Analysis of Brain Wave Data Using Neurosky Mindwave Mobile II

Morshad, Sarwar; Mazumder, Md. Rabiuzzaman; Ahmed, Fahad

doi:10.1145/3377049.3377053

Cited by 10 publications

(10 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since EEG indexes have severe fluctuations by nature, which is considered to inhibit the effectiveness of the objective function minimization, and the threshold value calculation of the machine learning algorithm, calculating the moving average is considered to help reduce this inhibition, and may result in the increase of accuracy of emotion estimation model. Table 1 shows the EEG indexes and their corresponding frequency bands and interpretations used in this study [30][31][32]. [25].…”

Section: Feature Extraction From Eeg/hrv Data 21 Eeg Indexesmentioning

confidence: 99%

Constructing an Emotion Estimation Model Based on EEG/HRV Indexes Using Feature Extraction and Feature Selection Algorithms

Suzuki

Laohakangvalvit

Matsubara

et al. 2021

Sensors

View full text Add to dashboard Cite

In human emotion estimation using an electroencephalogram (EEG) and heart rate variability (HRV), there are two main issues as far as we know. The first is that measurement devices for physiological signals are expensive and not easy to wear. The second is that unnecessary physiological indexes have not been removed, which is likely to decrease the accuracy of machine learning models. In this study, we used single-channel EEG sensor and photoplethysmography (PPG) sensor, which are inexpensive and easy to wear. We collected data from 25 participants (18 males and 7 females) and used a deep learning algorithm to construct an emotion classification model based on Arousal–Valence space using several feature combinations obtained from physiological indexes selected based on our criteria including our proposed feature selection methods. We then performed accuracy verification, applying a stratified 10-fold cross-validation method to the constructed models. The results showed that model accuracies are as high as 90% to 99% by applying the features selection methods we proposed, which suggests that a small number of physiological indexes, even from inexpensive sensors, can be used to construct an accurate emotion classification model if an appropriate feature selection method is applied. Our research results contribute to the improvement of an emotion classification model with a higher accuracy, less cost, and that is less time consuming, which has the potential to be further applied to various areas of applications.

show abstract

Section: Feature Extraction From Eeg/hrv Data 21 Eeg Indexesmentioning

confidence: 99%

Constructing an Emotion Estimation Model Based on EEG/HRV Indexes Using Feature Extraction and Feature Selection Algorithms

Suzuki

Laohakangvalvit

Matsubara

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Therefore, they concluded that using the Neurosky device for control was not so much plausible. Morshad et al [12] also used the Neurosky device to study its usability. By directly using the attention and mediation data from the Neurosky software, they had accuracy rates of 47.5% and 52.3% for attention and mediation states, respectively.…”

Section: Related Workmentioning

confidence: 99%

“…Since we have a small dataset, using the SVM is a better choice. For the experiments conducted by Morshad et al [12] and Rebolledo-Mendez et al [14], the features were directly obtained by the Neurosky software. In our case, we also consider the selection of different frequency bands.…”

Section: Related Workmentioning

confidence: 99%

“…It is then import to study whether one or two channels are sufficient to obtain high accuracy in actual applications. After reading some existing literature, the answer seems inconclusive, some with good accuracy [7,8], high correlation [9], or acceptable usability [10], whereas others with extremely low accuracy [11] or marginal accuracy (around 50%) [12]. Therefore, we intend to find out our own answer.…”

Section: Introductionmentioning

confidence: 98%

“…Therefore, we decided to classify only attention and meditation states. This problem has been studied by many researchers before, e.g., [5][6][7][8][9][10][11][12][13][14][15]. Although such a problem is a binary classification problem, it is actually not easy to achieve high accuracy.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Classification of Relaxation and Concentration Mental States with EEG

You

2021

Information

View full text Add to dashboard Cite

In this paper, we study the use of EEG (Electroencephalography) to classify between concentrated and relaxed mental states. In the literature, most EEG recording systems are expensive, medical-graded devices. The expensive devices limit the availability in a consumer market. The EEG signals are obtained from a toy-grade EEG device with one channel of output data. The experiments are conducted in two runs, with 7 and 10 subjects, respectively. Each subject is asked to silently recite a five-digit number backwards given by the tester. The recorded EEG signals are converted to time-frequency representations by the software accompanying the device. A simple average is used to aggregate multiple spectral components into EEG bands, such as α, β, and γ bands. The chosen classifiers are SVM (support vector machine) and multi-layer feedforward network trained individually for each subject. Experimental results show that features, with α+β+γ bands and bandwidth 4 Hz, the average accuracy over all subjects in both runs can reach more than 80% and some subjects up to 90+% with the SVM classifier. The results suggest that a brain machine interface could be implemented based on the mental states of the user even with the use of a cheap EEG device.

show abstract