A Complex Brain Learning Skeleton Comprising Enriched Pattern Neural Network System for Next Era Internet of Things

Abstract

The Internet of Things (IoT) is now growing dramatically on various levels and helps to digitize various vital industries quickly. The most difficult obstacle for BCIs to overcome is the fact that not everyone has the same brain. Every new session requires the BCI to learn from the user’s brain, which is accomplished via the use of machine learning. However, this learning process is time-consuming. Calibration time refers to the amount of time it takes for the BCI to adapt to the user’s brain in order to properly categorize their thoughts and determine their meaning. The patient has had to wait an arduous and tiresome length of time for the system to be completely functioning up until now because of this calibration, which may take up to 20–30 minutes. The aim of this paper was to find a way to decrease the amount of time required for calibration to the smallest amount feasible. In the first section of this paper, a first effort is made to determine the optimum number of features required for the BCI to operate reasonably, taking into consideration all of the calibration data provided. When the results were averaged across five participants, the percentage of properly identified thoughts was just 67.15 percent. Transfer learning was used in order to improve the performance of the BCI while simultaneously decreasing the calibration time. It is feasible to decrease the amount of calibration required for the categorization of thoughts coming from a new target subject by using knowledge collected from previously recorded subjects to the greatest extent possible in transfer learning. It was determined that existing methods were superior, and a new methodology was created that required just 24 seconds of calibration data while accurately identifying 86.8% of the thoughts. In order to alleviate mental stress and anger, the system suggested fits effectively with a deep learning network. This paper proposes a brain learning framework that uses a neural network model that is complex in nature and uses IoT for data collection from various wearable devices, and the same can be used for modelling the brain functions. Aside from the fact that categorization performance is assessed, a more relevant metric is the number of letters per minute that a user transmits. In addition to evaluating classification performance, there are methods that evaluate the amount of time necessary to complete specified tasks.