• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.2002-2004
• /
• 2001

In this paper, we propose the PAM fuzzy controller using intelligent digital redesign method for nonlinear system. We design the continuous-time controller using TSK fuzzy model of nonlinear system, and then design the intelligent digital PAM controller based on continuous-time controller. Finally, the feasibility and stability of the proposed method has been proven through a computer simulation.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.4
• /
• pp.534-540
• /
• 2014

In this paper, we propose a fuzzy combined Polynomial Neural Network(PNN) for pattern classification. The fuzzy combined PNN comes from the generic TSK fuzzy model with several linear polynomial as the consequent part and is the expanded version of the fuzzy model. The proposed pattern classifier has the polynomial neural networks as the consequent part, instead of the general linear polynomial. PNNs are implemented by stacking the simple polynomials dynamically. To implement one layer of PNNs, the various types of simple polynomials are used so that PNNs have flexibility and versatility. Although the structural complexity of the implemented PNNs is high, the PNNs become a high order-multi input polynomial finally. To estimate the coefficients of a polynomial neuron, The weighted linear discriminant analysis. The output of fuzzy rule system with PNNs as the consequent part is the linear combination of the output of several PNNs. To evaluate the classification ability of the proposed pattern classifier, we make some experiments with several machine learning data sets.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.6
• /
• pp.688-694
• /
• 2005

In this Paper, we Propose a new neuro-fuzzy modeling using clustering-based learning method. In the proposed clustering method, number of clusters is automatically inferred and its parameters are optimized simultaneously, Also, a neuro-fuzzy model is learned based on clustering information at same time. In the previous modelling method, clustering and model learning are performed independently and have no exchange of its informations. However, in the proposed method, overall neuro-fuzzy model is generated by using both clustering and model learning, and the information of modelling output is used to clustering of input. The proposed method improve the computational load of modeling using Subtractive clustering method. Simulation results show that the proposed method has an effectiveness compared with the previous methods.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.11a
• /
• pp.415-418
• /
• 2007

가까운 미래에 인간생활에 활용될 지능형 로봇은 인간과 공존하면서도 효과적으로 인간을 도와줄 수 있는 인간친화형 로봇이라 할 수 있다. 이러한 것을 실현하기 위해서 로봇은 미지의 환경 내에서 자신의 위치 및 방향을 인식해야 할 필요가 있다. 더욱이, 이것은 일상생활에서 자연스럽게 이뤄지는 것이 당연하다. 로봇을 제어하는 가장 중요한 문제중의 하나로서 이동로봇의 주행에서의 위치불확실성을 해결함으로서 로봇의 위치를 추정하는 것이 바람직하다 할 수 있다. 본 논문에서는 실내외 공간에서 인간을 포한함 이동물체의 영상정보를 이용하여 이동로봇의 자기위치를 인식하기 위한 방법을 제시하고 있다. 제시한 방법은 로봇자체의 DR센서 정보와 카메라에서 얻은 영상정보로부터 로봇의 위치추정방법을 결합 한 것이다. 그리고 이동물체의 이전 위치정보와 관측 카메라의 모델을 사용하여 이동물체에 대한 영상프레임 좌표와 추정된 로봇위치 간의 관계를 표현할 수 있는 식을 제시하고 있다. 또한 이동하는 인간과 로봇의 위치와 방향을 추정하기 위한 제어방법을 제시하고 이동로봇의 위치를 추정하기위해서 칼만필터 방법을 적용하였다. 그리고 시뮬레이션 및 실험을 통하여 제시한 방법을 검증하였다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.1
• /
• pp.6-11
• /
• 2005

In this paper, we propose a new fuzzy clustering scheme that optimizes the initial structure and the parameters to improve the performance of a intelligent systems. The proposed method keeps the good properties of clustering, and improves the total systems' performance at the same time, Especially, the proposed algorithm not only keeps robust to change threshold value in the optimization process, but also improves the performance of a system through the process of the self-organizing and the converging intelligent systems in its structure of cluster. In experiments, the superiority of the proposed scheme is presented by comparing its performance with other methods.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.4 no.2
• /
• pp.187-192
• /
• 2004

In this paper, we proposed the method to design fuzzy controller using the experience of the operating expert and experimental numeric data for the robust control about the noise and disturbance instead of the traditional PID controller for the main steam temperature control of the thermal power plant. The temperature of main steam temperature process has to be controlled uniformly for the stable electric power output. The process has the problem of the hunting for the cases of various disturbances. In that case, the manual action of the operator happened to be introduced in some cases. We adopted the TSK (Takagi-Sugeno-Kang) model as the fuzzy controller and designed the fuzzy rules using the informations extracted directly from the real plant and various operating condition to solve the above problems and to apply practically. We implemented the real fuzzy controller as the Function Block module in the DCS(Distributed Control System) and evaluated the feasibility through the experimental results of the simulation.

