Browsing by Author "Chung, IF"

Now showing 1 - 14 of 14

A GA-based fuzzy adaptive learning control network
(2000-05-16)
Chung, IF
;
Lin, CJ
;
Lin, CT
;
電控工程研究所
;
Institute of Electrical and Control Engineering
This paper addresses the structure and an associated learning algorithm of a feedforward multilayered connectionist network for realizing the basic elements and functions of a traditional fuzzy logic controller. The proposed fuzzy adaptive learning control network (FALCON) can be contrasted with the traditional fuzzy logic control systems in their network structure and learning ability. A structure/parameter learning algorithm, called FALCON-GA, is proposed for constructing the FALCON automatically. The FALCON-GA is a three-phase hybrid learning algorithm. In the first phase, the fuzzy ART algorithm is used to do fuzzy clustering in the input/output spaces according to the supervised training data. In the second phase, the genetic algorithm (GA) is used to find proper fuzzy logic rules by associating input clusters and output clusters. Finally, in the third phase, the backpropagation algorithm is used for tuning input:output membership functions. Hence, the FALCON GA combines the backpropagation algorithm for parameter learning and both the fuzzy ART and GAs for structure learning. It can partition the input/output spaces, tune membership functions and find proper fuzzy logic rules automatically. The proposed FALCON has two important features. First, it reduces the combinatorial demands placed by the standard methods for adaptive linearization of a system. Second, the FALCON is a highly autonomous system. In its learning scheme, only the training data need to be provided from the outside world. The users need not give the initial fuzzy partitions, membership functions and fuzzy logic rules. Computer simulations have been conducted to illustrate the performance and applicability of the proposed system. (C) 2000 Elsevier Science B.V. All rights reserved.
A neural fuzzy system for image motion estimation
(2000-09-01)
Lin, CT
;
Chung, IF
;
Sheu, LKM
;
電控工程研究所
;
Institute of Electrical and Control Engineering
Many methods for computing optical flow (image motion vector) have been proposed while others continue to appear. Block-matching methods are widely used because of their simplicity and easy implementation. The motion vector is uniquely defined, in block-matching methods, by the best fit of a small reference subblock from a previous image frame in a larger, search region from the present image frame. Hence, this method is very sensitive to the real environments (involving occlusion, specularity, shadowing, transparency, etc.). In this paper, a neural fuzzy system with robust characteristics and learning ability is incorporated with the block-matching method to make a system adaptive for different circumstances. In the neural fuzzy motion estimation system, each subblock in the search region is assigned a similarity membership contributing different degrees to the motion vector. This system is more reliable, robust, and accurate in motion estimation than many other methods including Horn and Schunck's optical flow, fuzzy logic motion estimator (FME), best block matching, NR, and fast block matching. Since fast block-matching algorithms can be used to reduce search time, a three-step fast search method is employed to find the motion vector in our system. However, the candidate motion vector is often trapped by the local minimum, which makes the motion vector undesirable. An improved three-step fast search method is tested to reduce the effect from local minimum and some comparisons about fast search algorithms are made. In addition, a Quarter Compensation Algorithm for compensating the interframe image to tackle the problem that the motion vector is not an integer but rather a floating point is proposed. Since our system can give the accurate motion vector, we may use the motion information in many different applications such as motion compensation, CCD camera auto-focusing or zooming, moving object extraction, etc. Two application examples will be illustrated in this paper. (C) 2000 Elsevier Science B.V. All rights reserved.
A neural network that learns from fuzzy data for language acquisition
(1996-12-01)
Lin, CT
;
Kan, MC
;
Chung, IF
;
電控工程研究所
;
Institute of Electrical and Control Engineering
This paper(a) proposes a four-layered fuzzy language acquisition network (FLAN) for acquiring fuzzy language. It can catch the intended information from a sentence (command) spoken in natural language with fuzzy terms. The intended information includes a meaningful semantic action and the fuzzy linguistic information of that action (for example, the phrase ''move forward'' represents the meaningful semantic action and the phrase ''very high speed'' represents the linguistic information in the fuzzy command ''Move forward in a very high speed.''). The proposed FLAN has two important features. First, we can make no restrictions whatever on the fuzzy language input which is used to specify the desired information, and the network requires no acoustic, prosodic, grammar and syntactic structure. Second, the linguistic information of an action is learned automatically and it is represented by fuzzy numbers based on alpha-level sets. A supervised learning scheme is proposed to train the FLAN on fuzzy training data. This learning scheme consists of the mutual-information (MI) supervised learning algorithm for learning meaningful semantic actions, and the fuzzy backpropagation (FBP) learning algorithm for learning linguistic information. An experimental system is constructed to illustrate the performance and applicability of the proposed FLAN.
