DOI: https://doi.org/10.15588/1607-3274-2020-4-17

INFORMATION-EXTREME HIERARCHICAL MACHINE LEARNING OF THE HAND BRUSH PROSTHESIS CONTROL SYSTEM WITH A NON-INVASIVE BIO SIGNAL READING SYSTEM

A. S. Dovbysh, V. Y. Piatachenko, J. V. Simonovskiy, O. A. Shkuropat

Abstract


Context. The actual problem of the information synthesis of learning and control systems for the prosthesis of the hand with a non-invasive system for reading biosignals has been solved.

Objective. The goal of the work is to increase the functional efficiency of the control system for the prosthesis of the hand with a non-invasive system for reading biosignals based on machine learning, which allows the system to operate in the operating mode to recognize the cognitive commands of the user of the prosthesis with high reliability and efficiency.

Method. Within the framework of informational and extreme intellectual technology (IEI technology) of data analysis based on maximizing the informational ability of a recognition system in machine learning, a method of informational synthesis of an intelligent control system for a prosthetic hand with a non-invasive biosignal reading system is proposed. In contrast to the existing methods of data mining, the method of information-extremal machine learning was developed as part of a functional approach to modeling the cognitive processes inherent in humans in the formation and adoption of classification decisions. This approach makes it possible to endow the prosthesis management system with adaptability properties to arbitrary initial conditions for the formation of cognitive teams and retraining while expanding the vocabulary of signs and the alphabet of recognition classes. In addition, the decision rules based on the geometric parameters of hyperspherical containers of recognition classes obtained during machine learning are almost invariant to the multidimensionality of the recognition feature space. Based on the proposed category model, a machine learning algorithm has been developed with optimization of the hierarchical data structure. At the same time, the influence on the functional efficiency of machine learning of data structures constructed in the form of dichotomous and decursion trees was studied. As a criterion for optimizing machine learning parameters, a modification of the informational Kullback measure is used, which is a functional of the accuracy characteristics of classification decisions.

Results. According to the experimental data obtained from the electromyographic sensor, an input structured learning matrix for the alphabet with four recognition classes is formed. The decision rules constructed in the process of hierarchical informational and extreme machine learning make it possible to recognize cognitive teams in real time with a rather high total probability of making correct classifying decisions. The results of physical modeling proved that when using a hierarchical data structure in the form of a decursive tree, the functional efficiency of machine learning increases in comparison with the data structure in the form of a dichotomous binary tree. 

Conclusions. The results of physical modeling confirmed a sufficiently high functional efficiency of the proposed method of information-extreme machine learning for the control system of the prosthesis of the wrist with a non-invasive system for reading biosignals. The obtained scientific results open up a new direction in the creation of intellectual prostheses of the hand with a noninvasive system for reading biosignals based on machine learning and pattern recognition. 


Keywords


Іnformation-extreme intellectual technology, machine learning, information criterion, control system, prosthesis, electromyographic sensor.

References


Sommer C., Gerlich D. Machine learning in cell biology – teaching computers to recognize phenotypes, Journal of Cell Science, 2013, Vol. 126, № 24, pp. 5529–5539. DOI: 10.1242/jcs.123604

Bishop C. M. Pattern Recognition and Machine Learning. Berlin, Springer, 2011.

Benatti S., Farella E., L. Benini, E. Gruppioni Analysis of robust implementation of an emg pattern recognition based control, Conference: International Conference on Bioinspired Systems and Signal. Angers: BIOSIGNALS, 2014, pp. 45–54.

Farrell T. R., Weir R. F. A comparison of the effects of electrode implantation and targeting on pattern classification accuracy for prosthesis control, IEEE Transactions on Biomedical Engineering, 2008, Vol. 55, № 9, pp. 2198– 2211.

Zhang T., Jiang L., Liu H. Design and Functional Evaluation of a Dexterous Myoelectric Hand Prosthesis With Biomimetic Tactile Sensor, IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2018, Vol. 26, No. 7, pp. 1391–1399.

Liang G., Wang Y., Mei D., Xi K., Chen Z. Flexible Capacitive Tactile Sensor Array With Truncated Pyramids as Dielectric Layer for Three-Axis Force Measurement, Journal of Microelectromechanical Systems, 2015, Vol. 24, No. 5, pp. 1510 – 1519.

Zhang T., Jiang L. Biomimetic Tactile Data Driven Closedloop Control of Myoelectric Prosthetic Hand, IEEE International Conference on Robotics and Biomimetics (ROBIO). – Kuala Lumpur: IEEE, 2018, pp. 1738–1742.

