Development of an expert multitask gadget controlled by voluntary eye movements T. Gandhi a, * , M. Trikha a , J. Santhosh b , S. Anand a a Rehaibilation Engineering Laboratory, Centre for Biomedical Engineering, Indian Institute of Technology, Delhi and All India Institute of Medical Sciences, New Delhi, India b Computer Service Centre, Indian Institute of Technology, Delhi, India article info Keywords: Deterministic Finite Automata (DFA) Electro-oculogram (EOG) Very High speed Hardware Description Language (VHDL) Smart house abstract Design of assistive technology using advanced soft computing techniques on proper hardware platform has been an important issue of research for the last two decades. In the present study, a novel scheme is presented to develop a multitask gadget controlled by eye movements for the disabled, especially for individuals with spinal injury disorders. Electro-oculogram (EOG) signals generated by horizontal, verti- cal and diagonal eye movements and blinks were measured using a pair of surface electrodes with respect to a reference electrode placed on forehead. After preprocessing, the acquired signals were amplified with AC-coupling in order to reduce unnecessary drifts. Classifier based on DFA (Deterministic Finite Auto- mata) was developed by using VHDL to discriminate 128 different EOG states from processed horizontal and vertical eye signals based on threshold settings specific to individuals. Later, online viability of the system was established by conducting some experiments on normal as well as disabled subjects. The util- ity of the proposed method was enhanced by implementing a robust algorithm for signal classification and training both the subjects and the device. It was found that with the proposed scheme, the accuracy of the detection and control of the specified gadget is 95.33%, with sensitivity and specificity as 95.6% and 95%, respectively. The proposed model can be used for designing smart houses for the disabled and elderly. Ó 2009 Elsevier Ltd. All rights reserved. 1. Introduction Assistive technology is essential for the disabled and elderly to live independently for rest of their lives. However accidentally dis- abled like spinal cord injury subjects, developmentally disabled individuals with motor paralysis, such as amyotropic lateral sclero- sis (ALS), Guillain–Barre Syndrome (NINDS, 2007) have difficulty in conveying their intentions, since the motor neurons influencing voluntary muscles are affected. Technology has made significant impact on social well-being of human beings who fall into the stra- ta of disabled and paralytic people. In the past few years, the focus on the development of assistive devices for people with severe dis- ability has increased by improving the traditional systems (Cherry, Cudd, & Hawley, 1996; Hori, Sakano, & Saitoh, 2004; Jung, Do, Kim, & Suh, 2005; Stefanov, Bien, & Bang, 2004). Assistive technology deals with the development of technological hardware and soft- ware that enables physically challenged people to overcome the hindrances in carrying out activities of daily living. Recent develop- ment in embedded systems technology have opened up a vast area of research and development of portable and affordable assistive devices tuned to specific applications for the physically challenged populace (Hori, Sakano, & Saitoh, 2006; Lacourse & Hludik, 1990; Naito, Nozawa, Tanaka, & Ide, 2002). Various assistive technologies supporting individual communication have been developed for the disabled using Brain-Computer interface (BCI) (Wickelgen, 2003; Wolpaw et al., 2000). Researchers are incessantly trying to find out the individuals’ residual ability to supplement their impaired functions with surviving functions. In particular, patients from Locked-in syndrome (http://www.ninds.nih.gov/disorders/lock- edinsyndrome) (Cerebromedullospinal Disconnection), ALS have only control over their eye movements since their eye movement muscles are usually not affected. Since, this is the most prominent voluntary muscle activity in the body; Electro-oculogram can play a vital role in development of such EOG based assistive devices. Several practical devices have used eye movements as the sig- nal source (Davison, 1980; Hansjorg & Hess, 1991; Norris & Wilson, 1997) . Magnetic field search coil technique has become the most commonly used method for quantitative studies of eye and head movements in both human and experimental animals. The tech- nique is based on phase-locked amplitude detection of the voltage induced in a search coil in the external AC magnetic field. This method can be used to detect eye movement in 2D and 3D (Hans- jorg & Hess, 1991). It has very large linear range and high resolu- tion. However the magnetic search coil has to be put inside the eye. The subject is not comfortable with this and it cannot be put for a long period. The video-oculogram, which detects eye move- ment from pictorial images of the eye ball, is expensive as well 0957-4174/$ - see front matter Ó 2009 Elsevier Ltd. All rights reserved. doi:10.1016/j.eswa.2009.11.082 * Corresponding author. E-mail address: gandhitk@gmail.com (T. Gandhi). Expert Systems with Applications 37 (2010) 4204–4211 Contents lists available at ScienceDirect Expert Systems with Applications journal homepage: www.elsevier.com/locate/eswa