Machine Learning Methods for Classifying Human Physical Activity from On-Body Accelerometers

By Andrea Mannini, Angelo Maria Sabatini. Italian National Conference on Sensors, 2010

792 citations recorded by the source corpus.

The use of on-body wearable sensors is widespread in several academic and industrial domains. Of great interest are their applications in ambulatory monitoring and pervasive computing systems; here, some quantitative analysis of human motion and its automatic classification are the main computational tasks to be pursued. In this paper, we discuss how human physical activity can be classified using on-body accelerometers, with a major emphasis devoted to the computational algorithms employed for this purpose. In particular, we motivate our current interest for classifiers based on Hidden Markov Models (HMMs). An example is illustrated and discussed by analysing a dataset of accelerometer time series.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/3ccf5c97d89f0f5d6eb40c8feb2bcd387223e9c0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Computer Vision and Pattern Recognition

In Signal Processing

Citations in the corpus

Activity recognition using cell phone accelerometers (2011, background): “Mannini and Sabitini [ 23 ] used five tri-axial accelerometers attached to the hip, wrist, arm, ankle, and thigh in order to recognize twenty activities from thirteen users.”
Context-Aware Computing, Learning, and Big Data in Internet of Things: A Survey (2018, methodology): “Mannini and Sabatini [168] used HMM for human physical activity reasoning in their studies.”
Gait Partitioning Methods: A Systematic Review (2016, methodology): “Mannini et al. in three studies [15,38,95] applied the HMM to the sagittal angular velocity of the foot in order to identify four gait phases.”
Data Mining for Wearable Sensors in Health Monitoring Systems: A Review of Recent Trends and Challenges (2013, background): “following studies [13–16] have provided the recent reviews on the topic of human activity monitoring.”
Physical Human Activity Recognition Using Wearable Sensors (2015, methodology): “As for the use of the K-means for human activity recognition, the reader can refer to [74,75].”
A robust human activity recognition system using smartphone sensors and deep learning (2018, background): “3 Thus, regarding different sensors in activity recognition, the accelerometer is the most commonly utilized sensor for focusing on human body motion [8].”
Estimating Three-Dimensional Orientation of Human Body Parts by Inertial/Magnetic Sensing (2011, background): “, walking, hand weaving, head shaking, and so forth, while the low-frequency component of the acceleration signal, aka the zero-frequency (DC) component, is related to the influence of gravity, and it can be exploited to identify static postures [63].”
Human Activity Recognition on Smartphones Using a Multiclass Hardware-Friendly Support Vector Machine (2012, methodology): “ML methods that have been previously employed for recognition include Naive Bayes, SVMs, Threshold-based and Markov chains [6].”
A Review of Accelerometry-Based Wearable Motion Detectors for Physical Activity Monitoring (2010, methodology): “The HMM is applied to determine unknown states at any time according to observable activity features (extracted from accelerometry data) corresponding to the states.”
Materials that couple sensing, actuation, computation, and communication (2015, methodology): “Gaussian mixture models (GMMs), where multivariate Gaussians are used for each component, have been used for classification though soft assignment to each category [3, 93], or”