Chowdhury R. H. Reaz M. B. I., Ali M. A. B. M., Bakar A. A. A., Chellappan K., T. G. Chang Surface Electromyography Signal Processing and Classification Techniques, Sensors, 2013, Vol. 13, № 9, pp. 12431–12466.

Farina D. (Deutschland), Popovic D. (Republic of Serbia), Graimann B., Markovic M., Dosen S. (Deutschland); Pat. 0371871 United States, IPC A61F 2/54. Control of limb device. Applicants: Georg-August-Universität Göttingen. Otto Bock HealthCare GmbH. № US 2014/0371871 A1; Date of filing: 12.06.2013; Date of publication: 17.12.2014, Bulletin № 51.

AI-Shayea Q. K. Artificial neural networks in medical diagnosis, IJCSI International Journal of computer scienc, 2011, Vol. 8, No. 2, pp. 150 – 154.

Khan I. Y., Zope P. H., Suralkar S. R. Importance of artificial neural network in medical diagnosis disease like acute nephritis disease and heart disease, International journal of engineering science and innovative technology (IJESIT), 201, Vol. 2, No. 2, pp. 210 – 217.

Stango А., Negro F., Farina D. Spatial correlation of high density emg signals provides features robust to electrode number and shift in pattern recognition for myocontrol, Neural Systems and Rehabilitation Engineering, 2015, Vol. 23, № 2, pp. 189–198.

Gheorghe M. A support vector machine approach for developing telemedicine solutions: medical diagnosis, Network intelligence studies, 2015, Vol. 3, No. 1(5), pp. 43– 48.

Rossi М., Benatti S., Farella E., Benini L. Hybrid EMG classifier based on HMM and SVM for hand gesture recognition in prosthetics, IEEE International Conference on Industrial Technology (ICIT). Seville, IEEE, 2015, pp. 1700–1705.

Conradt J., Uhde C., Berberich N. Artificial prosthetic limbs Problems and solutions for connecting brains and robots. Munchen, Technische Universitat Munchen, 2015, 39 p.

Subbotin S. The neuro-fuzzy network synthesis and simplification on precedents in problems of diagnosis and pattern recognition, Optical Memory and Neural Networks, 2013, Vol. 22, No. 2, pp. 97–103. doi:10.3103/s1060992x13020082

Moskalenko V. V., Korobov A. G. Information-extreme algorithm of the system for recognition of objects on the terrain with optimization parameter feature extractor / V.V.Moskalenko, // Radio Electronics, Computer Science, Control – 2017. – № 2. – P. 61–69. doi:10.15588/16073274-2017-2-7.

Korobov A., Moskalenko A., Nahornyi V. et al. Parameters Optimization Method of the Information-Extreme Object Recognition System on the Terrain, IEEE First International Conference on System Analysis & Intelligent Computing (SAIC), Kiev, 8–12 October, proceedings. Kiev, IEEE, 2018 pp. 1–5. DOI: 10.1109/SAIC.2018.8516771

Moskalenko V., Moskalenko A., Pimonenko S., Korobov A. Development of the method of features learning and training decision rules for the prediction of violation of service level agreement in a cloud-based environment, Eastern-European Journal of Enterprise Technologies, 2017, Vol. 5, No. 2 (89), pp. 26–33. DOI: 10.15587/1729-4061.2017.110073

Piotrowski A. Napiorkowski M., Napiorkowski J., Rowinski P. Swarm Intelligence and Evolutionary Algorithms: Performance versus speed, Information Sciences, 2017, Vol. 384, pp. 34–85. DOI: 10.1016/j.ins.2016.12.028

Dovbysh А. S., Moskalenko V. V., Rizhova A. S. Learning decision making support system for control of nonstationary technological process, Journal of automation and information sciences, 2016, Vol. 48, No. 6, pp. 39–48. doi:10.1615/JAutomatInfScien.v48.i6.40

Dovbysh A. S., Rudenko M. S. Information-extreme learning algorithm for a system of recognition of morphological images in diagnosing oncological pathologies, Cybernetiks and Systems Analysis, 2014, Vol. 50, No. 1, pp. 157–163. DOI: 10.15587/1729-4061.2016.71930

Dovbysh A. S., Zimovets V. I., Zuban Y. A., Prikhodchenko A. S. Mashine Training of the System of Functional Diagnostic of the Saft Lifting Mashine, Probleme energetucii regionale, 2019,Vol. 2, No. 43, pp. 88–102. DOI: 10.5281/zenodo.3367060

Avramenko V., Moskalenko A. Operative Recognition of Standard Signals in the Presence of Interference with Unknown Characteristics, Proceedings of the Second International Workshop on Computer Modeling and Intelligent Systems (CMIS-2019), Zaporizhzhia, 15–19 April 2019: proceedings. Zaporizhzhia, CEUR-WS,2019.

