Browsing by Author "Su, YL"

Now showing 1 - 7 of 7

Fractal extraction from a mixed fBm signal using discrete wavelet transforms
(1999-03-01)
Wu, BF
;
Su, YL
;
電控工程研究所
;
Institute of Electrical and Control Engineering
Since stationarity, ergodicity and self-similarity for the discrete wavelet transform of fractional Brownian motion (fBm) processes have been shown in previous works, these characteristics could be applied to extract the parameters of two fBm signals from a mixed fBm signal using time-average correlation functions. The goal of this paper is to distinguish the two identical power fBm signals from the mixed signal. In this case, we suppose that the mixed signal is available, but information on the parameters of the two fBm signals is not provided. A method is proposed to find the parameters of these two fBm signals. The smaller parameter can be detected from the fractal dimension of the mixed fBm signal. The parameter of the other fBm is estimated by processing the wavelet coefficients of the mixed fBm signal. Finally, the simulation results showed that this approach works well in increasing the difference between the parameters of the two fBms.
On stationarizability for nonstationary 2-D random fields using discrete wavelet transforms
(1998-09-01)
Wu, BF
;
Su, YL
;
電機資訊學士班
;
Undergraduate Honors Program of Electrical Engineering and Computer Science
The emphasis in this correspondence is on the study of nonstationary two-dimensional (2-D) random fields with wide-sense stationary increments, wide-sense stationary jumps, and 2-D fractional Brownian motion (fBm) fields. The effort made in this work is to develop a realizable method of stationarization provided for nonstationary 2-D random fields. We also present the correlation functions of the discrete wavelet transform relating to 2-D fBm fields that will decay hyperbolically fast.
On the relationship between the self-similarities of fractal signals and wavelet transforms
(1996)
Wu, BF
;
Su, YL
;
交大名義發表
;
電控工程研究所
;
National Chiao Tung University
Since many natural phenomena are occasionally defined as stochastic processes and the corresponding fractal characteristics are hidden from their correlation functions or power spectra. the topic would become very interest in signal processing. In this paper, we summarize the fractal dimensions and the relationship of the fractal in probability measure, variance, time series, time-averaging autocorre lation, ensemble-averaging autocorrelation, time-averaging power spectrum, average power spectrum and distribution functions for stationary and nonstationary processes. we also propose that the preservation of the one-dimensional self-similarity of a fractal signal is obtained by using the continuous wavelet transform (CWT) and the discrete wavelet transform (DWT) with the perfect reconstruction - quadrature mirror filter structure. Moreover, we extend the results to the two-dimensional case and point out the relationship of the self-similarities between the CWT and DWT of the fractal signals. A fractional Brownian motion process is provided as an example to show the results of this paper.
Stationarization of stochastic sequences with wide-sense stationary increments or jumps by discrete wavelet transforms
(1998-09-01)
Su, YL
;
Wu, BF
;
電控工程研究所
;
Institute of Electrical and Control Engineering
Owing to most physical phenomena observed as nonstationary processes and the form of discrete sequences, it becomes realistic to process the nonstationary sequences in the laboratory if there exists a bijective transformation for: stationarization. In this work, our study is emphasized on the class of nonstationary one-dimensional random sequences with wide-sense stationary increments (WSSI), wide-sense stationary jumps (WSSJ) and a famous case, the fractional Brownian motion (FBM) process. Also, the concept of linear algebra is applied to process the stationarization concisely. Our goal is to derive a stationarization theorem developed by linear operators such that a nonstationary sequence with WSSI/WSSJ may be stationarized by an easily realizable perfect reconstruction-quadrature mirror filter structure of the discrete wavelet transform. Some examples for FBM processes and nonstationary signals generated by autoregressive integrated moving average models are provided to demonstrate the stationarization. (C) 1998 The Franklin Institute. Published by Elsevier Science Ltd.
The effect of time pressure on expert system based training for emergency management
(1998-07-01)
Lin, DYM
;
Su, YL
;
工業工程與管理學系
;
Department of Industrial Engineering and Management
In many emergency situations, human operators are required to derive countermeasures based on contingency rules whilst under time pressure. In order to contribute to the human success in playing such a role, the present study intends to examine the effectiveness of using expert systems to train for the time-constrained decision domain. Emergency management of chemical spills was selected to exemplify the rule-based decision task. An Expert System in this domain was developed to serve as the training tool. Forty subjects participated in an experiment in which a computerized information board was used to capture subjects' rule-based performance under the manipulation of time pressure and training. The experiment results indicate that people adapt to time pressure by accelerating their processing of rules where the heuristic of cognitive availability was employed. The simplifying strategy was found to be the source of human error that resulted in undesired decision performance. The results also show that the decision behaviour of individuals who undergo the expert system training is directed to a normative and expeditious pattern, which leads to an improved level of decision accuracy. Implications of these findings are examined in the present study.
The ergodicity analysis of two-dimensional discrete wavelet-based fBm fields
(1998-03-01)
Wu, BF
;
Su, YL
;
電控工程研究所
;
Institute of Electrical and Control Engineering
The correspondence explores the ergodicity property of the two-dimensional (2-D) discrete wavelet transform for a fractional Brownian motion (fBm) field that consists of one approximation image and three detail images. In this correspondence, the decorrelation and ergodicity of the three detail images of fBm fields are shown to he achieved.
The impact of expert-system-based training on calibration of decision confidence in emergency management
(1998-01-01)
Su, YL
;
Lin, DYM
;
工業工程與管理學系
;
Department of Industrial Engineering and Management
In many emergency incidents, human operators need to derive countermeasures based an contingency rules under time pressure. Since people tend to be overconfident regarding their performance levels, it ir necessary that the operators be well trained to calibrate proper decision confidence in the safety-related domain. This paper examines the effectiveness of using expert systems to train for the desired calibration. Emergency management of chemical spills was selected to exemplify the rule-based decision task. An expert system in the domain was developed to serve as the training tool. A total of 40 student subjects participated in an experiment in which they were asked to resolve spill scenarios under the manipulation of training and deadline conditions. The experiment results indicate that people tend to overestimate their performance capabilities when reasoning with a rule-based knowledge set, especially with the presence of time constraints. The results also show that the manifestation of overconfidence can be reduced for individuals who undergo the expert-system calibration training. The implications of the findings are examined in this paper. (C) 1997 Elsevier Science Ltd.