Classifying creativity: Applying machine learning techniques to divergent thinking EEG data

A Machine Learning Approach to Classifying EEG Data Collected with or without Haptic Feedback during a Simulated Drilling Task

Artificial Intelligence (AI), computer simulations, and virtual reality (VR) are increasingly becoming accessible tools that can be leveraged to implement training protocols and educational resources. Typical assessment tools related to sensory and neural processing associated with task performance in virtual environments often rely on self-reported surveys, unlike electroencephalography (EEG), which is often used to compare the effects of different types of sensory feedback (e.g., auditory, visual, and haptic) in simulation environments in an objective manner. However, it can be challenging to know which aspects of the EEG signal represent the impact of different types of sensory feedback on neural processing. Machine learning approaches offer a promising direction for identifying EEG signal features that differentiate the impact of different types of sensory feedback during simulation training. For the current study, machine learning techniques were applied to differentiate neural circuitry associated with haptic and non-haptic feedback in a simulated drilling task. Nine EEG channels were selected and analyzed, extracting different time-domain, frequency-domain, and nonlinear features, where 360 features were tested (40 features per channel). A feature selection stage identified the most relevant features, including the Hurst exponent of 13-21 Hz, kurtosis of 21-30 Hz, power spectral density of 21-30 Hz, variance of 21-30 Hz, and spectral entropy of 13-21 Hz. Using those five features, trials with haptic feedback were correctly identified from those without haptic feedback with an accuracy exceeding 90%, increasing to 99% when using 10 features. These results show promise for the future application of machine learning approaches to predict the impact of haptic feedback on neural processing during VR protocols involving drilling tasks, which can inform future applications of VR and simulation for occupational skill acquisition.

Operating in a second language lowers cognitive interference during creative idea generation: Evidence from brain oscillations in bilinguals

Tasks measuring human creativity overwhelmingly rely on both language comprehension and production. Although most of the world's population is bilingual, few studies have investigated the effects of language of operation on creative output. This is surprising given that fluent bilinguals master inhibitory control, a mechanism also at play in creative idea evaluation. Here, we compared creative output in the two languages of Polish(L1)-English(L2) bilinguals engaged in a cyclic adaptation of the Alternative Uses Task increasing the contribution of idea evaluation (convergent thinking). We show that Polish-English bilinguals suffer less cognitive interference when generating unusual uses for common objects in the L2 than the L1, without incurring a significant drop in idea originality. Right posterior alpha oscillation power, known to reflect creative thinking, increased over cycles. This effect paralleled the increase in originality ratings over cycles, and lower alpha power (8-10 Hz) was significantly greater in the L1 than the L2. Unexpectedly, we found greater beta (16.5-28 Hz) desynchronization in the L2 than the L1, suggesting that bilingual participants suffered less interference from competing mental representations when performing the task in the L2. Whereas creative output seems unaffected by language of operation overall, the drop in beta power in the L2 suggests that bilinguals are not subjected to the same level of semantic flooding in the second language as they naturally experience in their native language.

EEG-based study of design creativity: a review on research design, experiments, and analysis

Brain dynamics associated with design creativity tasks are largely unexplored. Despite significant strides, there is a limited understanding of the brain-behavior during design creation tasks. The objective of this paper is to review the concepts of creativity and design creativity as well as their differences, and to explore the brain dynamics associated with design creativity tasks using electroencephalography (EEG) as a neuroimaging tool. The paper aims to provide essential insights for future researchers in the field of design creativity neurocognition. It seeks to examine fundamental studies, present key findings, and initiate a discussion on associated brain dynamics. The review employs thematic analysis and a forward and backward snowball search methodology with specific inclusion and exclusion criteria to select relevant studies. This search strategy ensured a comprehensive review focused on EEG-based creativity and design creativity experiments. Different components of those experiments such as participants, psychometrics, experiment design, and creativity tasks, are reviewed and then discussed. The review identifies that while some studies have converged on specific findings regarding EEG alpha band activity in creativity experiments, there remain inconsistencies in the literature. The paper underscores the need for further research to unravel the interplays between these cognitive processes. This comprehensive review serves as a valuable resource for readers seeking an understanding of current literature, principal discoveries, and areas where knowledge remains incomplete. It highlights both positive and foundational aspects, identifies gaps, and poses lingering questions to guide future research endeavors.

