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

Abstract

Human physical activity recognition from inertial sensors is shown to be a successful approach for monitoring elderly individuals and children in indoor and outdoor environments. As a result, researchers have shown significant interest in developing state-of-the-art machine learning methods capable of utilizing inertial sensor data and providing key decision support in different scenarios. This paper analyzes data-driven techniques for recognizing human daily living activities. Therefore, to improve the recognition and classification of human physical activities (for example, walking, drinking, and running), we introduced a model that integrates data preprocessing methods (such as denoising) along with major domain features (such as time, frequency, wavelet, and time–frequency features). Following that, stochastic gradient descent (SGD) is used to improve the performance of the extracted features. The selected features are catered to the random forest classifier to detect and monitor human physical activities. Additionally, the proposed HPAR system was evaluated on five benchmark datasets, namely the IM-WSHA, PAMAP-2, UCI HAR, MobiAct, and MOTIONSENSE databases. The experimental results show that the HPAR system outperformed the present state-of-the-art methods with recognition rates of 90.18%, 91.25%, 91.83%, 90.46%, and 92.16% from the IM-WSHA, PAMAP-2, UCI HAR, MobiAct, and MOTIONSENSE datasets, respectively. The proposed HPAR model has potential applications in healthcare, gaming, smart homes, security, and surveillance.

A Hybrid Human Activity Recognition Method Using an MLP Neural Network and Euler Angle Extraction Based on IMU Sensors

“…On several online human activity recognition datasets, they achieved a classification accuracy of 98.36%. Tahir [15] combined data preprocessing techniques with the primary domain features of human activities, such as time, frequency, wavelet, and time-frequency features. They employed a random forest classifier to monitor human body activities.…”

“…Subsequently, Euler angles are computed based on the sampled frequency-processing sequence data, with compensation provided through gyroscope and accelerometer data (lines [3][4][5][6][7][8][9][10][11][12]. Following this, the Euler angle vector is transformed into a rotation matrix, and from there into a quaternion and Rodrigues parameters (lines [13][14][15]. Finally, the ultimate pose angles are calculated and displayed (lines [16][17][18][19].…”

“…Transform Euler Angle vector to rotation matrix (14) Convert Euler Angle vector to quaternion (15) Convert quaternion to Rodrigues Parameters (16) Calculate Attitude Angle attitude (17) Convert radians to angles (18) end for (19) Output the final Attitude Angle attitude…”

Measurement of Functional Use in Upper Extremity Prosthetic Devices Using Wearable Sensors and Machine Learning

“…Recent results have shown that IMUs and machine learning classifiers are very effective in identifying activities in healthy controls [ 41 , 42 , 43 , 44 , 45 , 46 , 47 , 48 , 49 , 50 ]. The accuracies often rely on the number of IMUs used and their location, with the wrist, chest, ankle, and thigh commonly used.…”

“…The accuracies often rely on the number of IMUs used and their location, with the wrist, chest, ankle, and thigh commonly used. Accuracies higher than 90% are even possible from cell phone IMU data for detecting several classes of activities (i.e., walking, sitting, standing, jogging, upstairs, and downstairs) [ 46 ]. However, the detection of activities in patient populations is complicated by larger variability in movement patterns across the population.…”