Statistical features extraction for multivariate pattern analysis in meditation EEG using PCA
29 May 2016-pp 1-4
TL;DR: A clustering paradigm that used for the pattern analysis between meditators and non-meditators is presented, and a few higher order statistical measures such as variance, kurtosis, relative band energy, Shannon entropy, and Renyi entropy obtained from the data segments.
Abstract: This work was undertaken to study the specific statistical features of EEG data collected during meditation (Kriya Yoga) and normal conditions. The meditation practice changes the attentional allocation in the human brain to visualize this; statistical features are carefully calculated from different wavelet coefficients to categorize two diverse groups (i.e. Meditators and Non-Meditators). The entire time series of EEG data divided into overlapping segments, and statistical parameters calculated for each of these segments. Instead of using all the data points, we used only a few higher order statistical measures such as variance, kurtosis, relative band energy, Shannon entropy, and Renyi entropy obtained from the data segments. A standard clustering technique, i.e. Principal Component Analysis (PCA) used to get the distinct pattern from the statistical features in EEG. In this paper, we presented a clustering paradigm that used for the pattern analysis between meditators and non-meditators. We measured the EEG signal using 64 channels, with some peripheral physiological measures. 23 participants with varying experience in meditation practice and ten non-meditators (control group) are considered to visualize underlying clusters within the statistical features.
Citations
More filters
TL;DR: A survey of the pertinent scientific literature from 2015 to 2020 presents trends and a comparative analysis of algorithm applications in new implementations from a computer science perspective and provides insights for future developments.
Abstract: Affecting computing is an artificial intelligence area of study that recognizes, interprets, processes, and simulates human affects. The user's emotional states can be sensed through electroencephalography (EEG)-based Brain Computer Interfaces (BCI) devices. Research in emotion recognition using these tools is a rapidly growing field with multiple inter-disciplinary applications. This article performs a survey of the pertinent scientific literature from 2015 to 2020. It presents trends and a comparative analysis of algorithm applications in new implementations from a computer science perspective. Our survey gives an overview of datasets, emotion elicitation methods, feature extraction and selection, classification algorithms, and performance evaluation. Lastly, we provide insights for future developments.
131 citations
Cites background from "Statistical features extraction for..."
...Hjorth Features [52,59,60] These are statistical indicators whose parameters are normalized slope descriptors....
[...]
...Features can be computed in the domain of (1) time, (2) frequency, (3) time-frequency, or (4) space, as shown in Table 4 [31,38,39]....
[...]
...%) that are used to extract signal features automatically 24% 38% 21% 7% 5% 5% Features in the time-domain Features in the frequency domain Features in time-frequency domain Assymetry measures Spatial information Raw data Figure 8....
[...]
...Features with non-redundant information combined from different domains yield better classification results....
[...]
...%) that are used to extract signal features automatically 24% 38% 21% 7% 5% 5% Features in the time-domain Features in the frequency domain Features in time-frequency domain Assymetry measures Spatial information Raw data i re 9. t f t s f l rit s f r feat re extraction fro Table 8....
[...]
TL;DR: In this article , a review of the EEG-based emotion recognition methods is presented, including feature extraction, feature selection/reduction, machine learning methods (e.g., k-nearest neighbor), support vector machine, decision tree, artificial neural network, random forest, and naive Bayes) and deep learning methods.
Abstract: Abstract Affective computing, a subcategory of artificial intelligence, detects, processes, interprets, and mimics human emotions. Thanks to the continued advancement of portable non-invasive human sensor technologies, like brain–computer interfaces (BCI), emotion recognition has piqued the interest of academics from a variety of domains. Facial expressions, speech, behavior (gesture/posture), and physiological signals can all be used to identify human emotions. However, the first three may be ineffectual because people may hide their true emotions consciously or unconsciously (so-called social masking). Physiological signals can provide more accurate and objective emotion recognition. Electroencephalogram (EEG) signals respond in real time and are more sensitive to changes in affective states than peripheral neurophysiological signals. Thus, EEG signals can reveal important features of emotional states. Recently, several EEG-based BCI emotion recognition techniques have been developed. In addition, rapid advances in machine and deep learning have enabled machines or computers to understand, recognize, and analyze emotions. This study reviews emotion recognition methods that rely on multi-channel EEG signal-based BCIs and provides an overview of what has been accomplished in this area. It also provides an overview of the datasets and methods used to elicit emotional states. According to the usual emotional recognition pathway, we review various EEG feature extraction, feature selection/reduction, machine learning methods (e.g., k-nearest neighbor), support vector machine, decision tree, artificial neural network, random forest, and naive Bayes) and deep learning methods (e.g., convolutional and recurrent neural networks with long short term memory). In addition, EEG rhythms that are strongly linked to emotions as well as the relationship between distinct brain areas and emotions are discussed. We also discuss several human emotion recognition studies, published between 2015 and 2021, that use EEG data and compare different machine and deep learning algorithms. Finally, this review suggests several challenges and future research directions in the recognition and classification of human emotional states using EEG.
45 citations
01 May 2018
TL;DR: The satisfactory parametric measures of these methods, namely percent-root-mean square distortion, peak signal-to-noise ratio, root-mean-square error, and cross correlation, show their superiority over the state-of-the-art compression methods.
