scholarly journals Automatic Clustering of Students by Level of Situational Interest Based on Their EEG Features

2021 ◽  
Vol 12 (1) ◽  
pp. 389
Author(s):  
Ernee Sazlinayati Othman ◽  
Ibrahima Faye ◽  
Aarij Mahmood Hussaan

The usage of physiological measures in detecting student’s interest is often said to improve the weakness of psychological measures by decreasing the susceptibility of subjective bias. The existing methods, especially EEG-based, use classification, which needs a predefined class and complex computational to analyze. However, the predefined classes are mostly based on subjective measurement (e.g., questionnaires). This work proposed a new scheme to automatically cluster the students by the level of situational interest (SI) during learning-based lessons on their electroencephalography (EEG) features. The formed clusters are then used as ground truth for classification purposes. A simultaneous recording of EEG was performed on 30 students while attending a lecture in a real classroom. The frontal mean delta and alpha power as well as the frontal alpha asymmetry metric served as the input for k-means and Density-Based Spatial Clustering of Applications with Noise (DBSCAN) clustering algorithms. Using the collected data, 29 models were trained within nine domain classifiers, then the classifiers with the highest performance were selected. We validated all the models through 10-fold cross-validation. The high SI group was clustered to students having lower frontal mean delta and alpha power together with negative Frontal Alpha Asymmetry (FAA). It was found that k-means performed better by giving the maximum performance assessment parameters of 100% in clustering the students into three groups: high SI, medium SI and low SI. The findings show that the DBSCAN had reduced the performance to cluster dataset without the outlier. The findings of this study give a promising option to cluster the students by their SI level, as well as address the drawbacks of the existing methods, which use subjective measures.

2020 ◽  
Author(s):  
Aleksandra Kołodziej ◽  
Mikołaj Magnuski ◽  
Anastasia Ruban ◽  
Aneta Brzezicka

AbstractFor decades, the frontal alpha asymmetry (FAA) - a disproportion in EEG alpha oscillations power between right and left frontal channels - has been one of the most popular measures of depressive disorders (DD) in electrophysiology studies. Patients with DD often manifest a left-sided FAA: relatively higher alpha power in the left versus right frontal lobe. Recently, however, multiple studies failed to confirm this effect, questioning its reproducibility. Our purpose is to thoroughly test the validity of FAA in depression by conducting a multiverse analysis - running many related analyses and testing the sensitivity of the effect to changes in the analytical approach - on data from three independent studies. Only two of the 81 analyses revealed significant results. We conclude the paper by discussing theoretical assumptions underlying the FAA and suggest a list of guidelines for improving and expanding the EEG data analysis in future FAA studies.


PRILOZI ◽  
2015 ◽  
Vol 36 (2) ◽  
pp. 157-177 ◽  
Author(s):  
Aneta Demerdzieva ◽  
Nada Pop-Jordanova

Abstract Frontal alpha asymmetry (the relative difference in power between two signals in different hemispheres) has been suggested as biomarker for anxiety. The goal of this study was to evaluate alpha asymmetry in the frontal region for young people (7-18 years) with generalized anxiety disorder, diagnosed according to two statistic manuals (DMS-IV-R and ICD-10), the medical history and the neuropsychological assessment. The QEEG recording and analysis of the obtained results from alpha spectra power and log of alpha spectra power are made in four conditions (eyes open, eyes closed, VCPT and ACPT). The obtained results for alpha power in general showed higher cortical activity in the right hemisphere, associated with negative emotions. The calculated alpha asymmetry separate for eyes open, eyes closed, VCPT and ACPT conditions showed the right activation in all four conditions. In addition, the right frontal asymmetry was specific for the Fp1-Fp2 region, while a greater left frontal activation was recorded for the F7-F8 region. The log of alpha power in general was additionally analyzed. The calculated asymmetry score in general (in a way that the left log transformed score was subtracted from the right) confirmed a greater right activation. Testing the power of the whole alpha band (μV2) in general, for all four conditions and for frontal region confirmed the right alpha asymmetries in all participants. The right alpha asymmetry in the frontal region was specific only for the Fp1-Fp2 region (frontopolar region). The only greater left frontal activation was registered between the F7-F8 region. Our findings are supported by many other studies using specific localization methods like fMRI or LORETA source localization.


