Showing papers by "Qi Zhang published in 2011"
01 Dec 2011
TL;DR: The experimental results indicated that the RoughEn-based classification outperformed other entropy based methods for recognizing six hand motions from four-channel SEMG signals with the best recognition accuracy and suggest that RoughEn has the potential to be used in the SEMG-based prosthetic control as a method of feature extraction.
Abstract: The rough entropy (RoughEn) is developed based on the rough set theory. It has the advantage of low computational complexity, because there is no parameter to set in RoughEn. In this paper, we characterized the feature of surface electromyography (SEMG) signal with RoughEn and then used support vector machine to classify six different hand motions. The sample entropy, wavelet entropy and approximate entropy were compared with RoughEn to evaluate the performance of characterizing SEMG signals. The experimental results indicated that the RoughEn-based classification outperformed other entropy based methods for recognizing six hand motions from four-channel SEMG signals with the best recognition accuracy of 95.19 ± 2.99%. The results suggest that RoughEn has the potential to be used in the SEMG-based prosthetic control as a method of feature extraction.
9 citations
01 Jan 2011
TL;DR: A method for contour detection of plaque is proposed utilizing the prior knowledge of elliptic geometry of plaques, which outperformed a state-of-the-art method by 3.8 pixels and 4.8% in terms of the mean distance error and relativemean distance error.
Abstract: It is valuable for diagnosis of atherosclerosis to detect lumen and media-adventitia contours in intravascular ultrasound (IVUS) images of atherosclerotic plaques. In this paper, a method for contour detection of plaques is proposed utilizing the prior knowledge of elliptic geometry of plaques. Contours are initialized as ellipses by using ellipse template matching, where a matching function is maximized by particle swarm optimization. Then the contours are refined by boundary vector field snakes. The method was evaluated via 88 in vivo images from 21 patients. It outperformed a state-of-the-art method by 3.8 pixels and 4.8% in terms of the mean distance error and relative mean distance error, respectively.
2 citations