admin

Issue 4 (206), article 5

DOI:https://10.15407/kvt206.04.073

Cybernetics and Computer Engineering, 2021, 4(206)

VOVK М.І., PhD (Biology), Senior Researcher,
Head of Bioelectrical Control & Medical Cybernetics Department
ORCID: 0000-0003-4584-9553, e-mail: vovk@irtc.org.ua; imvovk3940@gmail.com

KUTSIAK О.А., PhD (Engineering),
Senior Researcher of the Bioelectrical Control & Medical Cybernetics Department
ORCID: 0000-0003-2277-7411, e-mail: spirotech85@ukr.net

International Research and Training Center for Information Technologies
and Systems of the NAS of Ukraine and of MES of Ukraine,
40, Acad. Hlushkov av. Kyiv, 03187, Ukraine

MOBILE AI-TECHNOLOGY FOR FORMING THE PERSONALIZED MOVEMENTS REHABILITATION PLAN AFTER A STROKE

Introduction. The consequences of stroke change seriously the quality of life. Especially motor activity suffers. Speech disorders occupy a significant place. The synthesis of effective technologies for restoration of limb movements, fine motor hand, that plays significant role in restoring the speech motor skills, is the urgent scientific and applied task.

Recently, the use of artificial intelligence in medicine has attracted attention. At the same time, mobile technologies are developing. It is considered that artificial intelligence in a smartphone will make the medicine of the future accessible for everybody.

The purpose of the paper is to develop the technology for movement restoration after a stroke that uses the artificial intelligence tool for increasing the effectiveness of rehabilitation process – specialized software module for mobile platforms to assist the user (physician) in the formation of personalized plans at different rehabilitation stages.

Results. The AI-technology for forming the personalized movement training plan to patient after a stroke is developed. This technology uses artificial intelligence tool – the software module for information assistance in forming the plan  “MovementRehabStroke 1.0 (MD)” that installed in  mobile platforms. This module provides the user with recommended movement training plan based on results of quantitative assessment of movements deficit is determined by software module “MovementTestStroke 1.1 (MD)” and patient general state. This plan may be corrected. The structural and functional model of user (physician) and software module “MovementRehabStroke 1.0 (MD)” interaction, and algorithm for forming the personalized movements rehabilitation plan – recommended and finally user-formed are given.

Conclusions. The usage of artificial intelligence tools reduces the physician error in diagnostic and treatment decisions, prevents complications, reduces the disability risks, improves the quality and widespread usage of medical and rehabilitation services for patients after stroke.

Keywords: stroke, AI-technology, personalized plan, movement training, rehabilitation, diagnostics, software module, structural and functional model, algorithm.

Download full text!

REFERENCES

1 Gorelick P.B. The global burden of stroke: Persistent and disabling. Lancet Neurol. 2019. Vol. 18. No 5. pp. 417-418.
https://doi.org/10.1016/S1474-4422(19)30030-4

2 Delpont B., et.al. Pain after stroke: A review. Revue neurologique. 2018. Vol. 174. No 10. pp. 671-674.
https://doi.org/10.1016/j.neurol.2017.11.011

3 Buono Lo, Corallo F., Bramanti P., Marino S. Coping strategies and health-related quality of life after stroke. 2017. J. Health Psychol. 2017. Vol. 22. No 1. pp. 16-28.
https://doi.org/10.1177/1359105315595117

4 Jorgensen H.S., Nakayama H., Raaschou H.O., Olsen T.S. Recovery of walking function in stroke patients: the Copenhagen Stroke Study. Archives of Physical Medicine and Rehabilitation. 1995. Vol. 76(1). pp. 27-32.
https://doi.org/10.1016/S0003-9993(95)80038-7

5 Holland A., Fridriksson J. Aphasia management during the early phases of recovery following stroke. American Journal of Speech-Language Pathology. 2001. Vol. 10 (1). pp. 19-28.
https://doi.org/10.1044/1058-0360(2001/004)

6 Berthier M.L. Poststroke aphasia: epidemiology, pathophysiology and treatment. Drugs Aging. 2005. Vol. 22(2). pp. 163-182.
https://doi.org/10.2165/00002512-200522020-00006

7 Hatem S.M., Saussez G., Faille M.D., Prist V. Rehabilitation of motor function after stroke: A multiple systematic review focused on techniques to stimulate upper extremity recovery. Frontiers Hum. Neurosci. 2016. Vol. 10. P. 442.
https://doi.org/10.3389/fnhum.2016.00442

8 Upper Limb Rehabilitation System for Stroke Survivors Based on Multi-Modal Sensors and Machine Learning / Sheng Miao, et.al. IEEE Access: Special section on AI and IoT convergence for smart health. 2021. Vol. 9. pp. 30283-30291.
https://doi.org/10.1109/ACCESS.2021.3055960

9 Hossain M.S. Cloud-supported cyber-physical localization framework for patients monitoring. IEEE Syst. J. 2015. Vol. 11. No 1. pp. 118-127.
https://doi.org/10.1109/JSYST.2015.2470644

10 Stinear C.M., Lang C.E., Zeiler S., Byblow W.D. Advances and challenges in stroke rehabilitation. Lancet Neurol. 2020. Vol. 19. No 4. pp. 348-360.
https://doi.org/10.1016/S1474-4422(19)30415-6

11 Vovk M.I., Galyan Ye.B. Restoring of motor component of speech based on muscle movement control. Theoretical grounding. Cybernetics and Computer Engineering. 2012. No 167. pp.51-60. (in Russian).