An EEG study on artistic and engineering mindsets in students in creative processes

This study aims to take higher-education students as examples to understand and compare artistic and engineering mindsets in creative processes using EEG. Fifteen Master of Fine Arts (MFA) visual arts and fifteen Master of Engineering (MEng) design engineering students were recruited and asked to complete alternative uses tasks wearing an EEG headset. The results revealed that (1) the engineering-mindset students responded to creative ideas faster than artistic-mindset students. (2) Although in creative processes both artistic- and engineering-mindset students showed Theta, Alpha, and Beta wave activity, the active brain areas are slightly different. The active brain areas of artistic-mindset students in creative processes are mainly in the frontal and occipital lobes; while the whole brain (frontal, oriental, temporal, and occipital lobes) was active in creative processes of engineering-mindset students. (3) During the whole creative process, the brain active level of artistic-mindset students was higher than that of engineering-mindset students. The results of this study fills gaps in existing research where only active brain areas and band waves were compared between artistic- and engineering-mindset students in creative processes. For quick thinking in terms of fluency of generating creative ideas, engineering students have an advantage in comparison to those from the visual arts. Also, the study provided more evidence that mindset can affect the active levels of the brain areas. Finally, this study provides educators with more insights on how to stimulate students' creative ability.

Reduced occipital alpha power marks a movement induced state change that facilitates creative thinking

Walking and minimized movement restriction has a positive effect on creativity, such as divergent thinking. Walking is further known to reduce occipital alpha activity. We used mobile EEG during free and restricted movement, while subjects (N = 23) solved a Guilford's alternate uses test, to understand if occipital alpha power is also affected by movement restriction and if it is a neural marker for creativity. We found that, independent of the task, relative occipital alpha power was higher during movement restriction and showed a negative relationship with creativity scores even though the task was purely based on auditory information. Alpha lateralization was only modulated during the task related think-time (mainly during sitting) and showed a positive relationship with creativity scores but no correlation with the relative alpha power. This indicates that the ongoing alpha power and alpha lateralization mark two independent processes. Overall, our work shows that movement and movement restriction leads to a general change in state which affects cognitive processes. Specifically, limiting one's movements e.g. due to sitting and fixating on a screen can introduce a state of increased occipital alpha power and lowered creativity.

Impacts of Cognitive Factors on Creativity Quality in Design: Identification from Performances in Recall, Association and Combination

The reason why people have different creativity quality levels may depend on their different performances relating to other cognitive factors that are important for creativity. This study was designed to identify the performance of three cognitive factors (recall, association, and combination) that a designer may use in a creative process and then identify how the differing performance for these cognitive factors will affect creativity quality levels. Seventy-one participants were recruited to undertake a design task and complete a semi-structured interview. The results indicate that, in a creative design process, similar performances in recall, association, and combination can result in differences in creativity quality level.

Beyond alpha-band: The neural correlate of creative thinking

The compound nature of creativity entails the interplay of multiple cognitive processes, making it difficult to attribute creativity to a single neural signature. Divergent thinking paradigms, widely adopted to investigate creative production, have highlighted the key role of specific mental operations subserving creativity, such as inhibition of external stimuli, loose semantic associations, and mental imagery. Neurophysiological studies have typically shown a high alpha rhythm synchronization when individuals are engaged in creative ideation. Also, oculomotor activity and pupil diameter have been proposed as useful indicators of mental operations involved in such a thinking process. The goal of this study was to investigate whether beyond alpha-band activity other higher frequency bands, such as beta and gamma, may subserve divergent and convergent thinking and whether those could be associated with a different gaze bias and pupil response during ideas generation. Implementing a within-subjects design we collected behavioral measures, neural activity, gaze patterns, and pupil dilation while participants performed a revised version of the Alternative Uses Task, in which divergent thinking is contrasted to convergent thinking. As expected, participants took longer to generate creative ideas as compared to common ones. Interestingly, during divergent thinking participants displayed alpha synchronization along with beta and gamma desynchronization, more pronounced leftward gaze shift, and greater pupil dilation. During convergent thinking, an opposite pattern was observed: desynchronization in alpha and an increase in beta and gamma rhythm, along with a reduction of leftward gaze shift and greater pupil constriction. The present study uncovered specific neural dynamics and physiological patterns during idea generation, providing novel insight into the complex physiological signature of creative production.

Functional brain activation patterns of creative metacognitive monitoring

Creative metacognitive monitoring represents the ability to accurately evaluate the quality of own ideas during idea generation. To the best of our knowledge, this study presents the first EEG investigation of creative metacognitive monitoring in the brain, using data, of 100 participants, who generated single, original uses of common objects (alternate uses task). After each response, participants subjectively rated the creative quality of their idea. Additionally, five independent external judges rated the creative quality of all ideas. The correspondence between the subjective and the external performance ratings served as a measure of monitoring accuracy. We applied a generalized linear mixed effects model to investigate effects of creative metacognitive monitoring and creative potential on EEG activity in the alpha band at idea and person level. Participants with both higher monitoring skills and higher creative potential showed stronger alpha power decreases at parietal/occipital sites during creative idea generation and evaluation. Interestingly, only more creative people with lower metacognitive monitoring skills showed the expected alpha power increases at parietal/occipital sites during both phases. Furthermore, metacognitive monitoring skills were associated with lower frontal and temporal/central alpha power during idea evaluation (compared to generation) at the person level. This pattern of findings seems to suggest that less internal attention, less memory load, and increased sensory processing are associated with more effective and accurate monitoring of the creative process. This study sheds first light on the brain mechanisms underlying the interplay of creative metacognitive monitoring skills and creative potential.

