• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.142-145
• /
• 2003

Many control applications using Neural Network need a priori information about the objective system. But it is impossible to get exact information about the objective system in real world. To solve this problem, several control methods were proposed. Reinforcement learning control using neural network is one of them. Basically reinforcement learning control doesn't need a priori information of objective system. This method uses reinforcement signal from interaction of objective system and environment and observable states of objective system as input data. But many methods take too much time to apply to real-world. So we focus on faster learning to apply reinforcement learning control to real-world. Two data types are used for reinforcement learning. One is reinforcement signal data. It has only two fixed scalar values that are assigned for each success and fail state. The other is observable state data. There are infinitive states in real-world system. So the number of observable state data is also infinitive. This requires too much learning time for applying to real-world. So we try to reduce the number of observable states by classification of states with Self-Organizing Map. We also use neural dynamic programming for controller design. An inverted pendulum on the cart system is simulated. Failure signal is used for reinforcement signal. The failure signal occurs when the pendulum angle or cart position deviate from the defined control range. The control objective is to maintain the balanced pole and centered cart. And four states that is, position and velocity of cart, angle and angular velocity of pole are used for state signal. Learning controller is composed of serial connection of Self-Organizing Map and two Multi-layer Feed-Forward Neural Networks.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.620-623
• /
• 2014

Network topology for communication between vehicles are quickly changing because vehicles have a special movement pattern, especially character which is quickly changed by velocity and situation of road. Because of these feature, it is not easy to apply reliable routing on VANET(Vehicular Ad-hoc Network). Clustering method is one of the alternatives which are suggested for overcoming weakness of routing algorithm. Clustering is the way to communicate and manage vehicles by binding them around cluster head. Therefore choosing certain cluster head among vehicles has a decisive effect on decreasing overhead in relevant clustering and determining stability and efficiency of the network. This paper introduces new cluster head selection algorithm using RSU(Road Side Unit) different from existing algorithms. We suggest a more stable and efficient algorithm which decides a priority of cluster head by calculating vehicles' velocity and distance through RSU than existing algorithms.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.147-147
• /
• 2021

A partition of water distribution network (WDN) into district metered areas (DMAs) brings the efficiency and efficacy for water network operation and management (O&M), especially in monitoring pressure and leakage. Traditionally, the DMA configurations (i.e., number, shape, and size of DMAs) are permanent and cannot be changed occasionally. This leads to changes in water quality and reduced network redundancy lowering network resilience against abnormal conditions such as water demand variability and mechanical failures. This study proposes a framework to automatically divide a WDN into dynamic DMA configurations, in which the DMA layouts can self-adapt in response to abnormal scenarios. To that aim, a complex graph theory is adopted to sectorize a WDN into multiscale DMA layouts. Then, different failure-based scenarios are investigated on the existing DMA layouts. Here, an optimization-based model is proposed to convert existing DMA layouts into dynamic layouts by considering existing valves and possibly placing new valves. The objective is to minimize the alteration of flow paths (i.e., flow direction and velocity in the pipes) while preserving the hydraulic performance of the network. The proposed method is tested on a real complex WDN for demonstration and validation of the approach.

• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.106.5-106
• /
• 2002

1. Introduction 2. Artificial Immune Networks and Navigation Algorithm 3. Obstacle Avoidance and Goal Approach Behavior 4. Weights Adjustment Using Neural Network 5. Velocity Control and Local Minimum Avoidance 6. Simulation 7. Conclusion

• Journal of KIISE:Databases
• /
• v.33 no.3
• /
• pp.283-298
• /
• 2006

The TPR-tree is the time-parameterized indexing scheme that supports the querying of the current and projected future positions of such moving objects by representing the locations of the objects with their coordinates and velocity vectors. If this index is, however, used in environments that directions and velocities of moving objects, such as vehicles, are very often changed, it increases the communication cost between the server and moving objects because moving objects report their position to the server frequently when the direction and the velocity exceed a threshold value. To preserve the communication cost regularly, there can be used a manner that moving objects report their position to the server periodically. However, the periodical position report also has a problem that lineal time functions of the TPR-tree do not guarantee the accuracy of the object's positions if moving objects change their direction and velocity between position reports. To solve this problem, we propose the query processing scheme and the data structure using road networks for predicting uncertainty positions of moving objects, which is reported to the server periodically. To reduce an uncertainty of the query region, the proposed scheme restricts moving directions of the object to directions of road network's segments. To remove an uncertainty of changing the velocity of objects, it puts a maximum speed of road network segments. Experimental results show that the proposed scheme improves the accuracy for predicting positions of moving objects than other schemes based on the TPR-tree.

