Software
Complex Optimization Toolbox
The Complex Optimization Toolbox (COT) is a MATLAB toolbox for optimizing problems in complex variables. Real optimization is possible as well without any performance penalty. Included are generalized algorithms for unconstrained nonlinear optimization and nonlinear least squares, among others. COT is a part of Tensorlab. Please consult the manual to get started with COT.
NMF Segmentation GUI – Matlab software suite for semi-automated brain tumor segmentation from MRI data
Semi-automated framework for brain tumor segmentation on multi-parametric MRI data based on non-negative matrix factorization (NMF). The method does not require any training step and can be applied to any individual multi-parametric MRI dataset. L1-regularization is incorporated into the NMF objective function to promote spatial consistency and sparseness of the tissue abundance maps. The pathological source vectors are initialized through user-defined voxel selection. Knowledge about the spatial location of the selected voxels is combined with tissue adjacency constraints in a post-processing step to enhance segmentation quality.
Tensor-based detection of irregular heartbeats
This demo shows an overview of the different steps in tensor-based classification of irregular heartbeats in ECG data.
Tensor-based detection of T-wave alternans
This demo presents a novel TWA detection method based on tensor decompositions. The method is fully automated and both detects and quantifies the amount of T Wave Alternans in a multilead ECG signal.
Tensor-based EEG artifact Removal
The tool removes EEG artefacts that can be modelled as rational functions. The separation of rational functions is achieved by loewner tensorization and decomposition in block terms of rank (L,L,1).
Tensor-based MRSI GUI
This MATLAB based graphical user interface (GUI) implements tensor-based approaches for residual water suppression and tissue type differentiation using Magnetic Resonance Spectroscopic Imaging (MRSI) signals.
Tensorlab
Tensorlab is a MATLAB toolbox for tensor computations, structured data fusion and complex optimization. In Tensorlab, datasets are stored as (possibly incomplete, sparse or structured) vectors, matrices and higher-order tensors, possibly obtained after tensorizing lower-order data. By mixing different types of tensor decompositions and factor transformations, a vast amount of factorizations can be computed. Furthermore, users can choose from a library of pre-implemented transformations and structures, including non-negativity, orthogonality, Toeplitz and Vandermonde matrices to name a few, or even define their own factor transformations. A collection of demos illustrating how Tensorlab can be used in various applications can be found here, while an extensive online manual can be accessed here.