| Title | : | Artifacts Analysis in EEG and its Applications in Building Brain-Computer Interfaces |
| Speaker | : | Srihari M (IITM) |
| Details | : | Tue, 23 Apr, 2019 3:30 PM @ Turing Hall (BSB 361 |
| Abstract: | : | Brain-Computer Interface (BCI) is a necessary mechanism of communication for persons with neuromuscular impairments. The most common BCI devices use electroencephalography (EEG) electrical activity recorded from the scalp. EEG signals are noisy owing to the presence of many artifacts, namely eye blink, head movement, and jaw movement. Such artifacts overwhelm the EEG signal and make EEG analysis challenging. This issue is addressed by locating the artifacts and excluding the EEG segment from the analysis which could lead to loss of useful information.
Most of the artifacts are involuntary and are not present when the person is listening silently or with eyes closed. The objective of our work is to classify different types of artifacts, namely eye blink, head nod, head turn and jaw movements in the EEG signal. The occurrence of the artifacts is first located in the EEG signal. The located artifacts are then classified using linear time and dynamic time warping techniques. The detected artifacts can be used by a person with a motor disability to control a smart-phone. A speech synthesis application that uses eye-blinks in a single channel EEG system is developed. Word prediction models are used for word completion thus reducing the number of eyeblinks required. |
