Pressure sensitive walkways are a commonly used measuring device for gait analysis. However, they can be prohibitively expensive for out-of-clinic measurements. An alternative approach to gait analysis is the use of a depth sensing camera (e.g., the Kinect). Our approach is to collect lower-body gait data using a single, inexpensive Kinect camera, with a line of sight perpendicular to the walking path. Participants with MS performed walking passes on a pressure sensitive walkway and in front of the camera. The following gait metrics were measured with both systems: step length, stride length, stride width, and stride velocity. We present the preliminary results of comparing gait metrics, showing Spearman correlations ranging from 0.857 to 0.976. These preliminary results suggest that inexpensive gait tracking may be a practical reality in non-clinical settings.
Extracting as much information as possible from electrocardiography (ECG) has been a target for researchers for decades. In this work, three DSP based R-peak detection methods are reviewed, including the Pan-Tompkins algorithm, and methods based on the Hilbert transform and wavelet transform. Those algorithms are applied to the publicly available MIT/BIH arrhythmia database and a database collected by the authors. While all three approaches derived the same results when applied to the authors' database, they showed slightly different performance when applied to the MIT/BIH arrhythmia database: Hilbert transform based method showed very good performance with 99.87% of accuracy, higher than those from wavelet transform based approach (99.55%) and Pan-Tompkins algorithm (99.34%). However, Pan-Tompkins algorithm is the most computationally efficient (approximately 4.3 times faster than wavelet transform method, and 42.5 times faster than Hilbert transform method).
Strabismus is a medical condition in which the eyes are misaligned, resulting in visual suppression and impaired stereoscopic depth perception. In normally-sighted subjects, eye movement (saccade) amplitudes can be manipulated independently in the two eyes using a saccadic adaptation procedure, which may have utility for rehabilitation in patients with strabismus. We evaluated the sensory effects of this procedure in 7 subjects (6 normally sighted, one with strabismus). Eye movements were measured using an eye tracker while saccade amplitudes were either recalibrated inwards for both eyes or in different directions for the two eyes. Sensory effects were then analyzed using a dichoptic Vernier task that measured the perceived alignment of lines shown to different eyes. Subjects' judgments indicated that transient strabismus can be induced in normally sighted individuals and temporary correction can be induced in a strabismic subject.
In this paper, a musical instrument recognition system is proposed. To realize the system, first we obtain the monophonic musical signals played by various kinds of instruments. Regardless of the relatively complicated feature selection process introduced in other work, we only extract features that stand for the vocal structures of instruments (LPCCs) and characteristics of human hearings (MFCCs), as well as their differential coefficients. By combining those features into feature vectors, certain classifiers (k-NN, SVM) have been selected to classify the vectors into different instruments. The results show that feature vectors containing MFCCs perform better than those without MFCCs. Nevertheless, the combination of the LPCCs and MFCCs yields the best results. For the selection of classifiers, although k-NN requires less training time in our system, SVM will be more favorable when the dimension of feature vectors and the number of samples increase.