beads.h File Reference

Baseline estimation and subtraction using Baseline Estimation And Denoising using Sparsity(BEADS). More...

#include <stdexcept>
#include <tuple>
#include <vector>

Go to the source code of this file.

Enumerations
enum class	sablib::BeadsPenalty { L1_v1 , L1_v2 }
	Penalty types for the BEADS algorithm.(see Table 1 in Duval's paper). More...

Functions
const std::tuple< std::vector< double >, std::vector< double > >	sablib::BaselineBeads (const std::vector< double > &y, const unsigned int s, const double frequency, const double r, const double lambda0, const double lambda1, const double lambda2, const unsigned int loop=30, const double eps=1e-3, const BeadsPenalty penalty=BeadsPenalty::L1_v2)
	Performs baseline estimation and denoising using Sparsity (BEADS).

Detailed Description

Baseline estimation and subtraction using Baseline Estimation And Denoising using Sparsity(BEADS).

Author

Izadori

References:

• Ning, X.; Selesnick, I. W.; Duval, L. Chromatogram baseline estimation and denoising using sparsity. Chemometrics and Intelligent Laboratory Systems, 2014, 139, 156-167.
• Duval's MATLAB implemetation
• Kotaro Saito's pybeads implementation

Definition in file beads.h.

Enumeration Type Documentation

BeadsPenalty

enum class sablib::BeadsPenalty

strong

Penalty types for the BEADS algorithm.(see Table 1 in Duval's paper).

Enumerator
L1_v1	Penalty type 1, using phi-B(x) function and it's derivative.
L1_v2	Penalty type 2, using phi-C(x) function and it's derivative.

Definition at line 24 of file beads.h.

Function Documentation

BaselineBeads()

const std::tuple< std::vector< double >, std::vector< double > > sablib::BaselineBeads	(	const std::vector< double > &	y,
		const unsigned int	s,
		const double	frequency,
		const double	r,
		const double	lambda0,
		const double	lambda1,
		const double	lambda2,
		const unsigned int	loop = 30,
		const double	eps = 1e-3,
		const BeadsPenalty	penalty = BeadsPenalty::L1_v2 )

Performs baseline estimation and denoising using Sparsity (BEADS).

Parameters

y	The input data.
s	Order of the derivative for baseline sparsity (typically 1 or 2).
frequency	Sampling frequency of the signal.
r	High-pass filter parameter (cut-off frequency relative to sampling frequency).
lambda0	Sparsity parameter for the baseline.
lambda1	Sparsity parameter for the first-order derivative of the signal.
lambda2	Sparsity parameter for the second-order derivative of the signal.
loop	Maximum number of iterations.
eps	Convergence threshold.
penalty	Penalty type (L1_v1 or L1_v2).

Returns

A tuple containing (baseline, denoised signal).

Exceptions

std::invalid_argument

One or more parameters are wrong.

Definition at line 70 of file beads.cpp.