Multi-class Emotion Classification Using EEG Signals

Acharya, Divya; Jain, Riddhi; Panigrahi, Siba Smarak; Sahni, Rahul; Jain, Siddhi; Deshmukh, Sanika Prashant; Bhardwaj, Arpit

doi:10.1007/978-981-16-0401-0_38

Cited by 21 publications

(7 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Al. [15] had obtained 88% detection accuracy but the training and testing datasets have been contaminated by data with the same sample space. However, the presented model obtained 96.01% accuracy while training and testing the model with data from a different group of people.…”

Section: Comparison With State Of the Artmentioning

confidence: 99%

“…Fast Fourier transformation have earlier been used with EEG signals to detect multiple moods with around 88% accuracy. However, in the experiment, both the training and testing dataset contained signals from the same sample space making it lesser reliable in the uncontrolled environment [15]. Experiments have been performed using neural networks on the EEG spectrum for identifying different features but they have not shown any robust signal processing method [4,11].…”

Section: Literature Surveymentioning

confidence: 99%

See 1 more Smart Citation

Optimized EEG based mood detection with signal processing and deep neural networks for brain-computer interface

Adhikary¹,

Jain

Saha³

et al. 2023

Biomed. Phys. Eng. Express

View full text Add to dashboard Cite

Electroencephalogram (EEG) is a very promising and widely implemented procedure to study brain signals and activities by amplifying and measuring the post-synaptical potential arising from electrical impulses produced by neurons and detected by specialized electrodes attached to specific points in the scalp. It can be studied for detecting brain abnormalities, headaches, and other conditions. However, there are limited studies performed to establish a smart decision-making model to identify EEG's relation with the mood of the subject. In this experiment, EEG signals of 28 healthy human subjects have been observed with consent and attempts have been made to study and recognise moods. Savitzky-Golay band-pass filtering and Independent Component Analysis have been used for data filtration. Different neural network algorithms have been implemented to analyze and classify the EEG data based on the mood of the subject. The model is further optimised by the usage of Blackman window-based Fourier Transformation and extracting the most significant frequencies for each electrode. Using these techniques, up to 96.01% detection accuracy has been obtained.

show abstract

Section: Comparison With State Of the Artmentioning

confidence: 99%

Section: Literature Surveymentioning

confidence: 99%

Optimized EEG based mood detection with signal processing and deep neural networks for brain-computer interface

Adhikary¹,

Jain

Saha³

et al. 2023

Biomed. Phys. Eng. Express

View full text Add to dashboard Cite

show abstract

“…One such technique that can be used for this purpose is the k-folds cross-validation [67]- [70]. The k-folds cross-validation results in a less biased model compared to other validation methods such as the train-test split [71], [72] because, in this method, it is ensured that every observation from the original dataset has a chance of appearing in the training and validation set. This is extremely helpful in our particular case of limited dataset.…”

Section: Cnn Trainingmentioning

confidence: 99%

Coded-Aperture Computational Millimeter-Wave Image Classifier Using Convolutional Neural Network

et al. 2021

View full text Add to dashboard Cite

A millimeter-wave (mmW) classifier system applied to images synthesized from a codedaperture based computational imaging (CI) radar is presented. A developed physical model of a CI system is used to generate the image dataset for the classification algorithm. A convolutional neural network (CNN) is integrated with the physical model and trained using the dataset comprising of synthesized mmW images obtained directly from the developed CI physical model. A k-fold cross validation technique is applied during the training process to validate the classification model. The coded-aperture CI concept enables image reconstruction from a significantly reduced number of back-scattered measurements by facilitating physical layer compression. This physical layer compression can substantially simplify the data acquisition layer of imaging radars, which is realized using only two channels in this article. The integration of the classification algorithm with the CI numerical model is particularly important in enabling the training step to be carried out using relevant system metrics and without the necessity for experimental data. Leveraging the CI numerical model generated data, training step for the classification algorithm is achieved in real-time while also confirming that the numerically trained CI classifier offers high accuracy with both simulated and experimental data. The classifier integrated physical model also enables performance analysis of the classification algorithm to be carried out as a function of key system metrics such as signal-to-noise (SNR) level, ensuring a complete understanding of the classification accuracy under different operating conditions. The trained CI system is tested with synthesized mmW images from the physical model and a classification accuracy of 89% is achieved. The proposed model is also verified using experimental data validating the fidelity of the developed CI integrated classifier system. A classification latency of 3.8 ms per frame is achieved, paving the way for real-time automated threat detection (ATD) for security-screening applications.INDEX TERMS Millimetre-wave, imaging radars, computational imaging, neural networks, image classification, coded-aperture.

show abstract

“…Due to its different characteristics when engaging with an emotion, EEG is thought to be the most appropriate approach to record data in multiple modalities [ 21 , 22 ]. EEG is a nonintrusive, quick, and cost-effective approach that makes it a favorite way of testing the brain's reactions to feelings targeting personality trait stimuli [ 23 ]. EEG signals frequency varies from 0.5 Hz to 100 Hz and are grouped into five bands: delta, theta, alpha, beta, and gamma, as shown in Figure 1 , and all the bands have different frequencies.…”

Section: Introductionmentioning

confidence: 99%

Personality Prediction with Hybrid Genetic Programming using Portable EEG Device

Bhardwaj

Tomar

Sakalle

et al. 2022

Computational Intelligence and Neuroscience

Self Cite

View full text Add to dashboard Cite

This work suggests a method to identify personality traits regarding the targeted film clips in real-time. Such film clips elicit feelings in people while capturing their brain impulses using the electroencephalogram (EEG) devices and examining personality traits. The Myers–Briggs Type Indicator (MBTI) paradigm for determining personality is employed in this study. The fast Fourier transform (FFT) approach is used for feature extraction, and we have used hybrid genetic programming (HGP) for EEG data classification. We used a single-channel NeuroSky MindWave 2 dry electrode unit to obtain the EEG data. In order to collect the data, thirty Hindi and English video clips were placed in a conventional database. Fifty people volunteered to participate in this study and willingly provided brain signals. Using this dataset, we have generated four two-class HGP classifiers (HGP1, HGP2, HGP3, and HGP4), one for each group of MBTI traits overall classification accuracy of the HGP classifier as 82.25% for 10-fold cross-validation partition.

show abstract

Multi-class Emotion Classification Using EEG Signals

Cited by 21 publications

References 21 publications

Optimized EEG based mood detection with signal processing and deep neural networks for brain-computer interface

Optimized EEG based mood detection with signal processing and deep neural networks for brain-computer interface

Coded-Aperture Computational Millimeter-Wave Image Classifier Using Convolutional Neural Network

Personality Prediction with Hybrid Genetic Programming using Portable EEG Device

Contact Info

Product

Resources

About