Olga Sushkova - Academia.edu (original) (raw)

Papers by Olga Sushkova

Метод частотно-временного анализа совместных измерений электроэнцефалограмм, электромиограмм и механического тремора при болезни Паркинсона

Радиотехника и электроника, 2015

The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, May 12, 2023

This work aims to study and develop methods and tools for analyzing video-EEG monitoring of delay... more This work aims to study and develop methods and tools for analyzing video-EEG monitoring of delayed cerebral ischemia after subarachnoid haemorrhage. A study was made of methods and algorithms for processing video images, which are supposed to be used to recognize life events and medical care for a patient, which can lead to artefacts in the patient's EEG records. An approach to video monitoring of the patient was proposed and tested on real video monitoring data using object-oriented logic programming methods in combination with neural network methods for image analysis.

Journal of physics, Sep 1, 2018

virtual machine for low-level video processing in the Actor Prolog object-oriented logic language... more virtual machine for low-level video processing in the Actor Prolog object-oriented logic language. The principle of operation of this machine is the following one: (1) The machine keeps a sequence of commands of the low-level video processing. This sequence of commands is to be applied to every frame of the video. The loading of these commands into the machine is performed using predicates of the VideoProcessingMachine built-in class. (2) The machine keeps internal data arrays that are related to various sub-stages of the lowlevel video processing. Currently, the following sub-stages of the processing are implemented in the machine: preprocessing of the frame; processing of the frame in the pixel representation; selection of and processing the foreground pixels in the frame; extraction and tracing the blobs in the sequence of the frames. (3) The machine supports a stack of masks of foreground pixels. This stack enables the processing of different groups of blobs using different methods of image processing. (4) The result of the processing the frame of the video is a set of graphs that contain information about the movements of the blobs as well as other attributes of the blobs in the video scene during given time interval.

Lecture Notes in Computer Science, 2018

Experimental means developed in the Actor Prolog parallel object-oriented logic language for impl... more Experimental means developed in the Actor Prolog parallel object-oriented logic language for implementation of heterogeneous multichannel intelligent visual surveillance systems are considered. These means are examined by the instance of a logic program for permanent monitoring of people's body parts temperature in the area of visual surveillance. The logic program implements a fusion of heterogeneous data acquired by two devices: (1) 3D coordinates of the human body are measured using a time-of-flight (ToF) camera; (2) 3D coordinates of the human body skeleton are computed on the base of 3D coordinates of the body; (3) a thermal video is acquired using a thermal imaging camera. In the considered example, the thermal video is projected to the 3D surface of the human body; then the temperature of the human body is projected to the vertices and edges of the skeleton. A special logical agent (i.e., the logic program that is written in Actor Prolog) implements these operations in real-time and transfers the data to another logical agent. The latter agent implements a time average of the temperature of the human skeletons and displays colored 3D images of the skeletons; the average temperature of the vertices and edges of the skeletons is depicted by colors. The logic programming means under consideration are developed for the purpose of the implementation of logical analysis of video scene semantics in the intelligent visual surveillance systems.

Радиоэлектроника, наносистемы, информационные технологии, Oct 1, 2018

The aim of this work is automation of neurophysiological experiments, namely, intelligent video m... more The aim of this work is automation of neurophysiological experiments, namely, intelligent video monitoring of the behaviour of laboratory rats during the social recognition cognitive test on the working memory. The test is conducted in the box with a sawdust background, simultaneously with EEG recording. Automatic video processing supplies objectivity of the interpretation of the results of the testing and provides new possibilities for the standardizing of the neurophysiological experiments. In the paper, methods and means for the logical description and analysis of the behaviour of experimental animals are considered. Recommendations for improving the experimental technique of the social recognition test are elaborated on the base of the results of the experiments with the automatical video processing.

The problem of the video monitoring the laboratory rats by the means of the object-oriented logic... more The problem of the video monitoring the laboratory rats by the means of the object-oriented logic programming is considered. The main task of the video monitoring is the analysis of the behavior of the animals in cognitive testing. An essential feature of the video records is in that the experiments are conducted in the same cage where the animal lives, that is, the background of the cage is sawdust. The color of the animals is about the same as the color of the sawdust; thus the detection of the animals is not a simple task. An additional difficulty is in that the videos were recorded simultaneously with electroencephalograms (EEG) in the animals; thus the head of the rat is connected with EEG cable that moves and causes false detections of recognition algorithms. In the paper, development of low-level algorithms for video analysis as well as logical methods for the analysis of the animal behavior is discussed. The methods and algorithms are implemented in the Actor Prolog object-oriented logic language.

