• Journal of Electrical Engineering and Technology
• /
• v.12 no.4
• /
• pp.1657-1662
• /
• 2017

Facial expression recognition systems using video devices have emerged as an important component of natural human-machine interfaces which contribute to various practical applications such as security systems, behavioral science and clinical practices. In this work, we present a new method to analyze, represent and recognize human facial expressions using a sequence of facial images. Under our proposed facial expression recognition framework, the overall procedure includes: accurate face detection to remove background and noise effects from the raw image sequences and align each image using vertex mask generation. Furthermore, these features are reduced by principal component analysis. Finally, these augmented features are trained and tested using Hidden Markov Model (HMM). The experimental evaluation demonstrated the proposed approach over two public datasets such as Cohn-Kanade and AT&T datasets of facial expression videos that achieved expression recognition results as 96.75% and 96.92%. Besides, the recognition results show the superiority of the proposed approach over the state of the art methods.

• Korean Management Science Review
• /
• v.13 no.1
• /
• pp.57-70
• /
• 1996

This paper develops an adaptive scheduling policy for flexible manufacturing systems. The inductive learning methodology used for constructing this state-dependent scheduling policy provides and understanding of the relative importance of the various system parameters in determining the appropriate scheduling rule. Experimental studies indicated the superiority of the suggested approach over the alternative approach involving the repeated application of a single scheduling rule for randomly generated test problems as well as a real system, and under both stationary and nonstationary conditions. In particular, its relative performance improves further when there are frequent disruptions, and when disruptions are caused by the introduction of tiiight due date jobs, one of the most common surces of disruptions in most manufacturing systems.

• Nuclear Engineering and Technology
• /
• v.52 no.3
• /
• pp.544-551
• /
• 2020

Reactor control is a standout amongst the most vital issues in the nuclear power plant. In this paper, the optimal design of variable structure controller (VSC) based on the lightning search algorithm (LSA) is proposed for a nuclear reactor power system. The LSA is a new optimization algorithm. It is used to find the optimal parameters of the VSC instead of the trial and error method or experts of the designer. The proposed algorithm is used for the tuning of the feedback gains and the sliding equation gains of the VSC to prove a good performance. Furthermore, the parameters of the VSC are tuned by the genetic algorithm (GA). Simulation tests are carried out to verify the performance and robustness of the proposed LSA-based VSC compared with GA-based VSC. The results prove the high performance and the superiority of VSC based on LSA compared with VSC based on GA.

• Journal of Advanced Marine Engineering and Technology
• /
• v.21 no.3
• /
• pp.256-266
• /
• 1997

The authors apply the transfer influence coefficient method to the 3. dimensional vibration analysis of beam with multi - joints and formulate a general algorithm to analyse the longitudinal, flexural and torsional coupled forced vibration. In this paper, a structure which is mainly found in the robot arms, cranes and so on, has some crooked parts, subsystems and joints, but has no closed loop in this system. It is modeled as the beam of a distributed mass system with massless translational, rotational and torsional springs in each node, and joint elements of release or roll at node which the displacement vector is discontinuous. The superiority of the present method to the transfer matrix method in the computation accuracy was confirmed from the numerical computation results. Moreover, we confirmed that boundary and intermediate conditions could be controlled by varying the values of the spring constants.

• Journal of Advanced Marine Engineering and Technology
• /
• v.33 no.3
• /
• pp.403-410
• /
• 2009

The aim of this research is to develop the Bees Algorithm named 'the dynamic allocated Bees Algorithm' for multi-objective problem, especially in order to be suit for Pareto optimality. In addition two new neighbourhood search methods have been developed to produce enhanced solutions for a multi-objective problem named 'random selection neighbourhood search' and 'weighted sum neighbourhood search' and they were compared with the basic neighbourhood search in the dynamic allocated Bees Algorithm. They were successfully applied to an Environmental/Economic (electric power) dispatch (EED) problem and simulation results presented for the standard IEEE 30-bus system and they were compared to those obtained using other approaches. The comparison shows the superiority of the proposed dynamic allocated Bees Algorithms and confirms its suitability for solving the multi-objective EED problem.