12 Varun H Buch, Irfan Ahmed, Mahiben Maruthappu. Artificial intelligence inmedicine: current trends and future possibilities. Br J Gen Pract. 2018. No 68(668). pp. 143-144.
https://doi.org/10.3399/bjgp18X695213

13 The Oxford Dictionary of Current English. Oxford: Oxford University Press, 2001. 3rdedition. 1083 p.

14 Ahuja A.S. The impact of artificial intelligence in medicine on the future role of the physician. PeerJ. 2019.
https://doi.org/10.7717/peerj.7702

15 Artificial intelligence in medicine: the main trends in the world. URL:https://medaboutme.ru/zdorove/publikacii/stati/sovety_vracha/iskusstvennyy_intellekt_v_meditsine_glavnye_trendy_v_mire/ (Last accessed: 1.04.2021) (in Russian).

16 Vovk M.I., Kutsiak O.A. AI-Technology of Motor Functions Diagnostics after a Stroke. Cybernetics and Computer Engineering. 2021. No 2 (204). pp. 84-100.
https://doi.org/10.15407/kvt204.02.084

17 Vovk M.I., Kutsyak O.A. Software module for personal diagnostics of motor functions after stroke. Cybernetics and Computer Engineering. 2019. No 4 (198). pp. 62-77.
https://doi.org/10.15407/kvt198.04.062

18 Belova A., Shchepetova O. Scales, tests and questionnaires in medical rehabilitation. Moscow: Antidor, 2002. 440 p. (in Russian)

19 Smychek V., Ponomareva E. Craniocerebral trauma (clinic, treatment, examination, rehabilitation). Minsk: Research Institute of ME and R, 2010. 430 p. (in Russian)

20 Vovk M.I., Kutsyak O.A. Information technology for forming a personal movement rehabilitation plan after a stroke. Cybernetics and Computer Engineering. 2020. No 3 (201). pp. 87-99.
https://doi.org/10.15407/kvt201.03.087

21 Vovk M.I. Information technology of movement control. Evolution of synthesis and development prospects. Cybernetics and Computer Engineering. 2018. No 4 (194). pp. 79-97. (in Ukrainian).
https://doi.org/10.15407/kvt194.04.079

Received 15.09.2021

admin

Issue 4 (206), article 4

DOI:https://10.15407/kvt206.04.054

Cybernetics and Computer Engineering, 2021, 4(206)

KRYVOVA O.A.,
Researcher, Medical Information Systems Department
ORCID: 0000-0002-4407-5990, e-mail: ol.kryvova@gmail.com

KOZAK L.M., DSc (Biology), Senior Researcher,
Leading Researcher, Medical Information Systems Department
ORCID: 0000-0002-7412-3041, e-mail: lmkozak52@gmail.com

KOVALENKO O.S., DSc (Medicine), Professor,
Head of Medical Information Systems Department
ORCID: 0000-0001-6635-0124, e-mail: askov49@gmail.com

NENASHEVA L.V.
Junior Researcher, Medical Information Systems Department
ORCID: 0000-0003-1760-2801, e-mail: larnen@ukr.net

International Research and Training Center for Information Technologies
and Systems of the National Academy of Sciences of Ukraine
and Ministry of Education and Science of Ukraine,
40, Acad. Glushkov av., Kyiv, 03187, Ukraine

PREDICTION OF SURGERY CONTROL PARAMETERS IN CARDIOLOGY TO OPTIMIZE THE EMISSION FRACTION VALUES WITH THE HELP OF NEURAL NETWORKS

Introduction. In the Big Data era, decision tree methods, machine learning, and neural networks, along with other Data Mining methods became an alternative to classical statistical methods as a more useful tool for analyzing large and inhomogeneous data. Neural Networks methods have emerged as a more accurate and effective technology in a wide range of medical problems such as diagnosis, prediction, treatment. 

The purpose of the paper is to identify the control parameters of the surgical intervention to optimize the EF ejection fraction after the surgery using a Data Mining method (neural network) models.

Results. The analysis of changes in hemodynamic parameters of children with severe heart defects due to surgery — implantation of conduit. Changes in these parameters after surgery were analyzed using analysis of variance for repeated measurements (RepANOVA). It was determined that after the surgery there was a significant, statistically significant decrease in 3 hemodynamic parameters (end diastolic index, aortic pressure gradient, and augmentation index). According to the cluster analysis, three groups of patients were identified, which were differed in all hemodynamic parameters and in the peculiarities of changes in the studied parameters after surgery. A model based on a neural network of the RBF type (with radial-based activation functions) was built using the Data Mining Automated Neural Networksmodule of the STATISTICA package. According to the developed models, the dependence of the emission fraction after the surgery on the control parameters — dopamine dose and conduit diameter was determined.

