Tracking by a modified rotor model of neural network

Baginyan, S.A.; Glazov, A.; Kisel, I.; Konotopskaya, E.V.; Neskoromnyi, V.; Ososkov, G.

doi:10.1016/0010-4655(94)90065-5

Cited by 11 publications

(7 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For applications of the Hopfield network in experiments see e.g. [11][12][13][14][15]. The energy function of the Hopfield network can be generalized in order to take into account the track model (see Sect.…”

Section: Neural Networkmentioning

confidence: 99%

Pattern Recognition and Reconstruction

Frühwirth¹,

Strandlie²

2011

Detectors for Particles and Radiation. Part 1: Principles and Methods

View full text Add to dashboard Cite

Track reconstruction is the task of finding and estimating the trajectory of a charged particle, usually embedded in a static magnetic field to determine its momentum and charge. It involves pattern recognition algorithms and statistical estimation methods. Depending on the physics goals, not all charged tracks have to be reconstructed. For instance, in many cases there is a physically motivated lower limit on the momentum or transverse momentum of the particles to be found. Other examples are short-range secondary particles, such as δ-electrons, that normally need not be reconstructed. It may also be useful to reconstruct electron-positron pairs from photon conversions in order to check the distribution of material in the detector. Track reconstruction frequently proceeds in several steps: 1. Pattern recognition or Track finding: Finds the detector signals (hits) that are generated by the same charged particle. 2. Track fitting: Estimates for each track candidate the track parameters and the associated covariance matrix. 3. Test of track hypothesis: Tests for each track candidate whether all hits do indeed belong to the track and identifies outliers.

show abstract

Section: Neural Networkmentioning

confidence: 99%

Pattern Recognition and Reconstruction

Frühwirth¹,

Strandlie²

2011

Detectors for Particles and Radiation. Part 1: Principles and Methods

View full text Add to dashboard Cite

show abstract

“…After a number of sector orientations are tested, the edgel orientation is set to the same direction as the maximum number of other edges found within the sector. The actual steering algorithm implements an angular histogramming technique [ Baginyan et al , 1994], which is a version of the linear Hough Transform (HT) reworked for a higher computing efficiency.…”

Section: Corpral Descriptionmentioning

confidence: 99%

“…The cocircularity constraint gives preference to rotors that are aligned tangential to a circular arc connecting them. Figure 5 illustrates calculations involved in long‐range facilitation of edgel V j on V i [ Baginyan et al , 1994]. The strength of interaction is maximal when both edgels are tangential to the circle connecting edgels i and j .…”

Section: Corpral Descriptionmentioning

confidence: 99%

See 1 more Smart Citation

Automated exploration of the radio plasma imager data

et al. 2004

View full text Add to dashboard Cite

[1] As research instruments with large information capacities become a reality, automated systems for intelligent data analysis become a necessity. Scientific archives containing huge volumes of data preclude manual manipulation or intervention and require automated exploration and mining that can at least preclassify information in categories. The large data set from the radio plasma imager (RPI) instrument on board the IMAGE satellite shows a critical need for such exploration in order to identify and archive features of interest in the volumes of visual information. In this research we have developed such a preclassifier through a model of preattentive vision capable of detecting and extracting traces of echoes from the RPI plasmagrams. The overall design of our model complies with Marr's paradigm of vision, where elements of increasing perceptual strength are built bottom up under the Gestalt constraints of good continuation and smoothness. The specifics of the RPI data, however, demanded extension of this paradigm to achieve greater robustness for signature analysis. Our preattentive model now employs a feedback neural network that refines alignment of the oriented edge elements (edgels) detected in the plasmagram image by subjecting them to collective global-scale optimization. The level of interaction between the oriented edgels is determined by their distance and mutual orientation in accordance with the Yen and Finkel model of the striate cortex that encompasses findings in psychophysical studies of human vision. The developed models have been implemented in an operational system ''CORPRAL'' (Cognitive Online RPI Plasmagram Ranking Algorithm) that currently scans daily submissions of the RPI plasmagrams for the presence of echo traces. Qualifying plasmagrams are tagged in the mission database, making them available for a variety of queries. We discuss CORPRAL performance and its impact on scientific analysis of RPI data.

show abstract

“…Feedback ANNs, however, do not require reduction of trace shapes to a fixed number of patterns; it is the trace model that has to be fixed. Another modification was made to the evolving scheme itself: the ANN is given an estimate of the track configuration obtained by a more conventional one-dimensional angular histogramming technique (see Baginyan et al, [1994] for details). That brings the ANN close to the optimal solution so that it is no longer necessary to use time-consuming simulated annealing schemes.…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Feedback neural networks for ARTIST ionogram processing

Galkin¹,

Reinisch²,

Ososkov³

et al. 1996

Radio Science

View full text Add to dashboard Cite

Modern pattern recognition techniques are applied to achieve high quality automatic processing of Digisonde ionograms. An artificial neural network (ANN) was found to be a promising technique for ionospheric echo tracing. A modified rotor model was tested to construct the Hopfield ANN with the mean field theory updating scheme. Tests of the models against various ionospheric data showed that the modified rotor model gives good results where conventional tracing techniques have difficulties. Use of the ANN made it possible to implement a robust scheme of trace interpretation that considers local trace inclination angles available after ANN completes tracing. The interpretation scheme features a new algorithm for ƒ0F1 identification that estimates an α angle for the trace segments in the vicinity of the critical frequency ƒ0F1. First results from off‐line tests suggest the potential of implementing new operational autoscaling software in the worldwide Digisonde network.

show abstract

Tracking by a modified rotor model of neural network

Cited by 11 publications

References 11 publications

Pattern Recognition and Reconstruction

Pattern Recognition and Reconstruction

Automated exploration of the radio plasma imager data

Feedback neural networks for ARTIST ionogram processing

Contact Info

Product

Resources

About