2015 ◽  
Vol 2015 ◽  
pp. 1-11 ◽  
Author(s):  
Mei-chun Cheung ◽  
Agnes S. Chan ◽  
Joanne Yip

To examine the electrophysiological effects of microcurrent stimulation at the Shenmen acupoint, 40 healthy normal subjects were randomly assigned to a placebo group (sham stimulation) and an experimental group (bilateral electrocutaneous stimulation at the Shenmen). The following two electroencephalographic indicators were used to measure brain activity. (1) Arousal level was measured with reference to log-transformed absolute alpha power and power source and analyzed using low-resolution electromagnetic tomography and (2) frontal alpha asymmetry was used as an indicator of mood. After real stimulation for 10 minutes, absolute alpha power was globally reduced in the experimental group, particularly in the anterior and centrotemporal regions of the brain. This indicates a decline in the brain activity associated with arousal. Moreover, the reduction was more prominent in the left frontal region, as compared to the right frontal region, resulting in significant increase from negative to positive frontal alpha asymmetry scores and reflecting an increase in the brain activity associated with enhanced mood. However, the placebo group exhibited no significant changes in two indicators after sham stimulation. This study provides initial electrophysiological evidence of changes in brain activity associated with reduced arousal (and thus greater sleepiness) and enhanced mood after microcurrent stimulation at the Shenmen acupoint.


2019 ◽  
Vol 8 (12) ◽  
pp. 546 ◽  
Author(s):  
Merve Keskin ◽  
Kristien Ooms ◽  
Ahmet Dogru ◽  
Philippe De Maeyer

The aim of this research is to evaluate the use of ET and EEG for studying the cognitive processes of expert and novice map users and to explore these processes by comparing two types of spatial memory experiments through cognitive load measurements. The first experiment consisted of single trials and participants were instructed to study a map stimulus without any time constraints in order to draw a sketch map afterwards. According to the ET metrics (i.e., average fixation duration and the number of fixations per second), no statistically significant differences emerged between experts and novices. A similar result was also obtained with EEG Frontal Alpha Asymmetry calculations. On the contrary, in terms of alpha power across all electrodes, novices exhibited significantly lower alpha power, indicating a higher cognitive load. In the second experiment, a larger number of stimuli were used to study the effect of task difficulty. The same ET metrics used in the first experiment indicated that the difference between these user groups was not statistically significant. The cognitive load was also extracted using EEG event-related spectral power changes at alpha and theta frequency bands. Preliminary data exploration mostly suggested an increase in theta power and a decrease in alpha power.


2019 ◽  
Vol 3 (s1) ◽  
pp. 106-106
Author(s):  
Brandi C Fink

OBJECTIVES/SPECIFIC AIMS: The current study is the first investigation of frontal alpha asymmetry in distressed violent (DV) and distressed nonviolent (DNV) partners during a placebo-controlled alcohol administration and emotion-regulation study. Because this is the first study of the pharmacological effects of alcohol on FAA, the first portion of the study was conducted to characterize alcohol effects in DV and DNV partners during the baseline condition. The subsequent portions of the study were conducted to characterize the effects of alcohol and evocative stimuli on FAA in DV and DNV partners. We hypothesized that DV partners would demonstrated greater left frontal alpha asymmetry when intoxicated and viewing evocative partner stimuli than DNV partners. Lastly, we attempted to replicate previous research that has found associations between baseline measures of FAA and the State-Trait Anger Expression Inventory – 2 (Spielberger, 1999) subscales of Trait Anger, Anger Expression-Out, Anger Expression-In, Anger Control-Out, Anger Control-In (Hewig, Hagemann, Seifert, Naumann, & Bartussek, 2004). METHODS/STUDY POPULATION: Partners in the present study were drawn from a larger study investigating over-arousal as a mechanism between alcohol use and intimate partner violence (AA022367). Couples were recruited from the community via radio, television and newspaper advertisements, and eligibility screening occurred at the couple level. Participants included in the present analysis were 23 DV partners (12 female, 11 male), and 15 DNV partners (7 female, 9 male). The mean age of the sample was 32 (SD 4.8 years, range 23-40 years). Data from two DV partners were not included in the analyses of the FAA in the emotion-regulation tasks due to movement artifacts during the alcohol condition leaving too little data for analysis. RESULTS/ANTICIPATED RESULTS: The expected beverage by couple type interaction did not reach significance [F (1, 36) = 3.93, p = .055], but the between-subjects effects of couple type revealed a significant difference [F (1, 36) = 4.425, p = .042]. Contrary to our hypothesis, however, these results suggest that under conditions of alcohol, DV partners evidenced significantly greater relative right frontal alpha power asymmetry whereas DNV partners evidenced greater relative left frontal alpha power asymmetry. Although there was no significant between-subjects effect, there was a nearly significant interaction between beverage type and emotion regulation condition [F = (1, 36) = 4.032, p = .052] and a significant main effect of emotion regulation condition [F (1, 36) = 7.579, p = .009]. It appears that asking the participants to “not react” to their partners’ evocative stimuli caused significantly greater right frontal alpha asymmetry. Because intimate partner violence is best understood in the context of conflict between two partners, we also examined partner-reported experiences of anger as predictors of DV participant’s FAA. The model as a whole predicted 67.4% of the variance in DV partner FAA, R squared change =.674, F Change (5, 15) = 6.21, p = .003. Three anger experience scales were statistically significant. The partner Anger Control-Out (B = -1.23, p =.001) scale recorded a higher standardized beta value and accounted for 40% of the variance in this model. Anger Control-In (B = .63, p = .022) accounted for 14% of the variance in the model, and Anger Expression-Out scale (B = .57, p = .024) accounted for 13.7% of the variance in the model. DISCUSSION/SIGNIFICANCE OF IMPACT: The current study is the first pharmacological study of the effects of alcohol on frontal alpha asymmetry in distressed violent and distressed nonviolent partners. Contrary to our hypothesis, under acute alcohol intoxication during the baseline condition, DV partners exhibited significantly greater relative right FAA compared to DNV partners who exhibited significantly greater relative left FAA. Because intimate partner violence is best understood in the context of couple conflict, we examined the ability of partners’ anger experiences to predict DV and DNV partners’ FAA, and a very interesting pattern emerged among our DV participants and their partners. The anger experiences of our DV participants’ partners accounted for 67% of the variance in the FAA of our DV participants when they were intoxicated and viewing evocative stimuli.


