| | Study | Classification motions | Features selected | Classification methods | Accuracy |
| | Babita et al. [36] | Elbow flexion and extension | Wavelet packet transform | Linear SVM | 91.1% |
| | Yang et al. [37] | Fist turn downwards/upwards, Palm extension/enstrophe/ectropion/turn upwards/turn downwards, and clenching | Power spectral density | Genetic algorithm optimized SVM | 90.33% |
| | Sui et al. [38] | Elbow flexion/extension, wrist internal/external rotation, and fist clenching/unfolding | The energy and variance of the wavelet packet coefficients | Improved SVM | 90.66% |
| | Cai et al. [25] | Elbow flexion, and shoulder flexion/abduction/internal rotation/external rotation | RMS, VAR, WL, MAV, etc. | One-versus-one SVM | 94.18% |
| | Pan et al. [39] | Thumb/index/middle/ring/litter finger bending | Relative energy coefficient of wavelet packet | One-versus-one SVM | 97.78% |
| | Chen et al. [40] | Elbow flexion/extension and shoulder flexion/extension/adduction/abduction, | RMS | Two-step SVM | — |
| | Naik et al. [41] | Wrist flexion, ring-middle finger flexion, wrist flexion toward litter finger/thumb, finger and wrist flexion, finger and wrist flexion toward litter finger/thumb | RMS | Twin SVM | 84.83% |
| | Liu et al. [42] | Fist, open hand, radial/ulnar deviation, wrist flexion/extension, pronation, supination, fine pinch, key grip, ball/cylinder grasp | 6-order AR coefficients | Mixed LDA | 88.74% |
| | Dhindsa et al. [43] | Five classes of knee angle | IEMG, SSI, RMS, ZC, WL, WA, MNF, MF, PF, MP, SM1, 4 AR coefficients | LDA, NB, K-NN and SVM | 71.6% (LDA), 75.1% (NB), 87.9% (K-NN) and 92.2% (SVM) |
| | Pancholi et al. [33] | Soft/medium/hard gripping, wrist flexion/extension and hand open/close | IEMG, MAV, MMAV1, MMAV2, WAMP, RMS, WL, ZC, SSI, MNF, MDF, PKF, MFD, FMD, FMN and MFMD | LDA, K-NN, QDA, SVM, RT and RF | 75.38-99.54% |
| | Bian et al. [11] | Preform “shoot”/“rock”/“ok”/“yeah” gesture, twist a water bottle cap, turn a key, press an automatic pencil and press a nail clipper, | IEMG, SD, RMS, MPF and MF | LDA, RF, NB and SVM | 91.67% (LDA), 87.50% (RF), 86.83% (NB), and 92.25% (SVM) |
| | Alomari et al. [12] | Wrist flexion/extension, ulnar/radial deviation, grip, open hand, pinch and catch cylindrical subject. | Sample entropy, RMS, MYOP and DASDV | LDA, QDA and K-NN | 98.56% (LDA), 93.42% (QDA) and 94.25% (K-NN) |
| | Oleinikov et al. [27] | Different hand motions | MAV, DMAV, ZC, WL, PF, MPF, etc. | Three layers ANN | 91% |
| | Oweis et al. [44] | grasping, extension, flexion, ulna deviation and radial deviation | Seventeen time and time-series domain features | Three layers ANN | 96.7% |
| | Mane et al. [35] | Open palm, closed palm and wrist extension | Discrete wavelet transform | Three layers ANN | 93.25% |
| | Gandolla et al. [28] | Pinching, grasp an object and grasping. | — | Three layers ANN | 76% |
| | Ahsan et al. [29] | Different hand motions | MAV, RMS, VAR, SD, ZC, SSC and WL | Three layers ANN | 88.4% |
| | Shen et al. [21] | The phases of sit-to-stand motion | — | Three back-propagation neural networks | 93.48%. |
| | Park et al. [14] | Tip pinch grasp, prismatic four fingers grasp, power grasp, parallel extension grasp, lateral grasp and opening a bottle with a tripod grasp | — | Convolutional neural network | 90% |
| | Asai et al. [15] | Thumb open/close, fingers except thumb open/close | — | Convolutional neural network | 83% |
| | Bu et al. [45] | Flexion, extension, pronation, supination, grasping and opening | — | Five layers recurrent ANN | 88.4% |
| | Orjuela et al. [46] | Five wrist positions. | Discrete wavelet transform | Auto-encoder ANN | 73.41% |
|
|
