350 rub
Journal Biomedical Radioelectronics №5 for 2019 г.
Article in number:
Experimental model and software for the recognition of mental true and false responses on the basis of electroencephalogram analysis
Type of article: scientific article
DOI: 10.18127/j15604136-201905-05
UDC: 612.821.1
Keywords: Information technologies electroencephalogram (EEG) EEG wavelet transform machine learning brain mental activity consciousness polygraph truth and falseness.
Authors:

E.A. Yumatov – Dc. Sc. (Med.), Professor, Academician of the International Academy of Science (Russian Section);  Chief Research Scientist, P.K. Anokhin Research Institute of Normal Physiology (Moscow)

E-mail: eayumatov@mail.ru

V.Yu. Potapov – Engineer, AS “Interfax” (Moscow)

N.A. Karatygin – Ph.D. (Biol.), Research Scientist, P.K. Anokhin Research Institute of Normal Physiology (Moscow)

S.S. Pertsov – Dr.Sc. (Med.), Professor, Corresponding Member of RAS; Deputy Director on Scientific Work, Head of laboratory system mechanisms of an emotional stress, P.K. Anokhin Research Institute of Normal Physiology (Moscow);  Head of Department of Normal Physiology and Medical Physics, Moscow State Medico-Dental University  n.a. A.I. Evdokimov of the Ministry of Health of the Russian Federation

E-mail:s.pertsov@mail.ru

Abstract:

A polygraph, or lie detector, is extensively used in criminal investigations and vocational selection for the testing of false and truthful answers of a person. This technical equipment serves for the conduction of instrumental psychophysiological studies.

Polygraph testing has a serious disadvantage. The result is evaluated from recording of psychophysiological indices, which only indirectly reflect the individual subjective state and do not serve as the criteria for a real mental activity (i.e., deceitful or truthful state of the subject's brain).

In some countries, including Germany, Poland and USA, the results of psychophysiological examination are not considered as evidence.

The limitations of a polygraph study are associated with the fact that this method does not suggest direct recording of mental activity of the human brain, which reflects its deceitful or truthful state.

The brain represents a unique organization in the living nature that is capable of mental activity.

Up to the present time, direct recording and analysis of the signs for brain mental activity were impossible in psychophysiology and neurophysiology.

The advanced methods of electroencephalogram wavelet transform and machine learning were developed in recent years. The electroencephalogram wavelet transform allowed us to determine a principle possibility for the direct, objective recording of mental activity in the human brain. These data can be used to develop a new information technology for the recognition of truthful and false states of the human brain.

The overall goal of the research is to develop a fundamentally new information technology to identify in the brain's mental activity a truthful and deceitful state based on the wavelet transform of the electroencephalogram and machine learning.

For this purpose, an experimental model and software have been created and described in the article for recognizing the truthful and false mental responses of a person based on an analysis of the electroencephalogram.

The software was developed with Microsoft Visual Studio 2017 and Net Framework 4.5. This software is simple in use and works with the Russian language interface.

This work was designed to develop a fundamentally new information technology to identify a truthful and deceitful state in the brain mental activity, which suggests the EEG wavelet transform.

The developed experimental model and information-software allow us to compare electroencephalographic indicators of two mental states of brain activity, one of which is deceitful; the other is truthful.

Pages: 42-48
References
  1. Holodnyj YU.I. Analiz fiziologicheskih reakcij, registriruemyh v processe oprosa s ispol'zovaniem poligrafa: Prakticheskoe posobie. M. 1999. S. 6–52. 
  2. Ogloblin S.I., Molchanov A.YU. Instrumental'naya «detekciya lzhi»: akademicheskij kurs. YAroslavl': Nyuans. 2004. 464 s. 
  3. ZHurin S.I. Praktika i teoriya ispol'zovaniya detektorov lzhi. Izd. 2-e, stereotipn. M.: Goryachaya liniya – Telekom. 2011. 144 s. 
  4. Pavlov I.P. Dvadcatiletnij opyt ob"ektivnogo izucheniya vysshej nervnoj deyatel'nosti (povedeniya) zhivotnyh // Polnoe sobranie sochinenij. 1951. M.–

