People with severe motor-impairments due to Spinal Cord Injury (SCI) or Spinal Cord Dysfunction (SCD), often experience difficulty with accurate and efficient control of pointing devices (Keates et al., 02). Usually this leads to their limited integration to society as well as limited unassisted control over the environment. The questions “How can someone with severe motor-impairments perform mouse pointer control as accurately and efficiently as an able-bodied person?” and “How can these interactions be advanced through use of Computational Intelligence (CI)?” are the driving forces behind the research described in this paper. Through this research, a novel fuzzy mouse cursor control system (FMCCS) is developed. The goal of this system is to simplify and improve efficiency of cursor control and its interactions on the computer screen by applying fuzzy logic in its decision-making to make disabled Internet users use the networked computer conveniently and easily. The FMCCS core consists of several fuzzy control functions, which define different user interactions with the system. The development of novel cursor control system is based on utilization of motor functions that are still available to most complete paraplegics, having capability of limited vision and breathing control. One of the biggest obstacles of developing human computer interfaces for disabled people focusing primarily on eyesight and breath control is user’s limited strength, stamina, and reaction time. Within the FMCCS developed in this research, these limitations are minimized through the use of a novel pneumatic input device and intelligent control algorithms for soft data analysis, fuzzy logic and user feedback assistance during operation. The new system is developed using a reliable and cheap sensory system and available computing techniques. Initial experiments with healthy and SCI subjects have clearly demonstrated benefits and promising performance of the new system: the FMCCS is accessible for people with severe SCI; it is adaptable to user specific capabilities and wishes; it is easy to learn and operate; point-to-point movement is responsive, precise and fast. The integrated sophisticated interaction features, good movement control without strain and clinical risks, as well the fact that quadriplegics, whose breathing is assisted by a respirator machine, still possess enough control to use the new system with ease, provide a promising framework for future FMCCS applications. The most motivating leverage for further FMCCS development is however, the positive feedback from persons who tested the first system prototype.

This study aims to explore whether human intentions to move or cease to move right and left hands can be decoded from spatiotemporal features in non-invasive electroencephalography (EEG) in order to control a discrete two-dimensional cursor movement for a potential multi-dimensional Brain-Computer interface (BCI). Five naïve subjects performed either sustaining or stopping a motor task with time locking to a predefined time window by using motor execution with physical movement or motor imagery. Spatial filtering, temporal filtering, feature selection and classification methods were explored. The performance of the proposed BCI was evaluated by both offline classification and online two-dimensional cursor control. Event-related desynchronization (ERD) and post-movement event-related synchronization (ERS) were observed on the contralateral hemisphere to the hand moved for both motor execution and motor imagery. Feature analysis showed that EEG beta band activity in the contralateral hemisphere over the motor cortex provided the best detection of either sustained or ceased movement of the right or left hand. The offline classification of four motor tasks (sustain or cease to move right or left hand) provided 10-fold cross-validation accuracy as high as 88% for motor execution and 73% for motor imagery. The subjects participating in experiments with physical movement were able to complete the online game with motor execution at the average accuracy of 85.5±4.65%; Subjects participating in motor imagery study also completed the game successfully. The proposed BCI provides a new practical multi-dimensional method by noninvasive EEG signal associated with human natural behavior, which does not need long-term training.

In this text, we present two stereo-based head tracking techniques along with a fast 3D model acquisition system. The first tracking technique is a robust implementation of stereo-based head tracking designed for interactive environments with uncontrolled lighting. We integrate fast face detection and drift reduction algorithms with a gradient-based stereo rigid motion tracking technique. Our system can automatically segment and track a user's head under large rotation and illumination variations. Precision and usability of this approach are compared with previous tracking methods for cursor control and target selection in both desktop and interactive room environments. The second tracking technique is designed to improve the robustness of head pose tracking for fast movements. Our iterative hybrid tracker combines constraints from the ICP (Iterative Closest Point) algorithm and normal flow constraint. This new technique is more precise for small movements and noisy depth than ICP alone, and more robust for large movements than the normal flow constraint alone. We present experiments which test the accuracy of our approach on sequences of real and synthetic stereo images. The 3D model acquisition system we present quickly aligns intensity and depth images, and reconstructs a textured 3D mesh. 3D views are registered with shape alignment based on our iterative hybrid tracker. We reconstruct the 3D model using a new Cubic Ray Projection merging algorithm which takes advantage of a novel data structure: the linked voxel space. We present experiments to test the accuracy of our approach on 3D face modelling using real-time stereo images.