2019 ◽  
Vol 37 (2) ◽  
pp. 225-239 ◽  
Author(s):  
Hongqi Han ◽  
Yongsheng Yu ◽  
Lijun Wang ◽  
Xiaorui Zhai ◽  
Yaxin Ran ◽  
...  

PurposeThe aim of this study is to present a novel approach based on semantic fingerprinting and a clustering algorithm called density-based spatial clustering of applications with noise (DBSCAN), which can be used to convert investor records into 128-bit semantic fingerprints. Inventor disambiguation is a method used to discover a unique set of underlying inventors and map a set of patents to their corresponding inventors. Resolving the ambiguities between inventors is necessary to improve the quality of the patent database and to ensure accurate entity-level analysis. Most existing methods are based on machine learning and, while they often show good performance, this comes at the cost of time, computational power and storage space.Design/methodology/approachUsing DBSCAN, the meta and textual data in inventor records are converted into 128-bit semantic fingerprints. However, rather than using a string comparison or cosine similarity to calculate the distance between pair-wise fingerprint records, a binary number comparison function was used in DBSCAN. DBSCAN then clusters the inventor records based on this distance to disambiguate inventor names.FindingsExperiments conducted on the PatentsView campaign database of the United States Patent and Trademark Office show that this method disambiguates inventor names with recall greater than 99 per cent in less time and with substantially smaller storage requirement.Research limitations/implicationsA better semantic fingerprint algorithm and a better distance function may improve precision. Setting of different clustering parameters for each block or other clustering algorithms will be considered to improve the accuracy of the disambiguation results even further.Originality/valueCompared with the existing methods, the proposed method does not rely on feature selection and complex feature comparison computation. Most importantly, running time and storage requirements are drastically reduced.


2018 ◽  
Author(s):  
Pilleriin Sikka ◽  
antti revonsuo ◽  
Valdas Noreika ◽  
Katja Valli

Affective experiences are central not only to our waking life but also to rapid eye movement (REM) sleep dreams. While the neural correlates of REM sleep are well documented, we know little about the neural correlates of dream affect. Frontal alpha asymmetry (FAA) is considered a marker of affective states and traits as well as affect regulation in the waking state. Here, we explored whether FAA during REM sleep and during evening resting wakefulness is related to affective experiences in REM sleep dreams. Electroencephalography (EEG) recordings were obtained from participants who spent two nights in the sleep laboratory. Participants were awakened five minutes after the onset of every REM stage after which they provided a dream report and rated their dream affect. Two-minute pre-awakening EEG preceding each dream report were analyzed. Additionally, eight minutes of evening pre-sleep and morning post-sleep EEG were recorded during resting wakefulness. Mean spectral power in the alpha band (8-13 Hz) and corresponding FAA were calculated over the frontal (F4-F3) sites. Results showed that FAA during REM sleep, and during evening resting wakefulness, predicted ratings of dream anger. This suggests that individuals with lower right frontal activity (reflected in increased alpha power) may be less able to regulate (i.e., inhibit) strong affective states, such as anger, in dreams. Additionally, FAA was positively correlated across wakefulness and REM sleep. These findings imply that FAA may serve as a neural correlate of state and trait affect regulation not only in the waking but also in the dreaming state.