Rules and Rule Markup Languages for the Semantic Web, 2015

A method for the monitoring of anomalous human behaviour that is based on the logical description... more A method for the monitoring of anomalous human behaviour that is based on the logical description of complex human behaviour patterns and special kinds of blob (a separated area of a foreground image) motion statistical metrics is developed. The concurrent object-oriented logic language is used for the analysis of graphs of tracks of moving blobs; the graphs are supplied by low-level analysis algorithms implemented in a special built-in class of Actor Prolog. The blob motion statistics is collected by the low-level analysis procedures that are of the need for the discrimination of running people, people riding bicycles, and cars in a video scene. The first-order logic language is used for implementing the fuzzy logical inference based on the blob motion statistics. A research software platform is developed that is based on the Actor Prolog logic language and a state-of-the-art Prolog-to-Java translator for experimenting with the intelligent visual surveillance.

Rules and Rule Markup Languages for the Semantic Web, 2015

Actor Prolog is a concurrent object-oriented logic language developed in [1]. We demonstrate a st... more Actor Prolog is a concurrent object-oriented logic language developed in [1]. We demonstrate a state-of-the-art translator of Actor Prolog to Java developed in the framework of the Intelligent Visual Surveillance Logic Programming project [2]. The translator implements a set of high-level and low-level code optimization methods and generates a kind of the idiomatic (i.e., well-readable) source code in Java, that ensures a high speed, robustness, and openness of the executable code. Some applications of the Actor Prolog to Java translator are demonstrated, in particular, the real-time intelligent video surveillance, Actor Prolog with Java3D linking, and logic programming of Java applets.

Радиоэлектроника, наносистемы, информационные технологии, Oct 1, 2018

The aim of the work is to create methods and software tools for the terahertz range intelligent v... more The aim of the work is to create methods and software tools for the terahertz range intelligent video surveillance, that is, for automatic analysis of video images in the terahertz frequency range. Terahertz video surveillance provides unique prospects in the area of public safety; in particular, it allows you to remotely identify weapons and dangerous items hidden under clothing on the human body. However, such characteristics of terahertz video, as low resolution, low contrast, and low signal-to-noise ratio, lead to the need to develop new methods and approaches to automatic video analysis. To understand the terahertz video image, the operator of the industrial video surveillance system usually compares it with images in other frequency ranges (visible or infrared). The comparison of these images of different types helps the operator to interpret the colored and/ or one-color spots in the terahertz image in a proper way. In terms of automatic video analysis, this means that the context of the observed events and objects is taken into account, or in other words, a semantic fusion is implemented of the terahertz range video image with video images of other frequency ranges, e.g., near-infrared, visible, etc. The authors consider the semantic fusion of the video images as a critical component of the prospective terahertz intelligent video surveillance technology. A new method of the terahertz video surveillance based on the fusion of the terahertz video with 3D video is proposed. The means of the object-oriented logic programming developed for the semantic fusion of the terahertz and 3D video images are described. The developed method provides a real-time fusion of the terahertz video acquired using the THERZ-7A (Astrohn Technology Ltd) subterahertz scanning device (0.23-0.27 THz) and 3D video data acquired using the Kinect 2 (Microsoft Inc) time-of-flight sensor. The method and software tools for the semantic fusion of the terahertz and 3D video images are developed.

CEUR workshop proceedings, 2019

The terahertz video surveillance opens up new unique opportunities in the field of security in pu... more The terahertz video surveillance opens up new unique opportunities in the field of security in public places, as it allows to detect and thus to prevent usage of hidden weapons and other dangerous items. Although the first generation of terahertz video surveillance systems has already been created and is available on the security systems market, it has not yet found wide application. The main reason for this is in that the existing methods for analyzing terahertz images are not capable of providing hidden and fully-automatic recognition of weapons and other dangerous objects and can only be used under the control of a specially trained operator. As a result, the terahertz video surveillance appears to be more expensive and less efficient in comparison with the standard approach based on the organizing security perimeters and manual inspection of the visitors. In the paper, the problem of the development of a method of automatic analysis of the terahertz video images is considered. As a basis for this method, it is proposed to use the semantic fusion of video images obtained using different physical principles, the idea of which is in that the semantic content of one video image is used to control the processing and analysis of another video image. For example, the information about 3D coordinates of the body, arms, and legs of a person can be used for analysis and proper interpretation of color areas observed on a terahertz video image. Special means of the object-oriented logic programming are developed for the implementation of the semantic fusion of the video data, including special built-in classes of the Actor Prolog logic language for acquisition, processing, and analysis of video data in the visible, infrared, and terahertz ranges as well as 3D video data.

