Using acceleration measurements for activity recognition: An effective learning algorithm for constructing neural classifiers

By Jhun-Ying Yang, Jeen-Shing Wang. Pattern Recognition Letters, 2008

389 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Biomedical Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/2682ba41936a6e9c6079b6a539c875a8234ab4aa

How researchers see this paper

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

In Artificial Intelligence

In Biomedical Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Optimal Placement of Accelerometers for the Detection of Everyday Activities (2013, methodology): “Yang [1] Standing, sitting, walking, running, vacuuming, scrubbing brushing teeth (8) 7 Wrist Mean, correlation, energy, interquartile range, RMS Neural network (95%) kNN (87%)”
Recognizing Daily and Sports Activities in Two Open Source Machine Learning Environments Using Body-Worn Sensor Units (2014, neutral): “[50] 3D acc (×1) 8 pos, mot 3M 4F ANN: 95.”
A Survey on Activity Detection and Classification Using Wearable Sensors (2017, background): “Activities of interest to be classified with a single accelerometer based sensor, mounted at a location on the arm, typically the wrist, have included eating and drinking [96], dynamic and static activities [22], work types of activities [97], different arm movements [99], and long-term motions [98]”
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].”
On-body localization of wearable devices: An investigation of position-aware activity recognition (2016, background): “A similar distinction has been made in [19] to improve the accuracy of activity recognition.”
A Public Domain Dataset for Human Activity Recognition using Smartphones (2013, methodology): “Standard measures previously used in HAR literature [15] such as the mean, correlation, signal magnitude area (SMA) and autoregression coefficients [16] were employed for the feature mapping.”
Jointly Learning Energy Expenditures and Activities Using Egocentric Multimodal Signals (2017, background): “[65, 32] use recurrent networks for single triaxial accelerometer data, [41] for a heart rate controller, and [50] for multimodal wearable sensors.”
Activity Recognition Using Inertial Sensing for Healthcare, Wellbeing and Sports Applications: A Survey (2010, methodology): “Spectral Energy Energy feature can be used to capture data periodicity of the acceleration data in the frequency domain and it can be used to distinguish sedentary activities from vigorous activities[42].”
Activity recognition with smartphone sensors (2014, methodology): “Other classification methods used in activity recognition with mobile sensors include Gaussian Mixture Models[48, 49], Artificial Neural Networks (ANN)[50-52], Naive Bayes (NB)[53], Rule-Based classifier[54], and a fuzzy inference system[55].”
Direct measurement of human movement by accelerometry. (2008, background): “, but can also highlights extended eriods of ambulatory behaviour such as performing random hores involved during housework [53,61,74].”