| Researchers | Classifier Used | Findings | Reported Accuracy |
| Tsenov et. al (2006) | Artificial Neural Network (ANN)- | Classification performance of hand and finger movements was said to be significantly dependent upon feature extraction, which is very important to considerably improve the accuracy of classification. The identification procedure was described based on EMG patterns of forearm activity using various Neural Networks models. | 98% using 4-channel data set |
| Eman et. al. (2008) | Back-Propagation (BP) based Neural Network | ANN architectures with three layers (input layer, hidden layer and output layer) were used. The ANN architectures are expressed as strings showing the number of inputs, the number of nodes in the hidden layers and two output nodes. | 90.91% for 80 hidden layers |
| Fukuda et. al. (1999) | Log-Linearized Gaussian Mixture Network (LLGMN) based Probabilistic Neural Network (PNN) | This system can adapt itself to changes of the EMG patterns according to the differences among individuals, different locations of the electrodes, time variation caused by fatigue or sweat, and so on. Processing speed needs to improve. | Higher discrimination performance can be achieved than other neural network |
| Jong-Sung Kim et. al. (2004) | Fuzzy Mean Max Neural Network (FMMNN) | Difference Absolute Mean Value (DAMV) extracted from the EMG signals is used as the input vectors in learning and classifying the patterns | 97% |
| Farid Mobasser et al. (2006). | Radial Basis Function Artificial Neural Network (RBFNN) | The proposed method uses Moving Window Least Squares (MWLS) to identify dynamic parameters for a limited number of operating points in a variable space defined by elbow joint angle and velocity, and the electromyogram signals collected from upper-arm muscles. The dynamic parameters for these limited points are then employed to train a Radial Basis Function Artificial Neural Network (RBFNN). | Estimation accuracy can be improved by changing neural network input quantization level and more sensors for each muscle |
| Wheeler (2003) | Hidden Markov Model (HMM) | Among the most common methods like Short Time Fourier Transform (STFT), Wavelets, Moving Average, Auto-Regression (AR) Coefficients, they found moving average is the best and simplest for feature space. During classifier training, HMM provides large computational savings compared to MLP. HMM also has inherent ability to deal with spurious misclassification | 87% using a 4-channel data set |
| Alsayegh (2000) | Bayes Network | K-Nearest Neighbour (k-NN) classifier added with Bayes to obtain good result. Feature selection is important for better classification and increasing number of features does not always produce good result | 94% only one EMG sensor |