Understanding creativity process through electroencephalography measurement on creativity-related cognitive factors

Introduction

Neurotechnology approaches, such as electroencephalography (EEG), can aid understanding of the cognitive processes behind creativity.

Methods

To identify and compare the EEG characteristics of creativity-related cognitive factors (remote association, common association, combination, recall, and retrieval), 30 participants were recruited to conduct an EEG induction study.

Results

From the event-related potential (ERP) results and spectral analysis, the study supports that creativity is related to the frontal lobe areas of the brain and common association is an unconscious process.

Discussion

The results help explain why some creativity-related cognitive factors are involved either more or less readily than others in the creative design process from workload aspects. This study identifies the part of the brain that is involved in the combination cognitive factor and detects the ERP results on cognitive factors. This study can be used by designers and researchers to further understand the cognitive processes of creativity.

The time course of creativity: multivariate classification of default and executive network contributions to creative cognition over time

Research indicates that creative cognition depends on both associative and controlled processes, corresponding to the brain's default mode network (DMN) and executive control network (ECN) networks. However, outstanding questions include how the DMN and ECN operate over time during creative task performance, and whether creative cognition involves distinct generative and evaluative stages. To address these questions, we used multivariate pattern analysis (MVPA) to assess how the DMN and ECN contribute to creative cognition over three successive time phases during the production of a single creative idea. Training classifiers to predict trial condition (creative vs non-creative), we used classification accuracy as a measure of the extent of creative activity in each brain network and time phase. Across both networks, classification accuracy was highest in early phases, decreased in mid phases, and increased again in later phases, following a U-shaped curve. Notably, classification accuracy was significantly greater in the ECN than the DMN during early phases, while differences between networks at later time phases were non-significant. We also computed correlations between classification accuracy and human-rated creative performance, to assess how relevant the creative activity in each network was to the creative quality of ideas. In line with expectations, classification accuracy in the DMN was most related to creative quality in early phases, decreasing in later phases, while classification accuracy in the ECN was least related to creative quality in early phases, increasing in later phases. Given the theorized roles of the DMN in generation and the ECN in evaluation, we interpret these results as tentative evidence for the existence of separate generative and evaluative stages in creative cognition that depend on distinct neural substrates.

More creative ideas are associated with increased right posterior power and frontal-parietal/occipital coupling in the upper alpha band: A within-subjects study

The neurophysiological investigation of creative idea generation is a growing research area. EEG studies congruently reported the sensitivity of upper alpha power (10-12 Hz) for the creative ideation process and its outcome. However, the majority of studies were between-subject design studies and research directly comparing the neurophysiological activation pattern when generating more and less creative ideas within a person are rare. Therefore, the present study was specifically focused on investigating brain activation patterns associated with the generation of more vs. less creative ideas. We applied an alternate uses task (AU-task; i.e., finding original uses for everyday objects such as a brick) in a sample of 74 participants and recorded the brain activation during the AU-task and reference period. A portable EEG system with 21 dry electrodes arranged in the international 10-20 system and linked ear as reference was used. We found a higher increase of upper alpha power during creative ideation (relative to reference period, i.e., task-related power, TRP) over right posterior sites when people generated more compared to less creative ideas. This was accompanied by an increase of functional coupling (i.e., task-related coherence increase) between frontal and parietal/occipital sites, which suggests higher internal attention and more control over sensory processes. Taken together, these findings complement the existing creativity research literature and indicate the importance of alpha power for the creative ideation process also within people.

Power Spectrum and Connectivity Analysis in EEG Recording during Attention and Creativity Performance in Children

The present research aims at examining the power spectrum and exploring functional brain connectivity/disconnectivity during concentration performance, as measured by the d2 test of attention and creativity as measured by the CREA test in typically developing children. To this end, we examined brain connectivity by using phase synchrony (i.e., phase locking index (PLI) over the EEG signals acquired by the Emotiv EPOC neuroheadset in 15 children aged 9- to 12-years. Besides, as a complement, a power spectrum analysis of the acquired signals was performed. Our results indicated that, during d2 Test performance there was an increase in global gamma phase synchronization and there was a global alpha and theta band desynchronization. Conversely, during CREA task, power spectrum analysis showed a significant increase in the delta, beta, theta, and gamma bands. Connectivity analysis revealed marked synchronization in theta, alpha, and gamma. These findings are consistent with other neuroscience research indicating that multiple brain mechanisms are indeed involved in creativity. In addition, these results have important implications for the assessment of attention functions and creativity in clinical and research settings, as well as for neurofeedback interventions in children with typical and atypical development.