The goal of this study is development of a novel signal processing and analysis method for detail... more The goal of this study is development of a novel signal processing and analysis method for detailed investigation of the time-frequency dynamics of brain cortex electrical activity. The idea of our method of electroencephalograms (EEG) analyzing is in that we consider EEG signal as a composition of so-called wave trains. The wave train term is used to denote a signal localized in time, frequency, and space. We consider the wave train as a typical component of EEG, but not as a special kind of EEG signals. In contrast to papers devoted to detecting wave trains of one or two specific types, such as alpha spindles and sleep spindles, we analyze any kind of wave trains in a wide frequency band. Using this method, we have found three interesting frequency areas where differences were detected between a group of Parkinson's disease (PD) patients and a control group of healthy volunteers. The goal of this work is to check whether the regularities in the mu and beta frequency bands are independent ones, that is, the beta wave trains observed in the analysis were not the second harmonics of the mu wave trains. We have developed a special algorithm that eliminates from the analysis all beta wave trains in EEG signal that were observed simultaneously with the mu wave trains. Analysis of a real experimental data set processed by this algorithm has confirmed that the beta frequency band regularity is separate from the mu frequency band regularity. Moreover, a new significant difference between the left hand tremor and right hand tremor Parkinson's disease patients was discovered.

A method of analysis of EEG wave packets based on wavelets and nonparametric statistics is develo... more A method of analysis of EEG wave packets based on wavelets and nonparametric statistics is developed. The method is compared with standard methods based on Fourier spectra and complex Morlet wavelets by the example of Parkinson's disease experimental data. We demonstrate that these methods are complementary, that is, the standard methods and the wave packet analysis method reveal sufficiently different effects in the EEG data.

Радиоэлектроника, наносистемы, информационные технологии, 2017

INFORMATION TECHNOLOGIES Contents 1. IntroduCtIon (205) 2. the objeCt-orIented logIC programmIng ... more INFORMATION TECHNOLOGIES Contents 1. IntroduCtIon (205) 2. the objeCt-orIented logIC programmIng of the IntellIgent vIdeo surveIllanCe systems (207) 3. an example of logICal InferenCe on 3d data (208) 4. ConClusIon (210) referenCes (211)

An approach to the 3D intelligent video surveillance based on the means of the object-oriented lo... more An approach to the 3D intelligent video surveillance based on the means of the object-oriented logic programming is proposed. In contrast to the conventional 2D video surveillance, the methods of 3D vision provide reliable recognition of parts of the human body that makes possible a new statement of the problem and efficient practical application of methods of people behaviour analysis in the video surveillance systems. The logic-based approach to the intelligent video surveillance allows easily definition of people complex behaviour in terms of simpler activities and postures. The goal of this work is to implement the advantages of the logic programming approach in the area of 3D intelligent video surveillance.

Investigation of the multiple comparisons problem in the analysis of the wave train electrical activity of muscles in Parkinson’s disease patients

Journal of physics, Nov 1, 2019

A new method has been developed for the analysis of the wave train electrical activity of muscles... more A new method has been developed for the analysis of the wave train electrical activity of muscles based on the wavelet analysis and ROC analysis that enables to study the time-frequency characteristics of electromyograms (EMG) and acceleration (ACC) signals in patients with Parkinson’s disease (PD). The idea of the method is to find local maxima (that correspond to the wave trains) in the wavelet spectrogram and to calculate various characteristics describing these maxima: the leading frequency, the duration of the wave trains in periods, the bandwidth of the wave trains, the number of wave trains per second. The degree of difference between a group of patients and a control group of volunteers in the space of these parameters is analyzed. ROC analysis is used for this purpose. The functional dependence of AUC (the area under the ROC curve) on the values of the boundaries of parameters’ ranges under consideration is investigated. The developed method involves investigation of a big number of ranges of selected characteristics; therefore a multiple comparisons problem appears during statistical hypothesis testing. It is necessary to find a compromise between the degree of detail of the studied characteristics and the magnitude of the Bonferroni correction. The paper describes the statistical hypothesis testing on the data of early Parkinson’s disease patients.

