Information-extreme machine learning of wrist prosthesis control system based on the sparse training matrix

The article considers the problem of machine learning of a wrist prosthesis control system with a non-invasive biosignal reading system. The task is solved within the framework of information-extreme intelligent data analysis technology, which is based on maximizing the system’s information producti...

Full description

Saved in:
Bibliographic Details
Main Authors: Suprunenko M. K., Zborshchyk O. P., Sokolov O.
Format: Article
Language:English
Published: Sumy State University 2022-12-01
Series:Журнал інженерних наук
Subjects:
Online Access:https://jes.sumdu.edu.ua/information-extreme-machine-learning-of-wrist-prosthesis-control-system-based-on-the-sparse-training-matrix/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849702640810721280
author Suprunenko M. K.
Zborshchyk O. P.
Sokolov O.
author_facet Suprunenko M. K.
Zborshchyk O. P.
Sokolov O.
author_sort Suprunenko M. K.
collection DOAJ
description The article considers the problem of machine learning of a wrist prosthesis control system with a non-invasive biosignal reading system. The task is solved within the framework of information-extreme intelligent data analysis technology, which is based on maximizing the system’s information productivity in machine learning. The idea of information-extreme machine learning of the control system for recognition of electromyographic biosignals, as in artificial neural networks, consists in adapting the input information description to the maximum total probability of making correct classification decisions. However, unlike neuro-like structures, the proposed method was developed within a functional approach to modeling the cognitive processes of the natural intelligence of forming and making classification decisions. As a result, the proposed method acquires the properties of adaptability to the intersection of classes in the space of recognition features and flexibility when retraining the system due to the recognition class alphabet expansion. In addition, the decision rules constructed within the framework of the geometric approach are practically invariant to the multidimensionality of the space of recognition features. The difference between the developed method and the well-known methods of information-extreme machine learning is the use of a sparse training matrix, which allows for reducing the degree of intersection of recognition classes significantly. The optimization parameter of the input information description, the training dataset, is the quantization level of electromyographic biosignals. As an optimization criterion is considered the modified Kullback information measure. The proposed machine learning algorithm results are shown in the example of recognition of six finger movements and wrist.
format Article
id doaj-art-18ee4ef35f1e42518317ae9031c9c7c5
institution DOAJ
issn 2312-2498
2414-9381
language English
publishDate 2022-12-01
publisher Sumy State University
record_format Article
series Журнал інженерних наук
spelling doaj-art-18ee4ef35f1e42518317ae9031c9c7c52025-08-20T03:17:35ZengSumy State UniversityЖурнал інженерних наук2312-24982414-93812022-12-0192E28E3510.21272/jes.2022.9(2).e4Information-extreme machine learning of wrist prosthesis control system based on the sparse training matrixSuprunenko M. K.0Zborshchyk O. P.1Sokolov O.2Sumy State University, 2, Rymskogo-Korsakova St., 40007 Sumy, UkraineSumy State University, 2, Rymskogo-Korsakova St., 40007 Sumy, UkraineNicolaus Copernicus University in Torun, 5, Grudziadzka St., 87-100 Torun, PolandThe article considers the problem of machine learning of a wrist prosthesis control system with a non-invasive biosignal reading system. The task is solved within the framework of information-extreme intelligent data analysis technology, which is based on maximizing the system’s information productivity in machine learning. The idea of information-extreme machine learning of the control system for recognition of electromyographic biosignals, as in artificial neural networks, consists in adapting the input information description to the maximum total probability of making correct classification decisions. However, unlike neuro-like structures, the proposed method was developed within a functional approach to modeling the cognitive processes of the natural intelligence of forming and making classification decisions. As a result, the proposed method acquires the properties of adaptability to the intersection of classes in the space of recognition features and flexibility when retraining the system due to the recognition class alphabet expansion. In addition, the decision rules constructed within the framework of the geometric approach are practically invariant to the multidimensionality of the space of recognition features. The difference between the developed method and the well-known methods of information-extreme machine learning is the use of a sparse training matrix, which allows for reducing the degree of intersection of recognition classes significantly. The optimization parameter of the input information description, the training dataset, is the quantization level of electromyographic biosignals. As an optimization criterion is considered the modified Kullback information measure. The proposed machine learning algorithm results are shown in the example of recognition of six finger movements and wrist.https://jes.sumdu.edu.ua/information-extreme-machine-learning-of-wrist-prosthesis-control-system-based-on-the-sparse-training-matrix/information-extreme intelligent technologymachine learningprocess innovationsparse training matrixprosthesis control systeminformation criterionelectromyographic sensorbiosignal
spellingShingle Suprunenko M. K.
Zborshchyk O. P.
Sokolov O.
Information-extreme machine learning of wrist prosthesis control system based on the sparse training matrix
Журнал інженерних наук
information-extreme intelligent technology
machine learning
process innovation
sparse training matrix
prosthesis control system
information criterion
electromyographic sensor
biosignal
title Information-extreme machine learning of wrist prosthesis control system based on the sparse training matrix
title_full Information-extreme machine learning of wrist prosthesis control system based on the sparse training matrix
title_fullStr Information-extreme machine learning of wrist prosthesis control system based on the sparse training matrix
title_full_unstemmed Information-extreme machine learning of wrist prosthesis control system based on the sparse training matrix
title_short Information-extreme machine learning of wrist prosthesis control system based on the sparse training matrix
title_sort information extreme machine learning of wrist prosthesis control system based on the sparse training matrix
topic information-extreme intelligent technology
machine learning
process innovation
sparse training matrix
prosthesis control system
information criterion
electromyographic sensor
biosignal
url https://jes.sumdu.edu.ua/information-extreme-machine-learning-of-wrist-prosthesis-control-system-based-on-the-sparse-training-matrix/
work_keys_str_mv AT suprunenkomk informationextrememachinelearningofwristprosthesiscontrolsystembasedonthesparsetrainingmatrix
AT zborshchykop informationextrememachinelearningofwristprosthesiscontrolsystembasedonthesparsetrainingmatrix
AT sokolovo informationextrememachinelearningofwristprosthesiscontrolsystembasedonthesparsetrainingmatrix