• Journal of Power System Engineering
• /
• v.9 no.2
• /
• pp.33-39
• /
• 2005

Experiments are performed to study the mixed convection flow and heat transfer in an inclined parallel plates with the upper part cooled and the lower part heated uniformly. The Reynolds number ranges from $4.0{\times}10^{-3}\;to\;6.2{\times}10^{-2}$, the angle of inclination, ${\theta}$, from 0 to 45 degree from the horizontal line, and Pr of the high viscosity fluid is 909. In this paper, the PIV(Particle image velocimetry) with TLC(Thermo-sensitive liquid crystal) tracers is used for visualizing and analysis. This method allows simultaneous measurement of velocity and temperature field at a given instant of time. Quantitative data of the temperature and velocity are obtained by applying the color-image processing to a visualized image, and neural network is applied to the color-to-temperature calibration. This paper describes the methods, and presents the quantitative visualization of mixed convection. From this study, it is found that the flow pattern can be classified into three patterns which are affected by Reynolds number and the angle of inclination.

• The Bulletin of The Korean Astronomical Society
• /
• v.35 no.1
• /
• pp.51.2-51.2
• /
• 2010

We have carried out an extensive statistical analysis based on the results of simultaneous observations of SiO and $H_2O$ masers toward 166 known SiO and $H_2O$ maser sources using KVN_Yonsei radio telescope (Kim et al.2010, ApJS submitted). We investigate the distributions of the mean velocities and the intensity ratios between SiO and $H_2O$ maser emission including those between SiO v=1 and v=2,J=1-0 transitions according to type of evolved stars. We also investigate mutual relations between SiO and $H_2O$ maser properties(total flux densities and velocity structures etc.) according to stellar pulsation phases. Most of SiO masers appear around the stellar velocity (80 % within ${\pm}5km\;s^{-1}$), while $H_2O$ masers show a different characteristic compared with SiO masers (69% within ${\pm}5km\;s^{-1}$). In addition, we investigate a correlation between $SiO/H_2O$ maser emission and AKARIFIS flux density as well as the AKARI color characteristics of SiO and $H_2O$ observational results in the AKARIFIS two-color diagram.

• Structural Engineering and Mechanics
• /
• v.46 no.5
• /
• pp.673-693
• /
• 2013

This paper presents a systematic design and training procedure for the feed-forward back-propagation neural network (NN) modeling of both forward and inverse behavior of a rotary magnetorheological (MR) damper based on experimental data. For the forward damper model, with damper force as output, an optimization procedure demonstrates accurate training of the NN architecture with only current and velocity as input states. For the inverse damper model, with current as output, the absolute value of velocity and force are used as input states to avoid negative current spikes when tracking a desired damper force. The forward and inverse damper models are trained and validated experimentally, combining a limited number of harmonic displacement records, and constant and half-sinusoidal current records. In general the validation shows accurate results for both forward and inverse damper models, where the observed modeling errors for the inverse model can be related to knocking effects in the measured force due to the bearing plays between hydraulic piston and MR damper rod. Finally, the validated models are used to emulate pure viscous damping. Comparison of numerical and experimental results demonstrates good agreement in the post-yield region of the MR damper, while the main error of the inverse NN occurs in the pre-yield region where the inverse NN overestimates the current to track the desired viscous force.

• Journal of the Korea Computer Graphics Society
• /
• v.27 no.5
• /
• pp.33-43
• /
• 2021

In this paper, we propose a framework that transfers the information of style motions to content motions based on a variational autoencoder network combined with a style encoding in the latent space. Because we transfer a style to a content motion that is sampled from a variational autoencoder, we can increase the diversity of existing motion data. In addition, we can improve the unnatural motions caused by decoding a new latent variable from style transfer. That improvement was achieved by additionally using the velocity information of motions when generating next frames.

• The Journal of Korea Robotics Society
• /
• v.18 no.4
• /
• pp.427-435
• /
• 2023

This paper proposes a method of estimating the pose of a mobile robot by using a learning model. When estimating the pose of a mobile robot, wheel encoder and inertial measurement unit (IMU) data are generally utilized. However, depending on the condition of the ground surface, slip occurs due to interaction between the wheel and the floor. In this case, it is hard to predict pose accurately by using only encoder and IMU. Thus, in order to reduce pose error even in such conditions, this paper introduces a pose estimation method based on a learning model using data of the wheel encoder and IMU. As the learning model, long short-term memory (LSTM) network is adopted. The inputs to LSTM are velocity and acceleration data from the wheel encoder and IMU. Outputs from network are corrected linear and angular velocity. Estimated pose is calculated through numerically integrating output velocities. Dataset used as ground truth of learning model is collected in various ground conditions. Experimental results demonstrate that proposed learning model has higher accuracy of pose estimation than extended Kalman filter (EKF) and other learning models using the same data under various ground conditions.