學術出版;;Publications

Permanent URI for this communityhdl:11536/1

收集所有交通大學研究人員與學生個人或團體所發表之各項學術著作，涵蓋期刊論文、教師專書、學位論文等項。;;Collections of Publications of NCTU Researchers and Students Like Journal Papers and Thesis.

Browse

🏛️國立陽明交通大學機構典藏

Search Results

Now showing 1 - 10 of 80

Atomistic view of the recombinative desorption of H-2 from H/Si(100)
(2005-05-20)
Ferng, SS
;
Lin, CT
;
Yang, KM
;
Lin, DS
;
Chiang, TC
Scanning tunneling microscopy is employed to investigate the recombinative desorption of H-2 from hydrogenated Si(100) surfaces consisting of dihydride (SiH2) and monohydride (SiH) surface species organized in (1x1), (3x1), and (2x1) configurations. The results show that desorption from dihydrides involves a pair of neighboring dihydrides linked along the tetrahedral bond direction. Dihydrides in (3x1) domains are separated in the same direction by monohydrides, and desorption from a pair is geometrically impossible. The same desorption mechanism nevertheless applies via first a position switching of dihydrides with neighboring monohydrides.
An on-line self-constructing neural fuzzy inference network and its applications
(1998-02-01)
Juang, CF
;
Lin, CT
;
電控工程研究所
;
Institute of Electrical and Control Engineering
A self constructing neural fuzzy inference network (SONFIN) with on-line learning ability is proposed in this paper, The SONFIN is inherently a modified Takagi-Sugeno-Kang (TSK) type fuzzy rule-based model possessing neural network's learning ability, There are no rules initially in the SONFIN, They are created and adapted as on-line learning proceeds via simultaneous structure and parameter identification, In the structure identification of the precondition part, the input space is partitioned in a flexible way according to a aligned clustering-based algorithm. As to the structure identification of the consequent part, only a singleton value selected by a clustering method is assigned to each rule initially, Afterwards, some additional significant terms (input variables) selected via a projection-based correlation measure for each rule will be added to the consequent part (forming a linear equation of input variables) incrementally as learning proceeds, The combined precondition and consequent structure identification scheme can set up an economic and dynamically growing network, a main feature of the SONFIN, In the parameter identification, the consequent parameters are tuned optimally by either least mean squares (LMS) or recursive least squares (RLS) algorithms and the precondition parameters are tuned by backpropagation algorithm, Both the structure and parameter identification are done simultaneously to form a fast learning scheme, which is another feature of the SONFIN, Furthermore, to enhance the knowledge representation ability of the SONFIN, a linear transformation for each input variable can be incorporated into the network so that much fewer rules are needed or higher accuracy can be achieved, Proper linear transformations are also learned dynamically in the parameter identification phase of the SONFIN, To demonstrate the capability of the proposed SONFIN, simulations in different areas including control, communication, and signal processing are done, Effectiveness of the SONFIN is verified from these simulations.
Adaptive fuzzy command acquisition with reinforcement learning
(1998-02-01)
Lin, CT
;
Kan, MC
;
電機資訊學士班
;
Undergraduate Honors Program of Electrical Engineering and Computer Science
This paper proposes a four-layered adaptive fuzzy command acquisition network (AFCAN) for adaptively acquiring fuzzy command via interactions with the user or environment. It can catch the intended information from a sentence (command) given in natural language with fuzzy predicates, 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 at a very high speed"), The proposed AFCAN has three important features, First, we can make no restrictions whatever on the fuzzy command 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 adaptively and it is represented by fuzzy numbers based on alpha-level sets, Third, the network can learn during the course of performing the task, The AFCAN can perform off-line as well as on-line learning, For the off-line learning, the mutual-information (MI) supervised learning scheme and the fuzzy backpropagation (FBP) learning scheme are employed when the training data are available in advance, The former learning scheme is used to learn meaningful semantic actions and the latter learn linguistic information, The AFCAN can also perform on-line learning interactively when it is in use for fuzzy command acquisition, For the on-line learning, the MI-reinforcement learning scheme and the fuzzy reinforcement learning scheme are developed for the on-line learning of meaningful actions and linguistic information, respectively, An experimental system (fuzzy commands acquisition of a voice control system) is constructed to illustrate the performance and applicability of the proposed AFCAN.
