Nishant A. Mehta

Computer detection approaches for the identification of phasic electromyographic (EMG) activity during human sleep

BACKGROUND: Examination of spontaneously occurring phasic muscle activity from the human polysomnogram may have considerable clinical importance for patient care, yet most attempts to quantify the detection of such activity have relied upon laborious and intensive visual analyses. We describe in this study innovative signal processing approaches to this issue. METHODS: We examined multiple features of surface electromyographic signals based on 16,200 individual 1-second intervals of low impedance sleep recordings. We validated which of those features most closely mirrored the careful judgments of trained human observers in making discriminations of the presence of short-lived (100-500 msec) phasic activity, and also examined which features provided maximal differences across 1-second intervals and which features were least susceptible to residual levels of amplifier noise. RESULTS: Our data suggested particularly promising and novel features (e.g., Non-linear energy, 95(th) percentile of Spectral Edge Frequency) for developing automated systems for quantifying muscle activity during human sleep. CONCLUSIONS: The EMG signals recorded from surface electrodes during sleep can be processed with techniques that reflect the visually based analyses of the human scorer but also offer potential for discerning far more subtle effects, Future studies will explore both the clinical utility of these techniques and their relative susceptibility to and/or independence from signal artifacts.

Optimal Control Strategies for an SSVEP-Based Brain-Computer Interface

We evaluate the performance of 18 healthy subjects on a steady-state visually evoked potential brain–computer interface (BCI) under variation of two general control parameters. The BCI is a simple game amenable to performance measures such as the bitrate, decision accuracy, and optimality ratios based on an ideal human–machine system. The two parameters studied are the electroencephalography recording history length used to form a decision and the number of consecutive identical decisions that must be recognized before feedback is provided. To maximize the bitrate, it appears optimal to minimize the number of consecutive identical decisions required for feedback. When the task of interest often requires making the same decision multiple times in a row, a larger history of data seems preferable. When good performance on a task demands that decisions change rapidly, a smaller history seems optimal. Ultimately, we plan to connect this work to choosing appropriate control parameters for efficient wheelchair control by a BCI.

Recognizing Sign Language from Brain Imaging

Classification of complex motor activities from brain imaging is relatively new in the fields of neuroscience and brain-computer interfaces (BCIs). We report sign language classification results for a set of three contrasting pairs of signs. Executed sign accuracy was 93.3%, and imagined sign accuracy was 76.7%. For a full multiclass problem, we used a decision directed acyclic graph of pairwise support vector machines, resulting in 63.3% accuracy for executed sign and 31.4% accuracy for imagined sign. Pairwise comparison of phrases composed of these signs yielded a mean accuracy of 73.4%. These results suggest the possibility of BCIs based on sign language.