mireabulletinRussian Technological JournalRussian Technological Journal2782-32102500-316XRTU MIREA10.32362/2500-316X-2023-11-2-7-19mireabulletin-650Research ArticleИНФОРМАЦИОННЫЕ СИСТЕМЫ. ИНФОРМАТИКА. ПРОБЛЕМЫ ИНФОРМАЦИОННОЙ БЕЗОПАСНОСТИINFORMATION SYSTEMS. COMPUTER SCIENCES. ISSUES OF INFORMATION SECURITYПрименение робастной нейросетевой фильтрации в задачах построения интеллектуальных интерфейсовRobust neural network filtering in the tasks of building intelligent interfaceshttps://orcid.org/0000-0001-6712-0072ВасильевА. В.VasilievA. V.

Васильев Антон Владимирович, аспирант кафедры «Прикладные информационные технологии» Института кибербезопасности и цифровых технологий

119454, Москва, пр-т Вернадского, д. 78

Anton V. Vasiliev, Postgraduate Student, Department of Applied Information Technologies, Institute for Cybersecurity and Digital Technologies

78, Vernadskogo pr., Moscow, 119454

bysslaev@gmail.comhttps://orcid.org/0000-0003-1980-2727МельниковА. О.MelnikovA. O.

Alexey O. Melnikov, Cand. Sci. (Eng.), Associate Professor, Department of Applied Information Technologies, Institute for Cybersecurity and Digital Technologies

78, Vernadskogo pr., Moscow, 119454

melnikov.aleksey@gmail.comhttps://orcid.org/0000-0002-6641-1609ЛеськоС. А.LeskoS. A.

Лесько Сергей Александрович, кандидат технических наук, доцент, доцент кафедры «Прикладные информационные технологии» Института кибербезопасности и цифровых технологий 

Scopus Author ID 57189664364

119454, Москва, пр-т Вернадского, д. 78

Sergey A. Lesko, Cand. Sci. (Eng.), Associate Professor, Department of Applied Information Technologies, Institute for Cybersecurity and Digital Technologies

Scopus Author ID 57189664364

78, Vernadskogo pr., Moscow, 119454

sergey@testor.ruМИРЭА – Российский технологический университетРоссияMIREA – Russian Technological UniversityRussian Federation202306042023112719Copyright © Васильев А.В., Мельников А.О., Лесько С.А., 20232023Васильев А.В., Мельников А.О., Лесько С.А.Vasiliev A.V., Melnikov A.O., Lesko S.A.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://www.rtj-mirea.ru/jour/article/view/650

В последние годы возрос научный интерес к построению интеллектуальных интерфейсов для управления компьютером на основе биометрических данных. Одним из источников таких данных служит сигнал электромиографии (ЭМГ). Сигнал ЭМГ можно использовать для классификации жестов рук человека. Это позволяет организовать интуитивно понятный интерфейс «человек – компьютер». Основными проблемами при использовании сигналов ЭМГ являются наличие нелинейных шумов в сигнале и значительное влияние индивидуальных особенностей человека.

Цель работы – исследование возможностей применения нейронных сетей для фильтрации индивидуальных компонент сигнала ЭМГ.

Методы

Методы. Использованы математические методы обработки сигналов и методы машинного обучения.

Результаты

Результаты. Проведен анализ исследований по теме обработки ЭМГ-сигналов. Предложена концепция интеллектуальной обработки биологических сигналов. Разработана модель фильтрации сигнала, построена структура сверточной нейронной сети на основе технологий Python 3, TensorFlow и Keras. Проведен эксперимент на наборе данных ЭМГ по фильтрации индивидуальных компонент сигнала.

Выводы

Выводы. Продемонстрирована возможность применения искусственных нейронных сетей для выявления и подавления индивидуальных особенностей человека в биологических сигналах. При обучении сети основной упор делался на индивидуальные особенности, тестируя сеть на данных, полученных от субъектов, не участвующих в процессе обучения. Достигнуто уменьшение индивидуального шума в среднем на 5%. Для решения задачи классификации сигнала ЭМГ данный результат поможет избежать переобучения сети и повысить точность классификации жестов для новых пользователей.

