Prevention of accidents and catastrophes of anthropogenic origin,
caused by the so-called human factor, is today an actual scientific, methodological
and technical task. Analysis of major recent accidents shows that the range of
potentially hazardous facilities is not limited to the traditionally considered
objects of the nuclear, chemical, oil and gas industries. At the present time,
it is also necessary to consider the possibility of accidents caused by the
human factor on public transport, during mass sports events, on hydro and
thermal power stations and also in virtually all harmful industries.
The most effective solution to the problem should be
considered the implementation of the approach consisting in the continuous
monitoring of the current psycho-emotional and functional state of the operator
directly during the performance of his production or official duties [1]. The
most indicative in this regard is modern high-speed transport [2-5]. The basis
for implementing this approach in practice is the use of remote, non-contact
technologies for recording current bio-parameters of the operator in real time.
The most informative and safe from the medical point of view technologies for
remote registration of human bio-parameters nowadays are acoustic [6] and
optical [7] ones. It should be noted that, for example, acoustic technology of
stress diagnostics is quite actively used nowadays in sports [8-10] and ballet
[11]. Optical technologies of the visible range are mainly oriented to the
recognition of human emotions [12-21], or an analysis of the direction change
dynamics of the view [22, 23]. These technologies are passive, do not have any
effect on humans and suggest only the registration of natural radiation
emanating from it in the corresponding spectra. As registered bio-parameters,
the image of the operator's face in the visible and infrared [24, 25] optical
radiation range, as well as speech information, usually appear. The possibility
of processing the latter is due to the accepted order of communication between
operators and the group leader (the shift supervisor). This order, as a rule,
provides for mandatory repetition by the executor of received voice commands
and orders.
Unfortunately, the practical approaches to recording current
human bio-parameters are oriented mainly to the simultaneous use of an
extremely limited number of remote non-contact technologies or in general only
one of them. For example, only processing an image of a person's face in the
visible range of optical radiation [13-24], or only acoustic technology [8-11].
This situation largely limits the possible applications of
remote non-contact technologies. In practice, the effective application of
technology for the listed options for their use is possible only in the case of
a quasi-static arrangement of the operator. In the case of active human
movements, the presence of sharp turns and inclinations of his head, the use of
individual technologies is ineffective. The main reason is the occurrence of
so-called "dead" time intervals, during which the registration of bio-parameters
is impossible.
In [1, 6, 7], an author's integrated approach is proposed,
which makes it possible to increase the efficiency of recording human bio-parameters
and, as a consequence, the reliability of the evaluation of its current psycho-emotional
and functional state. The essence of the integrated approach is the
simultaneous registration of bio-parameters in three areas - acoustic, optical
visible range and infrared. This makes it possible to minimize or completely eliminate
dead time intervals.
The processing of the bio-parameters obtained in this way
with the help of specialized software makes it possible to determine a whole
set of parameters, first of all, characterizing the operation of the
cardiovascular system of the operator, the work of his respiratory system, and
the level of excitation of his peripheral nervous system [1]. Typical
parameters that characterize the current state of the cardiovascular system of
the operator are, for example, heart rate, blood pressure, heart rate
variability. The most informative parameters characterizing the current state
of the peripheral nervous system are: a reaction similar to GSR (skin-galvanic
reaction), the dynamics of the pupil size change, the level of the so-called
tremor in the speaker's voice. The total number of parameters characterizing the
current psychoemotional and functional state of the operator at each moment of time
is about 30 [1].
The complexity of displaying and analyzing the time dynamics
of changes in all of these parameters for each shift operator (brigade) makes
it practically impossible to carry out their constant monitoring by authorized
specialists. For this reason, in practice, integral estimates of the current
state are used, which are more convenient for rapid analysis and forecasting of
possible undesirable changes in the state of operators [1, 6, 7].
Unfortunately, the graphical representation of these estimates in the form of
graphs of time dependencies [2-5, 8-25] does not fully allow the realization of
the results comparison function. Especially it concerns the comparison of the
results obtained during the training sessions on the simulators and directly in
the process of production activity, as well as the results obtained at
different times by different operators.
The purpose of the work is to analyze the possibilities, as
well as present the results of laboratory testing of the proposed visualization
form of the current psychoemotional and functional state of the dangerous
objects management operators in the form of multifunctional pie charts.
