SVM classification of EEG signal to analyze the effect of OM Mantra meditation on the brain
01 Dec 2019-
TL;DR: Results show the significant changes in the delta band which represent the brain in deep sleep which gives the experience of deep sleep in Om mantra meditation.
Abstract: Meditation can significantly contribute to improving physical and mental health in modern stressful life. "OM" mantra is very easy to practice for meditation .This study is undertaken to classify the EEG band to observe abrupt changes in band as an effect of Om mantra meditation. Twenty-three naive meditators were experimented to chant OM mantra for 30 min and EEG signal recorded before and after meditation. The stationary wavelet transform is used to exact five bands from the EEG. The different statistical features were calculated. SVM classifier with Radial Basis Kernel is employed to classify the band. Results show the significant changes in the delta band which represent the brain in deep sleep. Thus OM meditation gives the experience of deep sleep. Thus study can be helpful to give new direction towards the meditation.
Citations
More filters
TL;DR: This study proposed a signal preprocessing and feature extraction method for EEG classification that consists of removing the artifacts by using Discrete Fourier Transform (DFT) as an ideal filter for specific frequencies.
Abstract: A crucial part of the brain-computer interface is a classification of electroencephalography (EEG) motor tasks. Artifacts such as eye and muscle movements corrupt EEG signal and reduce the classification performance. Many studies try to extract not redundant and discriminative features from EEG signals. Therefore, this study proposed a signal preprocessing and feature extraction method for EEG classification. It consists of removing the artifacts by using discrete fourier transform (DFT) as an ideal filter for specific frequencies. It also cross-correlates the EEG channels with the effective channels to emphases the EEG motor signals. Then the resultant from cross correlation are statistical calculated to extract feature for classifying a left and right finger movements using support vector machine (SVM). The genetic algorithm was applied to find the discriminative frequencies of DFT for the two EEG classes signal. The performance of the proposed method was determined by finger movement classification of 13 subjects and the experiments show that the average accuracy is above 93 percent.
24 citations
TL;DR: There is no versatile device suitable for all purposes in the field of wellbeing support, and the WellAff system able to recognize affective states for wellbeing support is proposed.
Abstract: Wearables equipped with pervasive sensors enable us to monitor physiological and behavioral signals in our everyday life. We propose the WellAff system able to recognize affective states for wellbeing support. It also includes health care scenarios, in particular patients with chronic kidney disease (CKD) suffering from bipolar disorders. For the need of a large-scale field study, we revised over 50 off-the-shelf devices in terms of usefulness for emotion, stress, meditation, sleep, and physical activity recognition and analysis. Their usability directly comes from the types of sensors they possess as well as the quality and availability of raw signals. We found there is no versatile device suitable for all purposes. Using Empatica E4 and Samsung Galaxy Watch, we have recorded physiological signals from 11 participants over many weeks. The gathered data enabled us to train a classifier that accurately recognizes strong affective states.
15 citations
Posted Content•
30 Apr 2020
TL;DR: There is no versatile device suitable for all purposes in recognition and analysis of emotion, stress, meditation, sleep, and physical activity in off-the-shelf devices revised.
Abstract: Wearables equipped with pervasive sensors enable us to monitor physiological and behavioral signals. In this study, we revised 55 off-the-shelf devices in recognition and analysis of emotion, stress, meditation, sleep, and physical activity, especially in field studies. Their usability directly comes from the types of sensors they possess as well as the quality and availability of raw signals. We found there is no versatile device suitable for all purposes. Empatica E4 and Microsoft Band 2 are good at emotion, stress, and together with Oura Ring at sleep research. Apple, Samsung, Garmin, and Fossil smart watches are proper in activity examination, while Muse and DREEM EEG headbands are suitable for meditation.
14 citations
TL;DR: The Objected-Oriented Bayesian Network (OOBN) application for risk assessment of the MOB scenario is presented, and the OOBN model is developed to probabilistically capture the key accident influencing factors in fragmented structures.
