EMG Signal Processing of Myo Armband Sensor for Prosthetic Hand Input using RMS and ANFIS

Arozi, Moh.; Ariyanto, Mochammad; Kristianto, Asa; Munadi, Munadi; Setiawan, Joga Dharma

doi:10.1109/icitacee50144.2020.9239169

Cited by 7 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The motion data consists of 8 channels of EMG data along with IMU data that contains unit quaternions, Euler angles for pitch, yaw, roll and 3-axis accelerometer, 3-axis gyroscope adding up to a total of 21 input signals for each recording. For each of the input signals, five time-domain features were captured [16][17][18][19][20]. These include: Mean Absolute Value (MAV), Root Mean Square (RMS), Waveform Length (WL), Zero Crossing (ZC) and Slope Sign Change (SSC) [16].…”

Section: ) Motion Feature Extractionmentioning

confidence: 99%

Ensemble of Multimodal Deep Learning Models for Violin Bowing Techniques Classification

Muhammed,

Karunakaran,

Bhat

et al. 2024

JAIT

View full text Add to dashboard Cite

Bowing gesture while playing violin refers to the motion of the violinist's arm. Violinists use different types of bow strokes to express musical phrases, played by the movement of the right arm holding the fiddle bow. Although the sound produced by each bow stroke is distinct, it can be difficult for new fiddlers to distinguish and recognize these bowing techniques. So, this paper presents a novel approach of an ensemble of multimodal deep learning models consisting of one Convolution Neural Network (CNN) and two Long Short-Term Memory (LSTM) models to classify into one of the five bowing classes: detaché , legato, martelé , spiccato and staccato. The dataset used consists of audio samples performed by 8 violinists along with the motion of their forearms measured using a Myo sensor device, to acquire 8-channels of Electromyogram (EMG) data and 13-channels of Inertial Measurement Unit (IMU) data. The audio features are extracted from audio excerpts and time domain features are extracted from EMG and IMU motion signals. These features are passed into an ensemble of deep learning models to make the final prediction using weighted voting. The proposed ensemble classifier was able to deliver optimal results with an overall accuracy of 99.5%, which is better than the previous studies that took only either audio or motion data into consideration.

show abstract

Section: ) Motion Feature Extractionmentioning

confidence: 99%

Ensemble of Multimodal Deep Learning Models for Violin Bowing Techniques Classification

Muhammed,

Karunakaran,

Bhat

et al. 2024

JAIT

View full text Add to dashboard Cite

show abstract

“…EMG sinyallerinden çıkartılan 16 öznitelik temel bileşen analizi (principal component analysis/PCA) kullanarak üçe indirgemiş ve sınıflandırma ortalama doğruluğunu %72 olarak elde etmiştir. Çalışma [6] ise proteze girdi sağlamak için sensörlerden elde edilen EMG sinyalinin işlenmesi ve örüntü tanımada kullanılması ile ilgili bir sistem önermişlerdir. Sinyallerden çıkartılan bir özniteliğe ait değerler ANFIS'te sınıflandırılmasıyla %98,09 doğruluk elde edilmiştir.…”

Section: Literatür öZeti (Literature Review)unclassified

“…Hareketi destekleme konusunda insan hayatını kolaylaştırmak için birçok sistem geliştirilmiştir ve bu alanda çoğunlukla EMG tabanlı miyoelektrik cihazlar kullanılmaktadır. Örneğin, sanal gerçeklik sistemleri, el protezleri ve dış iskeletler EMG kontrollü sistemlere birer örnektir [6][7][8]. Bahsedilen bu ve benzeri sistemlerde kontrol yaklaşımlarında kullanılan EMG sinyalleri, hareketin belirlenmesinde büyük fayda sağlasa da doğrusal ve durağan olmayan yapıları nedeniyle sinyallerin analizi çeşitli zorlukları beraberinde getirir [8,9].…”

Section: Giriş (Introduction)unclassified

A decision-making mechanism based on EMG signals and adaptive neural fuzzy inference system (ANFIS) for hand gesture prediction

