Learn More
We have developed and tested two electroencephalogram (EEG)-based brain-computer interfaces (BCI) for users to control a cursor on a computer display. Our system uses an adaptive algorithm, based on kernel partial least squares classification (KPLS), to associate patterns in multichannel EEG frequency spectra with cursor controls. Our first BCI, Target(More)
A new method for classification is proposed. This is based on kernel orthonormalized partial least squares (PLS) dimensionality reduction of the original data space followed by a support vector classifier. Unlike principal component analysis (PCA), which has previously served as a dimension reduction step for discrimination problems, orthonor-malized PLS is(More)
We are developing electromyographic and electroencephalographic methods, which draw control signals for human-computer interfaces from the human nervous system. We have made progress in four areas: 1) real-time pattern recognition algorithms for decoding sequences of forearm muscle activity associated with control gestures; 2) signal-processing strategies(More)
To determine if animals are capable of utilizing vestibular sensory input for spatial orientation, a six-arm radial maze with a rotating central turntable was constructed. Sprague-Dawley rats were trained on this apparatus by rotating them without visual, auditory, or olfactory cues. Animals were required to locate a reward (located in a constant position(More)
Normal and fornix-lesioned rats were trained to find water in a version of a spatial discrimination task involving the use of a cross maze modified for interspersing rotational stimulation before the start of each trial. The central (cross) portion of the maze rested on a turntable and consisted of a covered start box opening into the intersection of the(More)
OBJECTIVES To evaluate in a 12 month longitudinal study changes in hip and ankle range of motion and hip muscle strength in young female novice ballet dancers. METHODS Fifty three of the original 77 (69%) female dancers aged 8-11 years and 40 of the original 49 (82%) controls returned for follow up measurements one year later. Supine right active hip(More)
We measured multichannel EEG spectra during a continuous mental arithmetic task and created statistical learning models of cognitive fatigue for single subjects. Sixteen subjects (4 F, 18-38 y) viewed 4-digit problems on a computer, solved the problems, and pressed keys to respond (inter-trial interval = 1 s). Subjects performed until either they felt(More)
Two new computational models show that the EEG distinguishes three distinct mental states ranging from alert to fatigue. State 1 indicates heightened alertness and is frequently present during the first few minutes of time on task. State 2 indicates normal alertness, often following and lasting longer than State 1. State 3 indicates fatigue, usually(More)