A neuro-fuzzy combiner for multiobjective control
(2001)
Chung, IF
;
Lin, CT
;
電控工程研究所
;
Institute of Electrical and Control Engineering
This paper proposes a neuro-fuzzy combiner (NFC) with supervised learning capability for solving multiobjective control problems, The proposed NFC can combine n existing low-level controllers in a hierarchical way to form a multiobjective fuzzy controller. It is assumed that each low-level (fuzzy or nonfuzzy) controller has been well designed to serve a particular objective. The role of the NFC is to fuse the n actions decided by the n low-level controllers and determine a proper action acting on the environment (plant) at each time step. Hence, the NFC can combine low-level controllers and achieve multiple objectives (goals) at once. Here a NFC can be designed by proposed architecture and supervised learning scheme. Computer simulations have been conducted to illustrate the performance and applicability of the proposed architecture and learning scheme.
A reinforcement neuro-fuzzy combiner for multiobjective control
(1999-12-01)
Lin, CT
;
Chung, IF
;
電控工程研究所
;
Institute of Electrical and Control Engineering
This paper proposes a neuro-fuzzy combiner (NFC) with reinforcement learning capability for solving multiobjective control problems, The proposed NFC can combine n existing low-level controllers in a hierarchical way to form a multiobjective fuzzy controller, It is assumed that each low-level (fuzzy or nonfuzzy) controller has been well designed to serve a particular objective, The role of the NFC is to fuse the n actions decided by the n low-level controllers and determine a proper action acting on the environment (plant) at each time step. Hence, the NFC can combine low-level controllers and achieve multiple objectives (goals) at once. The NFC acts like a switch that chooses a proper action from the actions of low-level controllers according to the feedback information from the environment. In fact, the NFC is a soft switch; it allows more than one low-level actions to be active with different degrees through fuzzy combination at each time step, An NFC can be designed by the trial-and-error approach if enough a priori knowledge is available, or it can be obtained by supervised learning if precise input/output training data are available. In the more practical cases when there is no instructive teaching information available, the NFC can learn by itself using the proposed reinforcement learning scheme. Adopted with reinforcement learning capability, the NFC can learn to achieve desired multiobjectives simultaneously through the rough reinforcement feedback from the environment, which contains only critic information such as "success (good)" or "failure (bad)" for each desired objective. Computer simulations have been conducted to illustrate the performance and applicability of the proposed architecture and learning scheme.
Genetic algorithm-based neural fuzzy decision tree for mixed scheduling in ATM networks
(2002-12-01)
Lin, CT
;
Chung, IF
;
Pu, HC
;
Lee, TH
;
Chang, JY
Future broad-band integrated services networks based on the asynchronous transfer mode (ATM), technology are expected to support multiple types of multimedia information with diverse statistical characteristics and quality of service (QoS) requirements. To meet these requirements, efficient scheduling methods are important for traffic control in the ATM networks. Among the general scheduling schemes, the rate monotonic algorithm is simple enough to be used in high-speed networks, but it does not attain as high a system utilization as the deadline driven algorithm does. However, the deadline driven scheme is computationally complex and hard to implement in hardware. The mixed scheduling algorithm is the combination of the rate monotonic algorithm and the deadline driven algorithm; thus it can provide most of the benefits of these two algorithms. In this paper, we use the mixed scheduling algorithm to achieve high system utilization under the hardware constraint. Because there is no analytic method for the schedulability test of the mixed scheduling, we propose a genetic algorithm-based neural fuzzy decision tree (GANFDT) to realize it in a real-time environment. The GANFDT combines the GA and a neural fuzzy network into a binary classification tree. This approach also exploits the power of the classification tree. Simulation results show that the GANFDT provides an efficient way to carry out the mixed scheduling in the ATM networks.