GA-based reinforcement learning for neural networks
(1998-03-01)
Lin, CT
;
Jou, CP
;
Lin, CJ
;
電控工程研究所
;
Institute of Electrical and Control Engineering
A genetic reinforcement neural network (GRNN) is proposed to solve various reinforcement learning problems. The proposed GRNN is constructed by integrating two feedforward multilayer networks. One neural network acts as an action network for determining the outputs (actions) of the GRNN, and the other as a critic network to help the learning of the action network. Using the temporal difference prediction method, the critic network can predict the external reinforcement signal and provide a more informative internal reinforcement signal to the action network. The action network uses the genetic algorithm (GA) to adapt itself according to the internal reinforcement signal. The key concept of the proposed GRNN learning scheme is to formulate the internal reinforcement signal as the fitness function for the GA. This learning scheme forms a novel hybrid GA, which consists of the temporal difference and gradient descent methods for the critic network learning, and the GA for the action network learning. By using the internal reinforcement signal as the fitness function, the GA can evaluate the candidate solutions (chromosomes) regularly, even during the period without external reinforcement feedback from the environment. Hence, the GA can proceed to new generations regularly without waiting for the arrival of the external reinforcement signal. This can usually accelerate the GA learning because a reinforcement signal. This can usually accelerate the GA learning because a reinforcement signal may only be available at a time long after a sequence of actions has occurred in the reinforcement learning problems. Computer simulations have been conducted to illustrate the performance and applicability of the proposed learning scheme.
Runge-Kutta neural network for identification of dynamical systems in high accuracy
(1998-03-01)
Wang, YJ
;
Lin, CT
;
電控工程研究所
;
Institute of Electrical and Control Engineering
This paper proposes the Runge-Kutta neural networks (RKNN's) for identification of unknown dynamical systems described by ordinary differential equations (i.e., ordinary differential equation or ODE systems) in high accuracy. These networks are constructed according to the Runge-Kutta approximation method. The main attraction of the RKNN's is that they precisely estimate the changing rates of system states (i.e., the right-hand side of the ODE (x) over dot = f(x)) directly in their subnetworks based on the space-domain interpolation within one sampling interval such that they can do long-term prediction of system state trajectories. We show theoretically the superior generalization and long-term prediction capability of the RKNN's over the normal neural networks. Two types of learning algorithms are investigated for the RKNN's, gradient-and nonlinear recursive least-squares-based algorithms. Convergence analysis of the learning algorithms is done theoretically, Computer simulations demonstrate the proved properties of the RKNN's.
Application of fuzzy control to a road tunnel ventilation system
(1998-11-16)
Chen, PH
;
Lai, JH
;
Lin, CT
;
電控工程研究所
;
Institute of Electrical and Control Engineering
This paper deals with the serious problems of ventilation system in a large road tunnel. Higher visibility and lower concentration of carbon monoxide are the key issues concerning the ventilation system. Prior to designing the fuzzy control model, a configuration layout of the ventilation system including sensing, control and traffic prediction as well is conceptually constructed. Based on the layout that offers assignments of sensors and control elements, a fuzzy logic control model is developed. Membership functions of sensor errors and control increments are physically submitted in order to set up the fuzzy logic rules. Timing and spacing filtering in terms of weighting approaches is employed in the fuzzy logic rules. A dynamic equation describing the concentration of air pollution is also given so as to cooperate with the fuzzy logic rules and to play roles in the computer simulation. The result of computer simulation involving five cases indicates that a multi-level scheme is able to solve the engineering problems. (C) 1998 Elsevier Science B.V. All rights reserved.
A second-order learning algorithm for multilayer networks based on block Hessian matrix
(1998-12-01)
Wang, YJ
;
Lin, CT
;
電控工程研究所
;
Institute of Electrical and Control Engineering
