• Speech Sciences
• /
• v.12 no.4
• /
• pp.7-16
• /
• 2005

We investigate the effect of membership concentration on the performance of the speaker-independent recognition system by FVQ/HMM. For the membership function, we adopt the result obtained from the objective function approach by Bezdek. Membership concentration is done by varying the exponent in the membership function. The number of selected clusters is constrained to two for the sake of cheap computational cost. Experimental results showed that the recognition rate has its maximum value when the membership function was taken to be inversely proportional to the distance of the input vector from the cluster centroid. When the membership concentration was two weak or too strong, the performance was found to be relatively poor as expected. Except these extreme cases, the membership concentration was not shown to affect the recognition rate significantly. This is in accordance with the general observation that the fuzzy system is not much sensitive. to the detailed shape of the membership function as long as it is overlapped over multiple classes.

• Proceedings of the KSME Conference
• /
• 2001.06b
• /
• pp.319-324
• /
• 2001

This paper presents the motion control of a mobile robot with arc sensor for lattice type welding. Its dynamic equation and motion control method for welding speed and seam tracking are described. The motion control is realized in the view of keeping constant welding speed and precise target line even though the robot is driven along a straight line or corner. The mobile robot is modeled based on Lagrange equation under nonholonomic constraints and the model is represented in state space form. The motion control of the mobile robot is separated into three driving motions of straight locomotion, turning locomotion and torch slider controls. For the torch slider control, the proportional integral derivative (PID) control method is used. For the straight locomotion, a concept of decoupling method between input and output is adopted and for the turning locomotion, the turning speed is controlled according to the angular velocity value at each point of the comer with range of $90^{\circ}$ constrained to the welding speed. The experiment has been done to verify the effectiveness of the proposed controllers. These results are shown to fit well by the simulation results.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.2 no.2
• /
• pp.67-74
• /
• 2007

Chattering phenomenon is still a large drawback of VSS. To overcome this problem, various approaches have been reported. A new notion of sliding sector has been proposed recently. Inside this sector, a kind of norm of the state decreases without control input. Therefore, so long as the state is constrained inside this sector, the norm of the state approaches to zero. The sliding sector theory is elementary study step and is studied about only linear systems. In this paper, new methods of the tracking control of unstable nonlinear systems using the sliding sector is proposed. This paper analyzes the stability, using Lyapunov function on the sliding sector. Through the computer simulations for an inverted pendulum system, it is verified that sliding sector control is capable to reduce the chattering.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.8 no.4
• /
• pp.807-814
• /
• 2004

Chattering phenomenon is still a large drawback of VSS. To overcome this problem, various approaches have been reported. A new notion of sliding sector has been proposed recently. Inside this sector, a kind of norm of the state decreases without control input. Therefore, so long as the state is constrained inside this sector, the norm of the state approaches to zero. The sliding sector theory is elementary study step and is studied about only linear systems. In this paper, new methods of stabilizing unstable nonlinear systems using the sliding sector is proposed. This paper analyzes the stability, using Lyapunov function on the sliding sector. Through the computer simulations for an inverted pendulum system, it is verified that sliding sector control is capable to reduce the chattering.

• Journal of Electrical Engineering and Technology
• /
• v.9 no.2
• /
• pp.423-432
• /
• 2014

Non-dominated Sorting Genetic Algorithm-II (NSGA-II) is applied for solving Combined Economic Emission Dispatch (CEED) problem with valve-point loading of thermal generators. This CEED problem with valve-point loading is a nonlinear, constrained multi-objective optimization problem, with power balance and generator capacity constraints. The valve-point loading introduce ripples in the input-output characteristics of generating units and make the CEED problem as a nonsmooth optimization problem. To validate its effectiveness of NSGA-II, two benchmark test systems, IEEE 30-bus and IEEE 118-bus systems are considered. To compare the Pareto-front obtained using NSGA-II, reference Pareto-front is generated using multiple runs of Real Coded Genetic Algorithm (RCGA) with weighted sum of objectives. Comparison with other optimization techniques showed the superiority of the NSGA-II approach and confirmed its potential for solving the CEED problem. Numerical results show that NSGA-II algorithm can provide Pareto-front in a single run with good diversity and convergence. An approach based on Technique for Ordering Preferences by Similarity to Ideal Solution (TOPSIS) is applied on non-dominated solutions obtained to determine Best Compromise Solution (BCS).

