Mary Lou Padgett

PCNN models and applications

The pulse coupled neural network (PCNN) models are described. The linking field modulation term is shown to be a universal feature of any biologically grounded dendritic model. Applications and implementations of PCNNs are reviewed. Application based variations and simplifications are summarized. The PCNN image decomposition (factoring) model is described in new detail.

Neural networks and simulation: Modeling for applications

Artificial neural networks simulate biologi cal processes in an intriguing manner. Ideas gleaned from the study of neurophysiology and animal behavior have become realizable in recent years. The advent of computers capable of rapidly executing massively parallel and distributed processes has allowed ideas from diverse fields to be merged and tested. The resulting neural networks, simulated in software and/or hardware, provide an adaptable, robust modeling tool useful to simulationists in all disciplines.

The lateral and medial compartments of the olfactory tubercle and their relation to olfactory-related input as determined by artificial neural network analysis

The current literature indicates that olfactory bulbar input projects throughout layer IA of the entire olfactory tubercle, with apparently more fibres in the lateral part than in the medial part of the tubercle. In addition, olfactory cortical association fibers project to layers IB, II, and III in all regions of the tubercle. This study exploited the phenomenon of transsynaptic transfer of WGA-HRP after injection into the olfactory bulb or rats to explore the degree of olfactory-related input to the tubercle. A computerized image analysis system was employed to quantify the amount of tracer transferred to layer II neurons of the tubercle. Qualitative analysis of the data indicates that the lateral tubercle consists of areas that receive little olfactory-related input. Nonparametric statistical tests and a novel application of artificial neural networks indicate regionally heterogeneous labeling across the tubercle and broad connections between homologous regions of the bulb and tubercle. These results have implications for understanding how olfactory sensory information is integrated into limbic-motor circuits by the olfactory tubercle.

CMOS implementation of a pulse-coupled neuron cell

Recent applications of pulse-coupled neural networks have demonstrated the need for a simple pulse-coupled neuron circuit which can easily be implemented in CMOS technology. The proposed cell uses a positive feedback circuit with two capacitors. One capacitor corresponds to the external sodium ion potential, and the other to the internal potassium ion potential. This cell body circuit is also used as a neural segment in an artificial axon. When linked by large resistors, these neural segments display many properties expected in a biological axon. SPICE simulations verify proposed circuit operation.

Implementing the dynamic decay adjustment algorithm in a CNAPS parallel computer system

Abstract This paper presents the implementation of the Dynamic Decay Adjustment (DDA) algorithm in a CNAPS parallel computer system having 128 processing nodes. The DDA algorithm has several inherent advantages, and the implementation of it in the CNAPS system is shown to perform very well. The DDA implementation is first tested with noisy character patterns to demonstrate its general inherent noise resistance. A more realistic application test involving the identification of Higgs events is then presented. Using the momenta and transverse momenta of the four leading particles from the H 0 → Z 0 Z 0 → μ + μ − μ + μ − decay following gg and W + W − fusion, it is possible to obtain a good indentification of these events as well as good rejection of the background.

Neural networks and PCA for determining region of interest in sensory data preprocessing

Principal component analysis (PCA) and artificial neural networks are used to investigate electronic gas sensor responses for various alcohol chemicals. PCA is used to identify and visualize the best features to use for classification as well as for detecting outliers. A regular feed forward back propagation neural network (FBP) was used for the actual classification due to the fact that FBP determines better the non-linear borders of the various region of interest involved in the classification. Furthermore, we consider the tradeoff between classification speed and accuracy.

Pulse coupled neural networks (PCNN) and wavelets: biosensor applications

This paper focuses on the novel approaches to chemosensor signal analysis: (1) forming image patterns from the time sequences, (2) PCNN factor formation, and (3) factor classification using wavelets.

Pulse coupled neural networks (PCNN), wavelets and radial basis functions: olfactory sensor applications

This paper focuses on novel approaches to olfactory sensor signal analysis: 1) PCNN focusing, 2) wavelet characterization and 3) radial basis function detection of anomalies. Novel decision aide approaches are developed to facilitate design of routines to automatically trigger calibration and/or analysis when transient signals indicate an anomaly. These three signal analysis steps are integrated into a decision system to separate sensor faults from targets, and then recalibrate the target detection and identification procedures.

Feature-level signal processing for near-real-time odor identification

Rapid detection and classification of odor is of particular interest in applications such as manufacturing of consumer items, food processing, drug and explosives detection, and battlefield situation assessment. Various detection and classification techniques are under investigation so that end users can have access to useful information from odor sensor arrays in near-real-time. Feature-level data clustering and classification techniques are proposed that are (1) parallelizable to permit efficient hardware implementation, (2) adaptable to readily incorporate new data classes, (3) capable of gracefully handling outlier data points and failed sensor conditions, and (4) can provide confidence intervals and/or a traceable decision record along with each classification to permit validation and verification. Results from using specific techniques will be presented and compared. The techniques studied include principal components analysis, automated outlier determination, radial basis functions (RBF), multi-layer perceptrons (MLP), and pulse-coupled neural networks (PCNN). The results reported here are based on data from a testbed in which a gas sensor array is exposed to odor samples on a continuous basis. We have reported previously that more detailed and faster discrimination can be obtained by using sensor transient response in addition to steady state response. As the size of the data set grows we are able to more accurately model performance of a sensor array under realistic conditions.

Pulse-coupled neural networks (PCNN) and new approaches to biosensor applications

Recent developments in pulse coupled neural networks techniques provide an opportunity to extend the toolbox available for exploring new approaches to biosensor applications. This paper presents a demonstration of properties and limitations of new computational intelligence (CI) techniques as shown by and related to an application. New pulse coupled neural networks (PCNN) techniques are supplemented by combination with wavelet analysis and fine- tuned by radial basis functions. This toolbox is exercised to demonstrate its properties and limitations as related to the development of biosensor applications. The approach selected employs abstractions of biological models of peripheral vision and relates them to analysis of time series generated by biosensors such as chemosensors or motion detectors. Detection of targets (rare or interesting events) is facilitated by PCNN multi-scale image factorization. Interpretation of the resulting image set is aided by contrast enhancement and by segmentation using standard PCNNs. Wavelet coefficients provide supplemental discrimination and lead to characteristic sets of numbers useful in identifying image factors of interest. To complete the transition from acquisition of a complex, noisy image to recognition of targets of interest, radial basis function (RBF) analysis is appended. This five- step process (odor image generation, image factoring, PCNN analysis, wavelet analysis and RBF interpretation) was recently suggested, but is expanded and fully implemented here for the first time. This paper explores the properties and limitations of this approach for simulation of biosensors using small, incomplete sets of real-world data. The relationship between selection of appropriate design parameters and the need for supplementing the available data by simulation is investigated. Evolutionary computation is employed off line to explore and evaluate the possibilities and limitations. Sensor fault detection and RBF training vector generation are addressed. Results are analyzed to provide recommendations for further experimentation and collection of needed additional data without extraneous effort. This methodology is recommended for use in real-world applications where experimental data is difficult, expensive or time consuming to obtain.