  5. L.: Izd. AN SSSR. 

  6. Anohin P.K. Psihicheskaya forma otrazheniya dejstvitel'nosti. Sbornik Leninskaya teoriya otrazheniya i sovremennost' / Pod red. T. Pavlova. 1969. Sofiya. Razd. 1. Gl. 3. S. 109.
  7. Bekhtereva N.P., Budzen P.V., Gogolicyn YU.L. Mozgovye kody psihicheskoj deyatel'nosti. L.: Nauka. 1977. S. 165.
  8. Ivanickij A.M. Glavnaya zagadka prirody: kak na osnove processov mozga voznikayut sub"ektivnye perezhivaniya // Psihologicheskij zhurnal. 1999. T.

  9. 20. № 3. S. 93–104.

  10. Nagel' T. «Myslimost' nevozmozhnogo i problema duha i tela» // Voprosy filosofii. 2001. № 8.
  11. Sudakov K.V. Sistemnye mekhanizmy psihicheskoj deyatel'nosti // Nevrologiya i psihiatriya im. S.S. Korsakova. 2010. T. 110. № 2. S. 4–14.
  12. Popper K. Znanie i psihofizicheskaya problema: V zashchitu vzaimodejstviya: Per. s angl. I.V. ZHuravleva. M., 2008. 256 c.
  13. Crick F., Koch C. Why neuroscience may be able to explain consiousness // Scientific Amer. 1995. v.273, P. 66.
  14. Sperry R.W. Neurology and the mind-brain problem // Am. Sci. 1952. V. 40. P. 291–312. 
  15. YUmatov E.A. Psihicheskaya deyatel'nost' mozga – «klyuch» k poznaniyu // Vestnik Mezhdunarodnoj akademii nauk. Russkaya sekciya. 2013. № 1. C. 35–45.
  16. Yumatov E.A. To knowledge of the origin of the brain mental activity // World Journal of Neuroscience. 2014. V. 4. № 2. P. 170–18213. 
  17. YUmatov E.A. Distancionno-polevye proyavleniya psihicheskoj deyatel'nosti mozga // Biomedicinskaya radioelektronika. 2019. T. 22. № 1. S. 5–13.
  18. Grubov V.V., Sitnikova E.YU., Koronovskij A.A., Pavlov A.N., Hramov A.E. Avtomaticheskoe vydelenie i analiz oscillyatornyh patternov na nestacionarnyh signalah EEG s ispol'zovaniem vejvletnogo preobrazovaniya i metoda empiricheskih mod // Izv. RAN. Ser. fizicheskaya. 2012. № 76(12). S. 1520–1523.
  19. Koronovskij A.A., Makarov V.A., Pavlov A.N., Sitnikova E.YU., Hramov A.E. Vejvlety v nejrodinamike i nejrofiziologii. M.: Fizmatlit. 2013.
  20. Pavlov A.N., Hramov A.E., Koronovskij A.A., Sitnikova E.YU., Makarov V.A., Ovchinnikov A.A. Vejvlet-analiz v nejrodinamike // UFN. 2012. № 182(9). S. 905–939 (http://ufn.ru/ru/articles/2012/9/a/).
  21. Hramov A.E., Koronovskii A.A., Makarov V.A., Pavlov A.N., Sitnikova E.Yu. Wavelets in Neuroscience. Springer Heidelberg New York Dordrecht London. 2015. 318 p. 
  22. YUmatov E.A., Hramov A.E., Grubov V.V., Glazachev O.S, Dudnik E.N., Karatygin N.A. Issledovanie vozmozhnosti raspoznavaniya psihicheskoj deyatel'nosti mozga na osnove vejvletnogo analiza elektroencefalogrammy // Biomedicinskaya Radioelektronika. 2018. № 4. S. 3–12.
  23. Yumatov E.A., Hramov A.E., Grubov V.V., Glazachev O.S., Dudnik E.N., Karatygin N.A. Possibility for recognition of psychic brain activity with continuous wavelet analysis of EEG // Journal of Behavioral and Brain Science(JBBS). 2019. V. 9. № 3. 
  24. MacDonald M. Pro WPF 4.5 in C#: Windows Presentation Foundation in NET 4.5 Apress. 2012. 1095 p. 4th Edition.
Date of receipt: 10 апреля 2019 г.