This paper deals with the automatic detection of Myotonia from a task based on the sudden opening of the hand. Data have been gathered from 44 subjects, divided into 17 controls and 27 myotonic patients, by measuring a 2-point articulation of each finger thanks to a calibrated sensory glove equipped with a Resistive Flex Sensor (RFS). RFS gloves are proven to be reliable in the analysis of motion for myotonic patients, which is a relevant task for the monitoring of the disease and subsequent treatment. With the focus on a healthy VS pathological comparison, customized features were extracted, and several classifications entailing motion data from single fingers, single articulations and aggregations were prepared. The pipeline employed a Correlation-based feature selector followed by a SVM classifier. Results prove that it’s possible to detect Myotonia, with aggregated data from four fingers and upper/lower articulations providing the most promising accuracies (91.1%).
Automatic detection of myotonia using a sensory glove with resistive flex sensors and machine learning techniques / Cesarini, V.; Costantini, G.; Amato, F.; Errico, V.; Pietrosanti, L.; Calado, A. L.; Massa, R.; Frezza, E.; Irrera, F.; Manoni, A.; Saggio, G.. - (2023), pp. 194-199. (Intervento presentato al convegno 6th IEEE International Workshop on Metrology for Industry 4.0 and IoT, MetroInd4.0 and IoT 2023 tenutosi a Brescia; Italy) [10.1109/MetroInd4.0IoT57462.2023.10180176].
Automatic detection of myotonia using a sensory glove with resistive flex sensors and machine learning techniques
Cesarini V.
;Pietrosanti L.;Irrera F.;
2023
Abstract
This paper deals with the automatic detection of Myotonia from a task based on the sudden opening of the hand. Data have been gathered from 44 subjects, divided into 17 controls and 27 myotonic patients, by measuring a 2-point articulation of each finger thanks to a calibrated sensory glove equipped with a Resistive Flex Sensor (RFS). RFS gloves are proven to be reliable in the analysis of motion for myotonic patients, which is a relevant task for the monitoring of the disease and subsequent treatment. With the focus on a healthy VS pathological comparison, customized features were extracted, and several classifications entailing motion data from single fingers, single articulations and aggregations were prepared. The pipeline employed a Correlation-based feature selector followed by a SVM classifier. Results prove that it’s possible to detect Myotonia, with aggregated data from four fingers and upper/lower articulations providing the most promising accuracies (91.1%).File | Dimensione | Formato | |
---|---|---|---|
Cesarini_Automatic Detection_2023.pdf
solo gestori archivio
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
510.61 kB
Formato
Adobe PDF
|
510.61 kB | Adobe PDF | Contatta l'autore |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.