A fuzzy neural network approach for automatic K-complex detection in sleep EEG signal

Ranjan, Rakesh; Arya, Rajeev; Fernandes, Steven Lawrence; Sravya, Erukonda; Jain, Vinay

doi:10.1016/j.patrec.2018.01.001

Cited by 46 publications

(26 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Table 7 represents the performance comparisons among the seven reported methods (Devuyst et al, 2010; Erdamar et al, 2012; Vu et al, 2012; Krohne et al, 2014; Zamir et al, 2015; Patti et al, 2016; Ranjan et al, 2018). All these studies used the same database as discussed in section “EEG Data Description.” According to the results in Table 7, the proposed method is the best among the seven methods.…”

Section: Resultsmentioning

confidence: 99%

“…NREM sleep can be further divided into four stages of drowsiness (S1), light sleep (S2), deep sleep (S3) and very deep sleep (S4). Recently, the NREM sleep were reduced by American academy of sleep medicine (AASM) into three stages in which S3 and S4 were combined into one stage as slow waves stages (SWS) (Rechtschaffen and Kales, 1968; Iber et al, 2007; Ranjan et al, 2018). Figure 1 shows the sleep stage signals and their characteristics (Fraiwan et al, 2012).…”

Section: Introductionmentioning

confidence: 99%

“…Traditionally, k-complexes are visually examined and marked in an all-night sleep EEG recording by one or two well-trained experts. This process is time consuming, specialist dependent, and tedious, due to the fact that there are typically 1 to 3 k-complexes per minute in stage 2 for young adults (Amzica and Steriade, 2002; Kam et al, 2004; Ghanbari and Moradi, 2017; Ranjan et al, 2018). Therefore, the auto detection of k-complexes is a very important research topic.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Detection of EEG K-Complexes Using Fractal Dimension of Time Frequency Images Technique Coupled With Undirected Graph Features

Al-Salman

Wen

2019

Front. Neuroinform.

View full text Add to dashboard Cite

K-complexes identification is a challenging task in sleep research. The detection of k-complexes in electroencephalogram (EEG) signals based on visual inspection is time consuming, prone to errors, and requires well-trained knowledge. Many existing methods for k-complexes detection rely mainly on analyzing EEG signals in time and frequency domains. In this study, an efficient method is proposed to detect k-complexes from EEG signals based on fractal dimension (FD) of time frequency (T-F) images coupled with undirected graph features. Firstly, an EEG signal is partitioned into smaller segments using a sliding window technique. Each EEG segment is passed through a spectrogram of short time Fourier transform (STFT) to obtain the T-F images. Secondly, the box counting method is applied to each T-F image to discover the FDs in EEG signals. A vector of FD features are extracted from each T-F image and then mapped into an undirected graph. The structural properties of the graphs are used as the representative features of the original EEG signals for the input of a least square support vector machine (LS-SVM) classifier. Key graphic features are extracted from the undirected graphs. The extracted graph features are forwarded to the LS-SVM for classification. To investigate the classification ability of the proposed feature extraction combined with the LS-SVM classifier, the extracted features are also forwarded to a k-means classifier for comparison. The proposed method is compared with several existing k-complexes detection methods in which the same datasets were used. The findings of this study shows that the proposed method yields better classification results than other existing methods in the literature. An average accuracy of 97% for the detection of the k-complexes is obtained using the proposed method. The proposed method could lead to an efficient tool for the scoring of automatic sleep stages which could be useful for doctors and neurologists in the diagnosis and treatment of sleep disorders and for sleep research.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Detection of EEG K-Complexes Using Fractal Dimension of Time Frequency Images Technique Coupled With Undirected Graph Features

Al-Salman

Wen

2019

Front. Neuroinform.

View full text Add to dashboard Cite

show abstract

“…Such an approach improves uncertainty of the sequence generated since it integrates both good statistical properties of Pseudo Random Number Generator based on an Elliptic Curve and Pseudo Random Number Generator based on chaotic map. [20][21][22][23][24][25][26][27][28][29][30][31][32][33][34][35][36][37][38][39] This work proposes a new Pseudo Random Number Generator. In this scheme, double rounds of diffusion and substitution operations are performed.…”

Section: Literature Survey On Pseudo Random Number Generatormentioning

confidence: 99%

Generation of pseudo random number sequence from discrete oscillating samples of equally spread objects and application for stream cipher system

