Application of &amp;lt;i&amp;gt;k&amp;lt;/i&amp;gt;-means and Gaussian mixture model for classification of seismic activities in Istanbul

Küyük, H. Serdar; Yildirim, Eray; Doğan, Emrah; Horasan, Gündüz

doi:10.5194/npg-19-411-2012

Cited by 46 publications

(17 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This flexibility has led to GMM clustering being applied to various observation types, such as human skin tones (Yang & Ahuja 1998), seismic events (Kuyuk et al. 2012) and pulsars (Lee et al. 2012).…”

Section: Data Analysis Via Complex Systems Theorymentioning

confidence: 99%

“…Although both the GMM and k-means algorithms rely on the use of cluster centres, only the former can account for data covariance, implying that it is more flexible in discovering clusters of different shapes (Press et al 2007). This flexibility has led to GMM clustering being applied to various observation types, such as human skin tones (Yang & Ahuja 1998), seismic events (Kuyuk et al 2012) and pulsars (Lee et al 2012). As § 4.3 will show, that flexibility will also prove to be useful here as the data clusters in our system tend to be of different shapes.…”

Section: Cluster Analysis Of Recurrence Network Measuresmentioning

confidence: 99%

See 1 more Smart Citation

Synchronization and chimeras in a network of four ring-coupled thermoacoustic oscillators

et al. 2022

View full text Add to dashboard Cite

We take a complex systems approach to investigating experimentally the collective dynamics of a network of four self-excited thermoacoustic oscillators coupled in a ring. Using synchronization metrics, we find a wide variety of emergent multi-scale behaviour, such as (i) a transition from intermittent frequency locking on a $\mathbb {T}^{3}$ quasiperiodic attractor to a breathing chimera, (ii) a two-cluster state of anti-phase synchronization on a periodic limit cycle, and (iii) a weak anti-phase chimera. We then compute the cross-transitivity from recurrence networks to identify the dominant direction of the coupling between the heat-release-rate ( $q^{\prime }_{\mathbb {X}}$ ) and pressure ( $p^{\prime }_{\mathbb {X}}$ ) fluctuations in each individual oscillator, as well as that between the pressure ( $p^{\prime }_{\mathbb {X}}$ and $p^{\prime }_{\mathbb {Y}}$ ) fluctuations in each pair of coupled oscillators. We find that networks of non-identical oscillators exhibit circumferentially biased $p^{\prime }_{\mathbb {X}}$ – $p^{\prime }_{\mathbb {Y}}$ coupling, leading to mode localization, whereas networks of identical oscillators exhibit globally symmetric $p^{\prime }_{\mathbb {X}}$ – $p^{\prime }_{\mathbb {Y}}$ coupling. In both types of networks, we find that the $p^{\prime }_{\mathbb {X}}$ – $q^{\prime }_{\mathbb {X}}$ coupling can be symmetric or asymmetric, but that the asymmetry is always such that $q^{\prime }_{\mathbb {X}}$ exerts a greater influence on $p^{\prime }_{\mathbb {X}}$ than vice versa. Finally, we show through a cluster analysis that the $p^{\prime }_{\mathbb {X}}$ – $p^{\prime }_{\mathbb {Y}}$ interactions play a more critical role than the $p^{\prime }_{\mathbb {X}}$ – $q^{\prime }_{\mathbb {X}}$ interactions in defining the collective dynamics of the system. As well as providing new insight into the interplay between the $p^\prime_{\mathbb{X}}\text{--}p^\prime_{\mathbb{Y}}$ and $p^\prime_{\mathbb{X}}\text{--}q^\prime_{\mathbb{X}}$ coupling, this study shows that even a small network of four ring-coupled thermoacoustic oscillators can exhibit a wide variety of collective dynamics. In particular, we present the first evidence of chimera states in a minimal network of coupled thermoacoustic oscillators, paving the way for the application of oscillation quenching strategies based on chimera control.