Figure 1 shows the working window of specialized software,
which displays the results of bio-parameters processing using infrared
technology for their registration [1, 7]. This software is an integral part of
the experimental software and hardware complex for continuous assessment of the
current psycho-emotional and functional state of a person on the basis of using
remote, non-contact technologies for bio-parameters recording developed by the
authors. This form of graphical representation of the temporary change in human
bio-parameters is typical for the monitoring and visualization means used in practice
[2-5, 8-25]. As part of the specialized software, this form of graphical representation
is implemented mainly for test and diagnostic purposes.
Specificity of registration and processing
of biological parameters in the infrared radiation range is that such natural radiation
is almost completely absorbed by human clothing. As a result, to
register bio-parameters it is possible to use practically only the infrared
image of the face, sometimes the neck and hands.
Fig.1. Human bio-parameters
registration process visualization during the training sessions
(with a high load in the middle of classes)
The working window presented in Fig. 1 allows the
instructor, who is currently monitoring the operator's condition, to check the
quality of the original infrared image (1), as well as the correct positioning
of the operator's head in the field of view of the thermal imaging camera (2). Control
over the position and possible head inclinations is carried out automatically
in the analysis of the total heat flux recorded by the camera (Graph 3). This
information is necessary to identify the moments of time during which the most
reliable registration of bio-information is possible [1, 6, 7]. Charts 4-6 show
the change in time of heart rate (Heart Frq), respiration rate (Brth Fnc) and
motor activity (Motor R). Figure 7 shows the time variations of the integral
characteristic (IR Channel General Model), which allows you to assess the
current psycho-emotional and functional state of the operator. The values of
the integral characteristic are calculated on the basis of a model that takes
into account the deviations of the current bio-parameters from their values for
the normal quiet state of the operator [1, 6]. The length of time slots 8 is
set by the instructor before the start of the monitoring process. It is chosen
based on the planned total duration of the monitoring process. For example, for
an 8-hour work shift, it is usually 25-30 minutes. For training sessions with a
total duration of 2 hours, it can be 5-7 minutes. As a result of such time
intervals settings, the instructor has the opportunity to observe and analyze
the entire production or educational process. Levels 9 correspond to different
degrees of the operator fatigue [1, 7]. The contribution of each of the
parameters characterizing the work of the cardiovascular system, nervous system
and respiratory system, in the integral characteristic 7 is shown respectively
in red (10), blue (11) and green (12) colors.
The software under consideration also allows displaying the results
of remote measurement of bio-parameters with the help of acoustic technology,
as well as optical technology of the visible range, in a similar graphical
form. In Fig. 2 shows an example of the resulting function Q(t), which assesses
the current psycho-emotional and functional state of the operator on the basis
of bio-parameters monitoring using optical and acoustic technologies. The
values of this function are determined on the basis of a linear model that
takes into account the contribution of each of the above mentioned measuring technologies
(1, 2, 3) [1, 6, 7].
Fig.2. Monitoring
of the current psycho-emotional and functional state during the medium intensity
training sessions conduction for 2 hours.
Threshold values of Q1, Q2 and Q3 determine the boundaries
of a possible change in the state of the operator. The entire range of possible
values of the function Q(t) is usually subdivided into three regions. The range
of Q1≤ Q(t) ≤ Q2 corresponds to the normal operating
state of the operator. The ranges 0 ≤ Q(t) < Q1
and Q2 < Q(t) ≤ Q3 characterize the current state
of the operator, respectively, as strongly relaxed (sleepy) and stressed. The
values of Q(t) > Q3 correspond to strong mental and physical
fatigue.
The main drawbacks of this visualization technique are difficulties
in comparing the results obtained during training, training and work shifts of different
duration, as well as their low visibility.
In the paper, the use of unified pie charts is proposed to present
monitoring results. With the help of such diagrams, it is possible to
visualize, analyze and compare the results obtained at all stages of
preparation, testing and operational activities of operational personnel.
In Fig. 3 is presented a view of a unified pie chart showing
the change in the current functional and psycho-emotional state of the operator
(function Q (t)).
Fig. 3. An example of
a unified pie chart showing the change in the psycho-emotional and functional
state of the operator during a high intensity training session for 5 hours
The center of the pie chart corresponds to the beginning of
the monitoring (1). The peripheral part of the pie chart (2) corresponds to the
current time, or the time of the end of monitoring. Circles (3) correspond to
different moments of time. The quadrants 0-Q1, Q1-Q2, Q2-Q3 and Q3-0 correspond
to the characteristic domains of the operator possible states considered
earlier. Different colors show the contribution of different bioparameters
groups, similar to the information shown in Fig. 2.