Conclusions. The use of predictive models of neural networks developed by the type of RBF network with radially symmetric functions in single-layer networks, allowed to analyze the effectiveness of surgical interventions in the case of congenital heart disease in infants and children. Taking into account the results of the developed predictive model of the dependence of the cardiac output fraction on the parameters of surgery (dose, conduit diameter) and factors such as age, weight, hemodynamic status, gives the surgeon essential information to achieve good results of a surgery.

Keywords: Data Mining classification models, predictive models, neural networks, surgical efficiency

Download full text!

REFERENCES

1 Kalantari A. et all. Computational intelligence approaches for classification of medical data: State-of-the-art, future challenges and research directions. Neurocomputing. 2018, No 2(7), pp. 2-22.
https://doi.org/10.1016/j.neucom.2017.01.126

2 Dietterich T. G. Ensemble Methods in Machine Learning. International Workshop on Multiple Classifier Systems, 2000, Springer, Berlin, Heidelberg. Vol 18576, pp. 1-15.
https://doi.org/10.1007/3-540-45014-9_1

3 Acharya A., Hruschka E., Ghosh J., Acharyya S. C3E: A framework for combining ensembles of classifiers and clusterers. International Workshop on Multiple Classifier Systems. 2011, Vol. 6 (15), pp.269-278.
https://doi.org/10.1007/978-3-642-21557-5_29

4 Rahman A., Verma B. Cluster-based ensemble of classifiers. Expert Systems. 2013, Vol. 30, No. 3, pp. 270-282.
https://doi.org/10.1111/j.1468-0394.2012.00637.x

5 Shouman M, Turner T, Stocker R. Integrating Clustering with Different Data Mining Techniques in the Diagnosis of Heart Disease. J. Comput. Sci. Eng. 2013, Vol. 20(1), pp. 1-10.

6 Abawajy JH, Kelarev AV, Chowdhury M Multistage approach for clustering and classification of ECG data. Computer methods and programs. 2013, 112(3), pp. 720-730.
https://doi.org/10.1016/j.cmpb.2013.08.002

7 Mohan S, Thirumalai C, Srivastava G Effective heart disease prediction using hybrid machine learning techniques. IEEE Access. 2019, 7, pp.81542-81554.
https://doi.org/10.1109/ACCESS.2019.2923707

8 Dolce G, Quinteri M, Serra S, Lagani V, Pignolo L: Clinical signs and early prognosis in vegetative state: a decisional tree, data-minig study. Brain Inj. 2008, 22 (7-8), pp. 617-623.
https://doi.org/10.1080/02699050802132503

9 Exarchos T.P, Tzallas AT, D Baga, et all Using partial decision trees to predict Parkinson’s symptoms: A new approach for diagnosis and therapy in patients suffering from Parkinson’s disease. Computers in biology and medicine. 2012, 42 (2), pp.195-204.
https://doi.org/10.1016/j.compbiomed.2011.11.008

10 Takahashi O, Cook EF, Nakamura T, Saito J, Ikawa F, Fukui T: Risk stratification for in-hospital mortality in spontaneous intracerebral haemorrhage: a Classification and Regression Tree analysis. QJM, 2006, 99:743-50.
https://doi.org/10.1093/qjmed/hcl107

11 Gortzis LG, Sakellaropoulos F, Ilias I, Stamoulis K, Dimopoulou I: Predicting ICU survival: a meta-level approach. BMC Health Serv Res. 2008, 26:8-157.
https://doi.org/10.1186/1472-6963-8-157

12 Xie J., Su B., Li C.,. Lin K,. Li H, Hu Y., Kong G. A review of modeling methods for predicting in-hospital mortality of patients in intensive care unit. J Emerg Crit Care Med. 2017, 1(8) pp. 1-10.
https://doi.org/10.21037/jeccm.2017.08.03

13 Trujillano J., Badia M., Servia L. et al. Stratification of the severity of critically ill patients with classification trees. BMC Med Res Methodol. 2009, V. 9, no 83, pp. 1-80.
https://doi.org/10.1186/1471-2288-9-83

14 Romanyuk O.A., Kozak L.M., Kovalenko A.S., Kryvova O.A. Digital transformation in medicine: from formalized medical documents to information technologies of digital medicine. Cybernetics and Computer Engineering. 2018, no. 4(194), pp. 61-78.
https://doi.org/10.15407/kvt194.04.061

15 Kryvova O.A., Kozak L.M. Information Technology for Classification of Donosological and Pathological States Using the Ensemble of Data Mining Methods. Cybernetics and Computer Engineering. 2021, no. 1(203), pp. 77-94.
https://doi.org/10.15407/kvt203.01.077

16 Santos M., Portela F. and Vilas-Boas M. INTcare – Multi-agent Approach for Real-time Intelligent Decision Support in Intensive Medicine. In Proceedings of the 3rd International Conference on Agents and Artificial Intelligence (ICAART-2011), SciTePress 2011, pp. 364-369.