Journal of physics, Sep 1, 2018

new method of signal analysis based on wavelet analysis, ROCanalysis, and non-parametric statisti... more new method of signal analysis based on wavelet analysis, ROCanalysis, and non-parametric statistics for detailed investigation of the time-frequency dynamics of the electrical activity of the cerebral cortex. The idea of the method is in that the electroencephalogram (EEG) is considered as a set of wave trains (WT). WT is detected as a local maximum in the wavelet spectrogram of EEG. We consider WT as a typical component of EEG, but not as a special kind of EEG signals. The following parameters of WT are accounted: the frequency, the duration, the bandwidth, the number of WT per second, and the power spectral density (PSD). Differences between a group of the first stage Parkinson's disease patients and a group of healthy volunteers in the space of these parameters are investigated. ROC-analysis is used for this purpose. functional dependence of AUC on the boundaries of the ranges of these parameters. Using this method, we have identified three frequency ranges, where differences between the group of the patients and the healthy volunteers were discovered. The paper describes the results of the investigation of the specificity of these features of early stages of Parkinson's disease.

Zhurnal Nevrologii I Psikhiatrii Imeni S S Korsakova, 2018

Для анализа ЭЭГ разработано большое количество методов, основанных на анализе спектров Фурье, вей... more Для анализа ЭЭГ разработано большое количество методов, основанных на анализе спектров Фурье, вейвлет-анализе, авторегрессионных моделях, фильтрации и др. [1, 2]. Снижение частоты в α-диапазоне при болезни Паркинсона (БП) было показано многими авторами [3

Parkinsonism & Related Disorders, 2016

Investigation of Specificity of Parkinson's Disease Features Obtained Using the Method of Cerebral Cortex Electrical Activity Analysis Based on Wave Trains

In recent years, spindle-shaped electrical activity became interesting for researchers looking fo... more In recent years, spindle-shaped electrical activity became interesting for researchers looking for new methods of time-frequency electroencephalogram (EEG) analysis. We call signals of this type as wave trains; a wave train (a wave packet) is an electrical signal that is localized in space, frequency, and time. Examples of wave trains in EEG are alpha, beta, and sleep spindles. We analyze any kinds of wave train electrical activity of the brain in a wide frequency range. We have developed a new method for analyzing wave train electrical activity of the cerebral cortex based on wavelet analysis and ROC analysis that enables to study the detailed time-frequency features of EEG in patients with neurodegenerative diseases such as Parkinson's disease (PD). The idea of the method is to find local maxima in a wavelet spectrogram and to calculate various characteristics describing these maxima (called wave trains): the leading frequency, the duration (the full-width on the half-maximum of the peak in the spectrogram, FWHM), the bandwidth (FWHM), the number of wave trains per second. Then we conduct statistical analysis of these characteristics. In our previous papers, frequency ranges were found where the quantity of wave trains per second differs between a group of patients in early stage of PD and a group of healthy volunteers. In this paper, the specificity of these PD features is investigated in comparison with the patients with essential tremor (ET).

Investigation of Surface EMG and Acceleration Signals of Limbs’ Tremor in Parkinson’s Disease Patients Using the Method of Electrical Activity Analysis Based on Wave Trains

Lecture Notes in Computer Science, 2018

In recent years, spindle-shaped electrical activity became interesting for researchers looking fo... more In recent years, spindle-shaped electrical activity became interesting for researchers looking for new methods of time-frequency analysis of electromyograms (EMG) and acceleration (ACC) signals. We call signals of this type as wave trains; a wave train (a wave packet) is an electrical signal that is localized in space, frequency, and time. Examples of wave trains in electroencephalograms (EEG) are alpha spindles, beta spindles, and sleep spindles. We analyze all kinds of wave train electrical activity of the muscles in a wide frequency range. We have developed a new method for analyzing wave train electrical activity of muscles based on wavelet analysis and ROC analysis that enables to study the time-frequency features of EMG and ACC in limbs’ tremor in patients with neurodegenerative diseases such as Parkinson’s disease (PD).