If the pie chart is in the formation stage, it is dynamic.
If the diagram is fully formed, it is static (Fig. 3). Fig. 4 illustrates the
process of a static circular diagram forming, shown in Fig. 3. For this
purpose, a series of intermediate dynamic diagrams (a), (b), (c) and (d) are
shown for the time points of 1 hour, 2 hours, 3 hours and 4 hours, respectively.
Analysis of chart data allows you to trace trends in the operator current state
changes, as well as assess trends in its further change, for example, when
conducting training sessions on the simulator.
a)
b) c) d)
Fig. 4. A static
chart forming process illustration
From the above sequence of diagrams it is clearly visible
that the operator performing the training tasks has started to work in a normal
working condition. His indicators at this time were in the range of Q1-Q2
(Figure 4a). By the end of the second hour of training, the operator's
condition became more tense and approached the Q2 border (Figure 4b). During
the third and fourth hours of exercise, fatigue began to increase. Integral
estimates of the current state were in the range Q2-Q3 (Fig. 4c, d). The
obtained data allow the instructor to make a reasonable conclusion about the
level of professional training of this operator, and also to compare these
results with previous ones, as well as with the results obtained by other
operators.
Thus, the proposed form of visualization of the current
psycho-emotional and functional state of the dangerous object managing operator
is more convenient and visual. It makes it possible to simplify the analysis
and comparison of various results obtained during the conduct of training
sessions of various types and duration. This circumstance is also of great
importance for the decision-making process automation.
The form of information visualization can also be used to
display possible change trends in the operator state when the same operating
conditions are maintained. Under working conditions, one should understand the
complexity of the production or training tasks being solved, as well as climatic
and noise conditions. In Fig. 5 shows an example of a pie chart containing both
actual data about the current state of the operator and their forecast values.
Fig. 5. Visualization
of current and forecast indicators: 1, 2 – areas of forecast values;
3 – the area of
achieved indicators within 5 hours
Areas of predicted values (1 and 2) on the pie chart are
marked with red circles and have a less bright color in comparison with the
areas showing the achieved results. To obtain predicted values, one of the
extrapolation methods is used. The area of the nearest forecast 1 allows the
instructor to assess a possible change in the operator's state within 0.5-1
hours. The region of the long-range forecast 2 allows obtaining similar
estimates within 2-3 hours. As can be seen from the diagram above, the status of
the operator in question can be qualified as very tense, which indicates either
a low level of professional training, if it is a question of training sessions,
or about the need to change the conditions of production activities, including
the organization of breaks and rest.
In Fig. 6 shows the corresponding dynamic diagrams with a
projection of the predicted values.
a) b)
c) d)
Fig. 6. Dynamic diagrams
with prediction values 1 and 2
according to the achieved indicators, respectively, during 1, 2, 3 and 4 hours
of operation - respectively, diagrams a) – d)
It should be noted that the forecasting of a possible change
in the psycho-emotional and functional state of the operator is carried out
taking into account personal data stored in a specialized database. Such a
database usually contains information on the results of periodic scheduled
medical examinations, the results of testing in laboratories of
psycho-physiological support, as well as the results of all training sessions.
This allows you to accurately implement the forecast, taking into account personal
characteristics.
It is most expedient to apply this graphical form of the
operator current state visualization when solving the following tasks:
- assessment of the professional suitability and professional growth of
employees [1, 26];
- an assessment of the complexity of educational and training sessions [26];
- realization of biological feedback [1, 7, 26].
Assessment of the professional growth of employees can be
carried out using the dynamic pie charts discussed above, in which longer time
intervals, for example, 0.5-2 years, are used as the time samples. In this
case, as the integral characteristic of Q(t), it is necessary to use the
achieved results in carrying out scheduled periodic test and certification
activities. As components of the integral characteristic Q(t), in practice,
such indicators as the time of malfunctions elimination in case of emergency
modes of a hazardous object operation, the reaction time, the level of
self-control are used. Threshold values Q1, Q2 and Q3 in this case determine the
achieved professional level of preparation: range 0-Q1 - not high enough; Q1-Q2
- satisfactory; Q2-Q3 is good and Q3-0 is excellent.
