Human Activity Recognition Using Inertial/Magnetic Sensor Units

By Kerem Altun, Billur Barshan. International Workshop on Human Behavior Unterstanding, 2010

302 citations recorded by the source corpus.

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

View Paper: https://www.semanticscholar.org/paper/cf2a5c8e16e1e861dea4e32cef1dcceacad0262b

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

Context-Aware Computing, Learning, and Big Data in Internet of Things: A Survey (2018, background): “Backpropagation neural networks are used in human activity recognition (walking, running, sitting, etc.) with wearable sensors [139], [140].”
Window Size Impact in Human Activity Recognition (2014, background): “Altun and Barshan (2010) (8 subjects) [51] Sitting, playing basketball, standing, rowing, jumping and more (19) Chest, both wrists and sides of the knees (5) BDM (99.”
Fusion of Smartphone Motion Sensors for Physical Activity Recognition (2014, unknown): “In [7], the authors compare different classification methods for recognizing physical activities using data from three sensors (accelerometer, gyroscope and magnetometer).”
Human Action Recognition From Various Data Modalities: A Review (2020, methodology): “bination of accelerometers and other sensors has also been adopted for HAR [315], [321], [322].”
A survey of depth and inertial sensor fusion for human action recognition (2015, methodology): “In [3], five inertial sensor units each comprising a triaxial gyroscope, a triaxial accelerometer, and a triaxial magnetometer were employed for classifying human activities and different classification techniques consisting of Bayesian decision, least-squares, and dynamic time warping, were…”
A Convolutional Neural Network-Based Sensor Fusion System for Monitoring Transition Movements in Healthcare Applications (2018, methodology): “vision and inertial [5-6], have been used to perform action or gesture recognition.”
Physical Human Activity Recognition Using Wearable Sensors (2015, methodology): “Unlike other recent research works done in the same context of this study, only acceleration data are used, in this paper as a modality for estimating the activities [5,10].”
A review on vision techniques applied to Human Behaviour Analysis for Ambient-Assisted Living (2012, background): “Other sensing devices are also used in diverse works [2, 8, 63, 109, 132], or a combination of vision and RFID tags [129] either as a direct way to recognise the objects being manipulated, or as a means for supervised learning of visual object appearance (using the correspondence between the RFID an”
Recognizing Daily and Sports Activities in Two Open Source Machine Learning Environments Using Body-Worn Sensor Units (2014, background): “Details of the subject profiles are given in [60].”
A Survey on Human Activity Recognition using Wearable Sensors (2013, methodology): “¯ y = 1 n n i=1 y i (1) RM S(Y ) = 1 n n i=1 y i 2 (2) σ y = 1 n − 1 n i=1 (y i − ¯ y) 2 (3) σ 2 y = 1 n − 1 n i=1 (y i − ¯ y) 2 (4) TABLE II Mean, standard deviation, variance, interquartile range (IQR), mean absolute deviation (MAD), correlation between axes, entropy, and kurtosis [19], [23]–[25],”