Advanced Detection and Classification Algorithms for Acoustic-Color-Based Sonar Systems

SYNTHESIS OF NEURAL NETWORK ALGORITHMS FOR CLASSIFICATION OF MARINE OBJECTS IN LOW-FREQUENCY PASSIVE SONAR SYSTEMS

Bulletin of Dubna International University for Nature, Society, and Man. Series: Natural and engineering sciences ◽

10.37005/1818-0744-2019-3-3-8 ◽

2019 ◽

pp. 3-8

Author(s):

O.A. Andreev ◽

A.T. Trofimov

Keyword(s):

Neural Network ◽

Probabilistic Models ◽

Low Frequency ◽

Gaussian Mixture ◽

Classification Systems ◽

Classification Algorithms ◽

Correct Classification ◽

Passive Sonar ◽

Sonar Systems

The paper addresses the issue of insuring the required probability of correct classification of marine objects in low-frequency passive sonar systems. The solution to the issue is sought through the application of methods for the synthesis of neural network classification algorithms using poly-Gaussian probabilistic models (Gaussian mixture models, GMM). It is shown that the use of GMM makes it possible to solve a number of problems specific to the issue; classification algorithms synthesized using mentioned methods can be implemented in the form of neural networks, which in turn can be described in C++/VHDL to create endpoint computing devices or software systems. The results of modeling of synthesized classification algorithms on experimental data are presented; it is demonstrated that such algorithms make it possible to increase the probability of correct classification of marine objects and to satisfy typical requirements for classification systems in low-frequency passive sonar systems.

Download Full-text

Progress Report on Advanced Detection and Classification Algorithms for Acoustic-Color-Based Sonar Systems

10.21236/ada458870 ◽

2006 ◽

Author(s):

Lawrence Carin ◽

Nilanjan Dasgupta ◽

Steven Haron

Keyword(s):

Progress Report ◽

Classification Algorithms ◽

Sonar Systems

Download Full-text

Spectral and Topographic Microstructure of Brain Alpha Activity During Drowsiness at Sleep Onset and REM Sleep

Journal of Psychophysiology ◽

10.1027//0269-8803.14.3.151 ◽

2000 ◽

Vol 14 (3) ◽

pp. 151-158 ◽

Cited By ~ 6

Author(s):

José Luis Cantero ◽

Mercedes Atienza

Keyword(s):

Rem Sleep ◽

Spectral Component ◽

Sleep Onset ◽

Quantitative Information ◽

Maximum Energy ◽

Alpha Activity ◽

The Other ◽

Classification Algorithms ◽

Microstructural Properties ◽

Brain States

Abstract High-resolution frequency methods were used to describe the spectral and topographic microstructure of human spontaneous alpha activity in the drowsiness (DR) period at sleep onset and during REM sleep. Electroencephalographic (EEG), electrooculographic (EOG), and electromyographic (EMG) measurements were obtained during sleep in 10 healthy volunteer subjects. Spectral microstructure of alpha activity during DR showed a significant maximum power with respect to REM-alpha bursts for the components in the 9.7-10.9 Hz range, whereas REM-alpha bursts reached their maximum statistical differentiation from the sleep onset alpha activity at the components between 7.8 and 8.6 Hz. Furthermore, the maximum energy over occipital regions appeared in a different spectral component in each brain activation state, namely, 10.1 Hz in drowsiness and 8.6 Hz in REM sleep. These results provide quantitative information for differentiating the drowsiness alpha activity and REM-alpha by studying their microstructural properties. On the other hand, these data suggest that the spectral microstructure of alpha activity during sleep onset and REM sleep could be a useful index to implement in automatic classification algorithms in order to improve the differentiation between the two brain states.

Download Full-text