Neural and wavelet network models for financial distress classification

This work analyzes the use of linear discriminant models, multi-layer perceptron neural networks and wavelet networks for corporate financial distress prediction. Although simple and easy to interpret, linear models require statistical assumptions that may be unrealistic. Neural networks are able to discriminate patterns that are not linearly separable, but the large number of parameters involved in a neural model often causes generalization problems. Wavelet networks are classification models that implement nonlinear discriminant surfaces as the superposition of dilated and translated versions of a single "mother wavelet" function. In this paper, an algorithm is proposed to select dilation and translation parameters that yield a wavelet network classifier with good parsimony characteristics. The models are compared in a case study involving failed and continuing British firms in the period 1997-2000. Problems associated with over-parameterized neural networks are illustrated and the Optimal Brain Damage pruning technique is employed to obtain a parsimonious neural model. The results, supported by a re-sampling study, show that both neural and wavelet networks may be a valid alternative to classical linear discriminant models.

Invasive neural prosthesis for neural signal detection and nerve stimulation

This paper specifically examines the implantation of a microelectrode array into the median nerve of the left arm of a healthy male volunteer. The objective was to establish a bi-directional link between the human nervous system and a computer, via a unique interface module. This is the first time that such a device has been used with a healthy human. The aim of the study was to assess the efficacy, compatibility, and long term operability of the neural implant in allowing the subject to perceive feedback stimulation and for neural activity to be detected and processed such that the subject could interact with remote technologies. A case study demonstrating real-time control of an instrumented prosthetic hand by means of the bi-directional link is given. The implantation did not result in infection, and scanning electron microscope images of the implant post extraction have not indicated significant rejection of the implant by the body. No perceivable loss of hand sensation or motion control was experienced by the subject while the implant was in place, and further testing of the subject following the removal of the implant has not indicated any measurable long term defects. The implant was extracted after 96 days. Copyright © 2004 John Wiley & Sons, Ltd.

A fast identification algorithm for Box-Cox transformation based radial basis function neural network

In this letter, a Box-Cox transformation-based radial basis function (RBF) neural network is introduced using the RBF neural network to represent the transformed system output. Initially a fixed and moderate sized RBF model base is derived based on a rank revealing orthogonal matrix triangularization (QR decomposition). Then a new fast identification algorithm is introduced using Gauss-Newton algorithm to derive the required Box-Cox transformation, based on a maximum likelihood estimator. The main contribution of this letter is to explore the special structure of the proposed RBF neural network for computational efficiency by utilizing the inverse of matrix block decomposition lemma. Finally, the Box-Cox transformation-based RBF neural network, with good generalization and sparsity, is identified based on the derived optimal Box-Cox transformation and a D-optimality-based orthogonal forward regression algorithm. The proposed algorithm and its efficacy are demonstrated with an illustrative example in comparison with support vector machine regression.

Experimental design and model construction algorithms for radial basis function networks

New construction algorithms for radial basis function (RBF) network modelling are introduced based on the A-optimality and D-optimality experimental design criteria respectively. We utilize new cost functions, based on experimental design criteria, for model selection that simultaneously optimizes model approximation, parameter variance (A-optimality) or model robustness (D-optimality). The proposed approaches are based on the forward orthogonal least-squares (OLS) algorithm, such that the new A-optimality- and D-optimality-based cost functions are constructed on the basis of an orthogonalization process that gains computational advantages and hence maintains the inherent computational efficiency associated with the conventional forward OLS approach. The proposed approach enhances the very popular forward OLS-algorithm-based RBF model construction method since the resultant RBF models are constructed in a manner that the system dynamics approximation capability, model adequacy and robustness are optimized simultaneously. The numerical examples provided show significant improvement based on the D-optimality design criterion, demonstrating that there is significant room for improvement in modelling via the popular RBF neural network.

Detection of neural correlates of self-paced motor activity using empirical mode decomposition phase locking analysis

Transient episodes of synchronisation of neuronal activity in particular frequency ranges are thought to underlie cognition. Empirical mode decomposition phase locking (EMDPL) analysis is a method for determining the frequency and timing of phase synchrony that is adaptive to intrinsic oscillations within data, alleviating the need for arbitrary bandpass filter cut-off selection. It is extended here to address the choice of reference electrode and removal of spurious synchrony resulting from volume conduction. Spline Laplacian transformation and independent component analysis (ICA) are performed as pre-processing steps, and preservation of phase synchrony between synthetic signals. combined using a simple forward model, is demonstrated. The method is contrasted with use of bandpass filtering following the same preprocessing steps, and filter cut-offs are shown to influence synchrony detection markedly. Furthermore, an approach to the assessment of multiple EEG trials using the method is introduced, and the assessment of statistical significance of phase locking episodes is extended to render it adaptive to local phase synchrony levels. EMDPL is validated in the analysis of real EEG data, during finger tapping. The time course of event-related (de)synchronisation (ERD/ERS) is shown to differ from that of longer range phase locking episodes, implying different roles for these different types of synchronisation. It is suggested that the increase in phase locking which occurs just prior to movement, coinciding with a reduction in power (or ERD) may result from selection of the neural assembly relevant to the particular movement. (C) 2009 Elsevier B.V. All rights reserved.

