Network


Latest external collaboration on country level. Dive into details by clicking on the dots.

Hotspot


Dive into the research topics where Geza Szekely is active.

Publication


Featured researches published by Geza Szekely.


Nuclear Instruments & Methods in Physics Research Section A-accelerators Spectrometers Detectors and Associated Equipment | 1997

Intelligent detectors modelled from the cat's eye

Th. Lindblad; V. Becanovic; Clark S. Lindsey; Geza Szekely

Abstract Biologically inspired image/signal processing, in particular neural networks like the Pulse-Coupled Neural Network (PCNN), are revisited. Their use with high granularity high-energy physics detectors, as well as optical sensing devices, for filtering, de-noising, segmentation, object isolation and edge detection is discussed.


Nuclear Instruments & Methods in Physics Research Section A-accelerators Spectrometers Detectors and Associated Equipment | 1993

Filtering data from a drift-chamber detector using neural networks

Per Hörnblad; Thomas Lindblad; Clark S. Lindsey; Geza Szekely; Åge Eide

Abstract This paper describes the implementation of an analog neural network chip (Intel 80170NX ETANN) to filter a multi-signal read-out from flash-ADCs used in a liquid argon time projection chamber (ICARUS). The training and subsequent testing of the network is discussed in some detail. A network consisting of multiple sub-networks is proposed to perform signal filtering, determination of peak position and track finding.


Nuclear Instruments & Methods in Physics Research Section A-accelerators Spectrometers Detectors and Associated Equipment | 1996

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

Thomas Lindblad; Geza Szekely; Mary Lou Padgett; Åge Eide; Clark S. Lindsey

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.


international symposium on neural networks | 1999

Odor detection using pulse coupled neural networks

Geza Szekely; Mary Lou Padgett; Gerry Dozier; Thaddeus A. Roppel

Based on neural structure (not physiology) observed in clinical experiments, an odor image can be constructed for analysis with a cutting-edge image processing procedure termed pulse coupled neural networks factoring (PCNNf). Enhancement of an odor image using PCNNf can significantly increase detection accuracy. Selection of the proper parameters for the implementation usually requires analysis by an expert familiar with the application targeted. Once suitable parameters have been selected, the PCNNf procedure is very robust, and can typically be used in a large number of situations similar to the original application. The purpose of this research is to advance the methodology for selecting parameters with reduced input from experts. The approach selected is use of a set of evolutionary algorithms (EA) to find improved parameter sets and to establish automated procedures for setting bounds on parameters and weight matrices for particular applications.


Proceedings of SPIE | 1996

Wavelets and signal processing

Geza Szekely; Åge Eide; Thomas Lindblad; Clark S. Lindsey; M. Minerskjöld; Givi Sekhniaidze

We briefly review the use of the wavelet and wavelet packet transforms. We describe their application to signal processing as devices for feature extraction and reduction of data for neural networks, in particular their implementation in hardware for signal identification.


Nuclear Instruments & Methods in Physics Research Section A-accelerators Spectrometers Detectors and Associated Equipment | 1995

Implementing the new Zero Instruction Set Computer (ZISC036) from IBM for a Higgs search

Th. Lindblad; Clark S. Lindsey; M. Minerskjöld; Givi Sekhniaidze; Geza Szekely; Åge Eide

Abstract Implementation of the new IBM Zero Instruction Set Computer (ZISC036) on a PC/ISA-bus card as well as on a VME-card is reported. The ZISC circuit has 36 processing elements of a type similar to that of Radial Basis Function (RBF) neurons. It is a highly parallel and cascadable building block with on-chip learning capability, and is well suited for pattern recognition, signal processing, etc. Results of a test on identification of simulated Higgs events are given.


Nuclear Instruments & Methods in Physics Research Section A-accelerators Spectrometers Detectors and Associated Equipment | 1993

Investigation of a VLSI neural network chip as part of a secondary vertex trigger

Bruce Denby; Th. Lindblad; Clark S. Lindsey; Geza Szekely; J. Molnar; Åge Eide; S.R. Amendolia; A. Spaziani

Abstract An analog VLSI neural network chip (ETANN) has been trained to detect secondary vertices in simulated data for a fixed target heavy flavour production experiment. The detector response and associative memory track finding were modelled by a simulation, but the vertex detection was performed in hardware by the neural network chip and requires only a few microseconds per event. The chip correctly tags 30% of the heavy flavour events while rejecting 99% of the background, and is thus well adapted for secondary vertex triggering applications. A general purpose VME module for interfacing the ETANN to experiments, equipped with ADC/DAC circuits and a 68070 CPU, is also presented.


Nuclear Instruments & Methods in Physics Research Section A-accelerators Spectrometers Detectors and Associated Equipment | 1993

A hardware implementation of an analog neural network for Gaussian peak-fitting

Thomas Lindblad; B. Lund-Jensen; Geza Szekely; Åge Eide

Abstract This paper demonstrates the implementation in hardware of an electrically trainable analog neural network (ETANN) for finding the position and width (FWHM) of an ion-beam hitting a strip-detector. This is accomplished using a single ETANN chip with 32 neurons in one hidden layer. The network finds the maximum and the FWHM, with an error of 0.1 and 0.2, respectively, of the 16 wire input pitch. An extension of this linear peak-fitting problem to include finding the height is presented. Extensions to larger nets with 64 and 128 inputs are presented as multi-chip solutions. A track-finding problem using several chips is briefly discussed.


Nuclear Instruments & Methods in Physics Research Section A-accelerators Spectrometers Detectors and Associated Equipment | 1993

Filtering and unfolding using neural networks

Thomas Lindblad; Geza Szekely

Abstract This letter demonstrates how a neural network can be used to implement a “noise” filter in software as well as in hardware. An extension from this case to the problem of unfolding energy spectra recorded by high-resolution detectors is also presented.


congress on evolutionary computation | 1999

Evolutionary computation enhancement of olfactory system model

Geza Szekely; Mary Lou Padgett

Recent electron microscopy work on rat olfactory system anatomy suggests a structural basis for grouping input stimuli before processing to classify odors. For a simulated nose, the number of inputs per group is a design parameter. Previous results indicate that improvements in classification accuracy can be made by grouping inputs, but such an increase is expensive in terms of hardware and speed. This paper demonstrates that use of evolutionary algorithms (EA) to tune PCNN factoring parameters improves accuracy significantly, with a reasonable processing time, so an increase in inputs per group is not needed.

Collaboration


Dive into the Geza Szekely's collaboration.

Top Co-Authors

Avatar

Clark S. Lindsey

Royal Institute of Technology

View shared research outputs
Top Co-Authors

Avatar

Th. Lindblad

Royal Institute of Technology

View shared research outputs
Top Co-Authors

Avatar

Thomas Lindblad

Royal Institute of Technology

View shared research outputs
Top Co-Authors

Avatar

Åge Eide

Royal Institute of Technology

View shared research outputs
Top Co-Authors

Avatar

W. Klamra

Royal Institute of Technology

View shared research outputs
Top Co-Authors

Avatar
Top Co-Authors

Avatar

M. Minerskjöld

Royal Institute of Technology

View shared research outputs
Top Co-Authors

Avatar

B. Lund-Jensen

Royal Institute of Technology

View shared research outputs
Top Co-Authors

Avatar

Givi Sekhniaidze

Royal Institute of Technology

View shared research outputs
Top Co-Authors

Avatar
Researchain Logo
Decentralizing Knowledge