17 Kim S, Kim W, Park RW. A Comparison of intensive care unit mortality prediction models through the use of data mining Techniques. Healthc Inform Res. 2011; 17:232-243.
https://doi.org/10.4258/hir.2011.17.4.232

18 Amin M. Chiam Y., Varathan K. Identification of significant features and data mining techniques in predicting heart disease. Telematics and Informatics. 2019, 36, pp. 82-93.
https://doi.org/10.1016/j.tele.2018.11.007

19 Rubini L. J., Perumal E. Efficient classification of chronic kidney disease by using multi-kernel support vector machine and fruit fly optimization algorithm. International Journal of Imaging Systems and Technology. 2020, 30 (3), pp. 660-673.
https://doi.org/10.1002/ima.22406

20 Shillan D., Sterne J. A. C., Champneys, A. & Gibbison, G. Use of machine learning to analyze routinely collected intensive care unit data: a systematic review. Critical Care. 2019, 23 (1), pp. 284-295.
https://doi.org/10.1186/s13054-019-2564-9

21 Kaieski N, da Costa CA, da Rosa Righi R, Lora PS. Application of artificial intelligence methods in vital signs analysis of hospitalized patients: A systematic literature review Applied Soft Computing, 2020, vol. 96, 106612.
https://doi.org/10.1016/j.asoc.2020.106612

22 da Silva D. B., Schmidt D., da Costa C. A., da Rosa Righi R. & Eskofier, B. DeepSigns: A predictive model based on Deep Learning for the early detection of patient health deterioration. Expert Systems with Applications. 2021, 165, 113905.
https://doi.org/10.1016/j.eswa.2020.113905

23 Kwon J.M., Lee Y., Lee Y., Lee S., Park J. An Algorithm Based on Deep Learning for Predicting In-Hospital Cardiac Arrest. J Am Heart Assoc. 2018, 7(13), e008678.
https://doi.org/10.1161/JAHA.118.008678

24 Papapetrou P., Kollios G., Sclaroff S., Gunopulos D. Mining frequent arrangements of temporal intervals. Knowledge and Information Systems. 2009, 21 (2), pp.133-171.
https://doi.org/10.1007/s10115-009-0196-0

25 Moskovitch R., Choi H., Hripcsak G., Tatonetti N. Prognosis of clinical outcomes with temporal patterns and experiences with one class feature selection. EEE/ACM transactions on computational biology and bioinformatics. 2016, 14(3), pp. 555-563.
https://doi.org/10.1109/TCBB.2016.2591539

26 Choi E, Schuetz A, Stewart WF, Sun J. Using recurrent neural network models for early detection of heart failure onset. J Am Med Inform Assoc. 2017, 24, pp. 361-370.
https://doi.org/10.1093/jamia/ocw112

27 Bizopoulos P., Koutsouris D. Deep learning in cardiology IEEE reviews in biomedical engineering. 2018, 12, 168-193.
https://doi.org/10.1109/RBME.2018.2885714

28 SAS Data Mining URL: https://www.sas.com/ru_ua/industry/health-care.html (Last accessed: 06.08.2021)

29 Data Mining: http://statsoft.ru/products/STATISTICA_Data_Miner/ (Last accessed: 28.05.2021)

30 WEKA URL: https://www.cs.waikato.ac.nz/ml/weka/ (Last accessed: 06.08.2021)

31 RapidMiner URL: https://rapidminer.com/ (Last accessed: 06.08.2021)

32 KNIME URL: https://www.knime.com/ (Last accessed: 06.08.2021)

33 Poucke S.V., Zhang Z., Schmitz M., Vukicevic M. Scalable Predictive Analysis in Critically Ill Patients Using a Visual iOpen Data Analysis Platform. PLoS one. 2016, V. 11(1), pp. 1-21.
https://doi.org/10.1371/journal.pone.0145791

34 Kong G., Lin K., Hu Y. Using machine learning methods to predict in-hospital mortality of sepsis patients. BMC medical informatics and decision making. 2020, V. 20 (1), pp. 1-10.
https://doi.org/10.1186/s12911-020-01271-2

Received 01.09.2021

admin

Issue 4 (206), article 3

DOI:https://10.15407/kvt206.04.039

Cybernetics and Computer Engineering, 2021, 4(206)

VOLKOV O. Ye., PhD (Engineering),
Head of Intellectual Control Department
ORCID: 0000-0002-5418-6723, e-mail: alexvolk@ukr.net

TARANUKHA V. Yu., PhD (Phys.-Math.),
Senior Researcher of Intellectual Control Department
ORCID: 0000-0002-9888-4144, e-mail: taranukha@ukr.net

LINDER Ya. M., PhD (Phys.-Math.),
Senior Researcher of Intellectual Control Department
ORCID: 0000-0003-1076-9211, e-mail: dep185@irtc.org.ua

KOMAR M.M., PhD (Engineering),
Senior Research of Intellectual Control Department
ORCID: 0000-0001-9194-2850, e-mail: nickkomar08@gmail.com

VOLOSHENIUK D. O.,
Researcher of Intellectual Control Department
ORCID: 0000-0003-3793-7801, e-mail: p-h-o-e-n-i-x@ukr.net

International Research and Training Center for Information Technologies
and Systems of the National Academy of Sciences of Ukraine
and Ministry of Education and Science of Ukraine,
40, Acad. Glushkova av., Kyiv, 03187, Ukraine

DEVISING AN ACOUSTIC METHOD FOR INVESTIGATION OF A COMPLEX FORM OBJECT PARAMETERS

Introduction. The general principles of the technique of synthesis of reflective characteristics of complex surfaces for small wavelengths are considered in the article. The problem is set in the conditions of using sound waves and sonar. The calculated scattering characteristics are obtained using a facet model.

