Human Activities and Postures Recognition: From Inertial Measurements to Quaternion-Based Approaches

Abstract

This paper presents two approaches to assess the effect of the number of inertial sensors and their location placements on recognition of human postures and activities. Inertial and Magnetic Measurement Units (IMMUs)—which consist of a triad of three-axis accelerometer, three-axis gyroscope, and three-axis magnetometer sensors—are used in this work. Five IMMUs are initially used and attached to different body segments. Placements of up to three IMMUs are then considered: back, left foot, and left thigh. The subspace k-nearest neighbors (KNN) classifier is used to achieve the supervised learning process and the recognition task. In a first approach, we feed raw data from three-axis accelerometer and three-axis gyroscope into the classifier without any filtering or pre-processing, unlike what is usually reported in the state-of-the-art where statistical features were computed instead. Results show the efficiency of this method for the recognition of the studied activities and postures. With the proposed algorithm, more than 80% of the activities and postures are correctly classified using one IMMU, placed on the lower back, left thigh, or left foot location, and more than 90% when combining all three placements. In a second approach, we extract attitude, in term of quaternion, from IMMUs in order to more precisely achieve the recognition process. The obtained accuracy results are compared to those obtained when only raw data is exploited. Results show that the use of attitude significantly improves the performance of the classifier, especially for certain specific activities. In that case, it was further shown that using a smaller number of features, with quaternion, in the recognition process leads to a lower computation time and better accuracy.

The Importance of Respiratory Rate Monitoring: From Healthcare to Sport and Exercise

“…This problem can be partly overcome with the simultaneous measurement of other physiological and mechanical variables. For instance, it is important to characterize the postures and activities of the user, as commonly performed with the use of inertial sensors [299]. This is particularly relevant for monitoring dyspnea and physical effort during everyday life activities and exercise [27], but is also important for the identification of suitable portions of the respiratory signal (e.g., with no movements or artifacts) to compute resting f R [133].…”

D-SORM: A digital solution for remote monitoring based on the attitude of wearable devices

“…On the one hand, the recognition could be done by extracting handcrafted time-domain and frequency-domain features from raw signals, to feed classifiers like k-Nearest Neighbors (KNN), Random Forest (RF), and Deep Neural Network (DNN) [22,30,36]. Moreover, Random Subspace (RS) technique has been proposed to process Quaternions and Euler angles [37]. On the other hand, deep learning techniques like Convolutional Neural Networks (CNN) [9,12], and recurrent networks like Long Short-Term Memory (LSTM) [24,21] have been also proposed.…”

Machine Learning Methodology in a System Applying the Adaptive Strategy for Teaching Human Motions

“…The automatic assignment of an unknown signal (signals are also called objects) to individual classes can be assessed using a predefined metric function. This technique is utilized in the Nearest Neighbor (NN) method and its modifications (e.g., k-Nearest Neighbor (kNN); see Section 2.3) [28][29][30][31]. Motion signals can also be classified using methods in which the probability that an object belongs to a particular class is estimated (e.g., Bayesian classifier [27,28]).…”

“…Thus, the components of acceleration formed a vector, a = [a x a y a z ] T , which, after applying integration operations, could be utilized to calculate speed and position signals. The rotation was sent by means of the four values creating the quaternion [31,41]. This represents the rotation of the sensor in relation to its fixed, initial orientation.…”