Kalashnikov V. V., Avramenko V. V., Slipushko N. Y., Kalashnykova N. I., Konoplyanchenko A. E. Identification of quasi-stationary dynamic objects with the use of derivative disproportion functions, Procedia Comput Sci., 2017, Vol. 108, pp. 2100–2109. DOI: 10.1016/j.procs.2017.05.266


GOST Style Citations


1. Sommer C. Machine learning in cell biology – teaching computers to recognize phenotypes / C. Sommer, D. Gerlich // Journal of Cell Science. – 2013. – Vol. 126, № 24. – P.5529–5539. DOI: 10.1242/jcs.123604

2. Bishop C. M. Pattern Recognition and Machine Learning // C. M. Bishop. – Berlin : Springer, 2011.

3. Benatti S. Analysis of robust implementation of an emg pattern recognition based control / S. Benatti, E. Farella, L. Benini, E. Gruppioni // Conference: International Conference on Bio-inspired Systems and Signal. – Angers: BIOSIGNALS, 2014. – P. 45–54.

4. Farrell T. R. A comparison of the effects of electrode implantation and targeting on pattern classification accuracy for prosthesis control / T. R. Farrell, R. F. Weir// IEEE Transactions on Biomedical Engineering. – 2008. – Vol. 55, № 9. – P. 2198–2211.

5. Zhang T. Design and Functional Evaluation of a Dexterous Myoelectric Hand Prosthesis With Biomimetic Tactile Sensor / T. Zhang, L. Jiang, H. Liu // IEEE Transactions on Neural Systems and Rehabilitation Engineering. – 2018. – Vol. 26, № 7. – P. 1391–1399.

6. Liang G. Flexible Capacitive Tactile Sensor Array With Truncated Pyramids as Dielectric Layer for Three-Axis Force Measurement / [G. Liang, Y. Wang, D. Mei et al.] // Journal of Microelectromechanical Systems. – 2015. – Vol. 24, № 5. – P. 1510 – 1519.

7. Zhang T. Biomimetic Tactile Data Driven Closed-loop Control of Myoelectric Prosthetic Hand / T. Zhang, L. Jiang // IEEE International Conference on Robotics and Biomimetics (ROBIO). – Kuala Lumpur: IEEE, 2018. – P.1738–1742.

8. Chowdhury R. H. Surface Electromyography Signal Processing and Classification Techniques / [R. H. Chowdhury, M. B. I. Reaz, M. A. B. M. Ali et al.] // Sensors. – 2013. – Vol. 13, № 9. – P. 12431–12466.

9. Pat. 0371871 United States, IPC A61F 2/54. Control of limb device / D. Farina (Deutschland), D. Popovic (Republic of Serbia), B. Graimann, M. Markovic, S. Dosen (Deutschland); Applicants: Georg-August-Universität Göttingen / Otto Bock HealthCare GmbH. – № US 2014/0371871 A1; Date of filing: 12.06.2013; Date of publication: 17.12.2014, Bulletin № 51.

10. AI-Shayea Q. K. Artificial neural networks in medical diagnosis / Q. K. AI-Shayea // IJCSI International Journal of computer science. – 2011. – Vol. 8, № 2. – P. 150–154.

11. Khan I. Y. Importance of artificial neural network in medical diagnosis disease like acute nephritis disease and heart disease/ I. Y. Khan, P. H. Zope, S. R. Suralkar// International journal of engineering science and innovative technology (IJESIT). – 2013. – Vol. 2, № 2. – P. 210–217.

12. Stango А. Spatial correlation of high density emg signals provides features robust to electrode number and shift in pattern recognition for myocontrol / A. Stango, F. Negro, D. Farina // Neural Systems and Rehabilitation Engineering. – 2015. – Vol. 23, № 2. – P. 189–198.

13. Gheorghe M. A support vector machine approach for developing telemedicine solutions: medical diagnosis / M. Gheorghe // Network intelligence studies. – 2015. – Vol. 3, № 1(5). – P. 43 – 48.

