Browsing by Author "Hsu, Sheng-Chih"

Now showing 1 - 3 of 3

Development of Adaptive QRS Detection Rules Based on Center Differentiation Method for Clinical Application
(2012)
Yang, Shiau-Ru
;
Hsu, Sheng-Chih
;
Lu, Shao-Wei
;
Ko, Li-Wei
;
Lin, Chin-Teng
Interpretation of cardiac rhythms is highly dependent on accurate detection of atrial activity. The robustness is an important requirement for clinical usage. This study presents an adaptive QRS detection method for real-time clinical ECG signals. In this method, center differentiation is applied as a whitening filer, and a composite function enhances the high frequency QRS energy. To robustly detect clinical data, a novel threshold selection method based on statistics is proposed. Moreover, this study provides a benchmarking clinical dataset acquired from cardiac patients. Our extensive experimental results using the MIT-BIH arrhythmia database show that our technique can detect beats with 99.67% accuracy, and the sensitivity is 99.83%. With the exceptional QRS detection result, further testing of the proposed method with clinical data shows the accuracy for atrial and ventricular arrhythmias is 82.9% and 90.2%, respectively.
Face recognition using nonparametric-weighted Fisherfaces
(2012)
Li, Dong-Lin
;
Prasad, Mukesh
;
Hsu, Sheng-Chih
;
Hong, Chao-Ting
;
Lin, Chin-Teng
This study presents an appearance-based face recognition scheme called the nonparametric-weighted Fisherfaces (NW-Fisherfaces). Pixels in a facial image are considered as coordinates in a high-dimensional space and are transformed into a face subspace for analysis by using nonparametric-weighted feature extraction (NWFE). According to previous studies of hyperspectral image classification, NWFE is a powerful tool for extracting hyperspectral image features. The Fisherfaces method maximizes the ratio of between-class scatter to that of within-class scatter. In this study, the proposed NW-Fisherfaces weighted the between-class scatter to emphasize the boundary structure of the transformed face subspace and, therefore, enhances the separability for different persons' face. The proposed NW-Fisherfaces was compared with Orthogonal Laplacianfaces, Eigenfaces, Fisherfaces, direct linear discriminant analysis, and null space linear discriminant analysis methods for tests on five facial databases. Experimental results showed that the proposed approach outperforms other feature extraction methods for most databases.
Nonlinear System Control Using Functional-Link-Based Neuro-Fuzzy Network Model Embedded with Modified Particle Swarm Optimizer
(2012-03-01)
Su, Miin-Tsair
;
Lin, Chin-Teng
;
Hsu, Sheng-Chih
;
Li, Dong-Lin
;
Lin, Cheng-Jian
This study presents an evolutionary neural fuzzy system (NFS) for nonlinear system control. The proposed NFS model uses functional link neural networks (FLNNs) as the consequent part of the fuzzy rules. This study uses orthogonal polynomials and linearly independent functions in a functional expansion of the functional link neural networks. A learning algorithm, which consists of structure learning and parameter learning, is presented. The structure learning depends on the entropy measure to determine the number of fuzzy rules. The parameter learning, based on the particle swarm optimization (PSO) algorithm, can adjust the shape of the membership function and the corresponding weighting of the FLNN. The distance-based mutation operator, which strongly encourages a global search giving the particles more chance of converging to the global optimum, is introduced. The simulation results have shown the proposed method can improve the searching ability and is very suitable for the nonlinear system control applications.