Purpose. The purpose of the research is to create a method of acoustic research and determination of spatial characteristics of objects of complex shape, which contains the developed facet model of the object and the model of the reflected signal. This method consists artificial models of objects and models of the reflected signal, with the further purpose of research and determination of spatial characteristics of objects, recognition of objects, etc. It is expected that based on the simulation of signals reflected from these models, it will be possible to classify objects. An important difference from most studies is a number of assumptions about what to do with the model and how to calculate the result, because, as a rule, the main element of such studies is the reflection surface only.

Results. For the purpose of this research simplified model of signal reflection from a surface area in space is considered. We established a correspondence between wave propagation in the space and change of the value of the function representing reflecting wave. At any given moment of time the total reflected signal is the sum of all reflected signals from all surfaces. The integral form was proposed for this purpose. The analytical formula intended for the integral was designed for one of the specific cases of reflection. There were numerical experiments performed to test such formula with regard of facet model of the ship. Resulting waveform looks in accordance to expectations.

Conclusion. In accordance with the task the paper demonstrates the method of constructing a model of objects and sound signals reflected from them, paper also considers the general principles of the method of synthesis of reflective characteristics of complex surfaces for small wavelengths. It is shown why and how exactly such a model is built and the presence of a significant difference in the signal characteristics for different angles is clearly demonstrated. The main advantage of this model is the ability to conduct experiments exclusively in digital form, without the need for expensive field experiments. Further research should continue in the direction of selecting or creating an optimal recognition system based on neural networks.

Keywords: facet model, remote sensing, underlying surface, sonar image.

Download full text!

REFERENCES

1 Anisimov A.V., Volkov O.Ye., Linder Ya.M. Method of acoustic direction finding of mobile objects with unmanned aerial wehicle. Collection of scientific works of the Military Institute of Kyiv National Taras Shevchenko University . 2019, (64), pp. 14-24. (in Ukrainian)
https://doi.org/10.17721/2519-481X/2019/64-02

2 Volkov O.Ye., Taranukha V.Yu., Linder Ya.M. Acoustic monitoring technology, detection and localization of objects in a controlled space. Control Systems and Computers. 2020, No 4, pp. 35-43. (in Ukrainian)
https://doi.org/10.15407/csc.2020.04.035

3 Kalinin T.V., Bartsevych A.V., Petrov S.A. Radar recognition system modeling software package. Software products and systems. 2017, V. 30, No 4, pp. 733-738 (in Russian)

4 Scarafoni Daniel et al. Automatic target recognition and geo-location for side scan sonar imagery. The Journal of the Acoustical Society of America. 141, no. 5 (2017): 3925-3925.
https://doi.org/10.1121/1.4988877

5 Brekhovskyh O.V., Grinberg Ye.E., Evseenko M.S. Development of basics of technology of research for the objects of cultural heritage buried in uncompacted bottom sediments by a method of the parametric profilography with use of data of satellite navigation Oceanological research. 2018, Vol. 46, No 2, pp. 5-14
https://doi.org/10.29006/1564-2291.JOR-2018.46(2).1

6 Liu Yan-sen, Wang Yang, Xue-Meng Yang. Acoustic spectrum and signature analysis on underwater radiated noise of a passenger ship target based on the measured data. Eleventh International Conference on Signal Processing Systems, 2019, Chengdu, China URL: https://www.spiedigitallibrary.org/conference-proceedings-of-spie/11384/113840H/Acoustic-spectrum-and-signature-analysis-on-underwater-radiated-noise-of/10.1117/12.2559664.pdf (Last accessed:)
https://doi.org/10.1117/12.2559664

7 Zhu C., Seri S.G., Mohebbi-Kalkhoran H. et al. Long-range automatic detection, acoustic signature characterization and bearing-time estimation of multiple ships with coherent hydrophone array. Remote Sensing, 2020. 12(22), p. 3731. URL: https://www.mdpi.com/2072-4292/12/22/3731/pdf (Last accessed:)
https://doi.org/10.3390/rs12223731

8 Khrychov V.S., Legenky M.M. Facet model of an object of complex shape for the calculation of electromagnetic scattering. Bulletin of V.N. Karazin Kharkiv National University. Radiophysics and Electronics Series, 2019, (28), pp. 44-52. (in Ukrainian)

9 Maslovsky A.A., Legenky M.M. On reducing the visibility of radar targets located on the underlying surface . Bulletin of V.N. Karazin Kharkiv National University. Radiophysics and Electronics Series. 2014, Iss. 24, No 1115, pp.14-22 (in Russian)

10 Youssef N.N. Radar cross section of complex targets Proceedings of the IEEE. 1989, Vol. 77, Iss. 5, pp. 722-734.
https://doi.org/10.1109/5.32062

11 Murashkin A.V., Yudin V.A. Experimental studies of the correlation two-frequency method for the recognition of aerodynamic targets. Achievements of university science. 2016, (21), pp. 136-140. (in Russian).

