Classification of Transients using Wavelet Based Entropy and Radial Basis Neural Networks

This work aims to investigate new markers for the quantitative characterization of insomnia, in the context of sleep microstructure, as expressed by cyclic alternating pattern (CAP) sleep. The study group includes 11 subjects with normal sleep and 10 subjects with diagnosed primary insomnia. Differences between normal sleepers and insomniacs are investigated, in terms of dynamics and content of CAP events. The overall rate of CAP and of different phases is considered. The dynamic in the structure and alternation of CAP events is further studied in different scales by use of wavelet analysis, and calculation of energy/entropy features. The content of CAP events is studied in terms of electroencephalography (EEG) complexity analysis for the different types of events. Statistically significant differences are highlighted, both in structure and content. Besides confirming the increase in CAP rate, main findings regarding the microstructure difference in insomnia include: 1) as regards the deep sleep building phases, more irregular activation-deactivation patterns, with bigger deactivation time, i.e., distance between consecutive activation events, and appearing with higher EEG complexity in deactivation, and 2) a bigger duration of desynchronisation phases, with increased EEG complexity and more irregular patterns. This analysis extends previous findings on the relation between CAPrate increase and sleep instability mechanisms, proposing specific features of CAP that seem to play a role in insomnia (as consistently presented via classification analysis). This opens new perspectives for the understanding of the role of CAP in the quantitative characterization of sleep and its disorders.

show abstract

“…Wavelet entropy can signify the complexity of a nonstationary signal or system in both time and scale domain [14], [15].…”

Section: Cap Microstructure: the Cap Events As A Time Seriesmentioning

confidence: 99%

Cyclic Alternating Patterns in Normal Sleep and Insomnia: Structure and Content Differences

Chouvarda

Méndez

Rosso

et al. 2012

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

show abstract

“…Transient signals occurring in power systems and neuro magnetic brain responses have structural and temporal similarities with the glitch signals found in LIGO data streams. Wavelet based feature extraction for classifying these transients are detailed in [38,39]. Wavelet is a function having a smooth oscillatory pattern which vanishes near the ends [38].…”

Section: Feature Extractionmentioning

confidence: 99%

Transient classification in LIGO data using difference boosting neural network

et al. 2017

View full text Add to dashboard Cite

Detection and classification of transients in data from gravitational wave detectors are crucial for efficient searches for true astrophysical events and identification of noise sources. We present a hybrid method for classification of short duration transients seen in gravitational wave data using both supervised and unsupervised machine learning techniques. To train the classifiers we use the relative wavelet energy and the corresponding entropy obtained by applying one-dimensional wavelet decomposition on the data. The prediction accuracy of the trained classifier on nine simulated classes of gravitational wave transients and also LIGO's sixth science run hardware injections are reported. Targeted searches for a couple of known classes of non-astrophysical signals in the first observational run of Advanced LIGO data are also presented. The ability to accurately identify transient classes using minimal training samples makes the proposed method a useful tool for LIGO detector characterization as well as searches for short duration gravitational wave signals.

show abstract

“…with, There is actually an important reason for choosing the definition in Eqs. (2) and (4). In order to fulfill the requirements in point 3 and 4 in Sec.…”

Section: Mathematical Representationmentioning

confidence: 99%

Exhaustive search-based model for hybrid sensor network

Waskita¹,

Suhartanto²,

Akbar³

et al. 2012

2012 4th International Conference on Intelligent and Advanced Systems (ICIAS2012)

View full text Add to dashboard Cite

A new model for a cluster of hybrid sensors network with multi sub-clusters is proposed. The model is in particular relevant to the early warning system in a large scale monitoring system in, for example, a nuclear power plant. It mainly addresses to a safety critical system which requires real-time processes with high accuracy. The mathematical model is based on the extended conventional search algorithm with certain interactions among the nearest neighborhood of sensors. It is argued that the model could realize a highly accurate decision support system with less number of parameters. A case of one dimensional interaction function is discussed, and a simple algorithm for the model is also given.

show abstract

Classification of Transients using Wavelet Based Entropy and Radial Basis Neural Networks

Cited by 15 publications

References 11 publications

Cyclic Alternating Patterns in Normal Sleep and Insomnia: Structure and Content Differences

Cyclic Alternating Patterns in Normal Sleep and Insomnia: Structure and Content Differences

Transient classification in LIGO data using difference boosting neural network

Exhaustive search-based model for hybrid sensor network

Contact Info

Product

Resources

About