Determination of patterns in the EEG signals during relaxation through music using Bayesian Networks

Abstract—Today it is known that the brain waves behave during relaxation through music, however, it is not yet known whether there is a pattern of dependencies between different EEG frequencies during those processes. Brain oscillations are often underestimated as compared to slower oscillations. Mean  power  spectra  of  scalp  EEG  signals  exhibit  distinct  peaks  emerging  from  the  general  decrease  in  power  with  increasing  frequency,  suggesting  the  existence  of  characteristic  dependence oscillatory  modes  in  cortical field potentials. The interactions between peaks in different frequency bands, within and between cortical EEG sources, are not well understood. The reviewed evidence supports the theory that relaxation through music can lead to behavioral and neuron chemical changes with benefic effects. This study was to address this concept by focusing on Bayesian Networks (BN) to describe the relationship between the EEG frequencies during relaxation through music. It was obtained a model with 97.7% to accuracy, in which shows the relations between each EEG signals. The dependency probability distribution was calculated, according to the signal amplitude behavior. Music changes the behavior of the low frequency signals, synchronizing them inversely proportional. Delta and theta interactions over Alpha promote increase Alpha 1 powers in relaxation through music. This event is accompanied by synchronized interaction of low-sequence signals, from Beta 1 to Gamma. Alpha 2 remains an independent variable. Further studies are needed to understand the differences between music and their subsequent effects on behavior. However, Bayesian Networks has been show to an excellent tool of EEG signal Analysis.

Key word: Bayesian Networks, Brain, Machine learning, Data mining.

Click here to Download Full Paper

Medical Journal: Determination of patterns in the EEG signals during relaxation through music using Bayesian Networks

AD Publications is a rapidly growing academic publisher in the fields of Engineering, Medical-Health, Environmental Science and Agriculture Research. AD Publications is a registered organization broad-based open access and publishes most exciting researches with respect to the subjects of our journals. The Journals is being indexed and abstracted by all major global current awareness and alerting services.
The organization aims at undertaking, co- coordinating and promoting research and development. It provides professional and academic guidance in the field of basic education, Higher Education as well in the Technical Education. Our Aims is to Promote and support, High Quality basic, Scientific Research and development in fields of Engineering, Medical-Health, Environmental Science and Agriculture Research and to Generate Public awareness, provide advice to scholar’s researchers and communicate research outcomes.

Some Important Links About Research Journal
International Journal
Agriculture Journal
Medical Journal
Environmental Journal
Engineering Journal

Translate »