Received 02.09.2021

admin

Issue 4 (206), article 2

DOI:https://10.15407/kvt206.04.017

Cybernetics and Computer Engineering, 2021, 4(206)

SUROVTSEV I.V.1, DSc (Engineering), Senior Researcher,
Head of the Ecological Digital Systems Department
ORCID: 0000-0003-1133-6207, e-mail: dep115@irtc.org.ua, igorsur52@gmail.com

VELYKYI P.Y.1, PhD Student,
of the Ecological Digital Systems Department
e-mail: velykyi305@gmail.com

HRYTSAIENKO M.2, PhD Student
Joint Research Unit 7504,

GALIMOVA V.M.3, PhD (Chemistry), Associate Professor,
Department of Analytical and Inorganic
Chemistry and Water Quality
ORCID: 0000-0001-9602-1006, e-mail: galimova2201@gmail.com

1International Research and Training Center for
Information Technologies and Systems of the 
National Academy of Sciences of Ukraine 
and Ministry of Education and Science of Ukraine, 
40, Acad. Glushkov av., Kyiv, 03187, Ukraine

2Strasbourg Institute of Material Physics and Chemistry,
Joint Research Unit 7504, 
National Center for Scientific Research – 
University of Strasbourg,
4 Rue Blaise Pascal, 67081 Strasbourg, France

3National University of Life
and Environmental Sciences of Ukraine,
17, bldg. № 2, Heroes of Defense str., Kyiv, 03041, Ukraine

ANALYTICAL SYSTEM FOR ENVIRONMENTAL MONITORING AND RISK ASSESSING OF DRINKING WATER CONSUMPTION

Introduction. The use of the electrochemical analytical system “IHP Analyzer” allows the environmental monitoring the conditions of drinking water and water objects, assessing and predicting the risks of toxicants on human health and the environment.

The purpose of the paper is to propose information technology for rapid determining chemical elements concentrations and for assessing the risk of their impact on the biosphere.

Methods. Pulse methods of chronopotentiometry, chronoionometric method of direct potentiometry and methods of assessment of ecological risk of influence of chemicals on environment are used for measurement of concentrations.

Methods. Pulse chronopotentiometry methods, direct chronoionometric potentiometry methods and methods for assessing the risk of human health deterioration in the case of consumption of drinking water of different quality are used.

Results. Developed information technology that uses machine learning techniques, cloud technologies and intelligent models to study the mass of chemical elements additives. The application of IT allows the results of one measurement to quickly determine the elements concentrations  in the water objects by comparing signals and assess the impact risks of chemicals to human health when consuming contaminated drinking water.

Results. Developed information technology with machine learning, cloud technologies and the use of intelligent models of the mass of chemical element additives, that allows the results of one measurement to quickly determine the elements concentrations in the water objects by comparing signals and assess the impact risks of chemicals to human health when consuming contaminated drinking water.

Conclusions. Advanced analytical system “Analyzer SCP” allows you to quickly measure the concentration of 12 chemicals (Pb, Cd, Cu, Zn, Se, I, K, Na, Ca, F, NO3, NH4) in water bodies on site and eight more toxic elements (Hg, As, Sn, Ni, Co, Mn, Cr, Fe) in the laboratory, which allowed to quickly and fully determine the environmental quality of drinking water and the environment. The use of ion-selective and measuring electrodes based on precious metals increases the environmental friendliness and speed of research. The application of risk assessment methodology for the chemical elements impact on humans and the environment allows to predict the consequences and occurrence of diseases with long-term consumption of contaminated drinking water or the possibility of using water bodies for irrigation and fish farming.

Keywords: concentration, ecological risk, ion-selective electrode, inversion chronopotentiometry, drinking water.

Download full text (ua)!

REFERENCES

1 Surovtsev I.V., Velykyi P.Y., Galimova V.M., Sarkisova M.V. Ionometric method for determination of concentrations of microelements in research of digital medicine. Cyb. and comp. eng., 2020. No. 4 (220), 25-43.
https://doi.org/10.15407/kvt202.04.025

2 Surovtsev I.V., Galimov S.K., Galimova V.M., Sarkisova M.V. Method of chronoionometric determination of concentrations of fluorine, nitrate, ammonium in drinking water. Cyb. and comp. eng., 2021. No. 1 (203), 5-25.
https://doi.org/10.15407/kvt203.01.005

3 Kopilevich V.A., Maksin V.I., Galimova V.M., Surovtsev I.V., Lavrik R.V. Electrochemical Control of Microconcentrations of Cadmium in Aquatic Environments // Journal of water chemistry and technology, 2021, Vol. 43, P. 336-341.
https://doi.org/10.3103/S1063455X21040056

4 Eric Bakker and Erno Pretsch. Modern Potentiometry // Angew Chem Int Ed Engl. 2007 ; 46(30): 5660-5668. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2515866 Scientific Opinion on Dietary Reference Values for water. EFSA Panel on Dietetic Products, Nutrition, and Allergies (NDA) // EFSA Journal 2010; 8(3):1459
https://doi.org/10.2903/j.efsa.2010.1459

5 Huang, Y.; Wang, T.; Xu, Z.; Hughes, E.; Qian, F.; Lee, M.; Fan, Y.; Lei, Y.; Bruckner, C.; Li, B. Real-time in situ monitoring of nitrogen dynamics in wastewater treatment processes using wireless, solid-state, and ion-selective membrane sensors. Environ. Sci. Technol. 2019, 53, 3140-3148.
https://doi.org/10.1021/acs.est.8b05928