Sudeepa¹,

Aithal

2019

Concurrency and Computation

View full text Add to dashboard Cite

The demand on security privileged information has widely increased due to the sensitivity of the exchanged information over public communication channels. Nowadays, almost all organizations, mainly, business, financial, and government related areas, and also other regions are computerized, and sometimes, the data will be highly confidential. Since some areas dealing with confidential data, it is very much essential to provide the security for the data to avoid unauthorized access. Multimedia data security and security related issues have attracted many researchers towards it. Cryptography is necessary to protect the confidential information transmitting over the network. The strength of the cryptographic system, especially, stream cipher, is not only depending upon its encryption/decryption algorithm but also depends upon the randomness properties of the key sequence such as length, uniformity, independence, etc. In this work, a novel method of generating the pseudo random number that is based on the discrete equally spread oscillating points viewed orthogonally as an envelope has been considered for the generation. Depending on the number of samples, it is possible to get the higher length of the sequence. The random patterns generated by the discrete points of a moving wave are used to generate non binary random numbers. These numbers are used as key in stream cipher system. These are having greater advantages like one time padding to achieve perfect security in cryptographic application. The same non binary key sequence generated is applied for the cryptographic application, and the security parameters of the result obtained from cryptographic applications are also evaluated to observe the strength of security level. KEYWORDS discrete oscillating samples, Pseudo Random Number Generator, stream cipher system INTRODUCTIONData can be hacked during transmission through network channel. Hence, it is very essential to be transmitted in a secured manner. Cryptography is one of the major techniques to ensure security of data. Cryptography is a technique of transforming an original data into a particular form so that only those who know the key can read and process it. In cryptosystem, original message or data referred to as plain text. This could be transformed into non readable or scrambled form referred to as cipher text. This is done based on encryption algorithm. The encryption algorithm uses a key for changing the plain text into a cipher text. The cipher text can be recovered into its original form by an algorithm using a key known as decryption. The main goal of cryptography is data privacy (confidentiality), data authenticity, and data integrity (it cannot be modified in any way) in the digital world. Based on the type of key used for encryption/decryption, cryptography systems are categorized as symmetric key system and asymmetric key system. 1 The symmetric system can be categorized as stream and block cipher.Concurrency Computat Pract Exper. 2020;32:e5181. wileyonlinelibrary.com/journal/cpe Decryption Algor...

show abstract

“…It has also led to the development of data mining methods that discover potential patterns in the data, aiming at characterization of dynamic EEG behaviours. Representative examples include early detection of epileptic seizure [1][2][3], sleep process monitoring [4][5][6][7], and many other neurological disordering related health assessment and surgery problems [8][9][10].…”

Section: Introductionmentioning

confidence: 99%

Anomaly Detection in EEG Signals: A Case Study on Similarity Measure

Chen

Xie

et al. 2020

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Motivation. Anomaly EEG detection is a long-standing problem in analysis of EEG signals. The basic premise of this problem is consideration of the similarity between two nonstationary EEG recordings. A well-established scheme is based on sequence matching, typically including three steps: feature extraction, similarity measure, and decision-making. Current approaches mainly focus on EEG feature extraction and decision-making, and few of them involve the similarity measure/quantification. Generally, to design an appropriate similarity metric, that is compatible with the considered problem/data, is also an important issue in the design of such detection systems. It is however impossible to directly apply those existing metrics to anomaly EEG detection without any consideration of domain specificity. Methodology. The main objective of this work is to investigate the impacts of different similarity metrics on anomaly EEG detection. A few metrics that are potentially available for the EEG analysis have been collected from other areas by a careful review of related works. The so-called power spectrum is extracted as features of EEG signals, and a null hypothesis testing is employed to make the final decision. Two indicators have been used to evaluate the detection performance. One is to reflect the level of measured similarity between two compared EEG signals, and the other is to quantify the detection accuracy. Results. Experiments were conducted on two data sets, respectively. The results demonstrate the positive impacts of different similarity metrics on anomaly EEG detection. The Hellinger distance (HD) and Bhattacharyya distance (BD) metrics show excellent performances: an accuracy of 0.9167 for our data set and an accuracy of 0.9667 for the Bern-Barcelona EEG data set. Both of HD and BD metrics are constructed based on the Bhattacharyya coefficient, implying the priority of the Bhattacharyya coefficient when dealing with the highly noisy EEG signals. In future work, we will exploit an integrated metric that combines HD and BD for the similarity measure of EEG signals.

show abstract

A fuzzy neural network approach for automatic K-complex detection in sleep EEG signal

Cited by 46 publications

References 27 publications

Detection of EEG K-Complexes Using Fractal Dimension of Time Frequency Images Technique Coupled With Undirected Graph Features

Detection of EEG K-Complexes Using Fractal Dimension of Time Frequency Images Technique Coupled With Undirected Graph Features

Generation of pseudo random number sequence from discrete oscillating samples of equally spread objects and application for stream cipher system

Anomaly Detection in EEG Signals: A Case Study on Similarity Measure

Contact Info

Product

Resources

About