show abstract

Section: Data Analysis Via Complex Systems Theorymentioning

confidence: 99%

Section: Cluster Analysis Of Recurrence Network Measuresmentioning

confidence: 99%

Synchronization and chimeras in a network of four ring-coupled thermoacoustic oscillators

et al. 2022

View full text Add to dashboard Cite

show abstract

“…k-means clustering algorithms are discussed in detail in 51,[61][62][63][64] . Kuyuk et al 65 used the k-means to classify the seismic activities.…”

Section: K-means Clusteringmentioning

confidence: 99%

Discrimination between Small Earthquakes and Local Quarry Blasts Using Committee Machine

Lethy

Othman

Gabry

et al. 2021

Preprint

View full text Add to dashboard Cite

A combination of multiple discrimination artificial neural networks using different seismic source parameters is suggested using a committee machine. In this work, a committee machine was used to combine supervised and unsupervised artificial neural networks to discriminate between earthquakes and quarry blasts using data from the Egyptian National Seismological Network (ENSN). The unsupervised network is used as a measure of accuracy for the results of the supervised neural network. The unsupervised Self-Organized Map (SOM) and the k-means clustering algorithms are used to estimate support and confidence measures for the results. Meanwhile, the supervised neural network is used to discriminate between earthquakes and explosions. The artificial neural networks are trained using different input parameters which are the P wave spectrum corner frequency (PcF), S wave corner frequency (ScF), and the ratio (Rcf) of PcF to Scf. The combined approach succeeds to discriminate between earthquakes and quarry blasts in Northern Egypt. The method provides the results with a measure of confidence which eliminates false discrimination. The current paper represents an idea to implement artificial intelligence to assist experts in decision-making situations. The committee machine could identify the nature of a particular event, using the aid of several discrimination methods. The proposed committee machine could combine the results of several algorithms and expert opinions to form one single output with a confidence measure.

show abstract

“…To our knowledge, other than these two bodies of work, no others have aimed to cluster the NMSZ from a purely statistical perspective. It should be pointed out that in a more general sense, numerous statistical clustering approaches including Kmeans/Kmedian (Kamat and Kamath, 2017;Novianti et al, 2017;Kuyuk et al, 2012;Ramdani et al, 2015;Malyshev, 2016), mixture models (Rhoades and Gerstenberger, 2009;Erisoglu et al, 2011;Rhoades, 2013;Kuyuk et al, 2012)) and spatial point processes (Veen and Schoenberg, 2006;Ogata, 1998;Schoenberg, 2003;Bray and Schoenberg, 2013) have been applied to earthquake data, but not the NMSZ data specifically. Thus, this work was motivated by a desire to statistically identify temporal patterns among earthquake occurrences within the NMSZ.…”

Section: Introductionmentioning

confidence: 99%

A matrix-variate dirichlet process to model earthquake hypocentre temporal patterns

Ray

Bowman

Csontos

et al. 2020

Statistical Modelling

View full text Add to dashboard Cite

Earthquakes are one of the deadliest natural disasters. Our study focuses on detecting temporal patterns of earthquakes occurring along intraplate faults in the New Madrid seismic zone (NMSZ) within the middle of the United States from 1996–2016. Based on the magnitude and location of each earthquake, we developed a Bayesian clustering method to group hypocentres such that each group shared the same temporal pattern of occurrence. We constructed a matrix-variate Dirichlet process prior to describe temporal trends in the space and to detect regions showing similar temporal patterns. Simulations were conducted to assess accuracy and performance of the proposed method and to compare to other commonly used clustering methods such as Kmean, Kmedian and partition-around-medoids. We applied the method to NMSZ data to identify clusters of temporal patterns, which represent areas of stress that are potentially migrating over time. This information can then be used to assist in the prediction of future earthquakes.

show abstract

Application of <i>k</i>-means and Gaussian mixture model for classification of seismic activities in Istanbul

Cited by 46 publications

References 28 publications

Synchronization and chimeras in a network of four ring-coupled thermoacoustic oscillators

Synchronization and chimeras in a network of four ring-coupled thermoacoustic oscillators

Discrimination between Small Earthquakes and Local Quarry Blasts Using Committee Machine

A matrix-variate dirichlet process to model earthquake hypocentre temporal patterns

Contact Info

Product

Resources

About