6 Gemene Kebede L. Bakker E. Measurement of total calcium by flash chronopotentiometry at polymer membrane ion-selective electrodes. Analytica Chimica Acta. 2009. Vol. 648, 240-245.
https://doi.org/10.1016/j.aca.2009.07.004

7 Roy, S.; David-Pur, M.; Hanein, Y. Carbon nanotube-based ion selective sensors for wearable applications. ACS Appl. Mater. Interfaces 2017, 9, 35169-35177.
https://doi.org/10.1021/acsami.7b07346

8 Umezawa, Y.; Buhlmann, P.; Umezawa, K.; Tohda, K.; Amemiya, S. Potentiometric selectivity coefficients of ion-selective electrodes. Part I. Inorganic cations (technical report). Pure Appl. Chem. 2000, 72, 1851-2082.
https://doi.org/10.1351/pac200072101851

9 Guidance on harmonised methodologies for human health, animal health and ecological risk assessment of combined exposure to multiple chemicals // EFSA Journal 2019;17(3):5634.

10 Baas J, Augustine S, Marques GM and Dorne JL, 2018. Dynamic energy budget models in ecological risk assessment: from principles to applications. Science of the Total Environment, 628-629, 249-260
https://doi.org/10.1016/j.scitotenv.2018.02.058

11 Bopp S, Berggren E, Kienzler A, van der Linden S and Worth A, 2015. Scientific methodologies for the assessment of combined effects of chemicals – a survey and literature review. JRC Technical Reports, 64.

12 ECETOC (European Centre for Ecotoxicology and Toxicology of Chemicals), 2012. The European Centre for Ecotoxicology and Toxicology of Chemicals (ECETOC) 2012 Annual Report. Available online: http://www.ecetoc.org/wp-content/uploads/2013/06/ECETOC_2012_Annual_Report.pdf

13 EFSA PPR Panel (EFSA Panel on Plant Protection Products and their Residues), 2014. Scientific Opinion on good modelling practice in the context of mechanistic effect models for risk assessment of Plant Protection Products. EFSA Journal 2014;12(3):3589, 92 pp.
https://doi.org/10.2903/j.efsa.2014.3589

14 Meek ME, Boobis AR, Crofton KM, Heinemeyer G, Van Raaij M and Vickers C, 2011. Risk assessment of combined exposure to multiple chemicals: A WHO/IPCS framework. Regulatory Toxicology and Pharmacology, 60, S1-S14
https://doi.org/10.1016/j.yrtph.2011.03.010

15 Solomon KR, Wilks MF, Bachman A, Boobis A, Moretto A, Pastoor TP, Phillips R and Embry MR, 2016. Problem formulation for risk assessment of combined exposures to chemicals and other stressors in humans. Critical Reviews in Toxicology, 46, 835-844
https://doi.org/10.1080/10408444.2016.1211617

16 US EPA (Environmental Protection Agency), 2011. Vocabulary Catalog List Detail-Integrated Risk Information System (IRIS) Glossary

17 Van Gestel CAM, Jonker MJ, Kammenga JE, Laskowski R and Svendsen C, 2011. Mixture Toxicity. Linking Approaches from Ecological and Human Toxicology. SETAC Press, Pensacola, USA, 320 pp. ISBN 9781439830086

Received 26.09.2021

admin

Issue 4 (206), article 1

DOI:https://10.15407/kvt206.04.005

Cybernetics and Computer Engineering, 2021, 4(206)

MOROZ O.H., PhD (Engineering),
Senior Researcher of Dept. for Information Technologies of Inductive Modeling
ORCID: 0000-0002-0356-8780, e-mail: оlhahryhmoroz@gmail.com

STEPASHKO V.S., DSc (Engineering), Professor,
Head of Dept. for Information Technologies of Inductive Modeling
ORCID: 0000-0001-7882-3208, e-mail: stepashko@irtc.org.ua

International Research and Training Centre for Information Technologies
and Systems of the National Academy of Sciences of Ukraine and Ministry
of Education and Science of Ukraine,
40, Acad. Glushkov av., Kyiv, 03187, Ukraine

COMPARATIVE FEATURES OF MIA GMDH AND DEEP FEED-FORWARD NEURAL NETWORKS

Introduction. Deep neural networks are effective tools for solving actual tasks such as data mining, modeling, forecasting, pattern recognition, clustering, classification etc. They differ with respect to the architecture design, learning methods and so on. Most simple and widely used are deep feed-forward supervised NNs.

The purpose of the paper is to compare briefly main features of the deep feed-forward deterministic supervised networks with the Multilayered Iterative Algorithm of GMDH (MIA GMDH) and to formulate main ideas of constructing a new class of hybrid deep networks based on the MIA neural network.

Methods. Most usable deep feed-forward supervised neural networks have been studied: multilayered perceptron, convolutional NN and some its modifications, polynomial neural networks, genetic polynomial neural network etc.

Results. There was carried out a comparative analysis of main features of the MIA GMDH neural network with the characteristics of other deep deterministic supervised neural networks. The most promising approaches are identified to improve the performance of this network, particularly by hybridization with methods of computational intelligence. The main idea of building a new class of hybrid deep networks based on MIA GMDH is formulated.

