Wireless EEG signals based Neuromarketing system using Fast Fourier Transform (FFT)

Murugappan, M.; Murugappan, S.; Balaganapathy,; Gérard, C.

doi:10.1109/cspa.2014.6805714

Cited by 60 publications

(32 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Machine learning models are in ever‐growing use throughout the market and academia, and their utilization represents a very promising strategy, although it is still in its early stages. A somewhat related study was conducted by Murugappan, Murugappan, Balaganapathy, & Gerard (), who applied a probabilistic neural network and k‐nearest neighbor's prediction models in their experiment. They had participants view four commercials per four different vehicle brands, and extracted spectral energy (SE), power spectrum density (PSD), and spectral centroid (SC) of the alpha band as predictors, and participants' self‐assessments as a response.…”

Section: Current Findings In Eeg‐based Preference Predictionmentioning

confidence: 99%

A gateway to consumers' minds: Achievements, caveats, and prospects of electroencephalography‐based prediction in neuromarketing

Hakim

Levy

2018

WIRES Cognitive Science

View full text Add to dashboard Cite

In the last decade, the field of consumer neuroscience, or neuromarketing, has been flourishing, with numerous publications, academic programs, initiatives, and companies. The demand for objective neural measures to quantify consumers' preferences and predict responses to marketing campaigns is ever on the rise, particularly due to the limitations of traditional marketing techniques, such as questionnaires, focus groups, and interviews. However, research has yet to converge on a unified methodology or conclusive results that can be applied in the industry. In this review, we present the potential of electroencephalography (EEG)‐based preference prediction. We summarize previous EEG research and propose features which have shown promise in capturing the consumers' evaluation process, including components acquired from an event‐related potential design, inter‐subject correlations, hemispheric asymmetry, and various spectral band powers. Next, we review the latest findings on attempts to predict preferences based on various features of the EEG signal. Finally, we conclude with several recommended guidelines for prediction. Chiefly, we stress the need to demonstrate that neural measures contribute to preference prediction beyond what traditional measures already provide. Second, prediction studies in neuromarketing should adopt the standard practices and methodology used in data science and prediction modeling that is common in other fields such as computer science and engineering. This article is categorized under: Economics > Interactive Decision‐Making Economics > Individual Decision‐Making Psychology > Prediction Neuroscience > Cognition

show abstract

Section: Current Findings In Eeg‐based Preference Predictionmentioning

confidence: 99%

A gateway to consumers' minds: Achievements, caveats, and prospects of electroencephalography‐based prediction in neuromarketing

Hakim

Levy

2018

WIRES Cognitive Science

View full text Add to dashboard Cite

show abstract

“…Energy (i.e., spectral energy; cf. Bao & Intille, 2004;Murugappan, Murugappan, & Gerard; is calculated as the sum of the squared discrete FFT component magnitudes of the signal over the entire frequency range. Furthermore, the sum is divided by the length of the frame for normalization.…”

Section: Feature Extractionmentioning

confidence: 99%

Individual classification of elementary school children’s physical activity: A time-efficient, group-based approach to reference measurements

2016

View full text Add to dashboard Cite

The objective measurement of physical activity using accelerometers is becoming increasingly popular. There is little consensus, however, about how to analyze acceleration data. One promising approach is the use of reference measurements in which the subjects conduct specific activities. This makes it possible to identify data patterns that indicate these activities for each subject. The drawback of this approach is its rather high cost, in terms of both time and money. We propose a new approach in which a group of children conduct the reference measurements at the same time. We trained support vector machine models on the accelerometer data of 70 children (ages 8-11 years) to predict their activities during those reference measurements. We correctly classified activities with an accuracy of 96.9 % when fitting the individual models for each subject, and 87.5 % when fitting general models for all subjects. The obtained accuracies were comparable to results reported in previous reference measurement studies, in which each subject was measured individually. They were higher than the accuracies obtained by the traditional approach, which transfers accelerometer data to counts and classifies those on the basis of predefined cut points. We concluded that our approach can yield a valuable contribution, particularly to studies with larger samples.

show abstract

“…One of the major limitations of EEG studies is the small sample size due to the complexity of the technology, and the cost and time‐consuming nature of EEG data collection. The sample size in our EEG study ( n = 65) is considerable large compared to most EEG studies in economic decision making (e.g., n = 40, Baldo, Parikh, Piu, & Müller, ; n = 18, Khushaba, Wise, Kodagoda, Louviere, Kahn, & Townsend, ; n = 12, Murugappan, Murugappan, & Gerard, ; n = 33, Ravaja et al, ; n = 30, Wang, R. W. Y., Chang, & Chuang, ; n = 30, Wei, Wu, Wang, Supratak, Wang, & Guo, ) and we used a within‐subject design to increase the number of observations. However, there have been sample size concerns that may affect the reliability of EEG studies in general (e.g., Bernheim, , Button, Ioannidis, Mokrysz, Nosek, Flint, Robinson, & Munafò, ).…”

Section: Discussion and Concluding Remarksmentioning

confidence: 99%

US consumer reactions to China's Shuanghui acquisition of Smithfield Foods and its neural basis

et al. 2018

View full text Add to dashboard Cite

The $4.7 billion acquisition of Smithfield Foods by China's Shuanghui International (now WH Group) marks the largest Chinese takeover of a US company in history. Using electroencephalography along with an incentive compatible willingness-to-pay (WTP) elicitation mechanism, our study provides neural based evidence that the Shuanghui-Smithfield acquisition lowered consumers' preference for the Smithfield brand, but increased it for the Chinese brand.Consumers' neural preference for American brands increased after learning about the acquisition, implying a positive spillover effect to US brands in the US market. We also find that, after learning that an item is a product of the United States, consumers' neural preference decreased although their willingness-to-pay increased, consistent with some empirical reports that many US consumers prefer to purchase cheaper products made abroad rather than products of the United States with higher prices. K E Y W O R D Sconsumer willingness-to-pay, cross-border acquisitions, EEG, meat product, neural preference

show abstract

Wireless EEG signals based Neuromarketing system using Fast Fourier Transform (FFT)

Cited by 60 publications

References 12 publications

A gateway to consumers' minds: Achievements, caveats, and prospects of electroencephalography‐based prediction in neuromarketing

A gateway to consumers' minds: Achievements, caveats, and prospects of electroencephalography‐based prediction in neuromarketing

Individual classification of elementary school children’s physical activity: A time-efficient, group-based approach to reference measurements

US consumer reactions to China's Shuanghui acquisition of Smithfield Foods and its neural basis

Contact Info

Product

Resources

About