Метод частотно-временного анализа совместных измерений электроэнцефалограмм, электромиограмм и механического тремора при болезни Паркинсона

Радиотехника и электроника, 2015

The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, May 12, 2023

This work aims to study and develop methods and tools for analyzing video-EEG monitoring of delay... more This work aims to study and develop methods and tools for analyzing video-EEG monitoring of delayed cerebral ischemia after subarachnoid haemorrhage. A study was made of methods and algorithms for processing video images, which are supposed to be used to recognize life events and medical care for a patient, which can lead to artefacts in the patient's EEG records. An approach to video monitoring of the patient was proposed and tested on real video monitoring data using object-oriented logic programming methods in combination with neural network methods for image analysis.

Journal of physics, Sep 1, 2018

virtual machine for low-level video processing in the Actor Prolog object-oriented logic language... more virtual machine for low-level video processing in the Actor Prolog object-oriented logic language. The principle of operation of this machine is the following one: (1) The machine keeps a sequence of commands of the low-level video processing. This sequence of commands is to be applied to every frame of the video. The loading of these commands into the machine is performed using predicates of the VideoProcessingMachine built-in class. (2) The machine keeps internal data arrays that are related to various sub-stages of the lowlevel video processing. Currently, the following sub-stages of the processing are implemented in the machine: preprocessing of the frame; processing of the frame in the pixel representation; selection of and processing the foreground pixels in the frame; extraction and tracing the blobs in the sequence of the frames. (3) The machine supports a stack of masks of foreground pixels. This stack enables the processing of different groups of blobs using different methods of image processing. (4) The result of the processing the frame of the video is a set of graphs that contain information about the movements of the blobs as well as other attributes of the blobs in the video scene during given time interval.

Lecture Notes in Computer Science, 2018

Experimental means developed in the Actor Prolog parallel object-oriented logic language for impl... more Experimental means developed in the Actor Prolog parallel object-oriented logic language for implementation of heterogeneous multichannel intelligent visual surveillance systems are considered. These means are examined by the instance of a logic program for permanent monitoring of people's body parts temperature in the area of visual surveillance. The logic program implements a fusion of heterogeneous data acquired by two devices: (1) 3D coordinates of the human body are measured using a time-of-flight (ToF) camera; (2) 3D coordinates of the human body skeleton are computed on the base of 3D coordinates of the body; (3) a thermal video is acquired using a thermal imaging camera. In the considered example, the thermal video is projected to the 3D surface of the human body; then the temperature of the human body is projected to the vertices and edges of the skeleton. A special logical agent (i.e., the logic program that is written in Actor Prolog) implements these operations in real-time and transfers the data to another logical agent. The latter agent implements a time average of the temperature of the human skeletons and displays colored 3D images of the skeletons; the average temperature of the vertices and edges of the skeletons is depicted by colors. The logic programming means under consideration are developed for the purpose of the implementation of logical analysis of video scene semantics in the intelligent visual surveillance systems.

Радиоэлектроника, наносистемы, информационные технологии, Oct 1, 2018

The aim of this work is automation of neurophysiological experiments, namely, intelligent video m... more The aim of this work is automation of neurophysiological experiments, namely, intelligent video monitoring of the behaviour of laboratory rats during the social recognition cognitive test on the working memory. The test is conducted in the box with a sawdust background, simultaneously with EEG recording. Automatic video processing supplies objectivity of the interpretation of the results of the testing and provides new possibilities for the standardizing of the neurophysiological experiments. In the paper, methods and means for the logical description and analysis of the behaviour of experimental animals are considered. Recommendations for improving the experimental technique of the social recognition test are elaborated on the base of the results of the experiments with the automatical video processing.

The problem of the video monitoring the laboratory rats by the means of the object-oriented logic... more The problem of the video monitoring the laboratory rats by the means of the object-oriented logic programming is considered. The main task of the video monitoring is the analysis of the behavior of the animals in cognitive testing. An essential feature of the video records is in that the experiments are conducted in the same cage where the animal lives, that is, the background of the cage is sawdust. The color of the animals is about the same as the color of the sawdust; thus the detection of the animals is not a simple task. An additional difficulty is in that the videos were recorded simultaneously with electroencephalograms (EEG) in the animals; thus the head of the rat is connected with EEG cable that moves and causes false detections of recognition algorithms. In the paper, development of low-level algorithms for video analysis as well as logical methods for the analysis of the animal behavior is discussed. The methods and algorithms are implemented in the Actor Prolog object-oriented logic language.

