PCA and ICA Based Hybrid Dimension Reduction Model for Cardiac Arrhythmia Disease Diagnosis

Islam, Rashedul; Bhuiyan, Rasel Ahmed; Ahmed, Nadeem; Islam, Rajibul

doi:10.1109/hnicem.2018.8666331

Cited by 4 publications

(4 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The singular value decomposition method leads to a reduced space where, along the new axes, the observations/features have the highest variance. These new directions are known as the principal components [72]. SVD decomposes a matrix as [73]:…”

Section: Singular-value Decomposition: (Svd)mentioning

confidence: 99%

“…Independent component analysis (ICA) is a linear dimension reduction algorithm where the transformation is conducted on the original dataset to arrive at reduced features of independent components [63], [72]- [75]. This method iteratively optimizes and increase the independence between the features in the embedding space.…”

Section: Independent Component Analysis (Ica)mentioning

confidence: 99%

“…This, in turn, leads to a linear nonorthogonal projection of the original dataset into the embedding space. The observed vectors in the original space are then expanded as the linear combinations of unknown non-gaussian sources S. With the assumption of statistical independence, ICA determines the sources from the original observation [72], [73]. Using ICA, given that S is a source random vector, A = W −1 is a mixing matrix, and X is observation, then ICA finds W and S = WX [73].…”

Section: Independent Component Analysis (Ica)mentioning

confidence: 99%

See 2 more Smart Citations

Intelligent Photolithography Corrections Using Dimensionality Reductions

et al. 2019

View full text Add to dashboard Cite

With the shrinking of the IC technology node, optical proximity effects (OPC) and etch proximity effects (EPC) are the two major tasks in advanced photolithography patterning. Machine learning has emerged in OPC/EPC problems because conventional optical-solver-based OPC is time-consuming, and there is no physical model existing for EPC. In this work, we use dimensionality reduction (DR) algorithms to reduce the computation time of complex OPC/EPC problems while the prediction accuracy is maintained. Also, we implement a pure machine learning approach where the input masks are directly mapped to the output etched patterns. While one photolithographic mask can generate many experimental patterns at once, our pure ML-based approach can shorten the trial-and-error period in the photolithographic correction. Additionally, we demonstrate the automation in SEM images preprocessing using feature detection, and this facilitates intelligent manufacturing in semiconductor processing. The input vector dimensions are effectively reduced by two orders of magnitude while the observed mean squared error is not affected significantly. The computation runtime is reduced from 4804 s of the baseline calculation to 10 s-200 s The MSE values changed from the baseline 0.037 to 0.037 for singular value decomposition (SVD), to 0.039 for independent component analysis (ICA), and to 0.035 for factor analysis (FA).

show abstract

Section: Singular-value Decomposition: (Svd)mentioning

confidence: 99%

Section: Independent Component Analysis (Ica)mentioning

confidence: 99%

Section: Independent Component Analysis (Ica)mentioning

confidence: 99%

See 1 more Smart Citation

Intelligent Photolithography Corrections Using Dimensionality Reductions

et al. 2019

View full text Add to dashboard Cite

show abstract

“…O método foi capaz de reduzir o sinal original de 192 para 10 amostras, e alcançou uma acurácia de 79%. Em [7], é proposto um estudo em redução de dimensões em sinais de ECG, utilizando Independent Component Analysis (ICA) e PCA como métodos de compressão, que rendeu uma acurácia de 98.67%, mas foram utilizadas apenas 4 classes para a classificação.…”

Section: Introductionunclassified

Avaliação de Métodos Redutores de Dimensionalidade em Sinais de ECG para a Classificação de Anomalias Cardíacas

Roque¹,

Santos²,

Gomes³

2021

Anais Do XXXIX Simpósio Brasileiro De Telecomunicações E Processamento De Sinais

View full text Add to dashboard Cite

Resumo-Segundo a Organização Mundial de Saúde, os problemas cardíacos são um dos maiores causadores de mortes. Uma das formas de se fazer o diagnósticos desses problemas cardíacos é através da análise de sinais de ECG. Este trabalho apresenta um estudo do efeito combinado da taxa de amostragem e métodos redutores de dimensionalidade sobre o desempenho de classificadores de anomalias cardíacas. Os resultados mostram que a abordagem proposta alcança desempenhos superiores a trabalhos anteriores, chegando a acurácia de 99, 94%.

show abstract

Multi-label Anomaly Classification Based on Electrocardiogram

Li¹,

Sun²

2021

Health Information Science

View full text Add to dashboard Cite

PCA and ICA Based Hybrid Dimension Reduction Model for Cardiac Arrhythmia Disease Diagnosis

Cited by 4 publications

References 19 publications

Intelligent Photolithography Corrections Using Dimensionality Reductions

Intelligent Photolithography Corrections Using Dimensionality Reductions

Avaliação de Métodos Redutores de Dimensionalidade em Sinais de ECG para a Classificação de Anomalias Cardíacas

Multi-label Anomaly Classification Based on Electrocardiogram

Contact Info

Product

Resources

About