| Title:
|
EEG-Based Consumer Purchase State Detection Using Feature Selection and Prefrontal Analysis
|
| Author(s):
|
1
|
| Subject:
|
Advanced Techniques in Signal Acquisition and Image Processing
|
|
|
|
Presenter Author:
|
|
| Name:
|
Kiana Heydari
|
|
|
|
Author:
|
|
| Name 1:
|
Kiana Heydari - Corresponding - Presenter
|
| Affiliation 1:
|
Faculty of Biomedical Engineering. Biomedical Engineering Research Center. Tabriz University of Technology. Sahand New Town, Tabriz, Iran. k_heydari402@sut.ac.ir
|
|
|
| Name 2:
|
Sina Shamekhi
|
| Affiliation 2:
|
Faculty of Biomedical Engineering. Biomedical Engineering Research Center. Tabriz University of Technology. Sahand New Town, Tabriz, Iran. shamekhi@sut.ac.ir
|
|
|
| Name 3:
|
Fatemeh Shalchizadeh
|
| Affiliation 3:
|
Faculty of Biomedical Engineering. Biomedical Engineering Research Center. Tabriz University of Technology. Sahand New Town, Tabriz, Iran. f_shalchizadeh400@sut.ac.ir
|
|
|
| Name 4:
|
|
| Affiliation 4:
|
|
|
|
| Name 5:
|
|
| Affiliation 5:
|
|
|
|
| Name 6:
|
|
| Affiliation 6:
|
|
|
|
| Name 7:
|
|
| Affiliation 7:
|
|
|
|
| Name 8:
|
|
| Affiliation 8:
|
|
|
|
| Name 9:
|
|
| Affiliation 9:
|
|
|
|
| Name 10:
|
|
| Affiliation 10:
|
|
|
|
Abstract
|
Original Research
|
|
introduction :
|
Understanding consumers’ purchase decision-making is a challenge in the neuromarketing field. EEG-based approaches have demonstrated reliable results; however, their practical application is often limited by the complexity of the systems and the large number of recording channels. This study presents an approach to investigate whether a promising method for predicting purchase decisions can be achieved by reducing the utilization of EEG channels.
|
|
Methods:
|
EEG data from the Neuma dataset were analyzed under two conditions: (i) all EEG channels with the complete feature set, and (ii) prefrontal channels (fp1 and fp2). Feature extraction included PSD, DWT, and time-domain statistical features, followed by feature selection methods using mRMR and ReliefF. Hence, classification was performed using an SVM classifier to estimate the impact of channel reduction on purchase decision classification.
|
|
Results:
|
The highest classification accuracy was achieved by using all EEG channels and ReliefF feature selection, reaching 86%, and utilizing prefrontal channels resulted in an accuracy of 81%. These results are competitive with existing EEG-based neuromarketing studies, while employing a simpler method.
|
|
Conclusion:
|
Although the full channel condition yielded higher performance, the prefrontal channel approach still achieved comparative accuracy. This study provided reliable performance with considerably reduced complexity and highlights the potential of a low-channel EEG system for practical neuromarketing applications.
|
| Attachment:
|
|
| Keywords:
|
Neuromarketing, Neuma database, Electroencephalography, Signal Processing, Feature Selection
|
| Key message:
|
|
| Do you want your abstract to be indexed, if this is selected as one of the top 100
articles?
|
