Best Feature Extraction and Classification Algorithms For EEG Signals In Neuromarketing
Purpose: There are many methods for advertisements of products and neuromarketing is new area in this field. In neuromarketing, we use neuroscience information for reveal Consumer behavior by extraction brain activity. Functional magnetic resonance imaging (fMRI), Magnetoencephalography (MEG), and electroencephalography (EEG) are high efficacy tools for investigation the brain activity in neuromarketing. EEG signal is a high temporal resolution and cheap method for to examine the brain activity.
Materials and Methods: In this study, 32 subjects (16 males and 16 females) who aging between 20-35 years participated. We proposed neuromarketing method exploit EEG system for predicting consumer preferences while they view E-commerce products. We apply some important preprocessing steps for noise and artifacts elimination of the EEG signal. In next step feature extraction methods apply on the EEG data such as discrete wavelet transform (DWT) and statistical features. The goal of this study is classification of analyzed EEG signal to likes and dislikes using supervised algorithms. We use Support Vector Machine (SVM), Artificial Neural Network (ANN) and Random Forest (RF) for data classification. The mentioned methods used for whole and lobe brain data.
Results: The results show high efficacy for SVM algorithms than other methods. Accuracy, sensitivity, specificity and precision parameters used for evaluation of the model performance. The results shows high performance of SVM algorithms for classification of the data with accuracy more than 87% and 84% for whole and parietal lobe data.
Conclusion: We design a tool with EEG signals for extraction brain activity of consumers using neuromarketing methods. We investigate the effects of advertising on brain activity of consumers by EEG signals measures.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.