• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.3
• /
• pp.924-942
• /
• 2020

The facial expression is diverse and various among persons due to the impact of the psychology factor. Whilst the facial action is comparatively steady because of the fixedness of the anatomic structure. Therefore, to improve performance of the action unit recognition will facilitate the facial expression recognition and provide profound basis for the mental state analysis, etc. However, it still a challenge job and recognition accuracy rate is limited, because the muscle movements around the face are tiny and the facial actions are not obvious accordingly. Taking account of the moving of muscles impact each other when person express their emotion, we propose to make full use of co-occurrence relationship among action units (AUs) in this paper. Considering the dynamic characteristic of AUs as well, we adopt the 3D Convolutional Neural Network(3DCNN) as base framework and proposed to recognize multiple action units around brows, nose and mouth specially contributing in the emotion expression with putting their co-occurrence relationships as constrain. The experiments have been conducted on a typical public dataset CASME and its variant CASME2 dataset. The experiment results show that our proposed AU co-occurrence constraint 3DCNN based AU recognition approach outperforms current approaches and demonstrate the effectiveness of taking use of AUs relationship in AU recognition.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.5
• /
• pp.479-486
• /
• 2013

There exist two major difficulties in developing flight control system: nonlinear dynamic characteristics and time-varying properties of parameters of aircraft. Instead of the difficulties, many high reliable and efficient control methodologies have been developed. But, most of the developed control systems are based on the exact mathematical modelling of aircraft and, in the absence of such a model, it is very difficult to derive performance, robustness and nominal stability. From these aspects, recently, some approaches to utilizing the intelligent control theories such as fuzzy logic control, neural network and genetic algorithm have appeared. In this paper, one advanced intelligent lateral control system of a high speed fight has been developed utilizing type-2 fuzzy logic, which can deduce the uncertainty problem of the conventional fuzzy logic. The results will be verified through computer simulation.

• Journal of the Korean Society for Precision Engineering
• /
• v.20 no.12
• /
• pp.55-63
• /
• 2003

The traffic accident is the prerequisite of the traffic accident reconstruction. In this study, the traffic accident (forward collision) and traffic accident reconstruction (inverse collision) simulations are conducted to improve the quality and accuracy of the traffic accident reconstruction. The vehicle and tire models are used to simulate the trajectories for the post-impact motion of the vehicles after collision. The impact dynamic model applicable to the forward and inverse collision simulations is also provided. The accuracy of impact analysis for the vehicular collision depends on the accuracy of the coefficients of restitution and friction. The neural network is used to estimate these coefficients. The forward and inverse collision simulations for the multi-collisions are conducted. The new method fur the accident reconstruction is proposed to calculate the pre-impact velocities of the vehicles without using the trial and error process which requires the repeated calculations of the initial velocities until the forward collision simulation satisfies with the accident evidences. This method estimates the pre-impact velocities of the vehicles by analyzing the trajectories of the vehicles. The vehicle slides on a road surface not only under the skidding during an emergency braking but also under the steering. A vehicle over steering or cornering with excessive speed loses the traction and leaves tile yaw marks on the road surface. The new critical speed formula based on the vehicle dynamics is proposed to analyze the yaw marks and shows smaller errors than ones of the existing critical speed formula.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.59 no.3
• /
• pp.279-287
• /
• 2010

Interior permanent magnet synchronous motor(IPMSM) adjustable speed drives offer significant advantages over induction motor drives in a wide variety of industrial applications such as high power density, high efficiency, improved dynamic performance and reliability. This paper proposes efficiency optimization control of IPMSM drive using adaptive fuzzy learning controller(AFLC). In order to optimize the efficiency the loss minimization algorithm is developed based on motor model and operating condition. The d-axis armature current is utilized to minimize the losses of the IPMSM in a closed loop vector control environment. The design of the current based on adaptive fuzzy control using model reference and the estimation of the speed based on neural network using ANN controller. The controllable electrical loss which consists of the copper loss and the iron loss can be minimized by the optimal control of the armature current. The minimization of loss is possible to realize efficiency optimization control for the proposed IPMSM. The optimal current can be decided according to the operating speed and the load conditions. This paper considers the design and implementation of novel technique of high performance speed control for IPMSM using AFLC. Also, this paper proposes speed control of IPMSM using AFLC1, current control of AFLC2 and AFLC3, and estimation of speed using ANN controller. The proposed control algorithm is applied to IPMSM drive system controlled AFLC, the operating characteristics controlled by efficiency optimization control are examined in detail.

