Implementation of a real-time human movement classifier using a triaxial accelerometer for ambulatory monitoring

By D. Karantonis, M. Narayanan, M. Mathie, N. Lovell, B. Celler. IEEE Transactions on Information Technology in Biomedicine, 2006

1,324 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Pulmonary and Respiratory Medicine

View Paper: https://www.semanticscholar.org/paper/39ed8b124d8a0dbf57a7777468428b2d682d34ab

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

Citations in the corpus

Preprocessing techniques for context recognition from accelerometer data (2010, methodology): “It is also possible to use SMA as the basis for identifying periods of user activity [21].”
Direct measurement of human movement by accelerometry. (2008, background): “[62] Karantonis DM, Narayanan MR, Mathie M, Lovell NH, Celler BG.”
LSTM Networks Using Smartphone Data for Sensor-Based Human Activity Recognition in Smart Homes (2021, background): “A third-order Butterworth low-pass filter with a cutoff frequency of 20 Hz is sufficient for capturing human body motion since 99% of its energy is contained below 15 Hz [46].”
Activity identification using body-mounted sensors—a review of classification techniques (2009, methodology): “A simplified and computationally efficient version of this algorithm was later developed by Karantonis et al (2006) which used only simple threshold-based decisions at each node and demonstrated the potential of their hierarchical approach for real-time fall detection.”
Using acceleration measurements for activity recognition: An effective learning algorithm for constructing neural classifiers (2008, methodology): “Note that the SMA and AE are scalars.”
A Review of Accelerometry-Based Wearable Motion Detectors for Physical Activity Monitoring (2010, methodology): “Therefore, human postures, such as upright and lying, can be distinguished according to the magnitude of acceleration signals along sensitive axes from only one accelerometer worn at the waist and torso [16,17].”
Transition-Aware Human Activity Recognition Using Smartphones (2016, background): “These sensors need to provide measurements at frequencies higher than the energy spectrum of human body motion which lies within 0 Hz and 15 Hz [39].”
A Survey on Activity Detection and Classification Using Wearable Sensors (2017, methodology): “Some other earlier works did not even use a classification algorithm, but rather employed empirically determined thresholds for classification [38], [39], [173].”
A Triaxial Accelerometer-Based Physical-Activity Recognition via Augmented-Signal Features and a Hierarchical Recognizer (2010, methodology): “Comparatively, a small number of studies have investigated the use of a single accelerometer mounted at waist or sternum [4], [6], [7], [9], [12]–[14], [16], [22], [23].”
Gait Analysis Using Wearable Sensors (2012, background): “[85,86] reviewed the use of accelerometer-based systems in human movement, such as monitoring a range of different movements, measuring physical activity levels and identifying and classify movements performed by subjects, and discussed a real-time human movement classifier using a triaxial accelero”
Machine Learning Methods for Classifying Human Physical Activity from On-Body Accelerometers (2010, background): “[47] 1 3D acc Magnitude area/vector Tilt angle FFT Binary decision 10 6 90.”
Physical Human Activity Recognition Using Wearable Sensors (2015, methodology): “9% and was obtained when using an accelerometer placed at either waist level [15,18,28] or at wrist level [20,29].”
A survey on fall detection: Principles and approaches (2013, methodology): “Embedded intelligence was employed in [7] for the design of a system that performs the vast majority of signal processing onboard the wearable unit.”
A Public Domain Dataset for Human Activity Recognition using Smartphones (2013, background): “Similar work on HAR using special purpose sensors have shown comparable performance (90%-96%), such as in [3] where a system developed by collecting data from 6 volunteers for the classifaciton of 12 ADL using a waist-mounted triaxial accelerometer provided an accuracy of 90.”
Comparative study on classifying human activities with miniature inertial and magnetic sensors (2010, methodology): “The signal processing and motion detection techniques employed, and the configuration, number, and type of sensors differ widely among the studies, from using a single accelerometer [18,51,52] to as many as 12 [53] on different parts of the body.”
Human Activity Recognition Using Inertial/Magnetic Sensor Units (2010, background): “The number of sensors used vary between one [8,23] to twelve [4].”