Machine Learning for Functional Brain Mapping

Björnsdotter, Malin

doi:10.5772/8605

Cited by 3 publications

(1 citation statement)

References 77 publications

(80 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning algorithms, and their approach to data mining ranging from pattern recognition to classification, provide relevant tools for the analysis of neuroimaging data (see [ 1 – 12 ] for recent reviews and examples with different neuroimaging modalities and pathologies). Indeed, modern technologies such as magnetic resonance imaging (MRI), magnetoencephalography (MEG) and electroencephalography (EEG) generate an enormous amount of data per subject in a single recording session, which call for exactly these kind of algorithms to extract relevant information for applications such as, e.g., categorical discrimination of patients from matched healthy controls or prediction of individual (clinical and non clinical) variables.…”

Section: Introductionmentioning

confidence: 99%

The blessing of Dimensionality: Feature Selection outperforms functional connectivity-based feature transformation to classify ADHD subjects from EEG patterns of phase synchronisation

et al. 2018

View full text Add to dashboard Cite

Functional connectivity (FC) characterizes brain activity from a multivariate set of N brain signals by means of an NxN matrix A, whose elements estimate the dependence within each possible pair of signals. Such matrix can be used as a feature vector for (un)supervised subject classification. Yet if N is large, A is highly dimensional. Little is known on the effect that different strategies to reduce its dimensionality may have on its classification ability. Here, we apply different machine learning algorithms to classify 33 children (age [6-14 years]) into two groups (healthy controls and Attention Deficit Hyperactivity Disorder patients) using EEG FC patterns obtained from two phase synchronisation indices. We found that the classification is highly successful (around 95%) if the whole matrix A is taken into account, and the relevant features are selected using machine learning methods. However, if FC algorithms are applied instead to transform A into a lower dimensionality matrix, the classification rate drops to less than 80%. We conclude that, for the purpose of pattern classification, the relevant features should be selected among the elements of A by using appropriate machine learning algorithms.

show abstract

Section: Introductionmentioning

confidence: 99%

The blessing of Dimensionality: Feature Selection outperforms functional connectivity-based feature transformation to classify ADHD subjects from EEG patterns of phase synchronisation

et al. 2018

View full text Add to dashboard Cite

show abstract

Feeling good: on the role of C fiber mediated touch in interoception

2010

View full text Add to dashboard Cite

The human skin is innervated by a network of thin, slow-conducting afferent (C and Aδ) fibers, transmitting a diverse range of information. Classically, these fibers are described as thermo-, noci- or chemoreceptive, whereas mechanoreception is attributed exclusively to thick, fast-conducting (Aβ) afferents. A growing body of evidence, however, supports the notion that C tactile afferents comprise a second anatomically and functionally distinct system signaling touch in humans. This review discusses established as well as recent findings which highlight fundamental differences in peripheral and central information coding and processing between Aβ and C mechanoreception. We conclude that from the skin through the brain, C touch shares more characteristics with interoceptive modalities (e.g. pain, temperature, and itch) than exteroceptive Aβ touch, vision or hearing. In this light, we discuss the motivational-affective role of C touch as an integral part of a thin-fiber afferent homeostatic network for the maintenance of physical and social well-being.

show abstract