Kisa

Özdemir

Güren

et al. 2023

Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi

View full text Add to dashboard Cite

Üst ekstremite hareketi tam olarak sağlanamadığında, yapay zeka (artificial intelligence/AI) tabanlı sistemler hareketi destekleme ve kullanıcılara amaçlanan hareketin uygulanması konusunda yardımcı olurlar. AI tabanlı sistemlerde kontrolü sağlamak hareketlerin otomatik tahminini gerektirir. Kas elektriksel aktivitesinin temsili olan elektromiyografi (EMG), sanal gerçeklik uygulamaları ve protez kontrolleri gibi AI tabanlı sistemlerle kullanıldığında çeşitli faydalar sağlar. Bu çalışmada, bahsedilen sistemlere etkin kontrol sunmak ve tahmin performanslarını iyileştirmek amacıyla bulanık mantık (Fuzzy Logic/FL) tabanlı bir karar verme mekanizması sunulmuştur. Bu bağlamda, 30 katılımcıdan yedi farklı el hareketini taklit etmesi sonucunda oluşan EMG sinyalleri toplanmıştır. Gerekli ön işleme ve bölütleme işlemlerinin ardından elde edilen sinyallere Hilbert-Huang Dönüşümünün (HHD) ilk aşaması Görgül Kip Ayrışımı (GKA) metodu uygulandı ve İçsel Mod Fonksiyonları (İMF) elde edildi. İstatistiksel İMF seçim yöntemi ile belirlenen İMF’lere HHD uygulanmasıyla iyi çözünürlüklü zaman-frekans (time-frequency/TF) imgeleri elde edildi. Zaman ve frekans uzayının ortak temsiline dayalı görselleştirilmiş TF imgelerinden çeşitli ayırt edici öznitelikler çıkarıldı. İki farklı kümeleme tekniği uygulanan öznitelik veri seti, Uyarlamalı Sinirsel Bulanık Çıkarım Sistemi'ne (ANFIS) girdi olarak verildi. Yedi el hareketi sınıflandırması için Azaltımlı (Subtractive Clustering/SC) ve Bulanık C-ortalama (Fuzzy C-mean/FCM) kümeleme yöntemleri için ortalama doğruluk değerleri sırasıyla %93,88 ve %92,10 olarak elde edilmiştir. TF temsiline dayalı özniteliklerin FL yaklaşımlarıyla sınıflandırılması sonucu elde edilen bulgular, EMG gibi durağan ve doğrusal olmayan biyolojik sinyallerin sınıflandırılması için umut verici olduğunu göstermiştir.

show abstract

“…This is due to the fact that the sEMG signal is weak and can present a lot of artifacts (Konrad, 2005;Reaz et al, 2006), the analysis of sEMG requires appropriate preprocessing, which includes proper filtering and artifact removal methods (Qiu et al, 2015;Yeon, Herr, 2021;Boyer et al, 2023). The sEMG signal is usually smoothed by a method based on the root mean square (RMS) calculation (Burden et al, 2014;Arabadzhiev et al, 2010;Gupta et al, 2017;Rose, 2014;Karabulut et al, 2017;Arozi et al, 2020;Josephson, Knight, 2019). RMS reflects the mean power of the signal .…”

Section: Surface Emg Processing Pipelinementioning

confidence: 99%

Untitled

2023

SPSUTOM

View full text Add to dashboard Cite

Artificial intelligence (AI) can be applied in various areas of crisis management. It can provide numerous benefits concerning speed, effectiveness and precision of actions. AI accelerates the process of massive amounts of data processing, such as sensor data, satellite images, social data streams and much more. This enables to make quick analysis of a situation and make quick decisions in order to monitor various sources of information in real-time and detect early signals of a crisis. Advanced algorithms can identify patterns and anomalies enabling a quick response. AI can be used to model various crisis scenarios based on available historical and current data. This way it is possible to predict the probable effects of a given crisis and prepare for various situations. AI can analyze social media data to monitor community sentiments, identify potential threats and manage crisis communication. Automatic sentiment analysis systems can help understand society's response to a crisis. Advanced AI systems can be used to predict human behavior in various crisis scenarios. This allows to understand better how people may react and what their needs are in a given time. AI can help detect and combat cyber attacks, which constitute a serious threat, especially when it is necessary to maintain critical infrastructures. Integrating AI into crisis management requires caution because decisions made by AI systems should be consistent with ethical standards and they must consider the human supervision and assessment of the crisis situation. Design/methodology/approach: The paper analyzes the AI methods applied during crises. The results of interviews conducted with students, teachers and authors' personal experiences are provided. Findings: AI is a new way of solving problems, especially during crises. The new technologies determine the way and the speed of problems solving. Originality/value: Originality based on the interviews and post-crisis (COVID) points of view are the value.

show abstract

EMG Signal Processing of Myo Armband Sensor for Prosthetic Hand Input using RMS and ANFIS

Cited by 7 publications

References 9 publications

Ensemble of Multimodal Deep Learning Models for Violin Bowing Techniques Classification

Ensemble of Multimodal Deep Learning Models for Violin Bowing Techniques Classification

A decision-making mechanism based on EMG signals and adaptive neural fuzzy inference system (ANFIS) for hand gesture prediction

Untitled

Contact Info

Product

Resources

About