1. Which hardware is used to collect biofeedback and how the data is used?

Sensors are used to collect biometric data for detection and quantifying emotional reactions and triggers via wearable tech. We commonly use:
• ID Guardian headband that collects EEG data
• ID Guardian wristband that collect EDA, HRV and body temperature data
We use obtained data for:
• Determination of positive and negative reactions and their intensity
• Connecting reactions to specific emotions
• Correlation purposes
• Cross validation purposes

2. How do we detect and measure Affect?

• Neuroanatomical localisation of neural networks
Scientific literature have provided evidence that frontal cortical EEG activation asymmetry predicts responsively to affective manipulations.
Tasks that include a response component will be more likely to show affect-related Prefrontal cortex activation asymmetry in the dorsolateral regions and its activity in these regions that are most likely to be reflected in scalp-recorded brain electrical signals. In response to cues that signal the requirement to inhibit a dominant response, activation of right inferior and middle frontal gyrus has been widely described.
Right ventromedial prefrontal cortex also appears to play a specialized role in the inhibition of impulsive affective urges. Patients with damage specifically to this prefrontal cortex sector on the right side, but not on the left side, have profound abnormalities in emotion-related decision making. It appears that this sector of right prefrontal cortex may be particularly sensitive to punishment so that when it is damaged, patients no longer have the usual cues that signal threat and danger and so tend to act impulsively
However, with respect to the frontal EEG asymmetry literature, it is imperative that we be mindful of the fact that prefrontal cortex asymmetry represents only a small portion of the critical circuitry of emotion.
• Neural network's way of communication
A particular pattern of EEG activation asymmetry has been found to predict reactivity to specifically valence stimuli in a laboratory situation, and it's related to the Alpha frequency band
In neuroscience literature, the EEG pattern associated with food reward, on the other hand, is in the beta and theta rhythm localized to posterior-dorsal (parietal) cortex.
Our cross validation takes into account both, enabling us to point out affect in our tested end users.

3. How do we detect and measure Engagement?

• Neuroanatomical localisation of neural networks
The spatial tasks engaged the right hemisphere more than the verbal task, with the exception of complex mental rotation, which showed an EEG pattern similar to the verbal task. Most of the differences in EEG patterns between tasks were accounted for by differences in right hemisphere engagement. High left hemisphere engagement is related in scientific literature during mental rotation.
• Neural network's way of communication
Regarding engagement measurement, we analyse alpha, beta and gamma frequency band and their correlation.

4. Why do we use biofeedback in market research and what do we measure?

The data gathered via the biofeedback is a relatively new concept in market research, but nevertheless it is a concept which could revolutionize the way we gather data on product and brand desirability. Its potential uses are incredible, and it could contribute to once and for all resolving the age old problem in any market research - socially desirable responses by the study participants.

In our studies we gather biofeedback via four main variables: heart rate variability, heart rate, skin conductance and neurofeedback which were in turn used to identify biophysical peaks that are occurring during the testing with the study participants.

Peaks in this sense could be defined as moments of increased emotional or cognitive processing, and the measures used provide a relatively robust and well studied indication of same.

5. Our Methodology

We collect sensor data for various physiological signals such as: EEG, GSR, Heart Rate, temperature and potentially blood pressure. Our sensor collects EEG signal by a rate of 220 samples/sec from 4 channels ( fp1, tp9, tp10, fp2 by 10/20 system).
We apply various algorithms to:
- get important signal features and perform frequency analysis
- obtain theta, alpha, beta and gamma waves
- observe changes in those waves which are in correlation with emotional state
Also, we calculate nonlinear feature fractal dimension which represent complexity of nonlinear and chaotic EEG signal. By performing frequency analysis on Heart Rate, we obtain Heart Rate Variability feature which is in strong correlation with emotional state. With obtained set of features we train classification matrices with various classification algorithms such as fuzzy c-means or k nearest neighbours.
Our goal is determine matrix for each emotional class and perform classification for incoming (testing) set of features.

6. Scientific papers that we use to backup our methodology

• Davidson, Richard J. "What does the prefrontal cortex “do” in affect: perspectives on frontal EEG asymmetry research." Biological psychology 67.1 (2004): 219-234.
• Prichep, L. S., et al. "Quantitative EEG correlates of cognitive deterioration in the elderly." Neurobiology of aging 15.1 (1994): 85-90.
• Rosenfeld, J. Peter, et al. "Preliminary evidence that daily changes in frontal alpha asymmetry correlate with changes in affect in therapy sessions. “International Journal of Psychophysiology 23.1 (1996): 137-141.
• Berka, Chris, et al. "EEG correlates of task engagement and mental workload in vigilance, learning, and memory tasks." Aviation, space, and environmental medicine 78.Supplement 1 (2007): B231-B244.
• Dmochowski, Jacek P., et al. "Correlated components of on-going EEG point to emotionally laden attention–a possible marker of engagement?." Frontiers in human neuroscience 6 (2012).

7. Is your personal information secure?

Yes. To protect your information, we use Amazon Cloud servers as our online platform.
Amazon Cloud takes reasonable precautions and follows industry best practices to make sure your personal information is not inappropriately lost, misused, accessed, disclosed, altered or destroyed. All information you provide during the testing stays in the server and only our team can see it. Every respondent has an ID number that is visible on the results and there is no additional personal data to it.

8. Where the data is stored?

Your data will be stored on your mobile device and also securely stored on our cloud servers. All data is anonymized before being stored in the cloud. Unless you give us permission, no one will have access to the data stored on your device or in the cloud.

9. What do we do with the data? Can other people access this data?

All brainwave data is securely stored and is not publicly accessible. We follow strict ethics around data. Your data will remain strictly anonymous and confidential unless you give us explicit permission otherwise.


Please email us at support@idguardian.co.