Detrended fluctuation analysis of EEG recordings for epileptic seizure detection

Adda, Ahmed; Benoudnine, H.

doi:10.1109/biosmart.2016.7835461

Cited by 13 publications

(6 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, Márton et al (2014) recently published a methodology to analyze EEG signaling using DFA. A study by Adda and Benoudnine (2016) showed that DFA of EEG achieved high detection accuracy to distinguish epileptic seizures from normal healthy EEG. To date, only limited information is available regarding DFA of GMA, probably because the time series of EGG recordings in humans have a short-duration.…”

Section: Discussionmentioning

confidence: 99%

Sulprostone-Induced Gastric Dysrhythmia in the Ferret: Conventional and Advanced Analytical Approaches

Zhou

et al. 2021

Front. Physiol.

View full text Add to dashboard Cite

Nausea and emesis resulting from disease or drug treatment may be associated with disrupted gastric myoelectric activity (GMA). Conventional analytical techniques can determine the relative degrees of brady-, normo-, and tachygastric power, but lose information relative to the basic slow wave shape. The aim of the present study was to investigate the application of advanced analytical techniques in the analysis of disrupted GMA recorded after administration of sulprostone, a prostaglandin E3/1 agonist, in ferrets. Ferrets were implanted with radiotelemetry devices to record GMA, blood pressure, heart rate (HR) and core body temperature 1 week before the administration of sulprostone (30 μg/kg) or vehicle (saline, 0.5 mL/kg). GMA was initially analyzed using fast Fourier transformations (FFTs) and a conventional power partitioning. Detrended fluctuation analysis (DFA) was also applied to the GMA recordings to reveal information relative to the fluctuation of signals around local trends. Sample entropy (SampEn) analysis was used for examining the regularity of signals. Conventional signal processing techniques revealed that sulprostone increased the dominant frequency (DF) of slow waves, with an increase in the percentage power of the tachygastric range and a decrease in the percentage power of the normogastric range. DFA revealed that sulprostone decreased the fluctuation function, indicative of a loss of the variability of GMA fluctuations around local trends. Sulprostone increased SampEn values, indicating a loss of regularity in the GMA data. Behaviorally, sulprostone induced emesis and caused defecation. It also increased blood pressure and elevated HR, with an associated decrease in HR variability (HRV). Further analysis of HRV revealed a decrease in both low-frequency (LF) and high-frequency (HF) components, with an overall increase in the LF/HF ratio. Sulprostone did not affect core body temperature. In conclusion, DFA and SampEn permit a detailed analysis of GMA, which is necessary to understand the action of sulprostone to modulate gastric function. The action to decrease HRV and increase the LF/HF ratio may be consistent with a shift toward sympathetic nervous system dominance, commonly seen during nausea.

show abstract

Section: Discussionmentioning

confidence: 99%

Sulprostone-Induced Gastric Dysrhythmia in the Ferret: Conventional and Advanced Analytical Approaches

Zhou

et al. 2021

Front. Physiol.

View full text Add to dashboard Cite

show abstract

“…ML-ELM differs from ELM in fundamental ways. ML-ELM is based on the ELM auto-encoder [28], and is algorithmically similar to deep learning. The ELM auto-encoder operates on the weights (w) of the hidden layers during training with unsupervised learning.…”

Section: Research Methods 21 Multilayer Extreme Learning Machinementioning

confidence: 99%

Multilayer extreme learning machine for hand movement prediction based on electroencephalography

2020

View full text Add to dashboard Cite

Brain computer interface (BCI) technology connects humans with machines via electroencephalography (EEG). The mechanism of BCI is pattern recognition, which proceeds by feature extraction and classification. Various feature extraction and classification methods can differentiate human motor movements, especially those of the hand. Combinations of these methods can greatly improve the accuracy of the results. This article explores the performances of nine feature-extraction types computed by a multilayer extreme learning machine (ML-ELM). The proposed method was tested on different numbers of EEG channels and different ML-ELM structures. Moreover, the performance of ML-ELM was compared with those of ELM, Support Vector Machine and Naive Bayes in classifying real and imaginary hand movements in offline mode. The ML-ELM with discrete wavelet transform (DWT) as feature extraction outperformed the other classification methods with highest accuracy 0.98. So, the authors also found that the structures influenced the accuracy of ML-ELM for different task, feature extraction used and channel used.

show abstract

“…MDFA was proposed by Kantelhardt et al [19] as an extension of the detrended fluctuation analysis (DFA) algorithm. Although DFA was widely used to study the monofractal scaling properties of different time series, including physiological signals like EEG [20], yet in reality, it was observed that many biological signals are not monofractal in nature, i.e. instead of using a single scaling exponent, different scaling exponents are necessary to characterise different parts of the signal.…”

Section: Introductionmentioning

confidence: 99%

Feature extraction from multifractal spectrum of electromyograms for diagnosis of neuromuscular disorders

Chatterjee

Roy

Bose³

et al. 2020

IET Science, Measurement & Technology

View full text Add to dashboard Cite

Detrended fluctuation analysis of EEG recordings for epileptic seizure detection

Cited by 13 publications

References 26 publications

Sulprostone-Induced Gastric Dysrhythmia in the Ferret: Conventional and Advanced Analytical Approaches

Sulprostone-Induced Gastric Dysrhythmia in the Ferret: Conventional and Advanced Analytical Approaches

Multilayer extreme learning machine for hand movement prediction based on electroencephalography

Feature extraction from multifractal spectrum of electromyograms for diagnosis of neuromuscular disorders

Contact Info

Product

Resources

About