Smoothing and differentiation of data by simplified least square procedure.

By Jean. Steinier, Yves. Termonia, J. Deltour. 1964

Subfields: Statistics and Probability, Numerical Methods & Scientific Computing

How researchers see this paper

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

In Statistics and Probability

In Numerical Methods & Scientific Computing

Citations in the corpus

Co-Occurrence Feature Learning for Skeleton Based Action Recognition Using Regularized Deep LSTM Networks (2016, methodology): “To reduce the inﬂuence of noise in the captured skeleton data, we smooth each joint’s position of the raw skeleton using the ﬁlter ( − 3 , 12 , 17 , 12 , − 3) / 35 in the temporal domain (Savitzky and Golay 1964; Du, Wang, and Wang 2015).”
Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates (2017, methodology): “Both Co-occurrence LSTM [48] and Hierarchical RNN [30] adopt the Svaitzky-Golay ﬁlter [80] in the temporal domain to smooth the skeletal joint positions and reduce the inﬂuence of noise in the data collected by Kinect.”
Ionospheric Bow Waves and Perturbations Induced by the 21 August 2017 Solar Eclipse (2017, methodology): “For detection of TIDs, differential TEC was derived by subtracting a background TEC variation determined by a low-pass-filtering procedure using the Savitzky-Golay low-pass filter approach (Savitzky & Golay, 1964).”
In-field hyperspectral proximal sensing for estimating quality parameters of mixed pasture (2011, methodology): “The Savitzky– Golay filter, (Savitzky and Golay 1964) pre-processing smoothing procedure, was then used to improve signal-to-noise ratio.”
Identification of rice flour types with near-infrared spectroscopy associated with PLS-DA and SVM methods (2019, methodology): “Pretreatment of the spectra using derivatives [26] and multiplicative scatter correction (MSC) [24] were performed using Matlab®”
An empirical survey of data augmentation for time series classification with neural networks (2020, methodology): “First, the signals are smoothed with a Savitzky-Golay filter [72] and an offset is used to ensure that all values are greater than 0.”
Variable Selection in Visible and Near-Infrared Spectral Analysis for Noninvasive Determination of Soluble Solids Content of ‘Ya’ Pear (2014, methodology): “…before the selection of effective variables, different preprocessing methods including MSC (Helland et al. 1995), SNV (Barnes et al. 1989), SG (Savitzky and Golay 1964; Gorry 1990), first derivative, and second derivative (Tanvir et al. 1990) were performed to see if model’s performance can…”