22,99 €
inkl. MwSt.
Versandfertig in 6-10 Tagen
11 °P sammeln
Andere Kunden interessierten sich auch für
![MEMS Sensors for Measuring Gait Parameters]( "MEMS Sensors for Measuring Gait Parameters")
MEMS Sensors for Measuring Gait Parameters32,99 €![ANN Based Lung Cancer Classification using Chest Radiographs]( "ANN Based Lung Cancer Classification using Chest Radiographs")
ANN Based Lung Cancer Classification using Chest Radiographs53,99 €![Evaluation of Techniques for the Decomposition of EMG Signals]( "Evaluation of Techniques for the Decomposition of EMG Signals")
Evaluation of Techniques for the Decomposition of EMG Signals26,99 €![Hybrid Approach for Shot Boundary Detection Based on Machine Learning]( "Hybrid Approach for Shot Boundary Detection Based on Machine Learning")
Hybrid Approach for Shot Boundary Detection Based on Machine Learning59,99 €![On the Design of a Highly Linear CMOS Programmable Transconductor]( "On the Design of a Highly Linear CMOS Programmable Transconductor")
On the Design of a Highly Linear CMOS Programmable Transconductor36,99 €![Person Identification System using Handwritten signatures by ANN]( "Person Identification System using Handwritten signatures by ANN")
Person Identification System using Handwritten signatures by ANN26,99 €![Number Plate Recognition Using an Improved Segmentation]( "Number Plate Recognition Using an Improved Segmentation")
Number Plate Recognition Using an Improved Segmentation36,99 €
Exposure to physical therapy in rehabilitation shows a major interest in recent years for foot drop prevention by using ankle foot devices (AFO). In classifying the stance and swing phases, electromyography (EMG) signals were used to assist in utilising the AFO. Even though this approach has successfully controlled the actuator, classification model of EMG signals during stance and swing phases have not yet been discovered. Thus, a model to classify the stance and swing phases of EMG signals was proposed in this study. A model was developed by extracting the features using time domain (TD) and feeding it into artificial neural network (ANN) classifier. It was observed that Levenberg-Marquardt training algorithm of ANN with five TD features performed better than other features with an average percentage of classification accuracy of 87.4%. The outcome of this study could enhance the development of AFO and implementations in real time application were suggested for future applications.