Stochastic Recognition of Human Physical Activities via Augmented Feature Descriptors and Random Forest Model

Keyphrases

• Random Forest Regression 100%
• Human Physical Activity 100%
• Augmented Features 100%
• Feature Descriptor 100%
• Inertial Sensors 66%
• Time-frequency 66%
• UCI HAR 66%
• Benchmark Dataset 33%
• Recognition Rate 33%
• Wavelet 33%
• Developing States 33%
• State-of-the-art Techniques 33%
• Smart Surveillance 33%
• Random Forest Classifier 33%
• Indoor Environment 33%
• Sensor Data 33%
• Elderly People 33%
• Selected Features 33%
• Activities of Daily Living 33%
• Applications in Healthcare Systems 33%
• Stochastic Gradient Descent 33%
• Human Physical Activity Recognition 33%
• Machine Learning Techniques 33%
• Smart Home Security 33%
• Outdoor Environment 33%
• Data-driven Methods 33%
• Decision Support 33%
• Denoising 33%
• Data Preprocessing Technique 33%
• Home Surveillance 33%
• Domain-specific Features 33%

Computer Science

• Human Activity Recognition 100%
• Random Decision Forest 100%
• feature descriptor 100%
• Machine Learning 50%
• Integrate Data 50%
• Random Forest Classifier 50%
• Activity Recognition 50%
• Decision Support System 50%
• Gradient Descent 50%
• Learning System 50%
• Data Preprocessing 50%
• de-noising 50%
• Elderly Individual 50%
• Experimental Result 50%
• Potential Application 50%
• Recognition Rate 50%
• Extracted Feature 50%
• Domain Feature 50%
• Developing State 50%