PrimePatNet87: Prime pattern and tunable q-factor wavelet transform techniques for automated accurate EEG emotion recognition

Date

2021-11-01

Author

Doğan, Abdullah
Barua, Prabal Datta
Baygin, Mehmet
Dogan, Sengul
Tuncer, Turker
Doğru, Ali Hikmet

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

136
views

0
downloads

Nowadays, many deep models have been presented to recognize emotions using electroencephalogram (EEG) signals. These deep models are computationally intensive, it takes a longer time to train the model. Also, it is difficult to achieve high classification performance using for emotion classification using machine learning techniques. To overcome these limitations, we present a hand-crafted conventional EEG emotion classification network. In this work, we have used novel prime pattern and tunable q-factor wavelet transform (TQWT) techniques to develop an automated model to classify human emotions. Our proposed cognitive model comprises feature extraction, feature selection, and classification steps. We have used TQWT on the EEG signals to obtain the sub-bands. The prime pattern and statistical feature generator are employed on the generated sub-bands and original signal to generate 798 features. 399 (half of them) out of 798 features are selected using minimum redundancy maximum relevance (mRMR) selector, and misclassification rates of each signal are evaluated using support vector machine (SVM) classifier. The proposed network generated 87 feature vectors hence, this model is named PrimePatNet87. In the last step of the feature generation, the best 20 feature vectors which are selected based on the calculated misclassification rates, are concatenated. The generated feature vector is subjected to the feature selection and the most significant 1000 features are selected using the mRMR selector. These selected features are then classified using an SVM classifier. In the last phase, iterative majority voting has been used to generate a general result. We have used three publicly available datasets, namely DEAP, DREAMER, and GAMEEMO, to develop our proposed model. Our presented PrimePatNet87 model reached over 99% classification accuracy on whole datasets with leave one subject out (LOSO) validation. Our results demonstrate that the developed prime pattern network is accurate and ready for real-world applications.

Subject Keywords

Prime pattern networkm, RMR selector, Hand-crafted method, EEG signal Classification, Emotion recognition

URI

https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85115031697&origin=inward
https://hdl.handle.net/11511/92876

Journal

Computers in Biology and Medicine

DOI

https://doi.org/10.1016/j.compbiomed.2021.104867

Collections

Graduate School of Natural and Applied Sciences, Article

Suggestions

OpenMETU
Core

Discrete wavelet transform based shift invariant analysis scheme for transient sound signals Wasim, Ahmad; Hacıhabiboğlu, Hüseyin; Kondoz, Ahmet (2010-09-06) Discrete wavelet transform (DWT) has gained widespread recognition and popularity in signal processing due to its ability to underline and represent time-varying spectral properties of many transient and other nonstationary signals. However, DWT is a shift-variant transform. This shift-variance is a major problem with the use of DWT for transient signal analysis and pattern recognition applications. A number of modified forms of DWT have been investigated in recent years that provide approximate shift-invar...
RESPONSE BIAS SHIFT FOR POSITIVE WORDS IN OLDER ADULTS IN A SURPRISE RECOGNITION MEMORY TASK: AN INCIDENTAL ENCODING STUDY KAYNAK, HANDE; Gökçay, Didem (2017-01-01) Introduction: Although the advantages of positive words on memory enhancement have been documented, the specific effects of the two prominent emotional dimensions (valence and arousal) under incidental encoding require further investigation. The objective is to study memory accuracy and response bias for positive/negative and highly/medium arousing words in a surprise old/new recognition memory paradigm under incidental encoding.
A Sparse Temporal Mesh Model for Brain Decoding Afrasiyabi, Arman; Onal, Itir; Yarman Vural, Fatoş Tunay (2016-08-23) One of the major drawbacks of brain decoding from the functional magnetic resonance images (fMRI) is the very high dimension of feature space which consists of thousands of voxels in sequence of brain volumes, recorded during a cognitive stimulus. In this study, we propose a new architecture, called Sparse Temporal Mesh Model (STMM), which reduces the dimension of the feature space by combining the voxel selection methods with the mesh learning method. We, first, select the "most discriminative" voxels usin...
Short-term consolidation of information for episodic memory Özçelik, Erol; Tekman, Hasan Gürkan; Department of Cognitive Sciences (2008) Several lines of evidence from rapid serial visual presentation, attentional blink, and dual-task interference phenomena propose that human beings have a significant limitation on the short-term consolidation process. Short-term consolidation is transferring early representations to more durable forms of memory. Although previous research has shown that masks presented after targets interrupt the consolidation process of information, there is not enough evidence for the role of attention in consolidation fo...
Sleep stage classification based on filter bank optimization ORAL, EMİN ARGUN; Çodur, Muhammet Mustafa; ÖZBEK, İBRAHİM YÜCEL (2017-12-01) Sleep stage binary classification is studied using single channel EEG signals. The proposed approach is composed of two steps. In the first step, cepstrum coefficients based features are obtained from EEC signals using a filter bank approach which is tuned for sleep stage classification in terms of number of filters and their type. In the second step, these features are used with support vector machine approach for classification. It is observed that obtained results are comparable with the published result...

Citation Formats

A. Doğan, P. D. Barua, M. Baygin, S. Dogan, T. Tuncer, and A. H. Doğru, “PrimePatNet87: Prime pattern and tunable q-factor wavelet transform techniques for automated accurate EEG emotion recognition,” Computers in Biology and Medicine, vol. 138, pp. 0–0, 2021, Accessed: 00, 2021. [Online]. Available: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85115031697&origin=inward.