Enhancing Cognitive Workload Classification Using Integrated LSTM Layers and CNNs for fNIRS Data Analysis

The paper presents a deep learning model that integrates Long Short-Term Memory (LSTM) layers with Convolutional Neural Networks (CNNs) to improve cognitive workload classification using functional near-infrared spectroscopy (fNIRS) data. The study reports an increase in classification accuracy from 97.40% to 97.92% by addressing issues of spatial feature overfitting and temporal dependency. This advancement is significant for practitioners as it enhances the ability to accurately assess cognitive states, potentially improving applications in neuroergonomics and cognitive load monitoring.