EEG based preferential neuro-marketing cataloguing using deep learning mechanism using swarm optimization

Abstract

Conventional promotional methods (e.g., small screen advertisements and print media commercials fail to sell commodities since they do not adequately inspire buyers to buy a certain item for consumption. Such old-style promoting tactics intended to assess a consumer’s opinion about a product that might or might not reflect the authentic conduct at the point - of - procurement. The sole objective of this proposal is to bridge the gap between traditional market research that would be based on explicit customer responses, and neuro-marketing research that is based on implicit consumer attitudes. In neuro-marketing, EEG-based preference, recognition has been thoroughly examined. Other limitation in neuro-marketing study is the unavailability of comprehensive data-mining tools for consumer perception classification and prediction. Therefore, the consumer preferences are predicted with EEG signals in this research work using a deep-learning approach. The proposed work follows these most important phases such as Data Sources, Data Collection, treating data with the aid of Pre-processing followed feature abstraction and preference detection. Initially, the collected statistics is exposed to data cleaning and pre-processing, where the filtering network i.e. DBN is educated. To enrich its forecast efficacy, the parameters like biases and weights of DBN is honed via a novel enriched optimization mechanism denoted as Customized beetle swarm optimization i.e. (CBSO), which is the intangible enhancement of customary beetle swarm optimization i.e. (BSO) process.