Key result
A within-subject classification method using LDA and SVM was implemented to classify hemodynamic responses in a synthetic infant fNIRS dataset, investigating the impact of noise and HRF amplitudes.
This proof-of-concept study demonstrates the potential of LDA and SVM for classifying hemodynamic responses in infant fNIRS data.
No immediate clinical use in infant fNIRS; hypothesis-generating for LDA/SVM classifiers pending real-data validation.
This study presents the implementation of a within-subject classification method, based on the use of Linear Discriminant Analysis (LDA) and Support Vector Machines (SVM), for the classification of hemodynamic responses. Using a synthetic dataset that closely resembles real experimental infant functional near-infrared spectroscopy (fNIRS) data, the impact of different levels of noise and different HRF amplitudes on the classification performances of the two classifiers are quantitively investigated.
No takes yet. Share an insight, caveat, or question.
Jessica Gemignani (2021) studied Hemodynamic responses (infant fNIRS data). Linear Discriminant Analysis (LDA) and Support Vector Machines (SVM) was evaluated on Classification performances under different levels of noise and HRF amplitudes. A within-subject classification method using LDA and SVM was implemented to classify hemodynamic responses in a synthetic infant fNIRS dataset, investigating the impact of noise and HRF amplitudes.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: