. In the first stage, we apply a hybrid Genetic Algorithm and Expectation Maximization algorithm on clustering the large number of gene trajectories using the mixture of multiple linear regression models for fitting the trajectory data. In the second stage, we apply the Kalman Filter to identify a set of firstorder differential equations that describe the dynamics of the representative trajectories, and use these equations for discovering important gene interactions and predicting gene expression values at future time points. The proposed method is demonstrated on the human fibroblast response gene expression data. ©2004 IEEE.
View record details 
A computational neurogenetic model of a spiking neuron
Kasabov, N; Benuskova, L.; Wysoski, S. (20090527T22:18:51Z)
Conference paper
Auckland University of TechnologyThe paper presents a novel, biologically plausible spiking neuronal model that includes a dynamic gene network. Interactions of genes in neurons affect the dynamics of the neurons and the whole network through neuronal parameters that change as a function of gene expression. The proposed model is used to build a spiking neural network (SNN) illustrated on a real EEC data case study problem. The paper also presents a novel computational approach to brain neural network modeling that integrates dynamic gene networks with a neural network model. Interaction of genes in neurons affects the dynamics of the whole neural network through neuronal parameters, which are no longer constant, but change as a function of gene expression. Through optimization of the gene interaction network, initial gene/protein expression values and ANN parameters, particular target states of the neural network operation can be achieved, and statistics about gene intercation matrix can be extracted. It is illustrated by means of a simple neurogenetic model of a spiking neural network (SNN). The behavior of SNN is evaluated by means of the local field potential, thus making it possible to attempt modeling the role of genes in different brain states, where EEC data is available to test the model. We use standard signal processing techniques like FFT to evaluate the SNN output to compare it with real human EEC data. © 2005 IEEE.
View record details 
Neuro, genetic, and quantum inspired evolving intelligent systems
Kasabov, N (20090527T22:18:52Z)
Conference paper
Auckland University of TechnologyThis paper discusses opportunities and challenges for the creation of evolving artificial neural network (ANN) and more general  computational intelligence (CI) models inspired by principles at different levels of information processing in the brain  neuronal, genetic, and quantum, and mainly  the issues related to the integration of these principles into more powerful and accurate ANN models. A particular type of ANN, evolving connectionist systems (ECOS), is used to illustrate this approach. ECOS evolve their structure and functionality through continuous learning from data and facilitate data and knowledge integration and knowledge elucidation. ECOS gain inspiration from the evolving processes in the brain. Evolving fuzzy neural networks and evolving spiking neural networks are presented as examples. With more genetic information available now, it becomes possible to integrate the gene and the neuronal information into neurogenetic models and to use them for a better understanding of complex brain processes. Further down in the information processing hierarchy, are the quantum processes. Quantum inspired ANN may help solve efficiently the hardest computational problems. It may be possible to integrated quantum principles into braingene inspired ANN models for a faster and more accurate modeling. All the topics above are illustrated with some contemporary solutions, but many more open questions and challenges are raised and directions for further research outlined. © 2006 IEEE.
View record details 
Braingene ontology: integrating bioinformatics and neuroinformatics data, information and knowledge to enable discoveries
Kasabov, N; Jain, V.; Gottgtroy, P.; Benuskova, L.; Joseph, F. (20090527T22:18:52Z)
Conference paper
Auckland University of TechnologyThe paper presents some preliminary results on the braingene ontology (BGO) project that is concerned with the collection, presentation and use of knowledge in the form of ontology. BGO includes various concepts, facts, data, software simulators, graphs, videos, animations, and other information forms, related to brain functions, brain diseases, their genetic basis and the relationship between all of them. The first version of the braingene ontology has been completed as a hierarchical structure and as an initial implementation in the Protégé ontology building environment.
View record details