Rules and Rule Markup Languages for the Semantic Web, 2015

A method for the monitoring of anomalous human behaviour that is based on the logical description... more A method for the monitoring of anomalous human behaviour that is based on the logical description of complex human behaviour patterns and special kinds of blob (a separated area of a foreground image) motion statistical metrics is developed. The concurrent object-oriented logic language is used for the analysis of graphs of tracks of moving blobs; the graphs are supplied by low-level analysis algorithms implemented in a special built-in class of Actor Prolog. The blob motion statistics is collected by the low-level analysis procedures that are of the need for the discrimination of running people, people riding bicycles, and cars in a video scene. The first-order logic language is used for implementing the fuzzy logical inference based on the blob motion statistics. A research software platform is developed that is based on the Actor Prolog logic language and a state-of-the-art Prolog-to-Java translator for experimenting with the intelligent visual surveillance.

Rules and Rule Markup Languages for the Semantic Web, 2015

Actor Prolog is a concurrent object-oriented logic language developed in [1]. We demonstrate a st... more Actor Prolog is a concurrent object-oriented logic language developed in [1]. We demonstrate a state-of-the-art translator of Actor Prolog to Java developed in the framework of the Intelligent Visual Surveillance Logic Programming project [2]. The translator implements a set of high-level and low-level code optimization methods and generates a kind of the idiomatic (i.e., well-readable) source code in Java, that ensures a high speed, robustness, and openness of the executable code. Some applications of the Actor Prolog to Java translator are demonstrated, in particular, the real-time intelligent video surveillance, Actor Prolog with Java3D linking, and logic programming of Java applets.

Радиоэлектроника, наносистемы, информационные технологии, Oct 1, 2018

The aim of the work is to create methods and software tools for the terahertz range intelligent v... more The aim of the work is to create methods and software tools for the terahertz range intelligent video surveillance, that is, for automatic analysis of video images in the terahertz frequency range. Terahertz video surveillance provides unique prospects in the area of public safety; in particular, it allows you to remotely identify weapons and dangerous items hidden under clothing on the human body. However, such characteristics of terahertz video, as low resolution, low contrast, and low signal-to-noise ratio, lead to the need to develop new methods and approaches to automatic video analysis. To understand the terahertz video image, the operator of the industrial video surveillance system usually compares it with images in other frequency ranges (visible or infrared). The comparison of these images of different types helps the operator to interpret the colored and/ or one-color spots in the terahertz image in a proper way. In terms of automatic video analysis, this means that the context of the observed events and objects is taken into account, or in other words, a semantic fusion is implemented of the terahertz range video image with video images of other frequency ranges, e.g., near-infrared, visible, etc. The authors consider the semantic fusion of the video images as a critical component of the prospective terahertz intelligent video surveillance technology. A new method of the terahertz video surveillance based on the fusion of the terahertz video with 3D video is proposed. The means of the object-oriented logic programming developed for the semantic fusion of the terahertz and 3D video images are described. The developed method provides a real-time fusion of the terahertz video acquired using the THERZ-7A (Astrohn Technology Ltd) subterahertz scanning device (0.23-0.27 THz) and 3D video data acquired using the Kinect 2 (Microsoft Inc) time-of-flight sensor. The method and software tools for the semantic fusion of the terahertz and 3D video images are developed.

CEUR workshop proceedings, 2019

The terahertz video surveillance opens up new unique opportunities in the field of security in pu... more The terahertz video surveillance opens up new unique opportunities in the field of security in public places, as it allows to detect and thus to prevent usage of hidden weapons and other dangerous items. Although the first generation of terahertz video surveillance systems has already been created and is available on the security systems market, it has not yet found wide application. The main reason for this is in that the existing methods for analyzing terahertz images are not capable of providing hidden and fully-automatic recognition of weapons and other dangerous objects and can only be used under the control of a specially trained operator. As a result, the terahertz video surveillance appears to be more expensive and less efficient in comparison with the standard approach based on the organizing security perimeters and manual inspection of the visitors. In the paper, the problem of the development of a method of automatic analysis of the terahertz video images is considered. As a basis for this method, it is proposed to use the semantic fusion of video images obtained using different physical principles, the idea of which is in that the semantic content of one video image is used to control the processing and analysis of another video image. For example, the information about 3D coordinates of the body, arms, and legs of a person can be used for analysis and proper interpretation of color areas observed on a terahertz video image. Special means of the object-oriented logic programming are developed for the implementation of the semantic fusion of the video data, including special built-in classes of the Actor Prolog logic language for acquisition, processing, and analysis of video data in the visible, infrared, and terahertz ranges as well as 3D video data.

