Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Afyon Kocatepe Ünive...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
versions View all 2 versions
addClaim

Emg işaretleri ile kontrol edilen robot kol tasarımı

Authors: Aboodi, Sura Ali Kodi;

Emg işaretleri ile kontrol edilen robot kol tasarımı

Abstract

Özellikle yaşadığımız coğrafyaların bir kaderi olan savaş ve çeşitli yaralanmalar sonucu ampute bir hayat sürmek zorunda kalan engelli bireylerin yaşam koşullarını iyileştirmek adına akıllı protezlerin geliştirilmesi hayati bir önem arzetmekdir. Çeşitli nedenlerle uzuvlarını kaybeden bireyler için farklı protez tasarımları mevcuttur. Fakat mümkün olduğu durumlarda bireyin kolundan alınan EMG işaretlerinin analizi sonucu akıllı prototiplerin elektronik olarak hareket ettirilmesi teknolojik anlamda mümkün hale gelmiştir. Bu çalışmanın amacı ise, 3D yazıcı yardımıyla üretilen robotik kolu kontrol etmek ve EMG sinyallerine dayalı olarak insan kol hareketlerini öğrenmektir. Günlük yaşamda uygulanabilir yedi el hareketini ayırt edebilmek için Myo Armband tarafından beş sağlıklı denekten EMG sinyalleri elde edilmiştir. Örüntü tanıma sistemi, hareketler ile eşleştirilen sinyalleri üç aşamada (bölümleme, özellik çıkarma ve sınıflandırma) analiz etmek ve işlemek için kullanılmıştır. EMG sinyalleri girişim tekniği ile bölümlere ayrılmıştır. Zaman domeninde TD-PSD yöntemi ile altı özellik çıkarılmıştır. Sistemin optimum doğruluğunu bulmak ve aralarında karşılaştırma yapabilmek için LDA ve SVM sınıflandırıcıları tercih edilmiştir. Prototip bir robotik kolun gerçek zamanlı olarak çalışabileceği şekilde kontrol edilmesi için en iyi parametreler ve özellikler seçilerek gerekli kabul edilebilir sınıflandırma başarısı hedeflenmiştir. LDA (93.43%) ve SVM (92.30%) sınıflandırıcı algoritmaları birbirlerine yakın bir sınıflandırma başarısı göstermiştir. Sonuç itibarıyla deneklerden alınan EMG işaretleri başarı ile sınıflandırılarak yedi farklı el hareketinin EMG işaretleri tespit edilmiştir. Devamında prototip el tarafından yapılması mümkün olan dört farklı el hareketi deneklerden kablosuz yöntemlerle alınan EMG işaretleri analiz edilerek eş zamanlı bir şekilde başarı ile protez kol tarafından gerçekleştirilmiştir.

The development of smart prostheses is of vital importance, especially in order to improve the living conditions of disabled individuals who have to lead an amputated life as a result of war and various injuries, which are the fate of the geographies we live in. Different prosthesis designs are available for individuals who have lost their limbs for various reasons. However, as a result of the analysis of EMG signals taken from the arm of the individual, it has become technologically possible to move smart prototypes electronically. The aim of this study is to control the robotic prosthetic arm produced with the help of 3D printer and to learn human arm movements based on EMG signals. EMG signals were obtained from five healthy subjects by Myo Armband in order to distinguish the seven hand movements applicable in daily life. The pattern recognition system was used to analyze and process signals paired with movements in three stages (segmentation, feature extraction and classification). EMG signals are segmented by interference technique. Six features were extracted with the TD-PSD method in the time domain. LDA and SVM classifiers were preferred in order to find the optimum accuracy of the system and to make comparisons between them. In order to control a prototype robotic arm in such a way that it can operate in real time, the best parameters and features are selected and the required acceptable classification success is aimed. LDA (93.43%) and SVM (92.30%) classifier algorithms showed close classification success to each other. As a result, seven different hand movements were determined by successfully classifying the EMG signals obtained from the subjects. Afterwards, the four different hand movements that can be made by the prototype hand were analyzed by the EMG signals obtained from the subjects by wireless methods, and were successfully performed by the prosthetic arm simultaneously.

Country
Turkey
Keywords

Myo armband, EMG, Emg, Robotik kol, LDA, Lda, SVM, Svm, Myo Armband, Robotik Kol

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Green