14. Rossi М. Hybrid EMG classifier based on HMM and SVM for hand gesture recognition in prosthetics / [M. Rossi, S. Benatti, E. Farella, L. Benini] // IEEE International Conference on Industrial Technology (ICIT). – Seville: IEEE, 2015. – P. 1700–1705.

15. Conradt J. Artificial prosthetic limbs Problems and solutions for connecting brains and robots / J. Conradt, C. Uhde, N. Berberich // Munchen: Technische Universitat Munchen, 2015. – 39 p.

16. Subbotin S. The neuro-fuzzy network synthesis and simplification on precedents in problems of diagnosis and pattern recognition / S. Subbotin // Optical Memory and Neural Networks – 2013. – Vol. 22, № 2. – P. 97–103. DOI: 10.3103/s1060992x13020082

17. Moskalenko V.V. Information-extreme algorithm of the system for recognition of objects on the terrain with optimization parameter feature extractor / V. V. Moskalenko, A. G. Korobov // Radio Electronics, Computer Science, Control – 2017. – № 2. – P. 61–69. doi:10.15588/1607-3274-2017-2-7.

18. Parameters Optimization Method of the InformationExtreme Object Recognition System on the Terrain / [A. Korobov, A. Moskalenko, V. Nahornyi et al.] // IEEE First International Conference on System Analysis & Intelligent Computing (SAIC), Kiev, 8–12 October: proceedings. – Kiev:IEEE, 2018 – P. 1–5. DOI: 10.1109/SAIC.2018.8516771

19. Moskalenko, V. Development of the method of features learning and training decision rules for the prediction of violation of service level agreement in a cloud-based environment / V. Moskalenko, A. Moskalenko, S. Pimonenko, A. Korobov // Eastern-European Journal of Enterprise Technologies – 2017. – Vol. 5, № 2 (89). – P. 26–33. DOI: 10.15587/1729-4061.2017.110073

20. Piotrowski A. Swarm Intelligence and Evolutionary Algorithms: Performance versus speed / [A. Piotrowski, M. Napiorkowski, J. Napiorkowski, P. Rowinski] // Information Sciences – 2017. – Vol. 384. – P. 34–85. DOI: 10.1016/j.ins.2016.12.028

21. Dovbysh, А. S. Learning decision making support system for control of nonstationary technological process / А. S. Dovbysh, V. V. Moskalenko, A. S. Rizhova // Journal of automation and information sciences – 2016. – Vol. 48, № 6. – P. 39–48. DOI: 10.1615/JAutomatInfScien.v48.i6.40

22. Dovbysh, A.S. Information-extreme learning algorithm for a system of recognition of morphological images in diagnosing oncological pathologies/ A. S. Dovbysh, M. S. Rudenko // Cybernetiks and Systems Analysis. – 2014.– Vol. 50, № 1. – P. 157–163. DOI: 10.15587/17294061.2016.71930

23. Mashine Training of the System of Functional Diagnostic of the Saft Lifting Mashine / [A. S. Dovbysh, V. I. Zimovets, Y. A. Zuban, A. S Prikhodchenko] // Probleme energetucii regionale – 2019. – Vol. 2, № 43. – P. 88 – 102. DOI: 10.5281/zenodo.3367060

24. Avramenko V. Operative Recognition of Standard Signals in the Presence of Interference with Unknown Characteristics / V. Avramenko, A. Moskalenko // Proceedings of the Second International Workshop on Computer Modeling and Intelligent Systems (CMIS-2019), Zaporizhzhia, 15–19 April 2019: proceedings. – Zaporizhzhia: CEUR-WS,2019.

25. Kalashnikov V. V. Identification of quasi-stationary dynamic objects with the use of derivative disproportion functions / [V. V. Kalashnikov, V. V. Avramenko, N. Y. Slipushko et al] // Procedia Comput Sci. – 2017. – Vol. 108. – P. 2100–2109 DOI:10.1016/j.procs.2017.05.266







Copyright (c) 2020 A. S. Dovbysh, V. Y. Piatachenko, J. V. Simonovskiy, O. A. Shkuropat

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Address of the journal editorial office:
Editorial office of the journal «Radio Electronics, Computer Science, Control»,
National University "Zaporizhzhia Polytechnic", 
Zhukovskogo street, 64, Zaporizhzhia, 69063, Ukraine. 
Telephone: +38-061-769-82-96 – the Editing and Publishing Department.
E-mail: rvv@zntu.edu.ua

The reference to the journal is obligatory in the cases of complete or partial use of its materials.