Classification of Prefrontal Cortex Activity Based on Functional Near-Infrared Spectroscopy Data upon Olfactory Stimulation

Brain Sciences

Po-Lei Lee¹  Cheng-Hsuan Chen¹  Kuo-Kai Shyu¹  Chi-Wen Jao²  Cheng-Kai Lu³ 

[1] Department of Electrical Engineering, National Central University, No.300, Zhongda Rd., Zhongli District, Taoyuan City 32001, Taiwan;Institute of Biophotonics, National Yang-Ming University, No.155, Sec. 2, Linong Street, Taipei 11221, Taiwan;Institute of Health & Analytics for Personalised Care, Universiti Teknologi PETRONAS, Seri Iskander 32610, Perak, Malaysia;

关键词: functional near-infrared spectroscopy;    olfaction;    hemoglobin response function;    support vector machine;    classification;    machine learning technique;   

DOI  :  10.3390/brainsci11060701

来源: DOAJ

【 摘 要 】

The sense of smell is one of the most important organs in humans, and olfactory imaging can detect signals in the anterior orbital frontal lobe. This study assessed olfactory stimuli using support vector machines (SVMs) with signals from functional near-infrared spectroscopy (fNIRS) data obtained from the prefrontal cortex. These data included odor stimuli and air state, which triggered the hemodynamic response function (HRF), determined from variations in oxyhemoglobin (oxyHb) and deoxyhemoglobin (deoxyHb) levels; photoplethysmography (PPG) of two wavelengths (raw optical red and near-infrared data); and the ratios of data from two optical datasets. We adopted three SVM kernel functions (i.e., linear, quadratic, and cubic) to analyze signals and compare their performance with the HRF and PPG signals. The results revealed that oxyHb yielded the most efficient single-signal data with a quadratic kernel function, and a combination of HRF and PPG signals yielded the most efficient multi-signal data with the cubic function. Our results revealed superior SVM analysis of HRFs for classifying odor and air status using fNIRS data during olfaction in humans. Furthermore, the olfactory stimulation can be accurately classified by using quadratic and cubic kernel functions in SVM, even for an individual participant data set.

【 授权许可】

Unknown