Objectives

Objectives. In recent years, there has been growing scientific interest in the creation of intelligent interfaces for computer control based on biometric data, such as electromyography signals (EMGs), which can be used to classify human hand gestures to form the basis for organizing an intuitive human-computer interface. However, problems arising when using EMG signals for this purpose include the presence of nonlinear noise in the signal and the significant influence of individual human characteristics. The aim of the present study is to investigate the possibility of using neural networks to filter individual components of the EMG signal.

Methods

Methods. Mathematical signal processing techniques are used along with machine learning methods.

Results

Results. The overview of the literature on the topic of EMG signal processing is carried out. The concept of intelligent processing of biological signals is proposed. The signal filtering model using a convolutional neural network structure based on Python 3, TensorFlow and Keras technologies was developed. Results of an experiment carried out on an EMG data set to filter individual signal components are presented and discussed.

Conclusions

Conclusions. The possibility of using artificial neural networks to identify and suppress individual human characteristics in biological signals is demonstrated. When training the network, the main emphasis was placed on individual features by testing the network on data received from subjects not involved in the learning process. The achieved average 5% reduction in individual noise will help to avoid retraining of the network when classifying EMG signals, as well as improving the accuracy of gesture classification for new users.

цифровая обработка сигналачастотная фильтрацияэлектромиографиямашинное обучениенейронные сетиинтерфейсыуправление жестамиdigital signal processingfrequency filteringelectromyographymachine learningneural networksinterfacesgesture manipulationReferencesArruda L.M., Calado A., Boldt R.S., Yu.Y., Carvalho H., Carvalho M.A., Soares F., Matos D. Design and testing of a textile EMG sensor for prosthetic control. In: Garcia N.M., Rires I.M., Goleva R. (Eds.). IoT Technologies for HealthCare: 6th EAI International Conference, HealthyIoT 2019. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering. Springer; 2020;341:37–51. https://doi.org/10.1007/978-3-030-42029-1_3Arruda L.M., Calado A., Boldt R.S., Yu.Y., Carvalho H., Carvalho M.A., Soares F., Matos D. Design and testing of a textile EMG sensor for prosthetic control. In: Garcia N.M., Rires I.M., Goleva R. (Eds.). IoT Technologies for HealthCare: 6th EAI International Conference, HealthyIoT 2019. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering. Springer; 2020;341:37–51. https://doi.org/10.1007/978-3-030-42029-1_3Hu Y., Wang H., Sheikhnejad O., Xiong Y., Gu H., Zhu P., Sun R., Wong C.P. Stretchable and printable medical dry electrode arrays on textile for electrophysiological monitoring. In: IEEE 69th Electronic Components and Technology Conference (ECTC). 2019;243–248. https://doi.org/10.1109/ECTC.2019.00043Hu Y., Wang H., Sheikhnejad O., Xiong Y., Gu H., Zhu P., Sun R., Wong C.P. Stretchable and printable medical dry electrode arrays on textile for electrophysiological monitoring. In: IEEE 69th Electronic Components and Technology Conference (ECTC). 2019;243–248. https://doi.org/10.1109/ECTC.2019.00043Truong H., Zhang S., Muncuk U., Nguyen P., Bui N., Nguyen A., Dinh T.N., Vu T. CapBand: Battery-free successive capacitance sensing wristband for hand gesture recognition. In: Proceedings of the 16th ACM Conference on Embedded Networked Sensor Systems (SenSys ‘18). 2018;54–67. https://doi.org/10.1145/3274783.3274854Truong H., Zhang S., Muncuk U., Nguyen P., Bui N., Nguyen A., Dinh T.N., Vu T. CapBand: Battery-free successive capacitance sensing wristband for hand gesture recognition. In: Proceedings of the 16th ACM Conference on Embedded Networked Sensor Systems (SenSys ‘18). 