In Fig. 7 shows two demonstration variants of changes in the
level of professional training over a time interval of about 20 years (each
time interval is 4 years). Option a) corresponds to the constant growth of
professional skills, which reaches a maximum in the region of 15 years. In the
future, according to statistical data, usually due to age-related changes, this
level may undergo some changes. Option b) illustrates the gradual professional
degradation of a person. The forecast shows a probable deterioration in the
level of vocational training to an unsatisfactory degree.
a) b)
Fig. 7. Examples of predicted
changes in professional skills
Assessment of the complexity of training and training
sessions is carried out on the basis of analysis of static diagrams. As an
integral estimate in this case, we should use the function Q(t), averaged over
all participants in the class. In Fig. 8 shows typical examples of the training
sessions complexity assessment based on this approach. The diagrams thus
obtained can also be used to assess the level of training of teaching
personnel. To do this, it is necessary to compare the diagrams obtained by
carrying out the same trainings by different instructors.
à) á)
Fig. 8. Assessment of
the training sessions intensity with high (a) and low (b) complexity
Biological feedback in practice is widely used in conducting
training sessions in order to increase stress resistance on the basis of
developing skills of self-control and self-regulation. The use of compact
diagrams reflecting the current state of the trainee makes it possible to
automate the learning process using a wide range of software and hardware
systems and simulators. In Fig. 9 visualization of the training stress
resistance process with the use biological feedback technology [26] is
presented. For this purpose, dynamic pie charts with a prediction function are
usually used, which allows the trainee to develop self-monitoring skills for
his condition.
Fig. 9. Example of
training stress resistance: 1, 2 – moments of time of strong stress; 3, 4 –
activation of the self-control and self-regulation processes; 5 – return to
normal operating mode; 6. 7 – near and far forecasts of changes in the current
state of the trainee operator
The visualization technology under consideration has
undergone laboratory testing in the framework of specialized laboratory classes
on the design of modern high-speed digital devices on FPGAs with the SoC
structure of the Altera, Xilinx and MicroSemi (Actel) families. The
visualization technology was used to solve the following problems:
- creation of a set of training and test tasks for the
design of nodes and blocks of digital devices based on modern FPGAs;
- development of methodological tools for assessing the
level of acquired professional knowledge and practical competencies when
working with CAD FPGAs of specified manufacturers;
- adaptation of educational and training sessions to groups
of different specializations that have different sets of engineering
competences in the design of electronic devices.
The relevance of the proposed visualization technology when
conducting practical exercises on the electronic nodes and blocks design using
modern CAD FPGA Quartus, Xilinx and Libero is due to the following factors.
First of all, this is a large amount of processed graphic information, as well
as frequent change of working windows in CAD when switching from one level of
presentation of information to another. These factors lead to a strong
permanent eye strain and, as a result, to rapid fatigue and the growth of
erroneous actions.
The application of the considered visualization technology
allowed creating sets of educational and training tests oriented at 2, 4, 6 and
8 hour of practical exercises with controlled complexity. Managing the
complexity of test tasks was accomplished by adding or removing additional
electronic nodes. As a result, it was possible to develop a balanced set of
test tasks with increasing complexity, focused on cycles of practical exercises.
The application of the developed set in practice makes it possible to ensure
that the integral assessments of the current state of the training group on
average during the whole class will be in the area determined by the boundaries
of Q1 and Q3. Practical approbation of this approach has shown that it is
possible to reduce the number of erroneous actions up to 2-5 times.
The developed methodological tools for assessing the level
of acquired professional knowledge and practical competencies when working with
CAD FPGAs are based on the use of test tasks of a given complexity. The use of
pie charts makes it possible to correlate the achieved results with the time of
execution of the test project, its technical level of implementation, as well
as the number of mistakes made and with mental and physical costs incurred. The
application of these methodological tools permits one to more objectively
assess the depth of acquired professional knowledge and skills, as well as the
ability to apply them in practice.
The analysis of the visualization results of the final
psycho-emotional and functional state obtained during the practical sessions
with the contingents of the listeners of various specializations made it
possible to adapt the content and structure of the training and practical
training on CAD to different groups possessing a different set of engineering
competencies in the design of electronic devices.
The analysis of the visualization results of the
psychoemotional and functional state of listeners of various specializations
made it possible to adapt the content and structure of educational and
practical training on CAD to the available level of preparation.
Figure 10 presents typical examples of averaged results
visualization of the changes dynamics in the psycho-emotional and functional
state for two groups of listeners. The listeners of the first group specialized
in a deep study of electronics. They studied various disciplines on the basics
of digital and analog electronics, as well as on automated means for designing
electronic devices. Typical visualization results for the first group are shown
in Fig. 10a, b. At the same time, Fig.10a corresponds to the most successful
trainees, and Fig. 10b - less successful.
a) b)
c)
d)
Fig.10. Laboratory
approbation of the visualization method
The second group of students did not specialize in a deep
study of electronics. For her, electronic competencies were not the main ones.
