Conference Paper

Non-invasive neuroimaging: Generalized Linear Models for interpreting functional Near Infrared Spectroscopy signals

Dept. of Biomed. Eng., Polytech. Univ. of Milan
DOI: 10.1109/CNE.2007.369709 Conference: Neural Engineering, 2007. CNE '07. 3rd International IEEE/EMBS Conference on
Source: IEEE Xplore


Cognitive activity is related to important changes in the local blood flow level and in the oxygenation of the blood. These two effects lead to a modification of the optical properties of the cerebral cortex. With the aid of the functional near infrared spectroscopy (fNIRS) technique it is possible, through optical measures, to achieve information about the hemodynamic features of the brain activation. The aim of this study was to find a method to identify and to map the cerebral areas activated during a sustained attention task (Conner's continuous performance test - CPT) in a group of healthy subjects. This information will be of fundamental interest for a following study on a group of patients that will be administered the same examination. We propose a new analysis method based on the theory of generalized linear model (GLM) in order to obtain intuitive cerebral activation maps during the performing of cognitive tasks

Download full-text


Available from: Anna Rodriguez Merzagora,
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Passive brain-computer interfaces are designed to use brain activity as an additional input, allowing the adaptation of the interface in real time according to the user's mental state. The goal of the present study is to distinguish be- tween different levels of game difficulty using real-time, non-invasive brain activity measurement with functional near-infrared spectroscopy (fNIRS). The study is designed to lead to adaptive interfaces that respond to the user's brain activity in real time. Nine subjects played two levels of the game Pacman while their brain activity was measured using fNIRS. Statistical analysis and machine learning classifica- tion results show that we can discriminate well between subjects playing or resting, and distinguish between the two levels of difficulty with some success. These results show potential for using fNIRS in an adaptive game or user inter- face. This work is an improvement on previous fNIRS game studies which seldom try to tell apart two levels of brain activity.
    Human-Computer Interaction - INTERACT 2009, 12th IFIP TC 13 International Conference, Uppsala, Sweden, August 24-28, 2009, Proceedings, Part I; 08/2009
  • Source

    09/2013; 2(3):62-84. DOI:10.5898/JHRI.2.3.Canning