Human computer interface (HCI) system helps disabled people to interact with their surrounding world by physiological signals like, electroencephalogram (EEG), electro-oculogram (EOG) and electromyogram (EMG) etc. Most HCI systems use EEG and EOG components as control signals for real time applications. Among the various EEG components, SSVEP has been studied increasingly due to high information transfer rate (ITR) and minimal or negligible training time. The performance of SSVEP based HCI speller system depends on the total number of targets in the keyboard layout, classification accuracy and ITR. The practical SSVEP based keyboard systems have a tradeoff between the total number of targets and classification accuracy. Further, the HCI keyboard systems can be broadly categorized into synchronous and asynchronous systems. In synchronous systems the users/subjects are always in control state. In asynchronous case the users/subjects can have control on the system. They can change the system mode from active to idle and vice versa.
Present talk focuses on the design and performance of two synchronous systems with 36 targets and two asynchronous with 40 and 42 targets based on SSVEP and EOG signals. The two synchronous systems resulted classification accuracies of 98.33% and 94.16% and information transfer rates of 69.21 bits/min and 70.99 bits/min respectively. The two asynchronous systems resulted classification accuracies of 97.33% and 98.48% and information transfer rates of 100 bits/min and 126.65 bits/min respectively.
In this work, the synchronous and asynchronous keyboard/speller systems are designed and validated. The performance metrics of the proposed systems are compared with the conventional speller systems. The designed asynchronous speller systems achieved high performance metrics and it provides better user interface for real time usage.