Browsing by Author "Wang, CH"

Now showing 1 - 20 of 43

A coverage-based genetic knowledge-integration strategy
(2000-07-01)
Wang, CH
;
Hong, TP
;
Chang, MB
;
Tseng, SS
;
資訊工程學系
In this paper, we propose a coverage-based genetic knowledge-integration approach to effectively integrate multiple rule sets into a centralized knowledge base. The proposed approach consists of two phases: knowledge encoding and knowledge integration. In the knowledge-encoding phase, each rule in the various rule sets that are derived from different sources (such as expert knowledge or existing knowledge bases) is first translated and encoded as a fixed-length bit string. The bit strings combined together thus form an initial knowledge population. In the knowledge-integration phase, a genetic algorithm applies genetic operations and credit assignment at each rule-string to generate an optimal or nearly optimal rule set. Experiments on diagnosing brain tumors were made to compare the accuracy of a rule set generated by the proposed approach with that of the initial rule sets derived from different groups of experts or induced by various machine learning techniques. Results show that the rule set derived by the proposed approach is more accurate than each initial rule set on its own. (C) 2000 Elsevier Science Ltd. All rights reserved.
A fuzzy inductive learning algorithm for parallel loop scheduling
(1997)
Tsai, CJ
;
Tseng, SS
;
Wang, CH
;
Yang, CT
;
Jiang, MF
The conventional symbolic learning algorithm can not infer data that contains fuzzy information. In the past few years, we have designed a parallel loop scheduling based upon knowledge based approach that is called KPLS to choose an appropriate schedule for different loop to assign loop iterations to a multiprocessor system for achieving high speedup rates. Unfortunately, we found that these attributes that were applied in KPLS contain some fuzzy information, which are inapplicable to the traditional symbolic learning strategy for inferring some concept descriptions. In this paper, we apply fuzzy set concept to AQR learning algorithm that is called FAQR. FAQR which can induce fuzzy linguistic rules from fuzzy instances is then proposed to solve the above parallel loop scheduling problem. Some promising inference rules have been found and applied to infer the choice of parallel loop scheduling. Besides, we apply FAQR in IRIS Flower Classification Problem. Experimental results show that our method yields high accuracy in both different domains.
A fuzzy inductive learning strategy for modular rules
(1999-04-01)
Wang, CH
;
Liu, JF
;
Hong, TP
;
Tseng, SS
;
資訊工程學系
In real applications, data provided to a learning system usually contain linguistic information which greatly influences concept descriptions derived by conventional inductive learning methods. The design of learning methods to learn concept descriptions in working with vague data is thus very important. In this paper, we apply fuzzy set concepts to machine learning to solve this problem. A fuzzy learning algorithm based on the maximum information gain is proposed to manage linguistic information. The proposed learning algorithm generates fuzzy rules from "soft" instances, which differ from conventional instances in that they have class membership values. Experiments on the Sports and the Iris Flower classification problems are presented to compare the accuracy of the proposed algorithm with those of some other learning algorithms. Experimental results show that the rules derived from our approach are simpler and yield higher accuracy than those from some other learning algorithms. (C) 1999 Elsevier Science B.V. All rights reserved.
A genetics-based approach to knowledge integration and refinement
(2001-01-01)
Wang, CH
;
Hong, TP
;
Tseng, SS
;
資訊工程學系
;
Department of Computer Science
In this paper, we propose a genetics-based knowledge integration approach to integrate multiple rule sets into a central rule set. The proposed approach consists of two phases: knowledge encoding and knowledge integrating. In the encoding phase, each knowledge input is translated and expressed as a rule set, and then encoded as a bit string. The combined bit strings form an initial knowledge population, which is then ready for integrating. In the knowledge integration phase, a genetic algorithm generates an optimal or nearly optimal rule set from these initial knowledge inputs. Furthermore, a rule-refinement scheme is proposed to refine inference rules via interaction with the environment. Experiments on diagnosing brain tumors were carried out to compare the accuracy of a rule set generated by the proposed approach with that of initial rule sets derived from different groups of experts or induced by means of various machine learning techniques. Results show that the rule set derived using the proposed approach is much more accurate than each initial rule set on its own.
