A Gesture Classification SoC for Rehabilitation With ADC-Less Mixed-Signal Feature Extraction and Training Capable Neural Network Classifier.
Yijie WeiQiankai CaoKofi OtseiduLevi J. HargroveJie GuPublished in: IEEE J. Solid State Circuits (2021)
Keyphrases
- feature extraction
- training process
- multi layer perceptron
- neural network
- learning vector quantization
- training set
- feature extraction and classification
- feature space
- training samples
- classification method
- pattern recognition
- extracted features
- feature selection
- support vector machine
- support vector machine svm
- pattern classification
- feature set
- classification algorithm
- svm classifier
- decision trees
- classification accuracy
- feature vectors
- support vector
- binary decision tree
- low power
- nearest neighbour
- artificial neural networks
- training examples
- training data
- fisher linear discriminant
- image classification
- sufficient training data
- training phase
- training patterns
- image processing
- class labels
- text classifiers
- feed forward neural networks
- mixed signal
- face recognition
- train a neural network
- discriminative classifiers
- probabilistic neural network
- supervised learning
- vlsi circuits
- knn
- hardware and software
- power consumption
- back propagation