• Journal of the Korean Society for Railway
• /
• v.17 no.5
• /
• pp.321-327
• /
• 2014

In this paper, linear dynamic equations are derived from nonlinear dynamic equations of constrained multibody systems using the QR decomposition method. The derived linear equations are applied to a railway vehicle bogie. The vibration characteristics of the railway vehicle are investigated by calculating the natural mode and transfer function of the bogie frame in relation to rail-roughness input. The main modes of the bogie were found below 35Hz, and the local modes above 198Hz. The magnitude of the vertical transfer function varied with the forward velocity due to vertical and pitch modes, which were influenced by the forward velocity. The magnitude of the lateral transfer function was negligibly small, and the mode in the longitudinal direction was excited for longitudinal transfer function regardless of the forward velocity.

• Journal of Auto-vehicle Safety Association
• /
• v.14 no.2
• /
• pp.70-74
• /
• 2022

This paper describes the development of a target vehicle state estimation algorithm using vehicle-to-vehicle (V2V) communication. Perceiving the state of the target vehicle has great importance for successful autonomous driving and has been studied using various sensors and methods for many years. V2V communication has advantage of not being constrained by surrounding circumstances relative to other sensors. In this paper, we adopt the V2V signal for estimating the target vehicle state. Since applying only the V2V signal is improper by its low frequency and latency, the signal is used as additional measured data to improve the estimation accuracy. We estimate the target vehicle state using Extended Kalman filter (EKF); a point mass model was utilized in process update to predict the state of next step. The process update is followed by measurement update when ego vehicle receives V2V information. The proposed study evaluated state estimation by comparing input V2V information in an experiment where the ego vehicle follows the target vehicle behind it.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.19 no.3
• /
• pp.245-251
• /
• 2023

Facial expression recognition plays a significant role in understanding human emotional states. With the advancement of AI and computer vision technologies, extensive research has been conducted in various fields, including improving customer service, medical diagnosis, and assessing learners' understanding in education. In this study, we develop a model that can infer emotions in real-time from a webcam using transfer learning with TensorFlow.js and MobileNet. While existing studies focus on achieving high accuracy using deep learning models, these models often require substantial resources due to their complex structure and computational demands. Consequently, there is a growing interest in developing lightweight deep learning models and transfer learning methods for restricted environments such as web browsers and edge devices. By employing MobileNet as the base model and performing transfer learning, our study develops a deep learning transfer model utilizing JavaScript-based TensorFlow.js, which can predict emotions in real-time using facial input from a webcam. This transfer model provides a foundation for implementing facial expression recognition in resource-constrained environments such as web and mobile applications, enabling its application in various industries.

• Journal of the Korea Computer Graphics Society
• /
• v.30 no.2
• /
• pp.1-9
• /
• 2024

In this paper, we propose a new method to visualize different vector field patterns from density data. We use moving least squares (MLS), which is used in physics-based simulations and geometric processing. However, typical MLS does not take into account the nature of density, as it is interpolated to a higher order through vector-based constraints. In this paper, we design an algorithm that incorporates Monte Carlo-based weights into the MLS to efficiently account for the density characteristics implicit in the input data, allowing the algorithm to represent different forms of white noise. As a result, we experimentally demonstrate detailed vector fields that are difficult to represent using existing techniques such as naive MLS and divergence-constrained MLS.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1993.10a
• /
• pp.12-19
• /
• 1993

In general, the line balancing problem is defined as of finding an assignment of the given jobs to the workstations under the precedence constraints given to the set of jobs. Usually, the objective is either minimizing the cycle time under the given number of workstations or minimizing the number of workstations under the given cycle time. In this paper, we present a new type of an assembly line balancing problem which occurs in an electronics company manufacturing home appliances. The main difference of the problem compared to the general line balancing problem lies in the structure of the precedence given to the set of jobs. In the problem, the set of jobs is partitioned into two disjoint subjects. One is called the set of fixed jobs and the other, the set of floating jobs. The fixed jobs should be processed in the linear order and some pair of the jobs should not be assigned to the same workstations. Whereas, to each floating job, a set of ranges is given. The range is given in terms of two fixed jobs and it means that the floating job can be processed after the first job is processed and before the second job is processed. There can be more than one range associated to a floating job. We present a procedure to find an approximate solution to the problem. The procedure consists of two major parts. One is to find the assignment of the floating jobs under the given (feasible) assignment of the fixed jobs. The problem can be viewed as a constrained bin packing problem. The other is to find the assignment of the whole jobs under the given linear precedence on the set of the floating jobs. First problem is NP-hard and we devise a heuristic procedure to the problem based on the transportation problem and matching problem. The second problem can be solved in polynomial time by the shortest path method. The algorithm works in iterative manner. One step is composed of two phases. In the first phase, we solve the constrained bin packing problem. In the second phase, the shortest path problem is solved using the phase 1 result. The result of the phase 2 is used as an input to the phase 1 problem at the next step. We test the proposed algorithm on the set of real data found in the washing machine assembly line.