Jagannath Nalavade Nileema Prasad Gaikwad
This research presents the development and application of a new Brainwave Driven Advertisement Recommendation System that integrates the state-of-the-art Emotive Insight hardware, Brain-Computer Interface, and Artificial Intelligence. The primary objective of the proposed technology is to advance the state-of-the-art in both accuracy and personalization in ad recommendations through direct utilization of people's neural responses. The brain wave frequencies that will be recorded using Emotive Insight gear include: alpha, beta, theta, delta, and gamma waves. This rich dataset is diligently stored in both edf formats for further comprehensive processing. Three different commercials are shown to study participants: Snickers, Dairy Milk, and 5-star. The effect of each advertisement is tested by measuring their brain reactions concurrently. The users then comment on their favorite ads, therefore establishing a clear relationship between subjective beliefs and brainwave patterns. In order to make sure significant insights can be extracted, careful preprocessing, removal of artifacts, and features extraction were performed during the data analysis stage. A variety of machine learning approaches were used to build a robust prediction model, and the performances were cross-validated using metrics such as accuracy, precision, recall, and F1 score.