Abstract: The difficulty associated with processing and understanding the high dimensionality of electroencephalogram (EEG) data requires developing efficient and robust compression algorithms. In this paper, different lossless compression techniques of single and multichannel EEG data, including Huffman coding, arithmetic coding, Markov predictor, linear predictor, context-based error modeling, multivariate autoregression (MVAR), and a low complexity bivariate model have been examined and their performances have been compared. Furthermore, a high compression algorithm named general MVAR and a modified context-based error modeling for multichannel EEG have been proposed. The resulting compression algorithm produces a higher relative compression ratio of 70.64% on average compared with the existing methods, and in some cases, it goes up to 83.06%. The proposed methods are designed to compress a large amount of multichannel EEG data efficiently so that the data storage and transmission bandwidth can be effectively used. These methods have been validated using several experimental multichannel EEG recordings of different subjects and publicly available standard databases. The satisfactory parametric measures of these methods, namely percent-root-mean square distortion, peak signal-to-noise ratio, root-mean-square error, and cross correlation, show their superiority over the state-of-the-art compression methods.
26 citations
Cites methods from "Statistical features extraction for..."
...The EEG data were acquired while the subjects were performing short guided KriyaYoga meditation [41], [42]....
[...]
TL;DR: In this paper, a review of interpretation methods of Brain signals (EEG)) EEG during yoga and meditation was provided. But, the focus of the review was on the machine learning strategies applied for the interpretation of brain waves concerning physical and mental health.
18 citations
TL;DR: The experimental results indicated that the proposed method achieved 87.2% accuracy for classification and could be further extended to construct an accurate classification system for detection of meditators and non-meditators.
15 citations
References
More filters
TL;DR: A double-loop Expectation-Maximization (EM) algorithm has been introduced to the ME network structure for detection of epileptic seizure and the results confirmed that the proposed Me network structure has some potential in detecting epileptic seizures.
Abstract: Mixture of experts (ME) is modular neural network architecture for supervised learning. A double-loop Expectation-Maximization (EM) algorithm has been introduced to the ME network structure for detection of epileptic seizure. The detection of epileptiform discharges in the EEG is an important component in the diagnosis of epilepsy. EEG signals were decomposed into the frequency sub-bands using discrete wavelet transform (DWT). Then these sub-band frequencies were used as an input to a ME network with two discrete outputs: normal and epileptic. In order to improve accuracy, the outputs of expert networks were combined according to a set of local weights called the ''gating function''. The invariant transformations of the ME probability density functions include the permutations of the expert labels and the translations of the parameters in the gating functions. The performance of the proposed model was evaluated in terms of classification accuracies and the results confirmed that the proposed ME network structure has some potential in detecting epileptic seizures. The ME network structure achieved accuracy rates which were higher than that of the stand-alone neural network model.
1,053 citations
TL;DR: In this work, a versatile signal processing and analysis framework for Electroencephalogram (EEG) was proposed and a set of statistical features was extracted from the sub-bands to represent the distribution of wavelet coefficients.
Abstract: In this work, we proposed a versatile signal processing and analysis framework for Electroencephalogram (EEG). Within this framework the signals were decomposed into the frequency sub-bands using DWT and a set of statistical features was extracted from the sub-bands to represent the distribution of wavelet coefficients. Principal components analysis (PCA), independent components analysis (ICA) and linear discriminant analysis (LDA) is used to reduce the dimension of data. Then these features were used as an input to a support vector machine (SVM) with two discrete outputs: epileptic seizure or not. The performance of classification process due to different methods is presented and compared to show the excellent of classification process. These findings are presented as an example of a method for training, and testing a seizure prediction method on data from individual petit mal epileptic patients. Given the heterogeneity of epilepsy, it is likely that methods of this type will be required to configure intelligent devices for treating epilepsy to each individual's neurophysiology prior to clinical operation.
1,010 citations
01 Mar 2007
TL;DR: It is demonstrated that the wavelet coefficients and the Lyapunov exponents are the features which well represent the EEG signals and the multiclass SVM and PNN trained on these features achieved high classification accuracies.
Abstract: In this paper, we proposed the multiclass support vector machine (SVM) with the error-correcting output codes for the multiclass electroencephalogram (EEG) signals classification problem. The probabilistic neural network (PNN) and multilayer perceptron neural network were also tested and benchmarked for their performance on the classification of the EEG signals. Decision making was performed in two stages: feature extraction by computing the wavelet coefficients and the Lyapunov exponents and classification using the classifiers trained on the extracted features. The purpose was to determine an optimum classification scheme for this problem and also to infer clues about the extracted features. Our research demonstrated that the wavelet coefficients and the Lyapunov exponents are the features which well represent the EEG signals and the multiclass SVM and PNN trained on these features achieved high classification accuracies
308 citations
"Statistical features extraction for..." refers background in this paper
...All these unwanted signal components must be removed with proper preprocessing techniques [6]....
[...]
03 Oct 2006
TL;DR: The application of neural network models for classification of electroencephalogram (EEG) signals was described and it was confirmed that the proposed scheme has potential in classifying the EEG signals.
Abstract: Decision Support Systems have been utilised since 1960, providing physicians with fast and accurate means towards more accurate diagnoses and increased tolerance when handling missing or incomplete data. This paper describes the application of neural network models for classification of electroencephalogram (EEG) signals. Decision making was performed in two stages: initially, a feature extraction scheme using the wavelet transform (WT) has been applied and then a learning-based algorithm classifier performed the classification. The performance of the neural model was evaluated in terms of training performance and classification accuracies and the results confirmed that the proposed scheme has potential in classifying the EEG signals.
274 citations
TL;DR: It was found that Coiflets 1 is the most suitable candidate among the wavelet families considered in this study for accurate classification of the EEG signals.
263 citations