deletions | additions       diff --git a/Aside_from_using_EMG_signals__.tex b/Aside_from_using_EMG_signals__.tex  index b62e4a0..d8af8dd 100644  --- a/Aside_from_using_EMG_signals__.tex  +++ b/Aside_from_using_EMG_signals__.tex 
...
In a study conducted by Yoshikawa et al. \cite{Yoshikawa_2006}, a real-time hand motion estimation was conducted by using EMG signals with SVMs. The study involved an experiment wherein a subject was required to perform seven hand motions sequentially for 10 sessions. High accuracy is maintained through nine of the sessions, one exhibiting a performance of 94.17\% accuracy.  As stated in a study by Han et al. \cite{Han_Pang_Huang}, two issues exist concerning the classification of EMG signals. One of these is selecting a feature subset with the best discrimination ability, which they were able to solve by using a supervised feature mining (SFM) method, which is an intelligent approach based on genetic algorithms, fuzzy measure, and domain knowledge on pattern recognition. Experimental results shown in their paper exhibit that the optimal EMG feature subset obtained from SFM can obtain higher classification rates compared with using all feature candidates by K-NN method. The second issue on classification of EMG signal mentioned in the study is the design of the classifier. A summary of techniques used in EMG classification can be viewed in Table 2.2. These methodologies and algorithms techniques  are further discussed on a review paper conducted  by Ahsan et al. \cite{ahsan2009emg}.