A forward constrained selection algorithm for probabilistic neural network

A new probabilistic neural network (PNN) learning algorithm based on forward constrained selection (PNN-FCS) is proposed. An incremental learning scheme is adopted such that at each step, new neurons, one for each class, are selected from the training samples arid the weights of the neurons are estimated so as to minimize the overall misclassification error rate. In this manner, only the most significant training samples are used as the neurons. It is shown by simulation that the resultant networks of PNN-FCS have good classification performance compared to other types of classifiers, but much smaller model sizes than conventional PNN.

Prediction of Parkinson’s Disease tremor onset using a radial basis function neural network based on particle swarm optimization

Deep Brain Stimulation (DBS) has been successfully used throughout the world for the treatment of Parkinson's disease symptoms. To control abnormal spontaneous electrical activity in target brain areas DBS utilizes a continuous stimulation signal. This continuous power draw means that its implanted battery power source needs to be replaced every 18–24 months. To prolong the life span of the battery, a technique to accurately recognize and predict the onset of the Parkinson's disease tremors in human subjects and thus implement an on-demand stimulator is discussed here. The approach is to use a radial basis function neural network (RBFNN) based on particle swarm optimization (PSO) and principal component analysis (PCA) with Local Field Potential (LFP) data recorded via the stimulation electrodes to predict activity related to tremor onset. To test this approach, LFPs from the subthalamic nucleus (STN) obtained through deep brain electrodes implanted in a Parkinson patient are used to train the network. To validate the network's performance, electromyographic (EMG) signals from the patient's forearm are recorded in parallel with the LFPs to accurately determine occurrences of tremor, and these are compared to the performance of the network. It has been found that detection accuracies of up to 89% are possible. Performance comparisons have also been made between a conventional RBFNN and an RBFNN based on PSO which show a marginal decrease in performance but with notable reduction in computational overhead.

Inverse model control using recurrent networks

This paper illustrates how internal model control of nonlinear processes can be achieved by recurrent neural networks, e.g. fully connected Hopfield networks. It is shown that using results developed by Kambhampati et al. (1995), that once a recurrent network model of a nonlinear system has been produced, a controller can be produced which consists of the network comprising the inverse of the model and a filter. Thus, the network providing control for the nonlinear system does not require any training after it has been trained to model the nonlinear system. Stability and other issues of importance for nonlinear control systems are also discussed.

Artificial keys for botanical identification using a multilayer perceptron neural network (MLP)

In this paper, practical generation of identification keys for biological taxa using a multilayer perceptron neural network is described. Unlike conventional expert systems, this method does not require an expert for key generation, but is merely based on recordings of observed character states. Like a human taxonomist, its judgement is based on experience, and it is therefore capable of generalized identification of taxa. An initial study involving identification of three species of Iris with greater than 90% confidence is presented here. In addition, the horticulturally significant genus Lithops (Aizoaceae/Mesembryanthemaceae), popular with enthusiasts of succulent plants, is used as a more practical example, because of the difficulty of generation of a conventional key to species, and the existence of a relatively recent monograph. It is demonstrated that such an Artificial Neural Network Key (ANNKEY) can identify more than half (52.9%) of the species in this genus, after training with representative data, even though data for one character is completely missing.

The relative order and inverses of recurrent networks

Differential geometry is used to investigate the structure of neural-network-based control systems. The key aspect is relative order—an invariant property of dynamic systems. Finite relative order allows the specification of a minimal architecture for a recurrent network. Any system with finite relative order has a left inverse. It is shown that a recurrent network with finite relative order has a local inverse that is also a recurrent network with the same weights. The results have implications for the use of recurrent networks in the inverse-model-based control of nonlinear systems.

Dynamic recurrent neural network for system identification and control

A dynamic recurrent neural network (DRNN) that can be viewed as a generalisation of the Hopfield neural network is proposed to identify and control a class of control affine systems. In this approach, the identified network is used in the context of the differential geometric control to synthesise a state feedback that cancels the nonlinear terms of the plant yielding a linear plant which can then be controlled using a standard PID controller.

Neural network feature maps for Chinese phonemes

It has been shown through a number of experiments that neural networks can be used for a phonetic typewriter. Algorithms can be looked on as producing self-organizing feature maps which correspond to phonemes. In the Chinese language the utterance of a Chinese character consists of a very simple string of Chinese phonemes. With this as a starting point, a neural network feature map for Chinese phonemes can be built up. In this paper, feature map structures for Chinese phonemes are discussed and tested. This research on a Chinese phonetic feature map is important both for Chinese speech recognition and for building a Chinese phonetic typewriter.

Stable receding horizon control based on recurrent networks

The last decade has seen the re-emergence of artificial neural networks as an alternative to traditional modelling techniques for the control of nonlinear systems. Numerous control schemes have been proposed and have been shown to work in simulations. However, very few analyses have been made of the working of these networks. The authors show that a receding horizon control strategy based on a class of recurrent networks can stabilise nonlinear systems.

Givens rotation based fast backward elimination algorithm for RBF neural network pruning

A fast backward elimination algorithm is introduced based on a QR decomposition and Givens transformations to prune radial-basis-function networks. Nodes are sequentially removed using an increment of error variance criterion. The procedure is terminated by using a prediction risk criterion so as to obtain a model structure with good generalisation properties. The algorithm can be used to postprocess radial basis centres selected using a k-means routine and, in this mode, it provides a hybrid supervised centre selection approach.