A Sequential Study of Emotions through EEG using HMM

Chaurasiya, Rahul Kumar; Shukla, Shourya; Sahu, Tirath Prasad

doi:10.1109/cse/euc.2019.00029

Cited by 3 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast, there are not many studies that use HMMs for emotion recognition based on physiological signals. Despite the few works that use HMM to classify physiological signals according to emotions showing that performance is not worse than others that use different classifiers [4,8,10], most works use other machine learning methods that ignore the temporal evolution of the signal, such as SVM or k-NN [1,11,18] or use deep learning methods which generally require large amounts of data for training [2].…”

Section: Introductionmentioning

confidence: 99%

On the benefits of using Hidden Markov Models to predict emotions

Arevalillo‐Herráez

Katsigiannis

et al. 2022

Proceedings of the 30th ACM Conference on User Modeling, Adaptation and Personalization

View full text Add to dashboard Cite

The availability of low-cost wireless physiological sensors has allowed the use of emotion recognition technologies in various applications. In this work, we describe a technique to predict emotional states in Russell's two-dimensional emotion space (valence and arousal), using electroencephalography (EEG), electrocardiography (ECG), and electromyography (EMG) signals. For each of the two dimensions, the proposed method uses a classification scheme based on two Hidden Markov Models (HMMs), with the first one trained using positive samples, and the second one using negative samples. The class of new unseen samples is then decided based on which model returns the highest score. The proposed approach was validated on a recently published dataset that contained physiological signals recordings (EEG, ECG, EMG) acquired during a human-horse interaction experiment. The experimental results demonstrate that this approach achieves a better performance than the published baseline methods, achieving an F1-score of 0.940 for valence and 0.783 for arousal, an improvement of more than +0.12 in both cases. CCS CONCEPTS• Information systems → Sentiment analysis; • Mathematics of computing → Kalman filters and hidden Markov models; • Computing methodologies → Supervised learning by classification.

show abstract

Section: Introductionmentioning

confidence: 99%

On the benefits of using Hidden Markov Models to predict emotions

Arevalillo‐Herráez

Katsigiannis

et al. 2022

Proceedings of the 30th ACM Conference on User Modeling, Adaptation and Personalization

View full text Add to dashboard Cite

show abstract

“…To comprehend human feelings or perceptions, significant works of art involving brain-machine software Neuromarketing, market research, medicine, and security are only a few examples as the demand for such services grows (Hosseini 2017). The study's importance is to analyze the various components under EEG signals used to detect the emotions using the SVM and HMM classifiers to compare other classifiers based on their efficiency (Chaurasiya, Shukla, and Sahu 2019). *Corresponding author: vishnuvardhan.palem@gmail.com This study's application is to comprehend the working of SVM and HMM classifiers that would detect and measure the physiological signals with higher precision (Daimary et al 2018).…”

Section: Introductionmentioning

confidence: 99%

Wavelet based Extraction of Features from EEG Signals and Classification of Novel Emotion Recognition Using SVM and HMM Classifier and to Measure its Accuracy

Mohanambal¹,

Vardhan²

2021

alinteri

View full text Add to dashboard Cite

Aim: The study aims to extract features from EEG signals and classify emotion using Support Vector Machine (SVM) and Hidden Markov Model (HMM) classifier. Materials and methods: The study was conducted using the Support Vector Machine (SVM) and Hidden Markov Model (HMM) programs to analyze and compare the recognition of emotions classified under EEG signals. The results were computed using the MATLAB algorithm. For each group, ten samples were used to compare the efficiency of SVM and HMM classifiers. Result: The study’s performance exhibits the HMM classifier’s accuracy over the SVM classifier and the emotion detection from EEG signals computed. The mean value of the HMM classifier is 52.2, and the SVM classifier is 22.4. The accuracy rate of 35% with the data features is found in HMM classifier. Conclusion: This study shows a higher accuracy level of 35% for the HMM classifier when compared with the SVM classifier. In the detection of emotions using the EEG signal. This result shows that the HMM classifier has a higher significant value of P=.001 < P=.005 than the SVM classifier.

show abstract