Browsing by Author "Hwang, SY"

Now showing 1 - 10 of 10

A fair protocol for fast resource assignment in wireless PCS networks
(1999)
Wang, TP
;
Tseng, CC
;
Hwang, SY
;
資訊工程學系
;
Department of Computer Science
Efficient sharing of communication resources is essential to PCS networks since the wireless bandwidth is limited. The Resource Auction Multiple Access (RAMA) protocol was recently proposed for fast resource assignment and handover in wireless PCS networks. The RAMA protocol assigns available communication resources (e.g., TDMA time slots or frequency channels) to subscribers one at a time using a collision resolution protocol based on subscriber ID's. However, the RAMA protocol encounters an unfairness problem; furthermore, performance results also indicate that it is inefficient at transmitting fixed-length subscriber ID's. Moreover, the emerging services such as teleconferencing have been presenting new challenges to dynamic-priority resource assignment. Tn this paper, we propose a modification to the RAMA protocol to improve its performance and resolve the unfairness problem. The proposed protocol also adopts dynamic priority assignment to improve the QOS for subscribers in overload environments.
A genetic algorithm with disruptive selection
(1996-04-01)
Kuo, T
;
Hwang, SY
;
交大名義發表
;
資訊科學與工程研究所
;
National Chiao Tung University
Genetic algorithms are a class of adaptive search techniques based on the principles of population genetics. The metaphor underlying genetic algorithms is that of natural evolution. Applying the ''survival-of-the-fittest'' principle, traditional genetic algorithms allocate more trials to above-average schemata, However, increasing the sampling rate of schemata that are above average does not guarantee convergence to a global optimum; the global optimum could be a relatively isolated peak or located in schemata that have large variance in performance, In this paper we propose a novel selection method, disruptive selection. This method adopts a nonmonotonic fitness function that is quite different from traditional monotonic fitness functions, Unlike traditional genetic algorithms, this method favors both superior and inferior individuals. Experimental results show that GA's using the proposed method easily find the optimal solution of a function that is hard for traditional GA's to optimize, We also present convergence analysis to estimate the occurrence ratio of the optima of a deceptive function after a certain number of generations of a genetic algorithm, Experimental results show that GA's using disruptive selection in some occasions find the optima more quickly and reliably than GA's using directional selection, These results suggest that disruptive selection can be useful in solving problems that have large variance within schemata and problems that are GA-deceptive.
A graded approach to shape representation
(1996-06-01)
Chen, PC
;
Tsai, WC
;
Hwang, SY
;
交大名義發表
;
資訊工程學系
Human beings perceived real-world objects in a graded manner, with macroviews providing global information about the objects and microviews providing more detailed information. Consequently, researchers in computer vision have directed their efforts toward building graded representations of objects, especially shapes of objects. Most previous approaches employed operations such as smoothing, blurring, or grouping to gradually obtain representations with different degrees of detail. Parameters of these operations are used to indicate the degree of detail, One objection to using operator parameters is that these parameters are difficult for viewers to interpret intuitively. To overcome this objection, we propose using a graded approach guided by a given similarity requirement to construct a more concise shape description. Our shape representation matches human intuition about detailing degree and suits machine requirement for concise description. (C) 1996 Academic Press, Inc.
A graded approach to shape representation
(1996-06-01)
Chen, PC
;
Tsai, WC
;
Hwang, SY
;
資訊工程學系
;
Department of Computer Science
Human beings perceived real-world objects in a graded manner, with macroviews providing global information about the objects and microviews providing more detailed information. Consequently, researchers in computer vision have directed their efforts toward building graded representations of objects, especially shapes of objects. Most previous approaches employed operations such as smoothing, blurring, or grouping to gradually obtain representations with different degrees of detail. Parameters of these operations are used to indicate the degree of detail, One objection to using operator parameters is that these parameters are difficult for viewers to interpret intuitively. To overcome this objection, we propose using a graded approach guided by a given similarity requirement to construct a more concise shape description. Our shape representation matches human intuition about detailing degree and suits machine requirement for concise description. (C) 1996 Academic Press, Inc.
A machine learning approach for acquiring descriptive classification rules of shape contours
(1997-02-01)
Hsu, JC
;
Hwang, SY
;
資訊工程學系
;
Department of Computer Science
We devise a method to generate descriptive classification rules of shape contours by using inductive learning. The classification rules are represented in the form of logic programs. We first transform input objects from pixel representation into predicate representation. The transformation consists of preprocessing, feature extraction and symbolic transformation. We then use FOIL which is an indictive logic programming system to produce classification rules. Experiments on two sets of data were performed to justify our proposed method. Copyright (C) 1997 pattern Recognition Society.
