A FRAMEWORK FOR DECODING PHYSIOLOGICAL AND NEURAL SIGNAL USING LONG SHORT-TERM MEMORY (LSTM)

Abstract

Machine learning for deciphering physiological and neural signals holds great promise for use in creating brain-computer interfaces. (BCIs). Brain-computer interfaces (BCIs) are tools for using mental activity to operate mechanical or electronic equipment. To convert these signals into actionable instructions for the external device, machine learning algorithms are employed. Brain-computer interfaces (BCIs) have shown considerable promise in enhancing the lives of people who are unable to use their limbs normally due to injury or illness. This paper presents an LSTM model for the decoding of physiological and neural signals. In this paper, an electroencephalography brain signal data was used. The dataset was pre-processed so as to remove noise from the data. The pre-processed data was used in training the LSTM model. The LSTM model was trained on fourteen (14) steps. The result of the LSTM model showed an accuracy of 85% at the first step and a validation (testing) accuracy of 90%. For the fourteenth step, the model achieved an accuracy result of 98% for training and 94% for validation (testing). We also evaluated the performance of the model using a classification report and confusion matrix. The result of the classification report shows an accuracy of 95%. This means that the performance of the model on the test data is efficient. The confusion matrix was used in how well the model classified the electroencephalography signal The result of the confusion matrix shows that the model predicted the result correctly to be neutral 151 out of 153, positive to be 127 out of 142, and negative to be 128 out of 132. The result shows that the level of false positive and negative values is minimal.