Gauge Newsletter September 2017 | Page 45

mented based on different clas- sification techniques such as support vector machines, Naïve Bayesian and Neural networks. The theory behind the classifica- tion techniques is fascinating. A good example to describe the theory of classification is a deci- sion you take on seeing some- thing. You identify someone by their face, colour, skin and so on. The same thing happens in machine learning with classifica- tion. The machine interface learns and practices itself to identify and differentiate the features it’s fed with and form decision boundar- ies with new data. So, the final output is a machine interface that can analyze brain signals of a human and learn on its own to identify the actions of the brain. The output can be used for many purposes, be it medical or entertaining stuff. Automated wheelchairs, mind controlled home environments and humanoid robots are few examples for BCI applications. The author is proud to mention the University of Peradeniya, as an institute that has already carried out research related with BCI. Currently, there are sev- eral BCI related undergraduate projects ongoing at the Department of Electrical and Electronic Engineering of the University of Peradeniya. One such project is control- ling a robotic arm with EEG signals. The undergraduates are also carrying out a research to control a prosthetic arm using EOG signals. The projects are supervised by Dr. Janaka Wijeyakulasooriya and Dr. Ruwan Ranaweera. They are carried out in collaboration with the Faculty of Medicine of the University of Peradeniya. BCI interfaces are a promising area in the scope of bio-medical engi- neering. Dedication and hard work of many scientists and engineers in the field of BCI research have paved way for miracles such as humanoid robots. Scientists’ dreams are becoming reality as BCIs are improving day by day like the rest of science and engineering. So, let’s expect miracles in engineering in the future with BCI. Pasindu Perera Final Year Undergraduate Department of Electrical and Electronic Engineering References 1. Jorge Baztarrica Ochoa, Prof Touradj Ebrahimi, EEG Signal Classification for BrainComputer Interface Applications, 2002 2. Fabien Lotte, Marco Congedo, Anatole L_ ecuyer, Fabrice Lamarche, Bruno Arnaldi. A review of classification algorithms for EEG- based brain computer interfaces. Journal of Neural Engineering, IOP Publishing, 2007, 4, pp.24. 3. Mostafa Mohammadpour, Mohammad Kazem Ghorbanian, Saeed Mozaffari, Comparison of EEG Signal Features and Ensemble Learning Methods for Motor Imagery Classification,in 2016 Eighth International Conference on Information and Knowledge Technology (IKT), Hamedan, Iran Gauge Magazine University of Peradeniya 45