A machine learning approach for acquiring descriptive classification rules of shape contours
(1997-02-01)
Hsu, JC
;
Hwang, SY
;
資訊工程學系
;
Department of Computer Science
We devise a method to generate descriptive classification rules of shape contours by using inductive learning. The classification rules are represented in the form of logic programs. We first transform input objects from pixel representation into predicate representation. The transformation consists of preprocessing, feature extraction and symbolic transformation. We then use FOIL which is an indictive logic programming system to produce classification rules. Experiments on two sets of data were performed to justify our proposed method. Copyright (C) 1997 pattern Recognition Society.
Comparing the PCS location tracking strategies
(1996-02-01)
Lin, YB
;
Hwang, SY
;
交大名義發表
;
資訊工程學系
;
National Chiao Tung University
The cache scheme has been proposed to reduce the location tracking overhead of a personal communications services (PCS) network. In the previous papers, we studied the cache scheme under the assumptions that the home location register (HLR) access time is constant and the portable residence times have an exponential distribution. This paper compares the cache scheme with a basic scheme (such as IS-41). We generalize the previous models by considering the queueing effect of the HLR (i.e., we model the HLR by an M/G/1 queue) and by considering an arbitrary distribution for the portable residence times, Our study shows that the cache scheme is likely to outperform the basic scheme when 1) the net traffic to the HLR in the basic scheme saturates and the hit ratio in the cache scheme is larger than zero, 2) the portable mobility is low with respect to the call arrival rate, and 3) the variance of the HLR service time distribution is large (for a fixed mean service time). We also indicate an intuitive result that the cache hit ratio is high for a high call arrival rate and low portable mobility. For a fixed mean portable residence time, we show that a higher cache hit ratio is expected for a portable residence distribution with larger variance.
Registration area planning for PCS networks using genetic algorithms
(1998-08-01)
Wang, TP
;
Hwang, SY
;
Tseng, CC
;
資訊工程學系
;
Department of Computer Science
In a personal communication services (PCS's) network, the signaling traffic required to support user mobility is extremely high due to the huge numbers of users and the small sizes of cells. The requirement to minimize this traffic increases the importance of registration area (RA) planning in the PCS network design. In the literature, several heuristic algorithms have been proposed for RA planning, however, they may get trapped into local minimums and may lack robustness. In this paper, we reformulate the problem of RA planning as a cost-optimization problem and propose genetic algorithms for RA planning in PCS networks. Simulation results show that genetic algorithms are robust for RA planning.
Using disruptive selection to maintain diversity in Genetic Algorithms
(1997-07-01)
Kuo, T
;
Hwang, SY
;
交大名義發表
;
資訊科學與工程研究所
;
National Chiao Tung University
Genetic algorithms are a class of adaptive search techniques based on the principles of population genetics. The metaphor underlying genetic algorithms is that of natural evolution. With their great robustness, genetic algorithms have proven to be a promising technique for many optimization, design, control, and machine learning applications. A novel selection method, disruptive selection, has been proposed. This method adopts a nonmonotonic fitness function that is quite different from conventional monotonic fitness functions. Unlike conventional selection methods, this method favors both superior and inferior individuals. Since genetic algorithms allocate exponentially increasing numbers of trials to the observed better parts of the search space, it is difficult to maintain diversity in genetic algorithms. We show that Disruptive Genetic Algorithms (DGAs) effectively alleviate this problem by first demonstrating that DGAs can be used to solve a nonstationary search problem, where the goal is to track time-varying optima. Conventional Genetic Algorithms (CGAs) using proportional selection fare poorly on nonstationary search problems because of their lack of population diversity after convergence. Experimental results show that DGAs immediately track the optimum after the change of environment. We then describe a spike function that causes CGAs to miss the optimum. Experimental results show that DGAs outperform CGAs in resolving a spike function.
Why DGAs work well on GA-hard functions?
(1996)
Kuo, T
;
Hwang, SY
;
交大名義發表
;
資訊工程學系
;
National Chiao Tung University
What makes a problem easy or hard for a genetic algorithm (GA)? Much previous work has studied this question by applying Walsh analysis.(4)) In this paper, we demonstrate a function that is GA-hard by analyzing the Walsh coefficients of this function's Walsh decomposition. Then, we construct five functions with differing degrees of difficulty for genetic algorithms. Some are GA-easy and some are GA-hard. In a previous paper,(29)) wh have proposed a novel selection method, disruptive selection. This method devotes more trials to both better solutions and worse solutions than it does to moderate solutions, whereas the conventional method allocates its attention according to the performance of each solution. Experimental results show that DGAs (GAs using disruptive selection) perform very well on both GA-easy and GA-hard functions. Finally, we discuss why DGAs outperform conventional GAs.