• Smart Structures and Systems
• /
• v.17 no.2
• /
• pp.167-194
• /
• 2016

This paper investigates the Synergetics based Damage Detection Method (SDDM) for frame structures by using surface-bonded PZT (Lead Zirconate Titanate) patches. After analyzing the mechanism of pattern recognition from Synergetics, the operating framework with cooperation-competition-update process of SDDM was proposed. First, the dynamic identification equation of structural conditions was established and the adjoint vector (AV) set of original vector (OV) set was obtained by Generalized Inverse Matrix (GIM).Then, the order parameter equation and its evolution process were deduced through the strict mathematics ratiocination. Moreover, in order to complete online structural condition update feature, the iterative update algorithm was presented. Subsequently, the pathway in which SDDM was realized through the modified Synergetic Neural Network (SNN) was introduced and its assessment indices were confirmed. Finally, the experimental platform with a two-story frame structure was set up. The performances of the proposed methodology were tested for damage identifications by loosening various screw nuts group scenarios. The experiments were conducted in different damage degrees, the disturbance environment and the noisy environment, respectively. The results show the feasibility of SDDM using piezoceramic sensors and actuators, and demonstrate a strong ability of anti-disturbance and anti-noise in frame structure applications. This proposed approach can be extended to the similar structures for damage identification.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.9 no.5
• /
• pp.526-537
• /
• 1999

In the paper. we propose an evaluation model based the adaptive fuzzy systems, which can transform the physical features of a color pattern to the emotional features. The model is motivated by the Soen's psychological experiments, in which he found the physical features such as average hue, saturation, intensity and the dynamic components of the color patterns affects to the emotional features represented by a pair of adjective words having the opposite meanings. Our proposed model consists of two adaptive fuzzy rule-bases and the y-model, a l i r ~ r ys et operator, to fuze the evaluation values produced by them. The model shows con~parablep erformances to the neural network for the approximation of the nonlinear transforms, and it has the advantage to obtain the linbwistic interpretation from the trained results. We believe the evaluated results of a color pattern can be used to the emotion-based color image retrievals.

• Proceedings of the Korean Institute of IIIuminating and Electrical Installation Engineers Conference
• /
• 2009.05a
• /
• pp.408-411
• /
• 2009

In this paper, conventional PI, fuzzy neural network(FNN) and adaptive teaming mechanism(ALM)-FNN for rotor field oriented controlled(RFOC) induction motor are studied comparatively. The widely used control theory based design of PI family controllers fails to perform satisfactorily under parameter variation nonlinear or load disturbance. In high performance applications, it is useful to automatically extract the complex relation that represent the drive behaviour. The use of learning through example algorithms can be a powerful tool for automatic modelling variable speed drives. They can automatically extract a functional relationship representative of the drive behavior. These methods present some advantages over the classical ones since they do not rely on the precise knowledge of mathematical models and parameters. Comparative study of PI, FNN and ALM-FNN are carried out from various aspects which is dynamic performance, steady-state accuracy, parameter robustness and complementation etc. To have a clear view of the three techniques, a RFOC system based on a three level neutral point clamped inverter-fed induction motor drive is established in this paper. Each of the three control technique: PI, FNN and ALM-FNN, are used in the outer loops for rotor speed. The merit and drawbacks of each method are summarized in the conclusion part, which may a guideline for industry application.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.23 no.12
• /
• pp.154-161
• /
• 2009

A fuel cell power plant is a very complex system which has various control loops with some non-linearity. For control of a fuel cell power plant, dynamic models of fuel cell stacks have been developed and simplified process flow diagrams of a fuel cell power plant has been presented. Using such a model of a Molten Carbonate Fuel Cell (MCFC) power plant, this paper deals with development of an intelligent setpoint reference governor (I-SRG) to find the optimal setpoints and feed forward control inputs for the plant power demand. The I-SRG is implemented with neural network by using Particle Swarm Optimization (PSO) algorithm based on system constraints and performance objectives. The feasibility of the I-SRG is shown through simulation of an MCFC power plant for tracking control of its power demand.

• Journal of Korea Water Resources Association
• /
• v.35 no.6
• /
• pp.817-826
• /
• 2002

Many researchers have been tried to forecast the future as analyzing data characteristics and the forecasting methodology may be divided into two cases of deterministic and stochastic techniques. However, the understanding data characteristics may be very important for model construction and forecasting. In the sense of this view, recently, the deterministic method known as nonlinear dynamics has been studied in many fields. This study uses the geometrical methodology suggested by Poincare for analyzing nonlinear dynamic systems and we apply the methodology to understand the characteristics of known systems and hydrologic data, and determines the possibility of forecasting according to the data characteristics. Say, we try to understand the data characteristics as constructing Poincare map by using Poincare section and could conjecture that the data sets are linear or nonlinear and an appropriate model.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.5
• /
• pp.187-194
• /
• 2019

Traditional demand forecasting methods are difficult to meet the needs of companies due to rapid changes in the market and the diversification of individual consumer needs. In a diversified production environment, the right demand forecast is an important factor for smooth yield management. Many of the existing predictive models commonly used in industry today are limited in function by little. The proposed model is designed to overcome these limitations, taking into account the part where each model performs better individually. In this paper, variables are extracted through Gray Relational analysis suitable for dynamic process analysis, and statistically predicted data is generated that includes characteristics of historical demand data produced through ARIMA forecasts. In combination with the LSTM model, demand forecasts can then be calculated by reflecting the many factors that affect demand forecast through an architecture that is structured to avoid the long-term dependency problems that the neural network model has.