Human Activity Recognition System For Moderate Performance Microcontroller Using Accelerometer Data And Random Forest Algorithm

There has been increasing interest in the application of artificial intelligence technologies to improve quality support services healthcare. Some constraints, such as space, infrastructure, and environmental conditions, present challenges with assistive devices for humans. This paper proposed a wearable-based real-time human activity recognition system monitor daily activities. The classification was done directly on device, results could be checked over internet. accelerometer data collection developed device sampling frequency 20Hz, random forest algorithm embedded hardware. To accuracy system, feature vector 31 dimensions calculated used an input per time window. Besides, dynamic window method applied by model allowed us change (1-3 seconds) increase performance classification. experiment showed that classify 13 activities high 99.4%. rate correctly classified 96.1%. work is promising healthcare because convenience simplicity wearables.