Electroencephalogram Experimentation to Understand Creativity of Mechanical Engineering Students

Abstract Electroencephalogram (EEG) alpha power (8–13 Hz) is a characteristic of various creative task conditions and involved in ideation. Alpha varies as function creativity-related demands. This study investigated the event-related potentials (ERPs), activation, potential machine learning (ML) to classify neural responses engineering students with creativity task. All participants performed modified alternate uses (AUT), which categorized functions (or uses) for everyday objects either creative, nonsense, or common. At first, this fundamental ERPs over central parietooccipital temporal areas. The bio-responses understand demonstrates that nonsensical stimuli elicit larger N400 amplitudes (−1.107 mV −0.755 mV, respectively) than common (0.0859 mV) on 300–500 ms window. effect was observed window from grand average waveforms each electrode interest. ANOVA analysis identified significant main effect: decreased during ideation, especially (O1/2, P7/8) area. Machine used specific area data’s (creative, common). A k-nearest neighbors (kNN) classifier used, results were evaluated terms accuracy, precision, recall, F1- score using collected datasets participants. With an overall 99.92% accuracy under curve at 0.9995, kNN successfully classified participants’ responses. These have great broader adaptation techniques research.