A Litterman BVAR approach for production forecasting of technology industries
(2003-01-01)
Hsu, PH
;
Wang, CH
;
Shyu, JZ
;
Yu, HC
;
統計學研究所
Forecasting the production of technology industries is important to entrepreneurs and governments, but usually suffers from market fluctuation and explosion. This paper aims to propose a Litterman Bayesian vector autoregression (LBVAR) model for production prediction based on the interaction of industrial clusters. Related industries within industrial clusters are included into the LBVAR model to provide more accurate predictions. The LBVAR model possesses the superiority of Bayesian statistics in small sample forecasting and holds the dynamic property of the vector autoregression (VAR) model. Two technology industries in Taiwan, the photonics industry and semiconductor industry are used to examine the LBVAR model using a rolling forecasting procedure. As a result, the LBVAR model was found to be capable of providing outstanding predictions for these two technology industries in comparison to the autoregression (AR) model and VAR model. (C) 2002 Elsevier Science Inc. All rights reserved.
A neural network based transcoder for MPEG2 video compression
(1999)
Fu, HC
;
Chen, ZH
;
Xu, YY
;
Wang, CH
;
資訊工程學系
In this paper, we proposed a neural network method for the high efficiency requatization in the design of a transcoder In our design, there are two types of video bitrate control in the proposed transcoder. One is the global adjusting of quantizer scales in which the adjusting is based on the complication of the whole frame, the other is the adaptive adjusting of quantizer scales, that the adjusting is the complication of the current macroblock. From our experimental results, the prototype transcoder can achieve desirable bitrate (1.5 Mbps) with an acceptable image quality. In additional, we constructed a video multiplexer for PPV or NVOD applications on the proposed transcoder.
A new hybrid learning algorithm for non-linear boundaries
(1998-06-01)
Wang, CH
;
Hong, TP
;
Tseng, SS
;
資訊工程學系
;
Department of Computer Science
In this paper, we propose a new hybrid learning algorithm, ETNC, which incorporates the popular decision-tree learning algorithm ASSISTANT into a modified three-layer back-propagation learning method to construct an entropy-tree net classifier. The new Iearning algorithm also adopts a tree-pruning mechanism to avoid overfitting problems. The new algorithm decreases both the tree size and error rate, especially for complex classification problems. Furthermore, it is not necessary for users to lay out the structure of a tree net in advance; instead, the structure is automatically constructed in the tree-growing process. Finally, the results of experiments in diagnosing brain tumors and classifying sugar canes are described to compare the proposed algorithm with two other learning methods, the back-propagation learning algorithm and ASSISTANT, in terms of accuracy, knowledge complexity and learning speed. Experimental results show that the proposed learning algorithm can provide a good trade-off between accuracy, knowledge complexity and learning speed.
A novel LCD driver testing technique using logic test channels
(2003)
Su, CC
;
Wang, WJ
;
Wang, CH
;
Tseng, IS
;
電控工程研究所
This paper proposes a novel voltage measurement technique for LCD driver testing by the use of logic test channel of an ATE. The method is able to achieve less than 1mV error with the presence of 32mV RMS noise.
Adaptive hybrid intelligent control for uncertain nonlinear dynamical systems
(2002-10-01)
Wang, CH
;
Lin, TC
;
Lee, TT
;
Liu, HL
;
電控工程研究所
A new hybrid direct/indirect adaptive fuzzy neural network (FNN) controller with state observer and supervisory controller for a class of uncertain nonlinear dynamic systems is developed in this paper. The hybrid adaptive FNN controller, the free parameters of which can be tuned on-line by observer-based output feedback control law and adaptive law, is a combination of direct and indirect adaptive FNN controllers. A weighting factor, which can be adjusted by the tradeoff between,plant knowledge and control knowledge, is adopted to sum together the control efforts from indirect adaptive FNN controller and direct adaptive FNN controller. Furthermore, a supervisory controller is appended into the FNN controller to force the state to be within the constraint set. Therefore, if the FNN controller cannot maintain the stability, the supervisory controller starts working to guarantee stability. On the other hand, if the FNN controller works well, the supervisory controller will be deactivated. The overall adaptive scheme guarantees the global stability of the resulting closed-loop system in the sense that all signals involved are uniformly bounded. Two nonlinear systems, namely, inverted pendulum system and Chua's chaotic circuit, are fully illustrated to track sinusoidal signals. The resulting hybrid direct/indirect FNN control systems show better performances, i.e., tracking error and control effort can be made smaller and it is more flexible during the design process.
Automatically integrating multiple rule sets in a distributed-knowledge environment
(1998-08-01)
Wang, CH
;
Hong, TP
;
Tseng, SS
;
Liao, CM
;
資訊工程學系
In this paper, an actual knowledge application is made by means of evolution paradigms in terms of knowledge acquisition. rin automatic knowledge integration approach in a distributed-knowledge environment is thus proposed to integrate multiple rule sets into a single effective rule set. The proposed approach consists of two phases: knowledge encoding and knowledge integration. In the encoding phase, each knowledge input is translated and expressed as a rule set, then encoded as a bit string. The combined bit strings from multiple knowledge inputs form an initial knowledge population, which is then ready for integration. In the knowledge integration phase, a genetic search technique generates an optimal or nearly optimal rule set from these initial knowledge-input strings. Finally, experimental results from diagnosis of brain tumors show that the rule set derived by the proposed approach is much more accurate than each initial rule set.
Complementary sets and Reed-Muller codes for peak-to-average power ratio reduction in OFDM
(2006)
Chen, CY
;
Wang, CH
;
Chao, CC
;
電信工程研究所
;
Institute of Communications Engineering
One of the disadvantages of orthogonal frequency division multiplexing (OFDM) systems is the high peak-to-average power ratio (PAPR) of OFDM signals. Colay complementary sets have been proposed to tackle this problem. In this paper, we develop several theorems which can be used to construct Golay complementary sets and multipleshift complementary sets from Reed-Muller codes. We show that the result of Davis and Jedwab on Golay complementary sequences and those of Paterson and Schmidt on Colay complementary sets can be considered as special cases of our results.
CSO distortions due to the combined effects of self- and external-phase modulations in long-distance 1550-nm AM-CATV systems
(1999-06-01)
Wu, MC
;
Wang, CH
;
Way, WI
;
電信工程研究所
;
Institute of Communications Engineering
We found that the combined effects of self- and external-phase modulations must be considered in order to precisely predict the composite second-order distortions in a long-distance 1550-nm externally modulated AM-cable TV (CATV) system, especially when the applied phase modulation index and modulating tone frequency to the integrated phase modulator are high, This result has important implications to the optimum design of 1550-nm transmitter for long-distance Am- and QAM-CATV systems.
Design of a new fuzzy suction controller using fuzzy modeling for nonlinear boundary layer
(2005-10-01)
Tu, KY
;
Lee, TT
;
Wang, CH
;
電控工程研究所
;
Institute of Electrical and Control Engineering
There are two types of fuzzy modeling: 1) imitating an expert experiment or fulfilling an engineering knowledge, and 2) modeling a complex or unknown system. In this paper, based on the first type of fuzzy modeling, a new fuzzy suction controller (NFSC) is proposed using its linguistic rules to design nonlinear boundary layer. Two kinds of nonlinear boundary layers are discussed. The first kind is designed by three rules derived according to a new interpretation of the switching conditions for a suction controller such that the new controller reduces chattering and spends less energy than a suction controller does. A design procedure summarizes the NFSC design. The second kind of nonlinear boundary layer is the linguistic rules designed to have sliding sectors to control a mobile robot for trajectory tracking. The discussion emphasizes the advantage of nonlinear boundary layers, compared with traditional suction controllers usually using linear boundary. In addition, the proposed NFSC provides a flexible way to adjust the controller functions using linguistic rules based on the first type of fuzzy modeling.
Design of sampled-data systems with large plant uncertainty using quantitative feedback theory
(2001-03-01)
Lin, TC
;
Wang, CH
;
Teng, CC
;
Lee, TT
;
電控工程研究所
This paper proposes a new quantitative feedback theory (QFT) design framework for dealing,with sampled-data systems with large plant uncertainty. After the QFT-based design in the continuous-time domain is completed, the analogue controller can he transformed directly into a rational discrete-time transfer function via approximate Z transform with the sampling time as a free parameter. The sampling time can therefore be adjusted to make the uncertain sampled-data system robustly stable. In comparison with other approaches, our approach is much more systematic without the solvability problem and yet significant enough to guide the designer to realize the physical controller in which the plant transfer function has prescribed bounds on its parameters. Several examples are used to illustrate the proposed approach and excellent results are obtained.
Developing a sugar-cane breeding assistant system by a hybrid adaptive learning technique
(1996)
Jiang, MF
;
Wang, CH
;
Tseng, SS
;
交大名義發表
;
資訊工程學系
The traditional sugar-cane breeding process depends on the determination of experienced breeding researcher. It's well known that computer-aided methodology is very useful in many fields today, such as CAD, CAM, and CAI. Since the sugar-cane breeding problem in agriculture field is complex, it seems that using computer-aided methodology is very suitable to solve this problem. In this paper, we use the techniques of neural networks and genetic algorithms to construct a method in order to induce the sugar-cane cross model from the sugar-cane parent database which established by Taiwan Sugar Research Institute (TSRI) since 1990. The experimental results show that the correct percentage for testing is about 70%.