12 citations
07 Dec 2020
TL;DR: In this article, the WellAff system was proposed to recognize affective states for wellbeing support in patients suffering from bipolar disorder, in particular patients with chronic kidney disease and bipolar disorder.
Abstract: Wearables equipped with pervasive sensors enable us to monitor physiological and behavioral signals in our everyday life. We propose the WellAff system able to recognize affective states for wellbeing support. It also includes health care scenarios, in particular patients with chronic kidney disease suffering from bipolar disorders. For the need of a large-scale field study, we revised over 50 off-the-shelf devices in terms of usefulness for emotion, stress, meditation, sleep, and physical activity recognition and analysis. Their usability directly comes from the types of sensors they possess as well as the quality and availability of raw signals. We found there is no versatile device suitable for all purposes. Using Empatica E4 and Samsung Galaxy Watch, we have recorded physiological signals from 11 participants over many weeks. The gathered data enabled us to train a classifier that accurately recognizes strong affective states.
8 citations
References
More filters
TL;DR: In this paper, the effect of prayer and meditation on galvanic skin response (GSR) was investigated and the results revealed a significant increase in GSR values as an effect of meditation and prayer.
Abstract: The research was conducted with the purpose to study the effect of prayer and meditation on galvanic skin response (GSR). It was hypothesized that there was a significant positive effect of prayer and meditation (Om chanting) on galvanic skin response (GSR). The sample consisted of 20 normal, healthy female participants through purposive sampling. The age group of the sample was 18 to 24 years (Mean= 18.7, SD= 1.55). Gender was female and minimum education was graduation. The daily practice time of prayer and meditation session was 30 minutes for one month. Pre- Post data were recorded before and after intervention of prayer and meditation session by using single group pre-post research design. Recordings of galvanic skin response (GSR) were made on a computerized polygraph (Model Physiopac, PP 4, Medicaid Systems, Chandigarh, India) test. The results revealed a significant increase in GSR values as an effect of prayer and meditation which suggested the psychophysiological relaxation. Practicing prayer and meditation increases the galvanic skin response and hence decreases the stress level of the individual. Language: English
19 citations
01 Nov 2016
TL;DR: In this work, statistical features are used in classification of these two states along with Support Vector Machine (SVM) and k-Nearest Neighbour(k-NN) classifiers and it was found that the combination of kurtosis, IQR and MAD with k-NN classifier gave the mean accuracy of 77.92%.
Abstract: Electroencephalographic (EEG) patterns are electrical signals generated in the brain indicating brain functioning. Due to its non-invasive nature, it has been used in applications ranging from disorder detection, sleep analysis to Brain Machine Interface. A baseline state is required in all these applications to compare the required state with a reference state. In EEG analysis, Eyes Open (EO) and Eyes Closed (EC) relaxed states are the baselines used. The choice of baseline is important especially in Brain Machine Interface. Thus the system should be able to distinguish between these two states and hence the need for automated classification of EEG Baseline States. In the proposed approach, statistical features are used in classification of these two states along with Support Vector Machine (SVM) and k-Nearest Neighbour(k-NN) classifiers. Thirteen different statistical features are considered and it was found that the combination of kurtosis, IQR and MAD with k-NN classifier (k=7) gave the mean accuracy of 77.92%. The fact that kurtosis, IQR and MAD perform better implies that the underlying distributions of the two classes have significant difference.
14 citations
"SVM classification of EEG signal to..." refers methods in this paper
...In this work, 10 features were extracted for data analysis such as Mean, Standard deviation(STD), Variance, Kurtosis, and the electrical feature such as Zero crossing rate(ZCR), Interquartile range (IQR), Hurst exponent(Hurst), and Band power [24-29]....
[...]
01 Aug 2017
TL;DR: An automated diagnosis method using ANN was designed to classify Epilepsy from EEG based on different stages of EEG signal levels (Ictal, Inter-ictal, Pre-ictsal), which provides an accuracy of 96.9% and to reduce the dimensionality of dataset feature ranking was implemented.