The goal of this study is development of a novel signal processing and analysis method for detail... more The goal of this study is development of a novel signal processing and analysis method for detailed investigation of the time-frequency dynamics of brain cortex electrical activity. The idea of our method of electroencephalograms (EEG) analyzing is in that we consider EEG signal as a composition of so-called wave trains. The wave train term is used to denote a signal localized in time, frequency, and space. We consider the wave train as a typical component of EEG, but not as a special kind of EEG signals. In contrast to papers devoted to detecting wave trains of one or two specific types, such as alpha spindles and sleep spindles, we analyze any kind of wave trains in a wide frequency band. Using this method, we have found three interesting frequency areas where differences were detected between a group of Parkinson's disease (PD) patients and a control group of healthy volunteers. The goal of this work is to check whether the regularities in the mu and beta frequency bands are independent ones, that is, the beta wave trains observed in the analysis were not the second harmonics of the mu wave trains. We have developed a special algorithm that eliminates from the analysis all beta wave trains in EEG signal that were observed simultaneously with the mu wave trains. Analysis of a real experimental data set processed by this algorithm has confirmed that the beta frequency band regularity is separate from the mu frequency band regularity. Moreover, a new significant difference between the left hand tremor and right hand tremor Parkinson's disease patients was discovered.

A method of analysis of EEG wave packets based on wavelets and nonparametric statistics is develo... more A method of analysis of EEG wave packets based on wavelets and nonparametric statistics is developed. The method is compared with standard methods based on Fourier spectra and complex Morlet wavelets by the example of Parkinson's disease experimental data. We demonstrate that these methods are complementary, that is, the standard methods and the wave packet analysis method reveal sufficiently different effects in the EEG data.

Радиоэлектроника, наносистемы, информационные технологии, 2017

INFORMATION TECHNOLOGIES Contents 1. IntroduCtIon (205) 2. the objeCt-orIented logIC programmIng ... more INFORMATION TECHNOLOGIES Contents 1. IntroduCtIon (205) 2. the objeCt-orIented logIC programmIng of the IntellIgent vIdeo surveIllanCe systems (207) 3. an example of logICal InferenCe on 3d data (208) 4. ConClusIon (210) referenCes (211)

An approach to the 3D intelligent video surveillance based on the means of the object-oriented lo... more An approach to the 3D intelligent video surveillance based on the means of the object-oriented logic programming is proposed. In contrast to the conventional 2D video surveillance, the methods of 3D vision provide reliable recognition of parts of the human body that makes possible a new statement of the problem and efficient practical application of methods of people behaviour analysis in the video surveillance systems. The logic-based approach to the intelligent video surveillance allows easily definition of people complex behaviour in terms of simpler activities and postures. The goal of this work is to implement the advantages of the logic programming approach in the area of 3D intelligent video surveillance.

Investigation of the multiple comparisons problem in the analysis of the wave train electrical activity of muscles in Parkinson’s disease patients

Journal of physics, Nov 1, 2019

A new method has been developed for the analysis of the wave train electrical activity of muscles... more A new method has been developed for the analysis of the wave train electrical activity of muscles based on the wavelet analysis and ROC analysis that enables to study the time-frequency characteristics of electromyograms (EMG) and acceleration (ACC) signals in patients with Parkinson’s disease (PD). The idea of the method is to find local maxima (that correspond to the wave trains) in the wavelet spectrogram and to calculate various characteristics describing these maxima: the leading frequency, the duration of the wave trains in periods, the bandwidth of the wave trains, the number of wave trains per second. The degree of difference between a group of patients and a control group of volunteers in the space of these parameters is analyzed. ROC analysis is used for this purpose. The functional dependence of AUC (the area under the ROC curve) on the values of the boundaries of parameters’ ranges under consideration is investigated. The developed method involves investigation of a big number of ranges of selected characteristics; therefore a multiple comparisons problem appears during statistical hypothesis testing. It is necessary to find a compromise between the degree of detail of the studied characteristics and the magnitude of the Bonferroni correction. The paper describes the statistical hypothesis testing on the data of early Parkinson’s disease patients.

