Gait Pattern Recognition Using Accelerometers
This work addresses biometric identification for security or health monitoring, but it is incremental as it applies standard methods to a specific dataset.
The study tackled gait pattern recognition for human identity using accelerometer data from chest and ankle sensors, achieving 99.4% accuracy with a Decision Tree classifier and 100% accuracy with K-Nearest Neighbors.
Motion ability is one of the most important human properties, including gait as a basis of human transitional movement. Gait, as a biometric for recognizing human identities, can be non-intrusively captured signals using wearable or portable smart devices. In this study gait patterns is collected using a wireless platform of two sensors located at chest and right ankle of the subjects. Then the raw data has undergone some preprocessing methods and segmented into 5 seconds windows. Some time and frequency domain features is extracted and the performance evaluated by 5 different classifiers. Decision Tree (with all features) and K-Nearest Neighbors (with 10 selected features) classifiers reached 99.4% and 100% respectively.