Figure 10c, d shows the visualization results for this group. It can be seen
that the process of designing electronic devices for the second group of
listeners was more intense. Figure 10c corresponds to the most successfully
trained listeners of the second group, and Fig.10g - less successful. A
characteristic sign of insufficient preparation for the second group is the presence
of emissions (1, 2) at the initial moments of the test task. These emissions
indicate some fright, stress in the listeners when they become acquainted with
the conditions of the test task. They are evidence, among other things, of
insufficient experience in performing such tasks, as well as insufficient free
possession of the material and the ability to apply the knowledge gained in
practice.
The technology of visualization of the current psycho-emotional
and functional state of the operator is the basis for solving the problems of
managing the reliability of the human factor, which is an integral part of the
modern strategy to ensure the safe operation of dangerous objects that could
potentially cause technogenic accidents and disasters.
The technology of results visualization in the form of
static and dynamic pie charts is multifunctional and makes it possible in
practice to improve the efficiency of educational and training sessions of all
kinds. The technology allows automation and integration with most modern
computer educational tools and techniques.
The work was carried out at the National Research Nuclear
University «Moscow Engineering Physics Institute» with the support of the grant
of the Russian Scientific Foundation (RNF) No. 16-18-00069 "Reducing the
risk of occurrence and reducing the consequences of catastrophes of technogenic
origin due to minimizing the influence of the human factor on the reliability
and trouble-free operation of nuclear power plants and other dangerous
objects".
1.
Alyushin M.V., Alyushin V.M., Kolobashkina L.V. Metodologicheskie
aspekty avtomatizirovannogo prognozirovaniya chrezvychajnyh situacij
tekhnogennogo proiskhozhdeniya [Methodological aspects of automatized
forecasting of emergency situations of technogenic origin] // Voprosy
Psikhologii. – 2016. N 2. P.83–91. [In Russian]
2. An
Evaluation of Emerging Driver Fatigue Detection Measures and Technologies:
Final Report // US Department of Transportation. Federal Motor Carrier Safety
Administration. − 2009. P. 1– 41.
3. Qiang
Ji, Zhiwei Zhu and Peilin Lan. Real-time nonintrusive monitoring and prediction
of driver fatigue // IEEE Transactions on Vehicular Technology. − 2004.
Vol. 53. No.4. P. 1052–1068.
4. Recarte
M.A. and Nunes L.M. Mental Workload While Driving: Effects on Visual Search,
Discrimination and Decision Making // Journal of Experimental Psychology:
Applied 2003. Vol. 9. No.2. P. 119 –137.
5. Corbetta
M. and Shulman G.L. Control of goal-directed and stimulus-driven attention in
the brain. // Nature Reviews Neuroscience. − 2002. Vol. 3. P.
201–215.
6.
Alyushin V.M. Diagnostika psihoemocional'nogo
sostoyaniya na osnove sovremennyh akusticheskih tekhnologij [Diagnostics of
emotional states on the basis of contemporary acoustic technologies] //
Voprosy Psikhologii. 2015. No.3. P.145 –152. [In Russian]
7. Alyushin
M.V. i dr. Opticheskie tekhnologii dlya sistem monitoringa tekushchego
funkcional'nogo sostoyaniya operativnogo sostava upravleniya ob"ektami
atomnoj ehnergetiki [Optical technologies for the operational staff current
functional state monitoring systems for the atomic energy objects] / M.V.
Alyushin, À.V. Alyushin, V.M. Belopolsky, L.V. Kolobashkina, V.L.Ushakov //
Global Nuclear Safety. 2013. No.2(7). P. 69 –77. [In
Russian]
8.
