International Journal of Neural Systems

This paper presents a text-independent speaker verification system based on an online Radial Basis Function (RBF) network referred to as Minimal Resource Allocation Network (MRAN). MRAN is a sequential learning RBF, in which hidden neurons are added or removed as training progresses. LP-derived cepstral coefficients are used as feature vectors during training and verification phases. The performance of MRAN is compared with other well-known RBF and Elliptical Basis Function (EBF) based speaker verification methods in terms of error rates and computational complexity on a series of speaker verification experiments. The experiments use data from 258 speakers from the phonetically balancedcontinuous speech corpus TIMIT. The results show that MRAN produces comparable error rates to other methods with much less computational complexity.

A new more efficient variant of a recently developed algorithm for unsupervised fuzzy clustering is introduced. A Weighted Incremental Neural Network (WINN) is introduced and used for this purpose. The new approach is called FC-WINN (Fuzzy Clustering using WINN). The WINN algorithm produces a net of nodes connected by edges, which reflects and preserves the topology of the input data set. Additional weights, which are proportional to the local densities in input space, are associated with the resulting nodes and edges to store useful information about the topological relations in the given input data set. A fuzziness factor, proportional to the connectedness of the net, is introduced in the system. A watershed-like procedure is used to cluster the resulting net. The number of the resulting clusters is determined by this procedure. Only two parameters must be chosen by the user for the FC-WINN algorithm to determine the resolution and the connectedness of the net. Other parameters that must be specified are those which are necessary for the used incremental neural network, which is a modified version of the Growing Neural Gas algorithm (GNG). The FC-WINN algorithm is computationally efficient when compared to other approaches for clustering large high-dimensional data sets.

We consider the efficient initialization of structure and parameters of generalized Gaussian radial basis function (RBF) networks using fuzzy decision trees generated by fuzzy ID3 like induction algorithms. The initialization scheme is based on the proposed functional equivalence property of fuzzy decision trees and generalized Gaussian RBF networks. The resulting RBF network is compact, easy to induce, comprehensible, and has acceptable classification accuracy with stochastic gradient descent learning algorithm.

By analyzing the dynamic behaviors of the transiently chaotic neural network and greedy heuristic for the maximum independent set (MIS) problem, we present an improved transiently chaotic neural network for the MIS problem in this paper. Extensive simulations are performed and the results show that this proposed transiently chaotic neural network can yield better solutions to p-random graphs than other existing algorithms. The efficiency of the new model is also confirmed by the results on the complement graphs of some DIMACS clique instances in the second DIMACS challenge. Moreover, the improved model uses fewer steps to converge to stable state in comparison with the original transiently chaotic neural network.

Synchronization of neural networks by mutual learning has been demonstrated to be possible for constructing key exchange protocol over public channel. However, the neural cryptography schemes presented so far are not the securest under regular flipping attack (RFA) and are completely insecure under majority flipping attack (MFA). We propose a scheme by splitting the mutual information and the training process to improve the security of neural cryptosystem against flipping attacks. Both analytical and simulation results show that the success probability of RFA on the proposed scheme can be decreased to the level of brute force attack (BFA) and the success probability of MFA still decays exponentially with the weights' level L. The synchronization time of the parties also remains polynomial with L. Moreover, we analyze the security under an advanced flipping attack.

A speech act is a linguistic action intended by a speaker. Speech act classification is an essential part of a dialogue understanding system because the speech act of an utterance is closely tied with the user's intention in the utterance. We propose a neural network model for Korean speech act classification. In addition, we propose a method that extracts morphological features from surface utterances and selects effective ones among the morphological features. Using the feature selection method, the proposed neural network can partially increase precision and decrease training time. In the experiment, the proposed neural network showed better results than other models using comparatively high-level linguistic features. Based on the experimental result, we believe that the proposed neural network model is suitable for real field applications because it is easy to expand the neural network model into other domains. Moreover, we found that neural networks can be useful in speech act classification if we can convert surface sentences into vectors with fixed dimensions by using an effective feature selection method.