Digital model of martial artist
UDC 796:51-7
Dr. Biol., Professor S.I. Loginov1 Dr. Biol., Professor Y.N. Romanov2 PhD A.A. Egorov1 PhD O.V. Borisenko1
1Surgut State University, Surgut
2South Ural State University (National Research University), Chelyabinsk
Corresponding author: logsi@list.ru
Abstract
Objective of the study was to offer a theoretical and practical framework for digital modeling of the martial artist's performance, with judo taken for the case study.
Methods of the study. The researchers used a set of the relevant theoretical and mathematical tools to formalize the theoretical and practical training process.
Results and discussion. The judoka's digital model includes (1) Basic individual data: above 10 specifications; (2) General physical fitness: 24 test rates; (3) Special physical fitness: 33 test rates; (4) Morphology and functionality: 20 test rates; (5) Medical and biological data: above 10 indicators; (6) Social standing: above 10 indicators; (7) Psychophysical state: above 10 test rates; (8) Technical and tactical skills: dimensionless points; and (9) Sports track record.
The above test data make it possible to analyze the aerobic performance, muscular endurance, flexibility, speed, coordination, neural-psychic stress tolerance, adaptability, and the physique type and harmony. The authors believe that further progress in the global elite sports will increasingly depend on sports digitalization service based on a profound knowledgebase developed by the modern sports physiology and psychology.
The athlete's digital model offered and analyzed herein may provide solutions for the urgent problems of the theoretical and practical training and competitive processes since its offers to athletes and coaches reasonably limited test data arrays with analysis and timely progress recommendations. The new digital model was developed using modern IT tools and includes a database, knowledgebase and special customizable mathematical toolkit for digital modeling service.
Keywords: sport digitalization, digital model, judo.
Background. Modern elite sports may be defined as the ultimate competitive domain that requires every individual resource being mobilized for success; and this success can be achieved any more only by intensive physical trainings and advanced theoretical and practical training system design and management tools. Nowadays progress in modern elite sports is secured by joint efforts of athletes, coaches, researchers, physicians and technical personnel service for success in the training and competitive phases. The sports communities increasingly understand that high
ww.teoriya.ru
quality theoretical and practical training analysis and situational express analysis in competitions cannot be made "on the edge of the field" by single coaches or coaching teams. It is the modern digital technologies that increasingly contribute to the coaching service in every sport including martial arts [1-6, 9], although the latter are still in need of special software products for the theoretical and practical training system design and management purposes.
Objective of the study was to offer a theoretical and practical framework for digital modeling of a mar-
tial artist's performance, with judo taken for the case study.
Methods of the study. We used a set of the relevant theoretical and mathematical tools to formalize the theoretical and practical training process.
Results and discussion. Formally, an athlete's digital model may be represented as a finite set of quantitative and qualitative test rates to describe variations in the physiological, psychological and cognitive processes with account of the personal behavioral models [4]. Therefore, the digital model design process requires thorough, repeated and prolonged tests to generate reliable performance test data [1-3]. The performance rating for every martial art requires rather painstaking and difficult work, and therefore we limited our digital model by elite judo taken for the case study. The proposed basic classification may be applied, when needed, to similar sport disciplines, with some adjustments to the set of the key performance tests. For judo, the test set includes: (1) Basic individual data: above 10 specifications; (2) General physical fitness: 24 test rates; (3) Special physical fitness: 33 test rates; (4) Morphology and functionality: 20 test rates; (5) Medical and biological data: above 10 indicators; (6) Social standing: above 10 indicators; (7) Psychophysical state: above 10 test rates; (8) Technical and tactical skills rated by points; and (9) Sports track record.
The above test data makes it possible to analyze the aerobic performance, muscular endurance, flexibility, speed, coordination, neural/ psychic stress tolerance, adaptability, and physique type and harmony. The individual digital model provides an individual performance matrix to produce progress recommendations on the following: (1) Frequency and duration of trainings; (2) Training process intensity management; (3) Energy costs; (4) Physical training tools; and (5) Training system design.
An athlete's digital model was formed by around 120 parameters, including both the discrete and continuous ones, and this is why the key task in the digital model design process is to effectively limit the data dimensions with no significant loss for the quality of the data array.
The resulting model s describes the athlete' state at specific time point by an array of continuous indicators (including the primary ones) with the following systems of nonlinear differential and integral-differential equations: f(w)
dflwHx,z,
seS, s{w]{f,x,z,t) =
dt
x G R, z G Z, w G Q, t > 0,
where f = {f (w)} - unknown vector function describing one of the indicators of the resulting model,
xgR - integer indicators, xgR - continuous indicators; and, wgQ -resultant indicator.
The array of indicators M for the digital model is defined as:
M = {Un, Ph, Sp, M f , Mb, Soc, Ps, T, L}.
Un = [u1, u2, ..., un], n=10,
where u1, u2, ..., un - are the integer basic individual specifications.
Ph = [u1, u2, ..., un, 31, 32, ... 3m], n=8, m=16,
where u1, u2, ..., un u 31, 32, ... 3m - are the integer continuous general physical fitness test rates.
Sp = [u1, u2, ..., un , 31, 32, ... 3m], n=4, m=29,
where u1, u2, ..., un u 31, 32, ... 3m u - are the integer continuous special physical fitness test rates.
Mf = {u1, u2, ..., un , 31, 32, ... 3m} n=12, m=8,
where u1, u2, ..., un u 31, 32, ..., 3m - are the integer continuous values of the athlete's morphology and functionality.
Mb = [u1, u2, ..., un , 31, 32, ... 3m], n=4, m=6,
where u1, u2, ..., un u 31, 32, ... 3m - are the integer continuous medical and biological test rates.
