Identifying Electromyography Sensor Placement using Dense Neural Networks

Cappellari, Paolo; Gaunt, Robert A.; Beringer, Carl R.; Mansouri, Misagh; Novelli, Massimiliano

doi:10.5220/0006912501300141

Cited by 3 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…В [14] авторами разработана система идентификации мышц с помощью игольчатой ЭМГ для задач протезирования. Основными характеристикам этой модели являются следующие: использование игольчатой ЭМГ (16 датчиков) и кинематических перчаток, предобработка сигналов фильтрами нижних (10 Гц) и верхних (100 Гц) частот, использование искусственных нейронных сетей.…”

Section: анализ исследованийunclassified

Robust neural network filtering in the tasks of building intelligent interfaces

Vasiliev

Melnikov

Lesko

2023

Rossijskij tehnologičeskij žurnal

View full text Add to dashboard Cite

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

show abstract

Section: анализ исследованийunclassified

Robust neural network filtering in the tasks of building intelligent interfaces

Vasiliev

Melnikov

Lesko

2023

Rossijskij tehnologičeskij žurnal

View full text Add to dashboard Cite

show abstract

“…However, this control approach has critical dependencies on the correct identification of recorded commands (via electromyography, electroneurography or other methods) and estimation of unobserved commands -the activity of other muscles. The former is especially hard with amputees and is usually addressed by a physician and visual analysis of the recorded signals (Cappellari et al, 2018). The latter is sometimes addressed by employment of synergies within the controller, which supply the activity to the simulated muscles that are not recorded based on known correlations in the activity of the muscles in different tasks (Berger and d'Avella, 2014).…”

Section: Inverse Of Neuromechanical Controlmentioning

confidence: 99%

Description of motor control using inverse models

Sobinov¹

View full text Add to dashboard Cite

Description of motor control using inverse models Anton Sobinov Humans can perform complicated movements like writing or running without giving them much thought. The scientific understanding of principles guiding the generation of these movements is incomplete. How the nervous system ensures stability or compensates for injury and constraints-are among the unanswered questions today. Furthermore, only through movement can a human impose their will and interact with the world around them. Damage to a part of the motor control system can lower a person's quality of life. Understanding how the central nervous system (CNS) forms control signals and executes them helps with the construction of devices and rehabilitation techniques. This allows the user, at least in part, to bypass the damaged area or replace its function, thereby improving their quality of life. CNS forms motor commands, for example a locomotor velocity or another movement task. These commands are thought to be processed through an internal model of the body to produce patterns of motor unit activity. An example of one such network in the spinal cord is a central pattern generator (CPG) that controls the rhythmic activation of synergistic muscle groups for overground locomotion. The descending drive from the brainstem and sensory feedback pathways initiate and modify the activity of the CPG. The interactions between its inputs and internal dynamics are still under debate in experimental and modelling studies. Even more complex neuromechanical mechanisms are responsible for some non-periodic voluntary movements. Most of the complexity stems from internalization of the body musculoskeletal (MS) system, which is comprised of hundreds of joints and muscles wrapping around each other in a sophisticated manner. Understanding their control signals requires a deep understanding of their dynamics and principles, both of which remain open problems.

show abstract