2018;54–67. https://doi.org/10.1145/3274783.3274854Goto D., Shiozawa N. Can textile electrode for ECG apply to EMG measurement? In: World Congress on Medical Physics and Biomedical Engineering. 2018;431–434. https://doi.org/10.1007/978-981-10-9038-7_81Goto D., Shiozawa N. Can textile electrode for ECG apply to EMG measurement? In: World Congress on Medical Physics and Biomedical Engineering. 2018;431–434. https://doi.org/10.1007/978-981-10-9038-7_81Samuel O.W., Asogbon M.G., Geng Y., Al-Timemy A.H., Pirbhulal S., Ji N., Chen S., Li G. Intelligent EMG pattern recognition control method for upper-limb multifunctional prostheses: advances, current challenges, and future prospects. IEEE Access. 2019;7:10150–10165. https://doi.org/10.1109/ACCESS.2019.2891350Samuel O.W., Asogbon M.G., Geng Y., Al-Timemy A.H., Pirbhulal S., Ji N., Chen S., Li G. Intelligent EMG pattern recognition control method for upper-limb multifunctional prostheses: advances, current challenges, and future prospects. IEEE Access. 2019;7:10150–10165. https://doi.org/10.1109/ACCESS.2019.2891350Raheema M.N., Hussain J.S., Al-Khazzar A.M. Design of an intelligent controller for myoelectric prostheses based on multilayer perceptron neural network. In: IOP Conf. Ser.: Mater. Sci. Eng. 2020;671(1):012064. https://doi.org/10.1088/1757-899X/671/1/012064Raheema M.N., Hussain J.S., Al-Khazzar A.M. Design of an intelligent controller for myoelectric prostheses based on multilayer perceptron neural network. In: IOP Conf. Ser.: Mater. Sci. Eng. 2020;671(1):012064. https://doi.org/10.1088/1757-899X/671/1/012064Sosa M., Oviedo G., Fontana J.M., O’Brien R., Laciar E., Molisani L. Development of a serious game controlled by myoelectric signals. In: The 8th Latin American Conference on Biomedical Engineering and The 42nd National Conference on Biomedical Engineering. CLAIB 2019. IFMBE Proceedings. 2019;75:1171–1177. https://doi.org/10.1007/978-3-030-30648-9_152Sosa M., Oviedo G., Fontana J.M., O’Brien R., Laciar E., Molisani L. Development of a serious game controlled by myoelectric signals. In: The 8th Latin American Conference on Biomedical Engineering and The 42nd National Conference on Biomedical Engineering. CLAIB 2019. IFMBE Proceedings. 2019;75:1171–1177. https://doi.org/10.1007/978-3-030-30648-9_152McIntosh J., Marzo A., Fraser M., Phillips C. EchoFlex: Hand gesture recognition using ultrasound imaging. In: Proceedings of The 2017 CHI Conference on Human Factors in Computing Systems. (CHI ‘17). 2017; 1923–1934. https://doi.org/10.1145/3025453.3025807McIntosh J., Marzo A., Fraser M., Phillips C. EchoFlex: Hand gesture recognition using ultrasound imaging. In: Proceedings of The 2017 CHI Conference on Human Factors in Computing Systems. (CHI ‘17). 2017; 1923–1934. https://doi.org/10.1145/3025453.3025807Lukyanchikov A.I., Melnikov A.O., Lukyanchikov O.I. Algorithms for classifi of a single channel EMG signal for human-computer interaction. In: ITM Web of Conferences. 2018;18:02001. https://doi.org/10.1051/itmconf/20181802001Lukyanchikov A.I., Melnikov A.O., Lukyanchikov O.I. Algorithms for classifi of a single channel EMG signal for human-computer interaction. In: ITM Web of Conferences. 2018;18:02001. https://doi.org/10.1051/itmconf/20181802001Tavakoli M., Benussi C., Lopes P.A., Osorio L.B., de Almeida A.T. Robust hand gesture recognition with a double channel surface EMG wearable armband and SVM classifier. Biomed. Signal Process. Control. 2018;46: 121–130. https://doi.org/10.1016/j.bspc.2018.07.010Tavakoli M., Benussi C., Lopes P.A., Osorio L.B., de Almeida A.T. Robust hand gesture recognition with a double channel surface EMG wearable armband and SVM classifier. Biomed. Signal Process. Control. 2018;46: 121–130. https://doi.org/10.1016/j.bspc.2018.07.010Chen C., Ma S., Sheng X., Zhu X. Continuous estimation of grasp kinematics with real-time surface EMG decomposition. In: International Conference on Intelligent Robotics and Applications. 