Abstract: Epilepsy is one of the most common disorders in a neurological system that affects almost 50 million population of all ages worldwide. Epilepsy denotes “seizure disorders” which is characterized by unpredictable chronic seizures. Epilepsy is a spectrum condition with a broad range of seizure types varying from person-to-person & it is commonly diagnosed by EEG, Magnetic Resonance Imaging, and fMRI and also by using Magnetoencephalography. The traditional method of analyzing EEG is based on using strip charts to visually analyze the EEG activity which is a laborious and time-consuming task. Therefore in this work, an automated diagnosis method using ANN was designed to classify Epilepsy from EEG based on different stages of EEG signal levels (Ictal, Inter-ictal, Pre-ictal). After preprocessing the signal, features like mean, variance, skewness, kurtosis, standard deviation are extracted. Then for accuracy in classification & to reduce the dimensionality of dataset feature ranking was implemented. Finally, neural networks was implemented to classify Epilepsy based on risk levels & this method of classification provides an accuracy of 96.9%
11 citations
"SVM classification of EEG signal to..." refers methods in this paper
...In this work, 10 features were extracted for data analysis such as Mean, Standard deviation(STD), Variance, Kurtosis, and the electrical feature such as Zero crossing rate(ZCR), Interquartile range (IQR), Hurst exponent(Hurst), and Band power [24-29]....
[...]
TL;DR: The cortical activation associated with listening to sound “OM” in contrast to similar non-meaningful sound and listening to a meaningful Hindi word has been investigated using functional magnetic resonance imaging.
Abstract: The sound "OM" is believed to bring mental peace and calm. The cortical activation associated with listening to sound "OM" in contrast to similar non-meaningful sound (TOM) and listening to a meaningful Hindi word (AAM) has been investigated using functional magnetic resonance imaging (MRI). The behaviour interleaved gradient technique was employed in order to avoid interference of scanner noise. The results reveal that listening to "OM" sound in contrast to the meaningful Hindi word condition activates areas of bilateral cerebellum, left middle frontal gyrus (dorsolateral middle frontal/BA 9), right precuneus (BA 5) and right supramarginal gyrus (SMG). Listening to "OM" sound in contrast to "non-meaningful" sound condition leads to cortical activation in bilateral middle frontal (BA9), right middle temporal (BA37), right angular gyrus (BA 40), right SMG and right superior middle frontal gyrus (BA 8). The conjunction analysis reveals that the common neural regions activated in listening to "OM" sound during both conditions are middle frontal (left dorsolateral middle frontal cortex) and right SMG. The results correspond to the fact that listening to "OM" sound recruits neural systems implicated in emotional empathy.
8 citations
"SVM classification of EEG signal to..." refers background in this paper
...Many researchers have found the effect of OM mantra meditation on human beings using an auditory middle latency evoked potentials [5-6], skin resistance level, heart rate, respiratory rate [7-8 ], Functional magnetic resonance imaging [9-12]....
[...]
25 Sep 2014
TL;DR: In this article, a correlation analysis between the proposed EEG sub-band spectral centroid amplitude with the established band power features was performed for each scalp location to ascertain its relationship, and it was shown that the EEG subband spectral centerroid amplitude is highly correlated with the band power feature for all scalp locations.
Abstract: The paper elaborates on the correlation analysis between the proposed EEG sub-band spectral centroid amplitude with the established band power features. The study involves recording of resting EEG from 40 healthy university students. Initially, the EEG is pre-processed for noise removal and filtered into delta, theta, alpha and beta waves using band-pass filters. Next, the sub-band power spectral densities are estimated via Welch method. Subsequently, spectral centroid amplitude and band power features are then computed from the power spectral density of the respective sub-bands. Correlation analysis between the two features is performed for each scalp location to ascertain its relationship. Findings have revealed that the EEG sub-band spectral centroid amplitude is highly correlated with the band power features for all scalp locations.
7 citations
"SVM classification of EEG signal to..." refers methods in this paper
...In this work, 10 features were extracted for data analysis such as Mean, Standard deviation(STD), Variance, Kurtosis, and the electrical feature such as Zero crossing rate(ZCR), Interquartile range (IQR), Hurst exponent(Hurst), and Band power [24-29]....
[...]