 This research proposes a novel joint channel connectivity-based feature selection and classification algorithm for functional near-infrared spectroscopy, FNIRS, to detect stress and decision making. The algorithm combines feature selection and classifier modeling into a single process, while also taking into account the correlations between channels corresponding to the brain. This approach is able to identify discriminative features from the data, as well as determine the best channel settings for FNIRS. Furthermore, the correlation of brain regions calculated by feature selection has been confirmed in previous studies, which validates the effectiveness of the proposed method. Ultimately, this work could be beneficial for medical personnel to automatically detect stress in clinical decision-making situations. This article was authored by May-Yan Huang, Xiaoling Zhang, Xiumei Chen, and others.