Article Preview
Top1 Introduction
In recent years, hand gesture recognition has be-come a very active research theme because of its potential use in human- Computer interaction (HCI). Identification of hand gesture has numerous human computer interface (HCI) applications related to controlling machines and computers. Some of the commonly employed modalities include vision based systems, mechanical sensors, and the use of electromyogram, an indicator of muscle activity. Surface Electromyogram has an advantage of being easy to record, and is non-invasive. Surface Electromyogram (SEMG) is a result of the spatial and temporal integration of the motor unit action potential (MUAP) originating from different motor units. It can be recorded non-invasively and used for dynamic measurement of muscular function. It is typically the only in vivo functional examination of muscle activity used in the clinical environment. The analysis of EMG can be broadly categorized into two;
Hand movement is a result of complex combination of multiple muscles. While previous research have reported success in the use of multiple channels SEMG recording for the purpose, but the system is sensitive to the location of the electrodes and suitable for five discrete movements only (Rajesh & Kumar, 2009a). The cross-talk that exists due to multiple overlapping muscles in the forearm makes the system sensitive to the inter-subject variability and this problem is more significant when the muscle activation is relatively weak. To identify the movement and gesture of the hand more precisely, it is important to identify the muscle activity of each of the muscles responsible for the action. Similarity in the spectrum and other properties of the activity from the different muscles makes the separation of these difficult. There is a need to separate the muscle activity originating from different muscles. With little or no prior information of the muscle activity from the different muscles, this is a blind source separation (BSS) task.
Independent component analysis (ICA) is an iterative BSS technique that has been found to be very successful in audio and biosignal applications. ICA has been proposed for unsupervised cross talk removal from SEMG recordings of the muscles of the hand. Re- search that isolates MUAP originating from different muscles and motor units has been reported in 2004. A denoising method using ICA and high-pass filler banks has been used to suppress the interference of electrocardiogram (ECG) in EMG recorded from trunk muscles. Muscle activity originating from different muscles can be considered to be independent, and this gives an argument to the use of ICA for separation of muscle activity originating from the different muscles. This paper proposes the use of ICA (Greco, Costantino, Morabito, & Ver-Saci, 2003) for separation of muscle activity from the different muscles in the fore- arm to identify the hand action.
ICA is an iterative technique where the only approach is the model based approach that provides a well defined muscle activity pattern. The difficulty with this approach is the need for well defined location of the electrodes.