Dynamic multiple responses by ideal solution analysis
(2004-07-16)
Tong, LI
;
Wang, CH
;
Chen, CC
;
Chen, CT
;
工業工程與管理學系
High technology industry must continuously improve product quality and multiple correlated product quality characteristics must be assessed simultaneously due to product complexity. While many Taguchi method applications have addressed a state system problem, dynamic multi-response problems have seldom been examined. This study presents a novel optimization procedure for dynamic multiple responses based on Taguchi's parameter design. The signal to noise (SN) ratio and system sensitivity are used to assess the performance of each response. Principal component analysis is then performed on the SN values and system sensitivity values to obtain a set of uncorrelated components. The optimization direction for each component is also determined based on the corresponding variation mode chart. Finally, the relative closeness to the ideal solution resulting from the technique for order preference by similarity to ideal solution is determined as an overall performance index for multiple responses. A case study obtained from biological reduction of an ethyl acetoacetate process demonstrates the effectiveness of the proposed procedure. (C) 2003 Elsevier B.V. All rights reserved.
Dynamic optimal learning rates of a certain class of fuzzy neural networks and its applications with genetic algorithm
(2001-06-01)
Wang, CH
;
Liu, HL
;
Lin, CT
;
電控工程研究所
;
Institute of Electrical and Control Engineering
The stability analysis of the learning rate for a two-layer neural network (NN) Is discussed first by minimizing the total squared error between the actual and desired outputs for a set of training vectors. The stable and optimal learning rate, in the sense of maximum error reduction, for each iteration in the training (back propagation) process can therefore be found fur this two-layer NN, It has also been proven in this paper that the dynamic stable learning rate for this two-layer NN must be greater than zero. Thus it is guaranteed that the maximum error reduction can be achieved by choosing the optimal learning rate for the next training iteration. A dynamic fuzzy neural network (FNN) that consists of the fuzzy linguistic process as the premise part and the two-layer NN as the consequence part is then illustrated as an immediate application of our approach, Each part of this dynamic FNN has its own learning rate for training purpose. A genetic algorithm is designed to allow a more efficient tuning process of the two learning rates of the FNN. The objective of the genetic algorithm is to reduce the searching time by searching for only one learning rate, which is the learning rate of the premise part, in the FNN. The dynamic optimal learning rates of the two-layer NN can he found directly using our innovative approach, Several examples are fully illustrated and excellent results are obtained for the model car backing up problem and the identification of nonlinear first order and second order systems.
Dynamical optimal training for interval type-2 fuzzy neural network (T2FNN)
(2003)
Wang, CH
;
Cheng, CS
;
Lee, TT
;
電控工程研究所
;
Institute of Electrical and Control Engineering
Type-2 fuzzy logic system (FLS) cascaded with neural network called type-2 fuzzy neural network (T2FNN), is presented in this paper to handle uncertainty with dynamical optimal learning. A T2FNN consists of type-2 fuzzy linguistic process as the antecedent part and the two-layer interval neural network as the consequent part. The dynamical optimal training algorithm for the two-layer consequent part of interval T2FNN is first developed The stable and optimal left and right learning rates for the interval neural network, in the sense of maximum error reduction, can be derived for each iteration in the training process. It can also be shown both learning rates can not be both negative. Excellent results are obtained for the truck backing-up control, which yield more improved performance than those using type-1 FNN.
Dynamical optimal training for interval type-2 fuzzy neural network (T2FNN)
(2004-06-01)
Wang, CH
;
Cheng, CS
;
Lee, TT
;
電控工程研究所
;
Institute of Electrical and Control Engineering
Type-2 fuzzy logic system (FLS) cascaded with neural network, type-2 fuzzy neural network (T2FNN), is presented in this paper to handle uncertainty with dynamical optimal learning. A T2FNN consists of a type-2 fuzzy linguistic process as the antecedent part, and the two-layer interval neural network as the consequent part. A general T2FNN is computational-intensive due to the complexity of type 2 to type 1 reduction. Therefore, the interval T2FNN is adopted in this paper to simplify the computational process. The dynamical optimal training algorithm for the two-layer consequent part of interval T2FNN is first developed. The stable and optimal left and right learning rates for the interval neural network, in the sense of maximum error reduction, can be derived for each iteration in the training process (back propagation). It can also be shown both learning rates cannot be both negative. Further, due to variation of the initial MF parameters, i.e., the spread level of uncertain means or deviations of interval Gaussian MFs, the performance of back propagation training process may be affected. To achieve better total performance, a genetic algorithm (GA) is designed to search optimal spread rate for uncertain means and optimal learning for the antecedent part. Several examples are fully illustrated. Excellent results are obtained for the truck backing-up control and the identification of nonlinear system, which yield more improved performance than those using type-1 FNN.
Elongation of arrays of amorphous carbon tubes
(2005-10-01)
Wang, LS
;
Wang, CH
;
Peng, CW
;
Lee, CY
;
Chiu, HT