Design Meets Neuroscience: An Electroencephalogram Study of Design Thinking in Concept Generation Phase

Extant research on design thinking is subjective and limited. This manuscript combines protocol analysis and electroencephalogram (EEG) to read design thoughts in the core design activities of concept generation phase. The results suggest that alpha band power had event related synchronization (ERS) in the scenario task and divergent thinking occupies a dominant position. However, it had event related desynchronization (ERD) in analogy and inference activities, etc., and it is stronger for mental pressure and exercised cognitive processing. In addition, the parietooccipital area differs significantly from other brain areas in most design activities. This study explores the relationship of different design thinking and EEG data, which is innovative and professional in the field of design, providing a more objective data basis and evaluation method for future applied research and diverse educational practices.

Decoding motor expertise from fine-tuned oscillatory network organization

Can motor expertise be robustly predicted by the organization of frequency-specific oscillatory brain networks? To answer this question, we recorded high-density electroencephalography (EEG) in expert Tango dancers and naïves while viewing and judging the correctness of Tango-specific movements and during resting. We calculated task-related and resting-state connectivity at different frequency-bands capturing task performance (delta [δ], 1.5-4 Hz), error monitoring (theta [θ], 4-8 Hz), and sensorimotor experience (mu [μ], 8-13 Hz), and derived topographical features using graph analysis. These features, together with canonical expertise measures (i.e., performance in action discrimination, time spent dancing Tango), were fed into a data-driven computational learning analysis to test whether behavioral and brain signatures robustly classified individuals depending on their expertise level. Unsurprisingly, behavioral measures showed optimal classification (100%) between dancers and naïves. When considering brain models, the task-based classification performed well (~73%), with maximal discrimination afforded by theta-band connectivity, a hallmark signature of error processing. Interestingly, mu connectivity during rest outperformed (100%) the task-based approach, matching the optimal classification of behavioral measures and thus emerging as a potential trait-like marker of sensorimotor network tuning by intense training. Overall, our findings underscore the power of fine-tuned oscillatory network signatures for capturing expertise-related differences and their potential value in the neuroprognosis of learning outcomes.

Neural Decoding of EEG Signals with Machine Learning: A Systematic Review

Electroencephalography (EEG) is a non-invasive technique used to record the brain's evoked and induced electrical activity from the scalp. Artificial intelligence, particularly machine learning (ML) and deep learning (DL) algorithms, are increasingly being applied to EEG data for pattern analysis, group membership classification, and brain-computer interface purposes. This study aimed to systematically review recent advances in ML and DL supervised models for decoding and classifying EEG signals. Moreover, this article provides a comprehensive review of the state-of-the-art techniques used for EEG signal preprocessing and feature extraction. To this end, several academic databases were searched to explore relevant studies from the year 2000 to the present. Our results showed that the application of ML and DL in both mental workload and motor imagery tasks has received substantial attention in recent years. A total of 75% of DL studies applied convolutional neural networks with various learning algorithms, and 36% of ML studies achieved competitive accuracy by using a support vector machine algorithm. Wavelet transform was found to be the most common feature extraction method used for all types of tasks. We further examined the specific feature extraction methods and end classifier recommendations discovered in this systematic review.

Brain activation during the observation of real soccer game situations predicts creative goal scoring

Creativity is an important source of success in soccer players. In order to be effective in soccer, unpredictable, sudden and at the same time creative (i.e. unique, original and effective) ideas are required in situations with high time pressure. Accordingly, creative task performance in soccer should be primarily driven by rapid and automatic cognitive processes. This study investigated if functional patterns of brain activation during the observation/encoding of real soccer game situations can predict creative soccer task performance. A machine learning approach (multivariate pattern recognition) was applied in a sample of 35 experienced male soccer players. The results revealed that brain activation during the observation of the soccer scenes significantly predicted creative soccer task performance, while brain activation during the subsequent ideation/elaboration period did not. The identified brain network included areas such as the angular gyrus, the supramarginal gyrus, the occipital cortex, parts of the cerebellum and (left) supplementary motor areas, which are important for semantic information processing, memory retrieval, integration of sensory information and motor control. This finding suggests that early and presumably automatized neurocognitive processes, such as (implicit) knowledge about motor movements, and the rapid integration of information from different sources are important for creative task performance in soccer.