2019;11744: 108–119. https://doi.org/10.1007/978-3-030-27541-9_10Chen C., Ma S., Sheng X., Zhu X. Continuous estimation of grasp kinematics with real-time surface EMG decomposition. In: International Conference on Intelligent Robotics and Applications. 2019;11744: 108–119. https://doi.org/10.1007/978-3-030-27541-9_10Wang Y., Wang C., Wang Z., Wang X., Li Y. Hand gesture recognition using sparse autoencoder-based deep neural network based on electromyography measurements. In: Nano-, Bio-, Info-Tech Sensors, and 3D Systems II. 2018;105971D:163–169. https://doi.org/10.1117/12.2296382Wang Y., Wang C., Wang Z., Wang X., Li Y. Hand gesture recognition using sparse autoencoder-based deep neural network based on electromyography measurements. In: Nano-, Bio-, Info-Tech Sensors, and 3D Systems II. 2018;105971D:163–169. https://doi.org/10.1117/12.2296382Qi J., Jiang G., Li G., Sun Y., Tao B. Surface EMG hand gesture recognition system based on PCA and GRNN. Neural Comput. Appl. 2020;32(10):6343–6351. https://doi.org/10.1007/s00521-019-04142-8Qi J., Jiang G., Li G., Sun Y., Tao B. Surface EMG hand gesture recognition system based on PCA and GRNN. Neural Comput. Appl. 2020;32(10):6343–6351. https://doi.org/10.1007/s00521-019-04142-8Cappellari P., Gaunt R., Beringer C., Mansouri M., Novelli M. Identifying electromyography sensor placement using dense neural networks. In: Proceedings of The 7th International Conference on Data Science, Technology and Applications. 2018:130–141. http://dx.doi.org/10.5220/0006912501300141Cappellari P., Gaunt R., Beringer C., Mansouri M., Novelli M. Identifying electromyography sensor placement using dense neural networks. In: Proceedings of The 7th International Conference on Data Science, Technology and Applications. 2018:130–141. http://dx.doi.org/10.5220/0006912501300141Pal K.K., Banerjee P., Choudhuri S., Sampat S. Activity classification using Myo Gesture Control Armband data through machine learning. 2019. Available from URL: https://kuntalkumarpal.github.io/files/MC_Report.pdfPal K.K., Banerjee P., Choudhuri S., Sampat S. Activity classification using Myo Gesture Control Armband data through machine learning. 2019. Available from URL: https://kuntalkumarpal.github.io/files/MC_Report.pdfNoble W. What is a support vector machine? Nat. Biotechnol. 2006;24:1565–1567. https://doi.org/10.1038/nbt1206-1565Noble W. What is a support vector machine? Nat. Biotechnol. 2006;24:1565–1567. https://doi.org/10.1038/nbt1206-1565Breiman L. Random forests. Machine learning. 2001;45:5–32. https://doi.org/10.1023/A:1010933404324Breiman L. Random forests. Machine learning. 2001;45:5–32. https://doi.org/10.1023/A:1010933404324Wright R.E. Logistic regression. In: Grimm L.G., YarnoldP.R.(Eds.).Readingandunderstandingmultivariate statistics. American Psychological Association; 1995. P. 217–244. https://psycnet.apa.org/record/1995-97110-007Wright R.E. Logistic regression. In: Grimm L.G., YarnoldP.R.(Eds.).Readingandunderstandingmultivariate statistics. American Psychological Association; 1995. P. 217–244. https://psycnet.apa.org/record/1995-97110-007Chen T., Guestrin C. XGBoost: A scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD ‘16). New York, NY, USA: Association for Computing Machinery; 2016. P. 785–794. https://doi.org/10.1145/2939672.2939785Chen T., Guestrin C. XGBoost: A scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD ‘16). New York, NY, USA: Association for Computing Machinery; 2016. P. 785–794. https://doi.org/10.1145/2939672.2939785Ke G., Meng Q., Finley T., Wang T., Chen W., Ma W., Ye Q., Liu T.Y. LightGBM: A highly efficient gradient boosting decision tree. Advances in Neural Information Processing Systems (NIPS 2017). Long Beach, CA, USA: 2017;30. Available from URL: https://proceedings.neurips.cc/paper/2017/file/6449f44a102fde848669bdd9eb6b76fa-Paper.pdfKe G., Meng Q., Finley T., Wang T., Chen W., Ma W., Ye Q., Liu T.Y. LightGBM: A highly efficient gradient boosting decision tree. Advances in Neural Information Processing Systems (NIPS 2017). Long Beach, CA, USA: 2017;30. Available from URL: https://proceedings.neurips.cc/paper/2017/file/6449f44a102fde848669bdd9eb6b76fa-Paper.pdfSherstinsky A. Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network. Physica D: Nonlinear Phenomena. 2020 Mar. 1;404:132306. https://doi.org/10.1016/j.physd.2019.132306Sherstinsky A. Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network. Physica D: Nonlinear Phenomena. 2020 Mar. 1;404:132306. https://doi.org/10.1016/j.physd.2019.132306Shi X., Chen Z., Wang H., Yeung D.Y., Wong W.K., Woo W.C. Convolutional LSTM network: A machine learning approach for precipitation nowcasting. Advances in Neural Information Processing Systems (NIPS 2015). 2015;28. Available from URL: https://papers.nips.cc/paper/2015/hash/07563a3fe3bbe7e3ba84431ad9d055af-Abstract.htmlShi X., Chen Z., Wang H., Yeung D.Y., Wong W.K., Woo W.C. Convolutional LSTM network: A machine learning approach for precipitation nowcasting. Advances in Neural Information Processing Systems (NIPS 2015). 2015;28. Available from URL: https://papers.nips.cc/paper/2015/hash/07563a3fe3bbe7e3ba84431ad9d055af-Abstract.htmlChen C., Yu Y., Ma S., Sheng X., Lin C., Farina D., Zhu X. Hand gesture recognition based on motor unit spike trains decoded from high-density electromyography. Biomed. Signal Process. Control. 2020;55:101637. https://doi.org/10.1016/j.bspc.2019.101637Chen C., Yu Y., Ma S., Sheng X., Lin C., Farina D., Zhu X. Hand gesture recognition based on motor unit spike trains decoded from high-density electromyography. Biomed. Signal Process. Control. 2020;55:101637. https://doi.org/10.1016/j.bspc.2019.101637Atzori M., Müller H. The Ninapro database: A resource for sEMG naturally controlled robotic hand prosthetics. In: 2015 The 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). 2015:7151–7154. https://doi.org/10.1109/EMBC.2015.7320041Atzori M., Müller H. The Ninapro database: A resource for sEMG naturally controlled robotic hand prosthetics. In: 2015 The 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). 2015:7151–7154. https://doi.org/10.1109/EMBC.2015.7320041Андрианова Е.Г., Головин С.А., Зыков С.В., Лесько С.А., Чукалина Е.Р. Обзор современных моделей и методов анализа временных рядов динамики процессов в социальных, экономических и социотехнических системах. Российский технологический журнал. 2020;8(4):7–45. https://doi.org/10.32362/2500-316X-2020-8-4-7-45Andrianova E.G., Golovin S.A., Zykov S.V., Lesko S.A., Chukalina E.R. Review of modern models and methods of analysis of time series of dynamics of processes in social, economic and socio-technical systems. Rossiiskii tekhnologicheskii zhurnal = Russian Technological Journal. 2020;8(4):7–45 (in Russ.). https://doi.org/10.32362/2500-316X-2020-8-4-7-45]Никонов В.В., Горчаков А.В. Тренировка моделей машинного обучения с использованием современных средств контейнеризации и облачной инфраструктуры. Промышленные АСУ и контроллеры. 2021;6: 26–36. https://doi.org/10.25791/asu.6.2021.1288Nikonov V.V., Gorchakov A.V. Train machine learning models using modern containerization and cloud Infrastructure. Promyshlennye ASU I kontrollery = Industrial Automated Control Systems and Controllers. 2021;6:33–43 (in Russ.). https://doi.org/10.25791/asu.6.2021.1288Kingma D.P., Ba J. Adam: A method for stochastic optimization. arXiv preprint arXiv.1412.6980. 2014. https://doi.org/10.48550/arXiv.1412.6980Kingma D.P., Ba J. Adam: A method for stochastic optimization. arXiv preprint arXiv.1412.6980. 2014. https://doi.org/10.48550/arXiv.1412.6980Wang Z., Bovik A.C. Mean squared error: Love it or leave it? A new look at signal fidelity measures. In: IEEE Signal Processing Magazine. 2009;26(1):98–117. https://doi.org/10.1109/MSP.2008.930649Wang Z., Bovik A.C. Mean squared error: Love it or leave it? A new look at signal fidelity measures. In: IEEE Signal Processing Magazine. 2009;26(1):98–117. https://doi.org/10.1109/MSP.2008.930649

The authors declare that there are no conflicts of interest present.