Classifying Motion Intention from EMG signal: A k-NN Approach

Khairuddin, Ismail Mohd; Sidek, Shahrul Na’im; Majeed, Anwar P. P. Abdul; Puzi, Asmarani Ahmad

doi:10.1109/icom47790.2019.8952042

Cited by 13 publications

(8 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Next, the signals will undergo a feature extraction process to get better precision and accuracy. In this part, features such as mean absolute value (MAV), variance (VAR), standard deviation (STD), and root-mean-square (RMS) were extracted from the filtered signal to be classified accordingly [6]. For each feature, there will be three separations for the x, y and z-axis.…”

Section: Features Extractionmentioning

confidence: 99%

The Classification of Elbow Extension and Flexion: A feature selection investigation

et al. 2020

View full text Add to dashboard Cite

Nowadays, the worldwide primary reasons of long-term disability is stroke. When the blood supply to your brain is interupted and reduced, stroke occurs as it depriving brain tissue of nutrients and oxygen. In the modern world, advanced technology are revolutionizing the rehabilitation process. This research uses mechanomyography (MMG) and machine learning models to classify the elbow movement, extension and flexion of the elbow joint. The study will aid in the control of an exoskeleton for stroke patient's rehabilitation process in future studies. Five volunteers (21 to 23 years old) were recruited in Universiti Malaysia Pahang (UMP) to execute the right elbow movement of extension and flexion. The movements are repeated five times each for two active muscles for the extension and flexion motion, namely triceps and biceps. From the time domain based MMG signals, twenty-four features were extracted from the MMG before being classified by the machine learning model, namely k-Nearest Neighbors (k-NN). The k-NN has achieved the classification accuracy (CA) with 88.6% as the significant features are identified through the information gain approach. It may well be stated that the suggested process was able to classify the elbow movement well

show abstract

Section: Features Extractionmentioning

confidence: 99%

The Classification of Elbow Extension and Flexion: A feature selection investigation

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Regarding signal processing algorithms that recognize signals generated from complex structures in the human body, methods showing excellent performance in nonlinear and nonspecific data processing, such as fuzzy logic and neural network theory, are being extensively used [ 11 , 12 , 13 , 30 , 42 , 43 , 44 , 45 ]. Additionally, prior studies have combined fuzzy logic and neural network theory to complement each other [ 46 , 47 , 48 ].…”

Section: Introductionmentioning

confidence: 99%

Wearable Sensor for Forearm Motion Detection Using a Carbon-Based Conductive Layer-Polymer Composite Film

Park¹

2022

Sensors

View full text Add to dashboard Cite

In this study, we developed a fabrication method for a bracelet-type wearable sensor to detect four motions of the forearm by using a carbon-based conductive layer-polymer composite film. The integral material used for the composite film is a polyethylene terephthalate polymer film with a conductive layer composed of a carbon paste. It is capable of detecting the resistance variations corresponding to the flexion changes of the surface of the body due to muscle contraction and relaxation. To effectively detect the surface resistance variations of the film, a small sensor module composed of mechanical parts mounted on the film was designed and fabricated. A subject wore the bracelet sensor, consisting of three such sensor modules, on their forearm. The surface resistance of the film varied corresponding to the flexion change of the contact area between the forearm and the sensor modules. The surface resistance variations of the film were converted to voltage signals and used for motion detection. The results demonstrate that the thin bracelet-type wearable sensor, which is comfortable to wear and easily applicable, successfully detected each motion with high accuracy.

show abstract

“…The selection of an appropriate classification algorithm can also increase the accuracies of diagnostic processes. As classification methods, statistical methods [13], artificial neural networks (ANN) [1], fuzzy approaches (FL) [14], Bayesian techniques [15,16], k-nearest neighbor (k-NN) [17], linear discrimination analysis (LDA) [18] and support vector machines (SVM) have been used [15,19]. In addition to these methods, the convolutional neural network algorithm (CNN) has been also applied in EMG signal classification [20,21].…”

Section: Introductionmentioning

confidence: 99%

A New Feature Extraction Method for EMG Signals

Sevim¹

2022

View full text Add to dashboard Cite

Surface Electromyography (sEMG) is an important tool for gesture recognition. Features and classification methods have to be carefully selected to be successful in the recognition of electromyografic signals. In most of the sEMG studies, time and frequency domain features have been extracted and classified with a single classifier. But neither one feature nor one classifier alone has achieved high classification accuracies. Using a feature and classifier combination would be a solution for this problem, and increase the accuracies. As a contribution to this field, a new time domain EMG feature is suggested and its classification performance is examined for feature and classifier combinations in this study. According to the results of this study, the new feature has high classification accuracy, and when it is used with AR and ST features, the average of the classification accuracy reaches 99.57% for multiple SVM classifier. Besides, the new feature+AR+ ST feature combination shows high classification accuracy for single classifier, and this eliminates the need for multiple classifiers.

show abstract

Classifying Motion Intention from EMG signal: A k-NN Approach

Cited by 13 publications

References 14 publications

The Classification of Elbow Extension and Flexion: A feature selection investigation

The Classification of Elbow Extension and Flexion: A feature selection investigation

Wearable Sensor for Forearm Motion Detection Using a Carbon-Based Conductive Layer-Polymer Composite Film

A New Feature Extraction Method for EMG Signals

Contact Info

Product

Resources

About