Assessment of Subjective Creativity Skill Using EEG Induced Capsule Network

5 Jan 2021  ·  Sayantani Ghosh, Lidia Ghosh, Amit Konar, Atulya K. Nagar ·

Problem solving tests associated with convergent thinking are often used to analyze the creative ability of an individual. Such tests consist of problems whose solution can be reached by an analytical or a creative insight based approach... Detection of creative individuals amongst others undertaking such tests is thus quite challenging since a correct response to the presented problem can be reached using two different cognitive styles. The paper attempts to address a solution to this issue using EEG analysis system. The proposed technique intends to classify the two cognitive styles involved in solving convergent problems with the main motivation of selecting creative individuals amongst other examinees. Moreover, the proposed strategy also attempts to highlight the creative ability of every selected creative individual under three levels: low, medium or high. In other words, the present scheme aims to distinguish creative subjects along with their levels of creative ability from the analytical ones. The procurement of EEG signals from the subjects engaged in the problem solving test are fed to a novel attention induced capsule network to categorize the desired class labels after undergoing the pre-processing and feature extraction phases. Performance analysis undertaken confirms the superlative behavior of the proposed classifier over the state-of-the-art techniques. Thus, the proposed scheme can find its applications in the recruitment of creative individuals in various strata of organizations linked with creation and innovation such as advertising, business, engineering and the like. read more

PDF
No code implementations yet. Submit your code now

Tasks


Datasets


  Add Datasets introduced or used in this paper

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods