Multiple window time-frequency distribution and coherence of EEG using Slepian sequences and hermite functions.

Multiple window (MW) time-frequency analysis (TFA) is a newly developed technique to estimate a time-varying spectrum for random nonstationary signals with low bias and variance. In this paper, we describe the application of MW-TFA techniques to electroencephalogram (EEG) and compare the results with those of the conventional spectrogram. We find that the MW-TFA provide us with not only low bias and variance time-frequency (TF) distribution for EEG but also TF coherence estimation between a single realization of EEG recorded from two sites. We also compare the performance of the MW-TFA using two sets of windows, Slepian sequences, and Hermite functions. If care is taken in matching the two windows, we find no noticeable difference in the resulting TF representations.

Simple and robust methods for support vector expansions.

Most support vector (SV) methods proposed in the recent literature can be viewed in a unified framework with great flexibility in terms of the choice of the kernel functions and their constraints. We show that all these problems can be solved within a unique approach if we are equipped with a robust method for finding a sparse solution of a linear system. Moreover, for such a purpose, we propose an iterative algorithm that can be simply implemented. Finally, we compare the classical SV approach with other, recently proposed, cross-correlation based, alternative methods. The simplicity of their implementation and the possibility of exactly calculating their computational complexity constitute important advantages in a real-time signal processing scenario.

A dynamic channel assignment policy through Q-learning.

One of the fundamental issues in the operation of a mobile communication system is the assignment of channels to cells and to calls. Since the number of channels allocated to a mobile communication system is limited, efficient utilization of these communication channels by using efficient channel assignment strategies is not only desirable but also imperative. This paper presents a novel approach to solving the dynamic channel assignment (DCA) problem by using a form of realtime reinforcement learning known as Q-learning in conjunction with neural network representation. Instead of relying on a known teacher, the system is designed to learn an optimal channel assignment policy by directly interacting with the mobile communication environment. The performance of the Q-learning-based DCA was examined by extensive simulation studies on a 49-cell mobile communication system under various conditions. Comparative studies with the fixed channel assignment (FCA) scheme and one of the best dynamic channel assignment strategies, MAXAVAIL, have revealed that the proposed approach is able to perform better than the FCA in various situations and capable of achieving a performance similar to that achieved by the MAXIAVIAL, but with a significantly reduced computational complexity.

Beta-frequency (15-35 Hz) electroencephalogram activities elicited by toluene and electrical stimulation in the behaving rat.

Bursts of beta-frequency (15-35 Hz) electroencephalogram activity occur in the olfactory system during odour sampling, but their mode of propagation within the olfactory system and potential contribution to the mechanisms of learning and memory are unclear. We have elicited large-amplitude beta activity in the rat olfactory system by applying noxious olfactory stimuli (toluene), and have monitored the bursts via chronically-implanted electrodes. Following exposure to toluene, coherent bursts with a peak frequency of 19.8 +/- 0.9 Hz were observed in the olfactory bulb, piriform cortex, entorhinal cortex and dentate gyrus. The timing of the bursts and the phases of electroencephalogram cross-spectra indicate that beta bursts propagate in a caudal direction from the olfactory bulb to the entorhinal cortex. The time delays between peaks of bursts in these structures were similar to latency differences for field potentials evoked by olfactory bulb or piriform cortex test-pulses. Peaks of burst cycles in the dentate region, however, were observed just prior to those in the entorhinal cortex. Surprisingly, power in toluene-induced beta-frequency oscillations was not increased following long-term potentiation induced by tetanic stimulation of the olfactory bulb, piriform cortex and entorhinal cortex. The activity of local inhibitory mechanisms may therefore counteract the effects of synaptic enhancements in afferent pathways during beta bursts. Low-frequency electrical stimulation of the piriform cortex was most effective in inducing coherent oscillatory responses in the entorhinal cortex and dentate gyrus at stimulation frequencies between 12 and 16 Hz. The results show that repetitive polysynaptic volleys at frequencies in the beta band induced by either toluene or electrical stimulation are transmitted readily within the olfactory system. The propagation of neural activity within this frequency range may therefore contribute to the transmission of olfactory signals to the hippocampal formation, particularly for those odours which induce high-amplitude bursts of beta activity.

Compression of digital chest radiographs with a mixture of principal components neural network: evaluation of performance.

The performance of a new, neural network-based image compression method was evaluated on digital radiographs for use in an educational environment. The network uses a mixture of principal components (MPC) representation to effect optimally adaptive transform coding of an image and has significant computational advantages over other techniques. Nine representative digital chest radiographs were compressed 10:1, 20:1, 30:1, and 40:1 with the MPC method. The five versions of each image, including the original, were shown simultaneously, in random order, to each of seven radiologists, who rated each one on a five-point scale for image quality and visibility of pathologic conditions. One radiologist also ranked four versions of each of the nine images in terms of the severity of distortion: The four versions represented 30:1 and 40:1 compression with the MPC method and with the classic Karhunen-Loève transform (KLT). Only for the images compressed 40:1 with the MPC method were there any unacceptable ratings. Nevertheless, the images compressed 40:1 received a top score in 26%-33% of the evaluations. Images compressed with the MPC method were rated better than or as good as images compressed with the KLT technique 17 of 18 times. Four of nine times, images compressed 40:1 with the MPC method were rated as good as or better than images compressed 30:1 with the KLT technique.

Optimally adaptive transform coding.

The optimal linear block transform for coding images is well known to be the Karhunen-Loeve transformation (KLT). However, the assumption of stationarity in the optimality condition is far from valid for images. Images are composed of regions whose local statistics may vary widely across an image. While the use of adaptation can result in improved performance, there has been little investigation into the optimality of the criterion upon which the adaptation is based. In this paper we propose a new transform coding method in which the adaptation is optimal. The system is modular, consisting of a number of modules corresponding to different classes of the input data. Each module consists of a linear transformation, whose bases are calculated during an initial training period. The appropriate class for a given input vector is determined by the subspace classifier. The performance of the resulting adaptive system is shown to be superior to that of the optimal nonadaptive linear transformation. This method can also be used as a segmentor. The segmentation it performs is independent of variations in illumination. In addition, the resulting class representations are analogous to the arrangement of the directionally sensitive columns in the visual cortex.

Classification of radar clutter using neural networks.

A classifier that incorporates both preprocessing and postprocessing procedures as well as a multilayer feedforward network (based on the back-propagation algorithm) in its design to distinguish between several major classes of radar returns including weather, birds, and aircraft is described. The classifier achieves an average classification accuracy of 89% on generalization for data collected during a single scan of the radar antenna. The procedures of feature selection for neural network training, the classifier design considerations, the learning algorithm development, the implementation, and the experimental results of the neural clutter classifier, which is simulated on a Warp systolic computer, are discussed. A comparative evaluation of the multilayer neural network with a traditional Bayes classifier is presented.