This article proposes a new second-order learning algorithm for training the multilayer perceptron (MLP) networks. The proposed algorithm is a revised Newton's method. A forward-backward propagation scheme is first proposed for network computation of the Hessian matrix, H, of the output error function of the MLP. A block Hessian matrix, H-b, is then defined to approximate and simplify H. Several lemmas and theorems are proved to uncover the important properties of H and H-b, and verify the good approximation of H-b to H; H-b preserves the major properties of H. The theoretic analysis leads to the development of an efficient way for computing the inverse of H-b recursively. In the proposed second-order learning algorithm, the least squares estimation technique is adopted to further lessen the local minimum problems. The proposed algorithm overcomes not only the drawbacks of the standard backpropagation algorithm (i.e. slow asymptotic convergence rate, bad controllability of convergence accuracy, local minimum problems, and high sensitivity to learning constant), but also the shortcomings of normal Newton's method used on the MLP, such as the lack of network implementation of H, ill representability of the diagonal terms of H, the heavy computation load of the inverse of H, and the requirement of a good initial estimate of the solution (weights). Several example problems are used to demonstrate the efficiency of the proposed learning algorithm. Extensive performance (convergence rate and accuracy) comparisons of the proposed algorithm with other learning schemes (including the standard backpropagation algorithm) are also made. (C) 1998 Elsevier Science Ltd. All rights reserved.
Auditing user queries in dynamic statistical databases
(1999-01-01)
Shieh, SP
;
Lin, CT
;
資訊工程學系
;
Department of Computer Science
Chin proposed an audit scheme for inference control in statistical databases (SDBs) which can determine whether or not a query will lead to the compromise of an SDB. As Chin points out that the dynamic updates of an SDB are prohibited in this scheme because, otherwise, the time and storage requirements will become infinite. The restriction limits the use of this scheme since many SDBs need to be dynamically updated. In this paper, we propose an algorithm to remove this restriction so that updates can be allowed. We also propose an efficient audit scheme for dynamic SDBs which requires less time and storage requirements, and does not have the space explosion problem that appears in Chin's scheme. (C) 1999 Elsevier Science Inc. All rights reserved.
Optimal assignment of mobile agents for software authorization and protection
(1999-01-15)
Shieh, SP
;
Lin, CT
;
Wu, SY
;
資訊工程學系
;
Department of Computer Science
In this paper, a model for software authorization and protection in mobile code systems is proposed. In the model, a software is partitioned into objects, called mobile agents, and the privileges to access these agents are separated and distributed to the user's local system and a number of trusted servers called trusted computational proxies. The execution of a program (software) is conducted by cooperation of the agents and the proxies that contain them. Two agents are dependent if there is a message passing between them. To reduce the risk of software being attacked,dependent agents are distributed to different proxies. In this way, if a proxy is compromized, minimal information of the software will be disclosed. Methods for assigning agents to proxies are also proposed to minimize, under the security constraints, computation load of the proxies as well as communication load between the user's local system and proxies. (C) 1999 Elsevier Science B.V. All rights reserved.
Temperature control of rapid thermal processing system using adaptive fuzzy network
(1999-04-01)
Lin, CT
;
Juang, CF
;
Huang, JC
;
電控工程研究所
;
Institute of Electrical and Control Engineering
Temperature control of a rapid thermal processing (RTP) system using a proposed self-constructing adaptive fuzzy inference network (SCAFIN) is presented in this paper. First, the physical modeling of a RTP system is done. An integrated model is given for the components that make up a RTP system. These components are the lamp power dynamics, ray-tracing model, and the wafer thermal dynamic model. The models for the components are integrated in a numerical code to give a computer simulation of the complete RTP system. The simulation can be used to investigate the interaction of the furnace, lamp contour, and the control system. Then a direct inverse control scheme using the proposed SCAFIN is adopted to control the temperature of the RTP system. The SCAFIN is inherently a modified TSK-type fuzzy rule-based model possessing neural network's learning ability. There are no rules initially in the SCAFIN. They are created and adapted as on-line learning proceeds via simultaneous structure and parameter identification. Simulation results show that the control approach is able to track a temporally varying temperature trajectory and maintain the uniformity of the spatial temperature distribution of the wafer in the RTP system simultaneously. (C) 1999 Elsevier Science B.V. All rights reserved.

學術出版;;Publications

Browse

Filters

Settings

Sort By

Results per page

🏛️國立陽明交通大學機構典藏

Search Results