2019 ◽  
Vol 10 (02) ◽  
pp. 250-255
Author(s):  
Ambrish S. Dharmadhikari ◽  
Suyog Vijay Jaiswal ◽  
Avinash L. Tandle ◽  
Deoraj Sinha ◽  
Nandini Jog

ABSTRACTBackground: Depression, despite being the most common of mental illness lacks any quantifiable and absolute biomarker. Frontal alpha asymmetry (FAA) is proposed as biomarker of depression both in resting and activated state. Yet, the location of extraction of alpha, clinical utility as well as validity of FAA is uncertain. With aim of obtaining clarity on this confusion we conducted this study. Methodology: Electroencephalographic frontal alpha power was calculated in patients of depression (n = 24) and compared with healthy controls (n = 17) for the assessment of FAA. Both groups were studied for resting phase and activation phase changes in FAA. For activation phase, auditory stimuli in the form of Indian classical music were used. Results: Frontal alpha power was measured across FP1, FP2, F3, F4, F7, and F8. Mean powers were compared in resting (before), activated (during) and postactivated resting stage (after). FAA was statistically significant in F7–F8 pair of electrodes and on F7 electrode when compared between cases and controls. Conclusion: Quest for biomarker for depression churned out FAA as frontrunner. Despite of vast amount of research on it, practical utility eludes us. We need to revisit our approach from conventional search of the diagnostic biomarker; as FAA might reflect component of depression but not totally disorder. In our opinion, we are not yet ready for it and have a road ahead to travel.


2021 ◽  
Vol 3 (4) ◽  
pp. 157-162
Author(s):  
Dae Yun Hwang ◽  
Yang Rae Kim ◽  
Young-Min Park

Objective: Previous studies have compared depressive episodes between bipolar disorder (BD) and major depressive disorder (MDD) using quantitative electroencephalogram (QEEG); however, there are no distinct discriminating feature between them. Here, we used QEEG to directly compare the alpha asymmetry and absolute power of each band between patients with BD and MDD.Methods: Fifty in-patients with major depressive episodes between 2019 and 2021 were retrospectively enrolled. Self-reported questionnaires including the Beck Depression Inventory (BDI), Korean version of the Childhood Trauma Questionnaire, and Adult Attention-Deficit/Hyperactivity Disorder Self Report Scale (ASRS) were used to evaluate the symptoms. The absolute power of QEEG delta, theta, alpha, beta, high beta waves, and the Z-scores of frontal alpha asymmetry were collected. A t-test and Pearson’s correlation test were conducted using these data and based on these results, an analysis of covariance was conducted.Results: There were no significant differences between MDD and BD in QEEG power or alpha asymmetry. Patients with severe depression (BDI ≥29) had higher alpha power at FP1 (p=0.037), FP2 (p=0.028), F3 (p=0.047), F4 (p=0.016), and higher right frontal alpha asymmetry at F3–F4 (p=0.039). Adult patients with features consistent with ADHD (ASRS ≥4) had higher right frontal alpha asymmetry at F3–F4 (p=0.046). Patients with insomnia had higher left frontal alpha asymmetry at F3–F4 (p=0.003).Conclusion: QEEG limited the differential diagnosis of MDD and BD. However, frontal alpha asymmetry did exist in depression and affected cognitive impairment, insomnia, and depression severity in particular. Future studies with improved methodologies are needed for a better comparison.


eLife ◽  
2021 ◽  
Vol 10 ◽  
Author(s):  
Aleksandra Kołodziej ◽  
Mikołaj Magnuski ◽  
Anastasia Ruban ◽  
Aneta Brzezicka

For decades, the frontal alpha asymmetry (FAA) – a disproportion in EEG alpha oscillations power between right and left frontal channels – has been one of the most popular measures of depressive disorders (DD) in electrophysiology studies. Patients with DD often manifest a left-sided FAA: relatively higher alpha power in the left versus right frontal lobe. Recently, however, multiple studies failed to confirm this effect, questioning its reproducibility. Our purpose is to thoroughly test the validity of FAA in depression by conducting a multiverse analysis – running many related analyses and testing the sensitivity of the effect to changes in the analytical approach – on data from five independent studies. Only 13 of the 270 analyses revealed significant results. We conclude the paper by discussing theoretical assumptions underlying the FAA and suggest a list of guidelines for improving and expanding the EEG data analysis in future FAA studies.


Sign in / Sign up

Export Citation Format

Share Document