• Journal of the Korean Society for Precision Engineering
• /
• v.26 no.1
• /
• pp.130-137
• /
• 2009

This paper deals with the comparisons of methodologies to express finite rotations accounting for analysis of the rotor system. Researches have been made to predict a behavior of its rotational motion by introducing Euler angles which turned out to be lack in consistency and exactness of the analysis. To overcome this deficiency a new methodology is applied by using both spherical coordinate and quaternion in the rotor rotation and shows its superiority over choices of the Euler angle in terms of kinetic energy and rotation velocity. It is found through numerical examples that quaternion is a more useful and valid tool to derive the ideal numerical model of the rotor system.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.13 no.6
• /
• pp.608-616
• /
• 2013

This paper presents an adaptive sampling method for electrocardiogram (ECG) signal detection. First, by employing the strings matching process with compression dictionary, we recognize each segment of ECG with different characteristics. Then, based on the non-uniform sampling strategy, the sampling rate is determined adaptively. As the results of simulation indicated, our approach reconstructed the ECG signal at an optimized sampling rate with the guarantee of ECG integrity. Compared with the existing adaptive sampling technique, our approach acquires an ECG signal at a 30% lower sampling rate. Finally, the experiment exhibits its superiority in terms of energy efficiency and memory capacity performance.

• Journal of the Korea Society for Simulation
• /
• v.14 no.4
• /
• pp.55-68
• /
• 2005

The advancement in semiconductor technology is leading toward smaller critical dimension designs and larger wafer manufactures. Due to such phenomena, semiconductor industry is in need of an accurate control of the process. Photolithography is one of the key processes where the pattern of each layer is formed. In this process, precise superposition of the current layer to the previous layer is critical. Therefore overlay parameters of the semiconductor photolithography process is targeted for this research. The complex relationship among the input parameters and the output metrologies is difficult to understand and harder yet to model. Because of the superiority in modeling multi-nonlinear relationships, neural networks is used for the simulator modeling. For training the neural networks, conjugate gradient method is employed. An experiment is performed to evaluate the performance among the proposed neural network simulator, stepwise regression model, and the currently practiced prediction model from the test site.

• Journal of the military operations research society of Korea
• /
• v.22 no.2
• /
• pp.1-17
• /
• 1996

Sun Tzu once clarified that "One who knows the enemy and knows himself will not be endangered in a hundred engagements, " while Clausewitz explained that "A victory will be guaranteed for one who can overcome 'fog and friction' at a battlefield." Now the U.S. is striving hard to develop an American version of RMA (Revolution in Military Affairs)/MTR (Military Technical Revolution) by utilizing its rapidly emerging information technology in the information age. The U.S. firmly believes that its RMA/MTR with less defense expenditure can provide all combat players in the battlespace with "dominant battle awareness, " by which no nation will be able to challenge U.S. military superiority. In this paper, the recent efforts of the U.S. Armed Forces on RMA/MTR will be briefly introduced, some lessons and expertises from the U.S. RMA/MTR are extracted, and, in this regard, several suggestions are provided for the progress of the ROK Armed Forces.gress of the ROK Armed Forces.

• Journal of Sensor Science and Technology
• /
• v.15 no.6
• /
• pp.449-456
• /
• 2006

The purpose of urodynamic investigation is to obtain the information on the function of the urinary system. The aim of this study is to acquire the useful information of lower urinary tract symptom (LUTS) diagnosis through void force signal as noninvasive method. The system which could evaluate the function of compensatory hypertrophy with noninvasive and comfortable method was implemented to measure uroflow and void force during urination. The implemented system composes of the sensor parts, signal conditioning parts and PC monitoring program. For the evaluation of the implemented system, the simulation of control part of the system was performed and the model system for the lower urinary system was designed. The superiority of a measuring characteristic of the implemented system was verified using the model system. From the evaluation of the model system, we have found out that the void force was dependent on the occlusion degree and compensatory hypertrophy significantly.