AUTHOR=Pradeep V. , Jayachandra Ananda Babu , Askar S. S. , Abouhawwash Mohamed 

TITLE=Hyperparameter tuning using Lévy flight and interactive crossover-based reptile search algorithm for eye movement event classification

JOURNAL=Frontiers in Physiology

VOLUME=Volume 15 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/physiology/articles/10.3389/fphys.2024.1366910

DOI=10.3389/fphys.2024.1366910

ISSN=1664-042X

ABSTRACT=Eye movement is one of the cues which is used in human-machine interface technologies for predicting the intention of users. The developing application in eye movement event detection is the creation of assistive technologies for paralyzed patients. But, developing an effective classifier is one of the main issues in eye movement event detection. In this paper, bidirectional Long Short-Term Memory referred BILSTM is proposed along with hyperparameter tuning for achieving an effective eye movement event classification. The Lévy flight and Interactive Crossover based Reptile Search Algorithm (LICRSA) is used for optimizing the hyperparameters of BILSTM. The issues related to overfitting are avoided by using Fuzzy Data Augmentation (FDA) and deep neural network namely VGG-19 is used for extracting features from the eye movements. Therefore, the optimization of hyperparameters using LICRSA is used to enhance the classification of eye movement events using BILSTM. The proposed BILSTM-LICRSA is evaluated by using accuracy, precision, sensitivity, F1-score, Area Under the Receiver Operating Characteristic (AUROC) curve measure, and Area Under The Precision-Recall Curve (AUPRC) measure for four datasets namely, Lund2013, Collected dataset, GazeBaseR, and UTMultiView. The gazeNet, Human Manual Classification (HMC), and Multi-Source Information Embedded Approach (MSIEA) are utilized for comparison with the BILSTM-LICRSA. The F1-score of BILSTM-LICRSA for the GazeBaseR dataset is 98.99% which is higher when compared to the MSIEA.