Feasibility of local interpretable model-agnostic explanations (LIME) algorithm as an effective and interpretable...

Many feature selection methods have been evaluated in functional near-infrared spectroscopy (fNIRS)-related studies. The local interpretable model-agnostic explanation (LIME) algorithm is a feature selection method for fNIRS datasets that has not yet been validated; the demand for its validation is increasing. To this end, we assessed the feature selection performance of LIME for fNIRS datasets in terms of classification accuracy. A comparative analysis was conducted for the benchmark (classification accuracy obtained without applying any feature selection method), LIME, two filter-based methods (minimum-redundancy maximum-relevance and t-test), and one wrapper-based method (sequential forward selection). To ensure the fairness and reliability of the performance evaluation, several open-access fNIRS datasets were used. The analysis revealed that LIME greatly outperformed the other feature selection methods in most cases and could achieve a statistically significantly better classification accuracy than that of the benchmark methods. These findings implied the effectiveness of LIME as a feature selection approach for fNIRS datasets.