Abstract
Activity recognition is one of the most active areas of research in ubiquitous computing. In particular, gait activity recognition is useful to identify various risk factors in people’s health that are directly related to their physical activity. One of the issues in activity recognition, and gait in particular, is that often datasets are unbalanced (i.e., the distribution of classes is not uniform), and due to this disparity, the models tend to categorize into the class with more instances. In the present study, two methods for classifying gait activities using accelerometer and gyroscope data from a large-scale public dataset were evaluated and compared. The gait activities in this dataset are: (i) going down an incline, (ii) going up an incline, (iii) walking on level ground, (iv) going down stairs, and (v) going up stairs. The proposed methods are based on conventional (shallow) and deep learning techniques. In addition, data were evaluated from three data treatments: original unbalanced data, sampled data, and augmented data. The latter was based on the generation of synthetic data according to segmented gait data. The best results were obtained with classifiers built with augmented data, with F-measure results of 0.812 ( = 0.078) for the shallow learning approach, and of 0.927 ( = 0.033) for the deep learning approach. In addition, the data augmentation strategy proposed to deal with the unbalanced problem resulted in increased classification performance using both techniques.
Highlights
Activity recognition is one of the most active areas of research in ubiquitous computing with applications in behavior change, risk prediction and early diagnosis [1]
Human activity recognition using data from inertial sensors is commonly carried out through a process that begins with data acquisition and ends with the classification
In order to evaluate the gait classifiers based on statistical features, detailed in Section 3.3.1, feature vectors were divided in two levels: (i) type of sensor; and (ii) type of signal
Summary
Activity recognition is one of the most active areas of research in ubiquitous computing with applications in behavior change, risk prediction and early diagnosis [1]. Most of the works on activity recognition have started investigating from a general outlook, i.e., they focus on classifying activities that are very different from each other, such as walking vs drinking coffee, instead of a particular, such as walking vs running [3]. Due to the granularity of each type of activity, it is necessary to study each of them separately, e.g., gait activities, sleep phases, sedentary activities etc. Gait activities are directly related to people’s ambulation, deriving the classification: (i) by the speed with which people move, e.g., walking, jogging, running; or (ii) by the surface on which people move, e.g., walking on flat surfaces, walking on stairs, or walking on inclines. According to the type of Sensors 2020, 20, 4756; doi:10.3390/s20174756 www.mdpi.com/journal/sensors
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
