Empirical Comparison between Autoencoders and Traditional Dimensionality Reduction Methods

Fournier, Quentin; Aloise, Daniel

doi:10.1109/aike.2019.00044

Cited by 43 publications

(43 citation statements)

References 4 publications

(6 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The processing period for PCA was two orders of magnitude faster than its equivalents in the neural network. The two auto-encoders had a sufficiently broad dimension [78].…”

Section: Review For Pca Algorithmmentioning

confidence: 99%

A Review of Principal Component Analysis Algorithm for Dimensionality Reduction

Hasan

Abdulazeez

2021

JSCDM

119

View full text Add to dashboard Cite

Big databases are increasingly widespread and are therefore hard to understand, in exploratory biomedicine science, big data in health research is highly exciting because data-based analyses can travel quicker than hypothesis-based research. Principal Component Analysis (PCA) is a method to reduce the dimensionality of certain datasets. Improves interpretability but without losing much information. It achieves this by creating new covariates that are not related to each other. Finding those new variables, or what we call the main components, will reduce the eigenvalue /eigenvectors solution problem. (PCA) can be said to be an adaptive data analysis technology because technology variables are developed to adapt to different data types and structures. This review will start by introducing the basic ideas of (PCA), describe some concepts related to (PCA), and discussing. What it can do, and reviewed fifteen articles of (PCA) that have been introduced and published in the last three years.

show abstract

“…The processing period for PCA was two orders of magnitude faster than its equivalents in the neural network. The two auto-encoders had a sufficiently broad dimension [78].…”

Section: Review For Pca Algorithmmentioning

confidence: 99%

A Review of Principal Component Analysis Algorithm for Dimensionality Reduction

Hasan

Abdulazeez

2021

JSCDM

119

View full text Add to dashboard Cite

show abstract

“…The encoder extracts the important functions hidden in the input data in a compressed form, and the decoder recovers it based on the compressed data from the encoder. In general, as the number of neurons in the hidden layer that extracts important features is smaller than the input, data can be compressed [29]. The DAE is a slight modification of the basic AE learning method to further strengthen the restoration process [30].…”

Section: Denoising Autoencoder (Dae)mentioning

confidence: 99%

Multi-Scale Convolutional Recurrent Neural Network for Bearing Fault Detection in Noisy Manufacturing Environments

Han

Jeong

2021

Applied Sciences

View full text Add to dashboard Cite

The failure of a facility to produce a product can have significant impacts on the quality of the product. Most equipment failures occur in rotating equipment, with bearing damage being the biggest cause of failure in rotating equipment. In this paper, we propose a denoising autoencoder (DAE) and multi-scale convolution recurrent neural network (MS-CRNN), wherein the DAE accurately inspects bearing defects in the same environment as bearing vibration signals in the field, and the MS-CRNN inspects and classifies defects. We experimented with adding random noise to create a dataset that resembled noisy manufacturing installations in the field. From the results of the experiment, the accuracy of the proposed method was more than 90%, proving that it is an algorithm that can be applied in the field.

show abstract

“…However, by using PCA beforehand, this limitation can be overcome. A comparison of the respective advantages of AEs in contrast to PCA is given in [47]. The computational complexity depends on the target dimensionality d, the number of iterations i and the number of weights in a neural network w. It is O(in 2 ) for SM, O(inw) for AE, O(imd 3 ) for LLC and MC.…”

Section: Non-linear Non-convex Feature Extractionmentioning

confidence: 99%

State of the Art and Future Trends in Data Reduction for High-Performance Computing

2020

JSFI

View full text Add to dashboard Cite

Research into data reduction techniques has gained popularity in recent years as storage capacity and performance become a growing concern. This survey paper provides an overview of leveraging points found in high-performance computing (HPC) systems and suitable mechanisms to reduce data volumes. We present the underlying theories and their application throughout the HPC stack and also discuss related hardware acceleration and reduction approaches. After introducing relevant use-cases, an overview of modern lossless and lossy compression algorithms and their respective usage at the application and file system layer is given. In anticipation of their increasing relevance for adaptive and in situ approaches, dimensionality reduction techniques are summarized with a focus on non-linear feature extraction. Adaptive approaches and in situ compression algorithms and frameworks follow. The key stages and new opportunities to deduplication are covered next. An unconventional but promising method is recomputation, which is proposed at last. We conclude the survey with an outlook on future developments.

show abstract

Empirical Comparison between Autoencoders and Traditional Dimensionality Reduction Methods

Cited by 43 publications

References 4 publications

A Review of Principal Component Analysis Algorithm for Dimensionality Reduction

A Review of Principal Component Analysis Algorithm for Dimensionality Reduction

Multi-Scale Convolutional Recurrent Neural Network for Bearing Fault Detection in Noisy Manufacturing Environments

State of the Art and Future Trends in Data Reduction for High-Performance Computing

Contact Info

Product

Resources

About