Improvement of machining accuracy by fuzzy logic at corner parts for wire-EDM
(2001-09-16)
Lin, CT
;
Chung, IF
;
Huang, SY
;
電控工程研究所
;
Institute of Electrical and Control Engineering
Wire electrical discharge machining (wire-EDM) has always occupied an important position in some production fields, due to its capability of machining hard materials and intricate shapes. However, the machining accuracy, especially at corner parts, may be destroyed because of some phenomena such as wire deflection and vibration, etc. The purpose of this paper is to develop a control strategy based on fuzzy logic so that the machining accuracy at corner parts for wire-EDM can be improved. The fuzzy rules based on the wire-EDM's physical characteristics, experimental data, and operator's experience are constructed, so that the reduced percentage of sparking force can be determined by a multi-variables fuzzy logic controller. The objective of the total control is to improve the machining accuracy at corner parts, but still keep the cutting feedrate at fair values. As a result of experiments, machining errors of corner parts, especially in rough-cutting, can be reduced to less than 50% of those in normal machining, while the machining process time increases not more than 10% of the normal value. (C) 2001 Elsevier Science B.V. All rights reserved.
Machine learning for multi-class protein fold classification based on neural networks with feature gating
(2003)
Huang, CD
;
Chung, IF
;
Pal, NR
;
Lin, CT
;
電控工程研究所
The success of a classification system depends heavily on two things: the tools being used and the features considered. For the bioinformatics applications the role of appropriate features has not been paid adequate importance. In this investigation we use two novel ideas. First, we use neural networks where each input node is associated with a gate. At the beginning of the training all gates are almost closed, i.e., no feature is allowed to enter the network. During the training, depending on the requirements, gates are either opened or closed. At the end of the training, gates corresponding to good features are completely opened while gates corresponding to bad features are closed more tightly. And of course, some gates may be partially open. So the network can not only select features in an online manner when the learning goes on, it also does some feature extraction. The second novel idea is to use a hierarchical machine learning architecture. Where at the first level the network classifies the data into four major folds : all alpha, all beta, alpha + beta and alpha/beta. And in the next level we have another set of networks, which further classifies the data into twenty seven folds. This approach helps us to achieve the following. The gating network is found to reduce the number of features drastically. It is interesting to observe that for the first level using just 50 features selected by the gating network we can get a comparable test accuracy as that using 125 features using neural classifiers. The process also helps us to get a better insight into the folding process. For example, tracking the evolution of different gates we can find which characteristics (features) of the data are more important for the folding process. And, of course, it reduces the computation time. The use of the hierarchical architecture helps us to get a better performance also.
Multipurpose virtual-reality-based motion simulator
(2000-01-01)
Lin, CT
;
Chung, IF
;
Liann, SA
;
Su, FY
;
電控工程研究所
Public security has become an important issue everywhere. Especially, the safe manipulation and control of various machines and vehicles has gained special attention such that the authorities keep emphasizing the strict training and censoring of human operators. Currently, such training and censoring process usually relies on the actual machines, equipment, or vehicles in the real sites. This not only has high demands in space, time and cost, but also causes another phase of public security problem. In this connection, the world-wide trend is to tackle the above dilemma by using virtual reality (VR). However, the current researches or products on Vn are more matured in the software display part of VR. How to combine 3D VR display with motion platform to achieve the aforementioned training and censoring purposes is an important research issue. This paper focuses on this research issue, and the god is to develop a multipurpose virtual-reality-based motion simulation system to meet the requirements of public security in training and censoring of human operators.
Multipurpose virtual-reality-based motion simulator
(2000-01-01)
Lin, CT
;
Chung, IF
;
Liann, SA
;
Su, FY
;
電控工程研究所
Public security has become an important issue everywhere. Especially, the safe manipulation and control of various machines and vehicles has gained special attention such that the authorities keep emphasizing the strict training and censoring of human operators. Currently, such training and censoring process usually relies on the actual machines, equipment, or vehicles in the real sites. This not only has high demands in space, time and cost, but also causes another phase of public security problem. In this connection, the world-wide trend is to tackle the above dilemma by using virtual reality (VR). However, the current researches or products on Vn are more matured in the software display part of VR. How to combine 3D VR display with motion platform to achieve the aforementioned training and censoring purposes is an important research issue. This paper focuses on this research issue, and the god is to develop a multipurpose virtual-reality-based motion simulation system to meet the requirements of public security in training and censoring of human operators.
