A semi-parametric estimation method for the quantile spectrum with an application to earthquake classification using convolutional neural network

Chen, Tianbo; Sun, Ying; Li, Ta‐Hsin

doi:10.1016/j.csda.2020.107069

Cited by 11 publications

(8 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For this reason, normally the layers of CNNs are considered as blocks to detect the traits. The first layers, those immediately after the entry layer, are considered low-level features extractors, while the last layers, usually completely connected like those of the ANNs, are considered high-level features extractors [150].…”

Section: Convolutional Neural Network For Time Series Datamentioning

confidence: 99%

Machine Learning-Based Algorithms to Knowledge Extraction from Time Series Data: A Review

Ciaburro

Iannace

2021

Data

View full text Add to dashboard Cite

To predict the future behavior of a system, we can exploit the information collected in the past, trying to identify recurring structures in what happened to predict what could happen, if the same structures repeat themselves in the future as well. A time series represents a time sequence of numerical values observed in the past at a measurable variable. The values are sampled at equidistant time intervals, according to an appropriate granular frequency, such as the day, week, or month, and measured according to physical units of measurement. In machine learning-based algorithms, the information underlying the knowledge is extracted from the data themselves, which are explored and analyzed in search of recurring patterns or to discover hidden causal associations or relationships. The prediction model extracts knowledge through an inductive process: the input is the data and, possibly, a first example of the expected output, the machine will then learn the algorithm to follow to obtain the same result. This paper reviews the most recent work that has used machine learning-based techniques to extract knowledge from time series data.

show abstract

Section: Convolutional Neural Network For Time Series Datamentioning

confidence: 99%

Machine Learning-Based Algorithms to Knowledge Extraction from Time Series Data: A Review

Ciaburro

Iannace

2021

Data

View full text Add to dashboard Cite

show abstract

“…The quantile periodograms convert time series into two‐dimensional images. One way of utilizing these images for classification is to feed them directly to an image classifier, as was done in the work of Chen et al 29 The high dimensionality of the images and the high complexity of image classifiers typically demand a large number of training samples. An alternative method is to employ a dimension‐reduction technique to extract a small number of features and then to feed these features to a general‐purpose machine learning classifier.…”

Section: Quantile Periodogram and Qfamentioning

confidence: 99%

“…For unsmoothed quantile periodogram, the RMSE is equal to 0.409. Further discussions on the procedure can be found in the work of Chen et al 29 …”

Section: Classification Based On Qfa‐fpca Featuresmentioning

confidence: 99%

“…One way is to treat the quantile periodogram as an image and feed it directly to a deep‐learning image classifier such as the convolutional neural network 28 . This approach is taken in the work of Chen et al 29 for classifying a large number of earthquake waves. Another way of utilizing the quantile periodogram as a bivariate function is to subject it to a dimension‐reduction mechanism and feed the resulting features into a general‐purpose classifier such as the support vector machine 30 .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

From zero crossings to quantile‐frequency analysis of time series with an application to nondestructive evaluation

2019

Appl Stoch Models Bus & Ind

View full text Add to dashboard Cite

Represented by the pioneering works of Professor Benjamin Kedem, zero crossings of time-series data have been proven useful for characterizing oscillatory patterns in many applications such as speech recognition and brainwave analysis. Robustness against outliers and nonlinear distortions is one of the advantages of zero crossings in comparison with traditional spectral analysis techniques. This paper introduces a new tool of spectral analysis for time-series data that goes beyond zero crossings. It is called quantile-frequency analysis (QFA). Constructed from trigonometric quantile regression, QFA transforms a time series into a bivariate function of quantile level and frequency variable. For each fixed quantile level, it corresponds to a periodogram-like function, called the quantile periodogram, which characterizes the oscillatory behavior of the time series round the quantile. By coupling QFA with functional principal component analysis, new dimension-reduced features are proposed for discriminant analysis of time series. The usefulness of these features is demonstrated by a case study of classifying real-world ultrasound signals for nondestructive evaluation of aircraft panels. Various machine learning classifiers are trained and tested by cross-validation. The results show a clear advantage of the QFA method over its ordinary-periodogram-based counterpart in delivering higher out-of-sample classification accuracy.

show abstract

“…The QFA-DL idea was tested on a different data set in [16] with limited experimentation. The present paper provides a more comprehensive study.…”

Section: Introductionmentioning

confidence: 99%

Quantile-Frequency Analysis and Deep Learning for Signal Classification

2023

J Nondestruct Eval

Self Cite

View full text Add to dashboard Cite

This paper proposes a new method for signal classification based on a combination of recently introduced nonlinear spectral analysis technique called quantile-frequency analysis (QFA) and deep-learning (DL) image classifiers. The QFA method converts a one-dimensional signal into a two-dimensional representation of the signal's oscillatory behavior in the frequency domain at different quantiles or a sequence of such representations that are localized in time. The DL image classifiers utilize these representations for signal classification. The benefit of this QFA-DL classification method, especially in comparison with the traditional method based on the power spectrum and spectrogram, is demonstrated by a numerical experiment using real-world data from a nondestructive evaluation (NDE) application.

show abstract

A semi-parametric estimation method for the quantile spectrum with an application to earthquake classification using convolutional neural network

Cited by 11 publications

References 28 publications

Machine Learning-Based Algorithms to Knowledge Extraction from Time Series Data: A Review

Machine Learning-Based Algorithms to Knowledge Extraction from Time Series Data: A Review

From zero crossings to quantile‐frequency analysis of time series with an application to nondestructive evaluation

Quantile-Frequency Analysis and Deep Learning for Signal Classification

Contact Info

Product

Resources

About