EEG signal based Modified Kohonen Neural Networks for Classification of Human Mental Emotions

Hemanth, D. Jude

doi:10.33969/ais.2020.21001

Cited by 15 publications

(7 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, there are still several issues worth highlighting. First, from the algorithm perspective, most studies were concerned with classification issues in the field of EEG analysis (e.g., [230][231][232][233][234]), for example, human mental emotion classification [230], classification of forearm movement imagery [231], detection of acute pain signals [232], sleep stage classification [235], classification of individuals into a normal group and one with particular diseases [236], and classification of repeating stimuli as either old or new [237]. Furthermore, ensemble classifiers are more effective than a single strong learner [238].…”

Section: Latest Research Concerning Ai-enhanced Eeg Analysismentioning

confidence: 99%

Global research on artificial intelligence-enhanced human electroencephalogram analysis

Chen

Tao

Wang

et al. 2021

Neural Comput & Applic

View full text Add to dashboard Cite

The application of artificial intelligence (AI) technologies in assisting human electroencephalogram (EEG) analysis has become an active scientific field. This study aims to present a comprehensive review of the research field of AI-enhanced human EEG analysis. Using bibliometrics and topic modeling, research articles concerning AI-enhanced human EEG analysis collected from the Web of Science database during the period 2009-2018 were analyzed. After examining 2053 research articles published around the world, it was found that the annual number of articles had significantly grown from 78 to 468, with the USA and China being the most influential and prolific. The results of the keyword analysis showed that ''electroencephalogram,'' ''brain-computer interface,'' ''classification,'' ''support vector machine,'' ''electroencephalography,'' and ''signal'' were the most frequently used. The results of topic modeling and evolution analyses highlighted several important issues, including epileptic seizure detection, brain-machine interface, EEG classification, mental disorders, emotion, and alcoholism and anesthesia. The findings suggest that such visualization and analysis of the research articles could provide a comprehensive overview of the field for communities of practice and inquiry worldwide.

show abstract

Section: Latest Research Concerning Ai-enhanced Eeg Analysismentioning

confidence: 99%

Global research on artificial intelligence-enhanced human electroencephalogram analysis

Chen

Tao

Wang

et al. 2021

Neural Comput & Applic

View full text Add to dashboard Cite

show abstract

“…Samples with number of subjects below this threshold were considered not statistically significant. Studies claiming the best accuracy on emotional valence assessment are based on public EEG signal datasets: SEED [24][25][26][27][28][29] , DEAP [25][26][27][28][30][31][32][33][34][35][36][37][38][39][40] , and DREAMER 29,37,38 .…”

Section: Related Workmentioning

confidence: 99%

High-wearable EEG-Based Detection of Emotional Valence for Scientific Measurement of Emotions

Apicella

Arpaïa

Mastrati

et al. 2021

Preprint

View full text Add to dashboard Cite

An emotional-valence detection method for a very–high wearable EEG-based system is proposed. Valence detection occurs along the interval scale theorized by the circumplex model of emotions. The binary choice, positive valence vs negative valence, represents a first step towards the adoption of a metric scale with a finer resolution. Wearability is guaranteed by a wireless cap with conductive-rubber dry electrodes and 8 data acquisition channels. Experimental validation was realized on 25 volunteers without depressive disorders. The metrological reference was built by combining the rating of a standardized set of pictures from dataset Oasis and results from the Self Assessment Manikin questionnaire. Two different strategies for feature extraction were compared: (i) based on a-priory knowledge (i.e. Hemispheric Asymmetry Theories) and (ii) automated. A pipeline of a custom 12-band Filter Bank and Common Spatial Pattern algorithm is the method proposed for automated feature extraction. Four machine learning classifiers were tested for validating the proposed method in discriminating two classes (high or low emotional valence). An intra-individual average accuracy, 96.2 %, was obtained by a shallow artificial neural network, while K-Nearest Neighbors allowed obtaining 80.3 % of inter-individual accuracy. Considering the wearability, and the well-founded metrological reference, results are the state of the art in emotional valence detection.

show abstract

“…The electrical activity called nerve current or axon potential continues along the neuron [2]. The electrical signals formed during the activities of these nerve cells in the brain were recorded for the first time with the Electroencephalograph developed by [3,4,22,26,28]. These recorded signs are called EEG and can be obtained over a very large surface of the cerebral cortex.…”

Section: Open Accessmentioning

confidence: 99%

Binary particle swarm optimization (BPSO) based channel selection in the EEG signals and its application to speller systems

Arıcan¹,

Polat²

2020

AIS

View full text Add to dashboard Cite

Social participation of people with disabilities is tried to be increased with state-supported projects recently. However, even in neuromuscular diseases such as Motor Neurone Disease (MND), Full Sliding Status (TSD), even the communication skills of individuals are interrupted. Brain-Computer Interfaces (BBA), which have a few decades of history and an increasing number of studies with exponential momentum, are being developed to enable individuals with such disorders to communicate with their environment. Spelling systems are BBA systems that detect the letters that the person focuses on the matrix of letters and numbers on a screen and convert them into text through the application. In this context, with the random flashing of the letters on the screen, it aims to detect the electrical changes occurring in the brain as a result of the stimulus given to the person. Research reveals that the stimulus that the individual encounters cause an amplitude in the EEG signal called P300, between 250 and 500 ms. Brain-computer interfaces are used through EEG signals to provide environmental interactions for individuals with restricted movements due to stroke or neurodegenerative diseases. The multi-channel structure of EEG signals both increases system cost and reduces processing speed. For this reason, reducing the system cost by detecting more active electrodes during the process increases the accessibility of people. In this context, the use of optimization techniques in electrode selection is used to determine the most effective channels by a random selection method. In the study, particle herd optimization algorithm, one of the herd-based optimization techniques, was used with two classifiers, SVM and Boosted Tree, and the eight most frequently selected channels were determined to improve system performance in terms of speed and accuracy.

show abstract

EEG signal based Modified Kohonen Neural Networks for Classification of Human Mental Emotions

Cited by 15 publications

References 20 publications

Global research on artificial intelligence-enhanced human electroencephalogram analysis

Global research on artificial intelligence-enhanced human electroencephalogram analysis

High-wearable EEG-Based Detection of Emotional Valence for Scientific Measurement of Emotions

Binary particle swarm optimization (BPSO) based channel selection in the EEG signals and its application to speller systems

Contact Info

Product

Resources

About