Journal of physics, Sep 1, 2018

new method of signal analysis based on wavelet analysis, ROCanalysis, and non-parametric statisti... more new method of signal analysis based on wavelet analysis, ROCanalysis, and non-parametric statistics for detailed investigation of the time-frequency dynamics of the electrical activity of the cerebral cortex. The idea of the method is in that the electroencephalogram (EEG) is considered as a set of wave trains (WT). WT is detected as a local maximum in the wavelet spectrogram of EEG. We consider WT as a typical component of EEG, but not as a special kind of EEG signals. The following parameters of WT are accounted: the frequency, the duration, the bandwidth, the number of WT per second, and the power spectral density (PSD). Differences between a group of the first stage Parkinson's disease patients and a group of healthy volunteers in the space of these parameters are investigated. ROC-analysis is used for this purpose. functional dependence of AUC on the boundaries of the ranges of these parameters. Using this method, we have identified three frequency ranges, where differences between the group of the patients and the healthy volunteers were discovered. The paper describes the results of the investigation of the specificity of these features of early stages of Parkinson's disease.

Zhurnal Nevrologii I Psikhiatrii Imeni S S Korsakova, 2018

Для анализа ЭЭГ разработано большое количество методов, основанных на анализе спектров Фурье, вей... more Для анализа ЭЭГ разработано большое количество методов, основанных на анализе спектров Фурье, вейвлет-анализе, авторегрессионных моделях, фильтрации и др. [1, 2]. Снижение частоты в α-диапазоне при болезни Паркинсона (БП) было показано многими авторами [3

Parkinsonism & Related Disorders, 2016

Investigation of Specificity of Parkinson's Disease Features Obtained Using the Method of Cerebral Cortex Electrical Activity Analysis Based on Wave Trains

In recent years, spindle-shaped electrical activity became interesting for researchers looking fo... more In recent years, spindle-shaped electrical activity became interesting for researchers looking for new methods of time-frequency electroencephalogram (EEG) analysis. We call signals of this type as wave trains; a wave train (a wave packet) is an electrical signal that is localized in space, frequency, and time. Examples of wave trains in EEG are alpha, beta, and sleep spindles. We analyze any kinds of wave train electrical activity of the brain in a wide frequency range. We have developed a new method for analyzing wave train electrical activity of the cerebral cortex based on wavelet analysis and ROC analysis that enables to study the detailed time-frequency features of EEG in patients with neurodegenerative diseases such as Parkinson's disease (PD). The idea of the method is to find local maxima in a wavelet spectrogram and to calculate various characteristics describing these maxima (called wave trains): the leading frequency, the duration (the full-width on the half-maximum of the peak in the spectrogram, FWHM), the bandwidth (FWHM), the number of wave trains per second. Then we conduct statistical analysis of these characteristics. In our previous papers, frequency ranges were found where the quantity of wave trains per second differs between a group of patients in early stage of PD and a group of healthy volunteers. In this paper, the specificity of these PD features is investigated in comparison with the patients with essential tremor (ET).

Investigation of Surface EMG and Acceleration Signals of Limbs’ Tremor in Parkinson’s Disease Patients Using the Method of Electrical Activity Analysis Based on Wave Trains

Lecture Notes in Computer Science, 2018

In recent years, spindle-shaped electrical activity became interesting for researchers looking fo... more In recent years, spindle-shaped electrical activity became interesting for researchers looking for new methods of time-frequency analysis of electromyograms (EMG) and acceleration (ACC) signals. We call signals of this type as wave trains; a wave train (a wave packet) is an electrical signal that is localized in space, frequency, and time. Examples of wave trains in electroencephalograms (EEG) are alpha spindles, beta spindles, and sleep spindles. We analyze all kinds of wave train electrical activity of the muscles in a wide frequency range. We have developed a new method for analyzing wave train electrical activity of muscles based on wavelet analysis and ROC analysis that enables to study the time-frequency features of EMG and ACC in limbs’ tremor in patients with neurodegenerative diseases such as Parkinson’s disease (PD).