Accuracy Comparison of CNN, LSTM, and Transformer for Activity Recognition Using IMU and Visual Markers.
María Fernanda Trujillo-GuerreroStadyn Román-NiemesMilagros Jaén-VargasAlfonso CadizRicardo FonsecaJosé Javier Serrano OlmedoPublished in: IEEE Access (2023)
Keyphrases
- high accuracy
- prediction accuracy
- error rate
- cellular neural networks
- classification accuracy
- visual features
- absolute position
- highly accurate
- visual information
- computational efficiency
- computational complexity
- object detection
- fuzzy logic
- recurrent neural networks
- genetic algorithm
- neural network
- confusion matrices
- real time