RESUMEN
The use of assistive technologies can mitigate or reduce the challenges faced by individuals with motor disabilities to use computer systems. However, those who feature severe involuntary movements often have fewer options at hand. This work describes an application that can recognize the user's head using a conventional webcam, track its motion, model the desired functional movement, and recognize it to enable the use of a virtual keyboard. The proposed classifier features a flexible structure and may be personalized for different user need. Experimental results obtained with participants with no neurological disorders have shown that classifiers based on Hidden Markov Models provided similar or better performance than a classifier based on position threshold. However, motion segmentation and interpretation modules were sensitive to involuntary movements featured by participants with cerebral palsy that took part in the study.
Asunto(s)
Parálisis Cerebral , Dispositivos de Autoayuda , Comunicación , Movimientos de la Cabeza , Humanos , Movimiento , Interfaz Usuario-ComputadorRESUMEN
Functional electrical stimulation cycling has been proposed as an assistive technology with numerous health and fitness benefits for people with spinal cord injury, such as improvement in cardiovascular function, increase in muscular mass, and reduction of bone mass loss. However, some limitations, for example, lack of optimal control strategies that would delay fatigue, may still prevent this technology from achieving its full potential. In this work, we performed experiments on a person with complete spinal cord injury using a stationary tadpole trike when both cadence tracking and disturbance rejection were evaluated. In addition, two sets of experiments were conducted 6 months apart and considering activation of different muscles. The results showed that reference tracking is achieved above the cadence of 25 rpm with mean absolute errors between 1.9 and 10% when only quadriceps are activated. The disturbance test revealed that interferences may drop the cadence but do not interrupt a continuous movement if the cadence does not drop below 25 rpm, again when only quadriceps are activated. When other muscle groups were added, strong spasticity caused larger errors on reference tracking, but not when a disturbance was applied. In addition, spasticity caused the last experiments to result in less smooth cycling.