References in periodicals archive ?
Harmonic Linear Dynamical System (HLDS) uses eigendecomposition on transition matrix A in order to find harmonics as well as the mixing weight of harmonics.
In summary, HLDS includes four steps: (1) learning hidden variables using LDS, (2) taking eigendecomposition on transition matrix A to find the canonical form of hidden variables, which helps to find harmonics and mixing weight of harmonics, (3) taking the magnitude of the harmonic mixing matrix to eliminate phase shift, and (4) using SVD to combine harmonics.
In order to show the validation of the clustering by HLDS, we carry out experiments on real ECG dataset taken from PhysioNet http://www.physionet.org/physiobank/database/ [31, 32].
Compared to the previous feature extraction methods, the average performance of applied HLDS on real ECG datasets demonstrates significant performances, that is, 9.1%, 54.5%, 39.39%, and 57.57% clustering improvement against the LPCC, original Kalman filter, DFT, and PCA, respectively.
It is observed that the HLDS shows clear separation of dots compared to the other approaches.
The computational complexity of the HLDS is shown in Figure 5, executed on collection 1.
The initial portfolio of HLDS Hybrid Drives will be offered in a range of embedded flash memory capacities including 16GB, 32GB and 64GB.
Mann -- Whitney U-test for unmatched pairs Significant results % People unemployed 0.000(a) (High social deprivation) Mean population density 0.000(a) % Recent migrants 0.006(a) (High social disorganization) % Hlds without car 0.000(a) (High social deprivation) % Lone parent hlds 0.000(a) (high social disorganization) Segregation of hlds without car 0.004(b) Mann-Whitney U-test for unmatched pairs Non-significant results % Persons non-White 0.9638(b) (High social disorganization) % Employed people with no children 0.3670(a) % Hlds in non-self contained accom.
Acronyms browser ?
Full browser ?
- Hlestakov, Ivan Alexandrovich