Professor Dr. Tahir Ahmad
Universiti Teknologi Malaysia

Title: Hacking EEG Data of Epileptic Seizure

Abstract:

Data science is in-depth knowledge discovery through data inference and exploration. This discipline often involves using mathematic and algorithmic techniques to solve some of the most analytically complex problems, leveraging troves of raw information to uncover hidden insights that lie beneath the surface. It centers on evidence-based analytical rigour and building robust decision capabilities. It is multidisciplinary; the skill set of a data scientist lies at the intersection of 3 main competencies, namely mathematics expertise, hacking skills and strategy acumen. At the heart of deriving insight from data is the ability to view the data through a quantitative lens. There are patterns, dimensions, and correlations in data that can be expressed numerically, and discovering inference from data becomes a brain teaser of mathematical techniques. A sample of this brain teaser is the hacking of electrical signals, namely Electroencephalography (EEG) emanated from human brain, which can be collected from the scalp of the head. Careful analysis of the EEG data can provide new insights into the epileptogenic process and may have considerable utilization in the diagnosis and treatment of epilepsy. Surprisingly, EEG signals during epileptic seizure (brainstorm) contain ordered patterns, hence patterns of seizure. The EEG signals during epileptic seizure can be shown as a semigroup of square matrices under matrix multiplication whereby some patterns out of the seizure data are obtained using Krohn-Rhodes decomposition theorem. An extensive mathematical groundwork of elementary components will be presented, in particular the connection with number theory features.