• Speech Sciences
• /
• v.8 no.4
• /
• pp.17-33
• /
• 2001

In this paper, we implement the large variable vocabulary speech recognition system, which is characterized by no additional pre-training process and no limitation of recognized word list. We have designed the system in order to achieve the high recognition rate using the decision tree based state tying algorithm and in order to reduce the processing time using the gaussian selection based variable flooring algorithm, the limitation algorithm of the number of nodes and ENNS algorithm. The gaussian selection based variable flooring algorithm shows that it can reduce the total processing time by more than half of the recognition time, but it brings about the reduction of recognition rate. In other words, there is a trade off between the recognition rate and the processing time. The limitation algorithm of the number of nodes shows the best performance when the number of gaussian mixtures is a three. Both of the off-line and on-line experiments show the same performance. In our experiments, there are some differences of the recognition rate and the average recognition time according to the distinction of genders, speakers, and the number of vocabulary.

• Journal of the Korea Computer Industry Society
• /
• v.3 no.5
• /
• pp.575-584
• /
• 2002

On-line handwritten character recognition be achieved successful results since effectively neural networks divided the letter which is the time ordering of strokes and stroke position. But off-line handwritten character recognition is in difficulty of incomplete preprocessing because has not information of motion or time and has frequently overlap of the letter and many noise occurrence. consequently off-line handwritten character recognition needs study of various methods. This paper apply watershed algorithm to preprocessing for off-line handwritten hangul character recognition. This paper presents effective method in four steps in watershed algorithm as consider execution time of watershed algorithm and quality of result image. As apply watershed algorithm with effective structure to preprocessing, can get to the good result of image enhancement and binarization. In this experiment, this paper is estimate the previous method with this paper method for execution time and quality in image. Average execution time on the previous method is 2.16 second and Average execution time on this paper method is 1.72 second. While this paper method is remove noise effectively with overlap stroke, the previous method does not seem to be remove noise effectively with overlap stroke.

• 전기의세계
• /
• v.26 no.3
• /
• pp.84-91
• /
• 1977

A modified version of algorithm and computer program is proposed to improve the currently available contingency analysis methode for the security control of power system. The underlying principle is based upon the reasonable modification of the current methods suggested by Stagg, Tinny, Alsac, and Stott in consideration of speed, aceuracy, reliability and convergency characteristics. The algorithm and program are desirgned especially for On-Line operation, although Off-Line applications are readily available. Several case studies on the Koren Power Company's 48-bus, 91-line system have shown that the method proposed is efficiently powerful in a sense of practical applicability.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1992.10a
• /
• pp.34-38
• /
• 1992

Geometry based CAD/CAM system is hard to achieve "net shape machining" For a net shape machining, the machining errors should be compensated by off-line CAD/CAM system followed by on-line control system. In this paper, we investigate an off-line compensation scheme for the machining errors due to tool deflection in contouring operation. The significance of the deflection errors is first shown, and a compensation is sought via modifying the nominal tool path. In modification, tool deflection amount is iteratively compensated until the deflection amount is iteratively compensated until the deflected path results in the desired contour within a tolerance. The path modification algorithm has been tested via computer simulation. The developed algorithm can be used as a postprocessor for the current CAD/CAM system based on geometric modeling as a means for enhancing the machining accuracy.

• Proceedings of the IEEK Conference
• /
• 2000.06c
• /
• pp.13-16
• /
• 2000

In this paper, we propose hybrid control method of neural network using the 3-point search algorithm. Proposed control method is searched the weight using the 3-point search algorithm for off-line then control the on-line. In order to verify the usefulness of the proposed method, we simulated the proposed control method with one link manipulator system and confirmed the excellency.

• Journal of Korea Multimedia Society
• /
• v.8 no.12
• /
• pp.1589-1596
• /
• 2005

The imprecise real-time system provides flexibility in scheduling time-critical tasks. Most scheduling problems of satisfying both 0/1 constraint and timing constraints, while the total error is minimized, are NP complete when the optional tasks have arbitrary processing times. Liu suggested a reasonable strategy of scheduling tasks with the 0/1 constraint on uniprocessors for minimizing the total error. Song et al suggested a reasonable strategy of scheduling tasks with the 0/1 constraint on multiprocessors for minimizing the total error. But, these algorithms are all off-line algorithms. On the other hand, in the case of on line scheduling, Shih and Liu proposed the NORA algorithm which can find a schedule with the minimum total error for a task system consisting solely of on-line tasks that are ready upon arrival. But, for the task system with 0/1 constraint, it has not been known whether the NORA algorithm can be optimal or not in the sense that it guarantees all mandatory tasks are completed by their deadlines and the total error is minimized. So, this paper suggests an optimal algorithm to search minimum total error for the imprecise on-line real-time task system with 0/1 constraint. Furthermore, the proposed algorithm has the same complexity, O(N log N), as the NORA algorithm, where N is the number of tasks.

• Journal of Institute of Control, Robotics and Systems
• /
• v.6 no.4
• /
• pp.268-275
• /
• 2000

The increasing technological demands of today call for complex systems, which in turn involve a series of optimization problems with some equality or inequality constraints. In this paper, we presents a real-coded genetic algorithm(RCGA) as an optimization tool which is implemented by three genetic operators based on real coding representation. Through a lot of simulation works, the optimum settings of its control parameters are obtained on the basis of global off-line robustness for use in off-line applications. Two optimization problems are Presented to illustrate the usefulness of the RCGA. In case of a constrained problem, a penalty strategy is incorporated to transform the constrained problem into an unconstrained problem by penalizing infeasible solutions.

• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• pp.977-979
• /
• 1996

This paper presents an algorithm to control the undesirable sway of a suspended load in the crane system that has a trade-off between positioning the load and suppressing the sway of the load. The aim is to transport the load to a specified place with small sway angle as quickly as possible. Dynamic model is based on a simple pendulum driven by a velocity drive that is mostly used for actuating a trolley in industry. Proposed algorithm is composed of two parts : one is a off-line optimal trajectory generator, the other on-line tracking control. The former produces optimal trajectories minimizing energy under the speed constraint of velocity drive. The latter controls outputs to track the generated trajectories. Digital simulations and experiments are performed on a pilot crane to demonstrate the performance of the proposed control algorithm.

• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06a
• /
• pp.347-348
• /
• 2008

• 제어로봇시스템학회:학술대회논문집
• /
• 1988.10a
• /
• pp.511-517
• /
• 1988

Movement order program of robot operating program is generally made by teach-in method. Therefore in most cases it is sufficient as long as the robot system shows a reguired repeatability for the working conditions. But the trend in the robot application moves to the automatic generation of the working programs. A mathematical robot model similar to the reality is necessary for the analysis of the kinematic transformation of the robot system. The purposes of this paper are to make a better describing form and to suggest an automatic algorithm for kinematic parameter identification.