Multipurpose virtual-reality-based motion simulator
(2002)
Lin, CT
;
Chung, IF
;
Lin, JY
;
電控工程研究所
;
Institute of Electrical and Control Engineering
Public security has become an important issue everywhere. Especially, the safe manipulation and control of various machines and vehicles has gained special attention such that the authorities keep emphasizing the strict training and censoring of human operators. Currently, such training and censoring process usually relies on the actual machines, equipment, or vehicles in the real sites. This not only has high demands in space, time and cost, but also causes another phase of public security problem. In this connection, the world-wide trend is to tackle the above dilemma by using virtual reality (VR). However, the current researches or products on VR are more matured in the software display part of VR. How to combine 3D VR display with motion platform to achieve the aforementioned training and censoring purposes is an important research issue. This paper focuses on this research issue, and the goal is to develop a multipurpose virtual-reality-based motion simulation system to meet the requirements of public security in training and censoring of human operators.
Protein metal binding residue prediction based on neural networks
(2005-02-01)
Lin, CT
;
Lin, KL
;
Yang, CH
;
Chung, IF
;
Huang, CD
Over one-third of protein structures contain metal ions, which are the necessary elements in life systems. Traditionally, structural biologists were used to investigate properties of metalloproteins (proteins which bind with metal ions) by physical means and interpreting the function formation and reaction mechanism of enzyme by their structures and observations from experiments in vitro. Most of proteins have primary structures (amino acid sequence information) only; however, the 3-dimension structures are not always available. In this paper, a direct analysis method is proposed to predict the protein metal-binding amino acid residues from its sequence information only by neural networks with sliding window-based feature extraction and biological feature encoding techniques. In four major bulk elements (Calcium, Potassium, Magnesium, and Sodium), the metal-binding residues are identified by the proposed method with higher than 90% sensitivity and very good accuracy under 5-fold cross validation. With such promising results, it can be extended and used as a powerful methodology for metal-binding characterization from rapidly increasing protein sequences in the future.
Protein metal binding residue prediction based on neural networks
(2004)
Lin, CT
;
Lin, KL
;
Yang, CH
;
Chung, IF
;
Huang, CD
It is known that over one-third of protein structures contain metal ions, and they are the necessary elements in life system. Traditionally, structural biologists used to investigate properties of metalloproteins (proteins which bind with metal ions) by physical means and interpret the function formation and reaction mechanism of enzyme by their structures and observation from experiments in vitro. Most of proteins have primary structures (amino acid sequence information) only; however, the 3-dimension structures are not always available. In this paper, a direct analysis method is proposed to predict protein metalbinding amino acid residues only from its sequence information by neural network with sliding window-based feature extraction and biological feature encoding techniques and it can successfully detect 15 binding elements in protein, and 6 binding elements in enzyme.
Recognition of structure classification of protein folding by NN and SVM hierarchical learning architecture
(2003)
Chung, IF
;
Huang, CD
;
Shen, YH
;
Lin, CT
;
電控工程研究所
Classifying the structure of protein is a very important task in biological data. By means of the classification, the relationships and characteristics among known proteins can be exploited to predict the structure of new proteins. The study of the protein structures is based on the sequences and their similarity. It is a difficult task. Recently, due to the ability of machine learning techniques, many researchers have applied them to probe into this protein classification problem. We also apply here machine learning methods for multi-class protein fold recognition problem by proposing a novel hierarchical learning architecture. This novel hierarchical learning architecture can be formed by NN (neural networks) or SVM (support vector machine) as basic building blocks. Our results show that both of them can perform well. We use this new architecture to attack the multi-class protein fold recognition problem as proposed by Dubchak and Ding in 2001. With the same set of features our method can not only obtain better prediction accuracy and lower computation time, but also can avoid the use of the stochastic voting process in the original approach.