Viatkin Â.À. Spektral'nyj analiz golosa kak beskontaktnyj metod issledovaniya
psihicheskogo stressa v sporte [Spectral voice analysis as a contactless method
for studying mental stress in sports] // Aktual'nye voprosy teorii i praktiki
fizicheskogo vospitaniya i sporta. Perm'. – 1979. P. 8 – 9. [In
Russian]
9. Viatkin
Â.À., Markelov V.V. Permskie simpoziumy «Psihicheskij stress v sporte» [Perm symposia
"Mental stress in sport"] // Sportivnyj psiholog. – 2010. ¹1
(19). P .91– 96. [In Russian]
10. Popova V.V. Stress i
sovladanie v sporte v svete teorii integral'noj individual'nosti [Stress and
coping in sport in terms of the theory of integral individuality] // Theory and
practice of social development. – 2011. ¹8. P. 143 –146. [In Russian]
11. Sosnina D.N.
Osobennosti ispolnitel'skoj deyatel'nosti artistov baleta v usloviyah
scenicheskogo stressa [Peculiarities of ballet dancers performing activity
under stage stress] // Bulletin of Vaganova Ballet Academy. – 2011. ¹1 (25). P. 68–78.
[In Russian]
12. Adolphs R., Tranel D.,
Damasio H., and Damasio A. Impaired recognition of emotion in facial
expressions following bilateral damage to the human amygdala // Letters to
Nature. 1994. Vol. 372. P. 669 – 672.
13. Gunes H. and Piccardi M. Automatic temporal segment detection and
affect recognition from face and body display // IEEE Trans. SMC B. − 2009.
Vol. 39. No.1. P. 64 – 84.
14. Valstar M.F., Mehu M.,
Jiang B., Pantic M. and Scherer K.R. Metaanalysis of the first facial
expression recognition challenge // IEEE Trans. SMC B.−2012. Vol. 42. No.
4. P. 966 – 979.
15. Ma L. and Khorasani K.
Facial expression recognition using constructive feedforward neural networks //
IEEE Trans. SMC B. − 2004. Vol. 34. No. 3. P. 1588 – 1595.
16. Grigorescu C., Petkov
N. and Westenberg M.A. Contour detection based on nonclassical receptive field
inhibition // IEEE Trans. IP. − 2003. Vol. 12. No. 7. P. 729 – 739.
17. Shan C., Gong S. and
McOwan P.W. Facial expression recognition based on local binary patterns: A
comprehensive study // Image and Vision Computing. − 2009. Vol. 27.
No.6. P. 803– 816.
18. Fontaine J.R., Scherer K.R., Roesch E.B. and Ellsworth P.C. The world of
emotions is not two-dimensional // Psychological Science. − 2007.
Vol. 18. No.12. P. 1050–1057.
19. Essa I. and Pentland
A. Coding, analysis, interpretati on, and recognition of facial expressions //
IEEE Transactions on Pattern Analysis and Machine Intelligence. − July
1997. Vol. 19. No.7. P. 757–763.
20. Lanitis C. Taylor and Cootes T. Automatic interpretation and coding
of face images using flexible models // IEEE Transactions on Pattern Analysis
and Machine Intelligence. − July 1997. Vol. 19. No.7. P. 743–756.
21. Rahardja A., Sowmya A. and Wilson W. A neural network approach to
component versus holistic recognition of facial expressions in images //
Intelligent Robots and Computer Vision X: Algorithms and Techniques. − 1991.
Vol. 1607. P. 62–70.
22. Hutchinson T.E., White
K.P., Martin W.N., Reichert K.C. and Frey L.A. Human-computer interaction using
eye-gaze input // IEEE Trans. on Syst. Man, and Cybern. − 1989.
Vol. 19. P. 1527–1534.
23. Hammel K.R., Fisher
D.L. and Pradhan A.K. Verbal and spatial loading effects on eye movements in
driving simulators: A comparison to real world driving // Proceedings of the
Human Factors and Ergonomics Society 46th Annual Meeting. − 2002.
Vol. 46. No.26. P. 2174 - 2178.
24. Jarlier S., Grandjean D., Delplanque S., N’Diaye K., Cayeux I.,
Velazco M.I., Sander D., Vuilleumier P., Scherer K.R. Thermal analysis of
facial muscles contractions // IEEE Transactions on Affective Computing. − 2011.
Vol. 2. No.1, P. 2–8.
25. Kong S.G., Heo J., Abidi B.R., Paik J. and Abidi M.A. Recent
advances in visual and infrared face recognition - A review // Computer Vision
and Image Understanding. − 2005. Vol. 97, No.1. P. 103–135.
26. Abramova V.N.,
Alyushin M.V., Kolobashkina L.V. Psihologicheskij trening stressoustojchivosti
na osnove distancionnyh nekontaktnyh tekhnologij registracii bioparametrov [Psychological
training of resistance to stress on the basis of distance no-contact
technologies of registering biological parameters ]// Voprosy Psikhologii.
– 2014. No.6. P.144 –152. [In Russian]