Soc = [u1, u2, ..., un], n=10,
where u1, u2, ..., un u 31, 32, ... 3m - are the integer continuous social standing test rates.
Ps = [u1, u2, ..., un], n=10,
where u1, u2, ..., un u 31, 32, ... 3m - are the integer continuous psychophysical state test rates.
T = [h1, h2, ..., hn], n ^ N,
where h,, h„, ..., h - are the technical and tacti-
V 2 ' n
cal skills metering points, and N - limiting number.
L = [/1, ¡2, ..., /„], n ^ N,
where /1, /2, ..., /n - are the athlete's track record stage rating points, and N - limiting number.
Each of the above test data arrays M has its own test specifics. Moreover, each indicator in each array requires its own specific tests. For example, a 30m sprint test needs to be standardized based on some principles; whilst an athlete's stress tolerance may be tested by a few options including, e.g., the Luscher color test.
Most of the above test rates may be easily formalized to a degree and described by very specific methods. The situation is complicated when such methods are still underdeveloped or non-existing. For example, the tactical and technical skills are rather difficult for
16
Theory and Practice of Physical Culture I teoriya.ru I May № 5 2021
formalization process that needs a special mathematical toolkit. The same applies to the individual track record specifications. It is also clear that the individual competitive accomplishments are characteristic of the athlete's psychophysical state, albeit further detailed formalization of a track record requires an extensive set of criteria to describe the athlete's state in every time point and, hence, again requires its own mathematical toolkit.
The digital model design process is further complicated by the time flow, with every function being time-dependent. Time is accounted as the function time, but it is not specific and separate for every x or z indicator. Every indicator, in fact, requires its own timeframe not necessarily matching with the times of other indicators. V(x (t), Xj(Г)) M
It should be noted that the test time differences
At=t-f may be measured in months and even years. Some test rates are generated simultaneously to cause no generally negative effects on the model, but some parameters (for example, muscle mass), should be rated with At close to 0 for the modeling process accuracy: V: At ^
To design a digital model for an athlete with a five-year track record, we may need as many as 600 test rates to analyze the present performance and progress options, conditional on the tests run every year (and even more often, in fact). Note that correlations of the test rates - even when we consider only the meaningful ones - are multiple times higher. Therefore, classifications of the current performance and progress options are extremely difficult and achievable only for the modern cutting-edge IT systems.
It may be pertinent to mention that the similar modeling systems are developed by research teams in Chelyabinsk [1], Minsk [3], Spain and Brazil [5, 7]. We believe that further progress in the global elite sports will increasingly depend on sports digitalization service based on a profound knowledgebase developed by the modern sports physiology and psychology.
Conclusion. The athlete's digital model offered and analyzed herein may provide solutions for the urgent problems of the theoretical and practical training and competitive processes since its offers to athletes and coaches reasonably limited test data arrays with analyses and timely progress recommendations. The new digital model was developed using modern IT tools and includes a database, knowledgebase and special customizable mathematical toolkit for digital modeling service.
References
1. Epishev V.V., Isaev A.P., Miniakhmetov R.M. et al. Intelligent data analysis of physiological research in elite sport. Vestnik YuUrGU. Ser.: Vych. matem. inform. 2013. V. 2. no. 1. pp. 44-54.
2. Loginov S.I., Egorov A.A., Ermakov V.A. Data Mining System: «Judo Sport School» Module. Teoriya i praktika fiz. kultury. 2015. No. 2. pp. 90-93.
3. Filipovich L.V., Charykova I.A. Model of athletes' psychophysiological fitness for competitions (case study of judo). Prikladnaya sportivnaya nauka. 2015. No. 2. pp. 43-48.
4. Casals C., Huertas J.R., Franchini E. Judo. Fitness Test Level and Anthropometric Profile of Elite Spanish Judo Athletes. J. Strength Cond. Res. 2017 May; 31(5):1229-1235. doi: 10.1519/ JSC.0000000000001261.
5. Epishev V.V., Isaev A.P., Miniakhmetov R.M., Movchan A.V., Smirnov A.S. and others. The system of intellectual analysis of physiological research in sports of the highest achievements. Bulletin of SUSU. Series: Vych. matem. inform. 2013. T. 2. Release 1. pp. 44-54. doi: https:// doi.org/ 10.14529/ cmse13010.
6. Faro H.K.C., Machado D.G.DS., Bortolotti H. et al. Influence of Judo Experience on Neuro-electric Activity During a Selective Attention Task. Front Psychol. 2020 Jan 9;10:2838. doi: 10.3389/fpsyg.2019.02838.
7. Filipovich L.V., Chary'kova I.A. Model of psycho-physiological readiness of athletes for competitions (on the example of judo))] Applied sports science. 2015. N 2. pp. 43-48.
8. Franchini E., Del Vecchio FB., Matsushigue K.A., Artioli G.G. Physiological profiles of elite judo athletes. Sports Med. 2011. 41(2):147-66. doi: 10.2165/11538580-000000000-00000.
9. Loginov S.I., Egorov A.A., Ermakov V.A. Information system of data mining: module «Sports school of judo»] Theory and practice of physical culture. 2015. N 2. pp. 90-93.
10. Miarka B., Dal Bello F, Brito C.J., Del Vecchio FB., Amtmann J., Chamari K. A 12-Year Cohort Study of Doc-Stoppage in Professional Mixed Martial Arts. Int. J. Sports Physiol. Perform. 2019 May 1;14(5):606-611. doi: 10.1123/ ijspp.2017-0131.
11. Sanchez-Lopez J., Silva-Pereyra J., Fernandez T. Sustained attention in skilled and novice martial arts athletes: a study of event-related potentials and current sources. Peer J., 2016. 4, e1614. doi.org/10.7717/peerj.1614.
ww.teoriya.ru
17