A Novel Multi-Stage Training Approach for Human Activity Recognition from Multimodal Wearable Sensor Data Using Deep Neural Network

Keyphrases

• 5-fold Cross Validation 50%
• CNN Features 50%
• Combined Training 50%
• Deep CNN Architecture 50%
• Feature Extractor 50%
• Multi-stage Training 100%
• Multimodal Wearable Sensor 100%
• Raw Sensor Data 50%
• Training Approaches 100%
• UCI HAR 50%
• Wearable Data 100%

Chemical Engineering

• Deep Neural Network 100%

Computer Science

• Outstanding Performance 33%