Conclusions. MIA GMDH and its modifications are original representatives of the self-organizing networks potentially giving best results, especially for big data case. Hybridization of GMDH-based NNs with stochastic methods of computational intelligence is suggested to achieve a synergetic effect.

Keywords: multilayered iterative algorithm of GMDH (MIA GMDH), self-organizing neural network, neural network architecture, deep neural networks, feed-forward neural networks, supervised neural networks, deep learning.

Download full text!

REFERENCES
1 J. Schmidhuber. Deep Learning in Neural Networks: An Overview. Neural Networks. 2015, Vol. 61, pp. 85-117.
https://doi.org/10.1016/j.neunet.2014.09.003

2 Y. Bengio. Learning Deep Architectures for AI. Foundations and Trends in Machine Learning. 2009, Vol. 2: No. 1, pp. 1-127.
https://doi.org/10.1561/2200000006

3 Li Deng. A tutorial survey of architectures, algorithms, and applications for deep learning. APSIPA Transactions on Signal and Information Processing, Volume 3, E2, 2014, pp.1-29. doi:10.1017/atsip.2013.9
https://doi.org/10.1017/atsip.2013.9

4 Li Deng, Dong Yu. Deep Learning: Methods and Applications. Foundations and Trends in Signal Processing. 2014, Vol. 7: No. 3-4, pp. 197-387.
https://doi.org/10.1561/2000000039

5 A. Shahroudnejad. A Survey on Understanding, Visualizations, and Explanation of Deep Neural Networks. CoRR, 2021, URL: https://arxiv.org/pdf/2102.01792v1.pdf (Last accesed: 10.08.2021)

6 D. Shaveta, K. Munish, A. Maruthi Rohit, K. Gulshan. A Survey of Deep Learning and Its Applications: A New Paradigm to Machine Learning. Archives of Computational Methods in Engineering. 2020, 27 (4), pp. 1071-1092.
https://doi.org/10.1007/s11831-019-09344-w

7 URL: https://www.mdpi.com/2504-3900/47/1/9 (Last accesed: 15.08.2021)
https://doi.org/10.3390/proceedings47010015

8 Ivakhnenko A.G., Lapa V.G. Cybernetic Predicting Devices. CCM Information Corporationm, 1965, 256 p.

9 B. Ben-Bright, Y. Zhan, B. Ghansah, R. Amankwah, D. Keddy Wornyo, E. Ansah. Taxonomy and a Theoretical Model for Feedforward Neural Networks. International Journal of Computer Applications. 2017, 163(4), pp. 39-49.
https://doi.org/10.5120/ijca2017913513

10 J.J. Hopfield. Neural Networks and physical systems with emergent collective computational abilities. Proc. Natl. Acad. Sci. USA, 1982, 79, pp. 2554-2558.
https://doi.org/10.1073/pnas.79.8.2554

11 Z. Li, W. Yang, S. Peng, F. Liu. A Survey of Convolutional Neural Networks. Analysis, Applications, and Prospects. 2020, pp.21

12 URL: https://fanchenyou.github.io/homepage/docs/cnn_survey.pdf (Last accessed: 10.07.2021)

13 S. Srinivas et al. A Taxonomy of Deep Convolutional Neural Nets for Computer Vision. Frontiers in Robotics and AI. 2016, pp.?
https://doi.org/10.3389/frobt.2015.00036

14 G. Chrysos, S. Moschoglou, G. Bouritsas, J. Deng, Y. Panagakis, S. Zafeiriou. Deep Polynomial Neural Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2021.
https://doi.org/10.1109/CVPR42600.2020.00735

15 URL: https://towardsdatascience.com/an-introduction-to-convolutional-neural-networks-eb0b60b58fd7 (Last accessed: 17.07.2021)

16 Stepashko V. Developments and Prospects of GMDH-Based Inductive Modeling. Advances in Intelligent Systems and Computing II: Selected Papers from the International Conference on Computer Science and Information Technologies CSIT 2017 / N. Shakhovska, V. Stepashko, Editors. AISC book series, Springer, 2018, Vol. 689, pp. 474-491.
https://doi.org/10.1007/978-3-319-70581-1_34

17 Stepashko V. On the Self-Organizing Induction-Based Intelligent Modeling. Advances in Intelligent Systems and Computing III: Selected Papers from the International Conference on Computer Science and Information Technologies CSIT 2018 / N. Shakhovska, M.O. Medykovskyy, Editors. AISC book series, Springer, 2019, Vol. 871, pp. 433-448.
https://doi.org/10.1007/978-3-030-01069-0_31

18 S.-K. Oh, W. Pedrycz, B.-J. Park. Polynomial neural networks architecture: analysis and design. Computers and Electrical Engineering. 2003, 23, pp. 703-725.
https://doi.org/10.1016/S0045-7906(02)00045-9

19 S. Farzi. A New Approach to Polynomial Neural Networks based on Genetic Algorithm. International Scholarly and Scientific Research & Innovation. 2008, 2(8), pp. 2700-2707

20 Moroz O.H., Stepashko V.S. An overview of hybrid structures of GMDH-like neural networks and genetic algorithms. Inductive modeling of complex systems: Coll. sciences works. 2015,7, K .: IRTC ITS NASU, pp. 173-191.

Received 03.08.2021