• Journal of Korean Society on Water Environment
• /
• v.30 no.1
• /
• pp.31-43
• /
• 2014

Recently, Andong Reservoir and Imha Reservoir located in Nakdong River basin (Korea) are being connected by a tunnel (length 2km, diameter 5.5m) for a conjunctive use. The objectives of this study were to construct a two dimensional(2D) laterally-averaged model for two reservoirs, and examine the effects of connection on the water transportation and temperature stratification in the reservoirs. The 2D models for each reservoir were calibrated using field data obtained in 2006, and applied to the linked system for the year of 2002 when a severe flood intruded into Imha Reservoir during the typhoon Rusa. Simulation results showed that 364 million $m^3$ of water can be conveyed from Imha to Andong, while 291 million $m^3$ of water from Andong to Imha after connection. It resulted in 1.38 m increase of annual averaged water level in Andong Reservoir, whereas 3.75 m decrease in Imha Reservoir. The structures of thermal stratification in both reservoirs were influenced in line with the flow exchanges. In Andong Reservoir, the location of thermocline moved upward about 10 m compared to an independent operation. The results imply that the persistent turbidity issue of Imha Reservoir might be shifted to Andong Reservoir during a severe flood event after connection.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.2
• /
• pp.187-192
• /
• 2008

The Intelligent Space(ISpace) provides challenging research fields for surveillance, human-computer interfacing, networked camera conferencing, industrial monitoring or service and training applications. ISpace is the space where many intelligent devices, such as computers and sensors, are distributed. According to the cooperation of many intelligent devices, the environment, it is very important that the system knows the location information to offer the useful services. In order to achieve these goals, we present a method for representing, tracking and human Jollowing by fusing distributed multiple vision systems in ISpace, with application to pedestrian tracking in a crowd. This paper describes appearance based unknown object tracking with the distributed vision system in intelligent space. First, we discuss how object color information is obtained and how the color appearance based model is constructed from this data. Then, we discuss the global color model based on the local color information. The process of learning within global model and the experimental results are also presented.

• Journal of Soil and Groundwater Environment
• /
• v.16 no.5
• /
• pp.9-17
• /
• 2011

Positive effect of multiple-PGPR (Plan Growth Promoting Rhizobacteria), isolated from heavy metal contaminated soil, on the germination of Barnyard grass (Echinochloa crus-galli var. frumentacea) was quantitatively estimated in 5 heavy metal (Cd, As, Ni, Cu, and Pb) contaminated liquid medium. The $EC_{50}$ value for respective heavy metal was estimated by TSK (Trimmed Speraman-Karber) model based on germination rate. The results showed overall increase in $EC_{50}$ with PGPR inoculation. The $EC_{50}$ value increased 1.4% from 96.0 mg/L (control) to 97.4 mg/L (PGPR-treated) in As contaminated medium. In Ni contaminated medium, the $EC_{50}$ value increased 31.9% from 148.0 mg/L (control) to 195.2 mg/L (PGPR-treated), while the $EC_{50}$ showed 4.8% increase from 63.4 mg/L (control) to 66.5 mg/L (PGPR-treated) in Cu medium. Overall seedling growth was stronger in the PGPR treated seeds than that in the control, but positive effect on seedling growth was not conspicuous. At effective concentration of 100 mg/L, the average seedling length of the PGPR treatment in As, Cd, Cu, and Ni medium, respectively, was 1.13, 0.14, 0.40, and 0.06 cm longer than that in the control. However, the increase of seedling growth was statistically insignificant (p < 0.05). These results suggest that inoculation of the isolated-PGPR exerts positive effects on seed germination by reducing heavy metal toxicity and can be an effective tool for application of phytoremediation on heavy metal contaminated soils.