On Tiny Feature Engineering: Towards an Embedded EMG-Based Hand Gesture Recognition Model

Keyphrases

• Hand Gesture Recognition 100%
• Feature Engineering 100%
• Superficial Electromyography 100%
• Recognition Model 100%
• Popular 50%
• Machine Learning Algorithms 50%
• Generation Method 50%
• Functional Impairment 50%
• Index Tests 50%
• Robotics 50%
• Random Forest 50%
• T-test 50%
• K-nearest 50%
• Energy Conservation 50%
• Hand Gesture 50%
• Machine Learning Models 50%
• Embedded Applications 50%
• Hand Function 50%
• Neuronal Network 50%
• Context Features 50%
• Electromyography Signal 50%
• Four States 50%
• Gestures Classifier 50%
• Upper Limb Movement 50%
• Computation Energy 50%
• Computational Constraints 50%
• Latency Constraint 50%
• Art Features 50%
• Gesture Recognition 50%
• Computational Latency 50%
• Feature Generation 50%
• Davies-Bouldin Index 50%
• Minimum Redundancy Maximum Relevance (mRMR) 50%

INIS

• engineering 100%
• hands 100%
• constraints 66%
• machine learning 66%
• forests 66%
• energy 33%
• information 33%
• implementation 33%
• signals 33%
• datasets 33%
• performance 33%
• randomness 33%
• applications 33%
• algorithms 33%
• neural networks 33%
• therapy 33%
• limbs 33%
• redundancy 33%

Computer Science

• Electromyography 100%
• hand gesture recognition 100%
• Machine Learning Algorithm 50%
• Random Decision Forest 50%
• Embedded Application 50%
• Machine Learning 50%
• Learning System 50%
• Embedded Hardware 50%
• Minimum Redundancy 50%
• Gesture Recognition 50%
• Feature Generation 50%