Segmentation of design protocol using EEG

Abstract

Design protocol data analysis methods form a well-known set of techniques used by design researchers to further understand the conceptual design process. Verbal protocols are a popular technique used to analyze design activities. However, verbal protocols are known to have some limitations. A recurring problem in design protocol analysis is to segment and code protocol data into logical and semantic units. This is usually a manual step and little work has been done on fully automated segmentation techniques. Physiological signals such as electroencephalograms (EEG) can provide assistance in solving this problem. Such problems are typical inverse problems that occur in the line of research. A thought process needs to be reconstructed from its output, an EEG signal. We propose an EEG-based method for design protocol coding and segmentation. We provide experimental validation of our methods and compare manual segmentation by domain experts to algorithmic segmentation using EEG. The best performing automated segmentation method (when manual segmentation is the baseline) is found to have an average deviation from manual segmentations of 2 s. Furthermore, EEG-based segmentation can identify cognitive structures that simple observation of design protocols cannot. EEG-based segmentation does not replace complex domain expert segmentation but rather complements it. Techniques such as verbal protocols are known to fail in some circumstances. EEG-based segmentation has the added feature that it is fully automated and can be readily integrated in engineering systems and subsystems. It is effectively a window into the mind.

A framework for studying design thinking through measuring designers’ minds, bodies and brains

“…The correlation of results from different paradigms increases the overall understanding of the phenomenon being studied. Merging techniques to measure a task related to design has the potential to inform emotional evaluation of design 23/40 products, a key aspect of feedback in designing that informs designers (Tomico et al 2008;Kim et al 2012), design creativity (Carroll & Latulipe 2012), connection between emotions and CAD software for design tasks (Liu et al 2014), or can provide new methods to segment design protocols (Nguyen et al 2015(Nguyen et al , 2019. For example, Tomico et al (2008) explored the comfortableness of a designed object (pencils) based on the measurement of participants' emotions while evaluating the object, with a two-point EEG to monitor the fluctuation of alpha waves (design physiology) and a structured interview to gather subjective assessment of the object (design cognition).…”

“…The authors used a fuzzy model approach to define the emotions based on valence measured with EEG signals and arousal based on GSR and HR signals. Nguyen et al (2015Nguyen et al ( , 2019 pointed out the limits of manually segmented design protocols and explored how to use EEG data to perform that task. In their study, they compared manual segmentation to a set of algorithms that automatically segment the EEG dataset.…”

“…Using physiological or neurocognitive data to study design protocols can be a more efficient way to analyze design situations. As explored by Nguyen et al (2015Nguyen et al ( , 2019, EEG-based protocol segmentation is relevant to revealing design actions over time.…”

Review of the use of neurophysiological and biometric measures in experimental design research

“…The findings show a specific band, namely alpha, is highly correlated with the designer's resting in contrast to high-frequency bands associated with more active design segments. This stream of studies has so far reached maturation in Nguyen et al (2019), in which EEG-based algorithms are tested against manual segmentation of design activities. The most effective algorithm in terms of predicting design segments, based on microstate transitions already discussed in Nguyen et al (2015), is almost indistinguishable than manual segmentation if specific statistical tools are used.…”

“…(2014),Hill and Bohil (2016),Lohmeyer and Meboldt (2016),Balters and Steinert (2017),Ergan et al (2019),and Nguyen et al (2019). Anyway, the measures that are benefitted from in each source and the variables and phenomena that are associated to them are also included in…”