Advancing Object Recognition: Integrating AI with Laser-Integrated Graphene Electrodes for Enhanced Neural Signal Analysis

Object recognition by the human mind seems almost instantaneous, however there is an involved visual processing time that has to be accounted in the calculations. In this work, exploratory factor analyses, machine learning and artificial algorithms for peak amplitudes obtained from 15 participants using reduced graphene oxide electrode-based setup were used. In previous work, these electrodes have demonstrated to have low signal to noise ratio, high biocompatibility, and high reproducibility making them suitable for neurocognitive signal investigation. In this work, the machine learning algorithms were used to check usability of artificial intelligence on detecting visual factors from neural signal data. Machine learning models included, decision tree classifier, random forest classifier, support vector machine, k-nearest neighbors, and neural network algorithm. Furthermore, feature importance was also discussed to form a basis for further research. Our analyses reveal the utility of artificial intelligence and machine learning models in real time object detection, particularly living versus non-living objects from neural signals.