• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.6
• /
• pp.2056-2069
• /
• 2014

In order to implement interactive and personalized Web services properly, it is necessary to understand the tangible and intangible responses of the users and to recognize their emotional states. Recently, some studies have attempted to build emotional state estimation models based on facial expressions. Most of these studies have applied multiple regression analysis (MRA), artificial neural network (ANN), and support vector regression (SVR) as the prediction algorithm, but the prediction accuracies have been relatively low. In order to improve the prediction performance of the emotion prediction model, we propose a novel SVR model that is optimized using a genetic algorithm (GA). Our proposed algorithm-GASVR-is designed to optimize the kernel parameters and the feature subsets of SVRs in order to predict the levels of two aspects-valence and arousal-of the emotions of the users. In order to validate the usefulness of GASVR, we collected a real-world data set of facial responses and emotional states via a survey. We applied GASVR and other algorithms including MRA, ANN, and conventional SVR to the data set. Finally, we found that GASVR outperformed all of the comparative algorithms in the prediction of the valence and arousal levels.

• Journal of Institute of Control, Robotics and Systems
• /
• v.7 no.12
• /
• pp.985-992
• /
• 2001

This paper proposes a self-organizing fuzzy modeling(SOFUM)which an create a new hyperplane shaped cluster and adjust parameters of the fuzzy model in repetition. The suggested algorithm SOFUM is composed of four steps: coarse tuning. fine tuning cluster creation and optimization of learning rates. In the coarse tuning fuzzy C-regression model(FCRM) clustering and weighted recursive least squared (WRLS) algorithm are used and in the fine tuning gradient descent algorithm is used to adjust parameters of the fuzzy model precisely. In the cluster creation, a new hyperplane shaped cluster is created by applying multiple regression to input/output data with relatively large fuzzy entropy based on parameter tunings of fuzzy model. And learning rates are optimized by utilizing meiosis-genetic algorithm in the optimization of learning rates To check the effectiveness of the suggested algorithm two examples are examined and the performance of the identified fuzzy model is demonstrated via computer simulation.

• Nuclear Engineering and Technology
• /
• v.44 no.3
• /
• pp.273-282
• /
• 2012

A new effective methodology for optimizing the enrichment of low-enriched zones as well as gadolinia fuel ($UO_2/Gd_2O_3$) rod designs in PLUS7 fuel assemblies was developed to minimize the maximum peak power in the core and to maximize the cycle lifetime. An automated link code was developed to integrate the genetic algorithm (GA) and the core design code package of ALPHA/PHOENIX-P/ANC and to generate and evaluate the candidates to be optimized efficiently through the integrated code package. This study introduces an optimization technique for the optimization of gadolinia fuel rod designs in order to effectively reduce the peak powers for a few hot assemblies simultaneously during the cycle. Coupled with the gadolinia optimization, the optimum enrichments were determined using the same automated code package. Applying this technique to the reference core of Ulchin Unit 4 Cycle 11, the gadolinia fuel rods in each hot assembly were optimized to different numbers and positions from their original designs, and the maximum peak power was decreased by 2.5%, while the independent optimization technique showed a decrease of 1.6% for the same fuel assembly. The lower enrichments at the fuel rods adjacent to the corner gap (CG), guide tube (GT), and instrumentation tube (IT) were optimized from the current 4.1, 4.1, 4.1 w/o to 4.65, 4.2, 4.2 w/o. The increase in the cycle lifetime achieved through this methodology was 5 effective full-power days (EFPD) on an ideal equilibrium cycle basis while keeping the peak power as low as 2.3% compared with the original design.

• International Journal of Highway Engineering
• /
• v.17 no.3
• /
• pp.97-105
• /
• 2015

PURPOSES : The Toll Collection System (TCS) operated by the Korea Expressway Corporation provides accurate traffic counts between tollgates within the expressway network under the closed-type toll collection system. However, although origin-destination (OD) matrices for a travel demand model can be constructed using these traffic counts, these matrices cannot be directly applied because it is technically difficult to determine appropriate passenger car equivalent (PCE) values for the vehicle types used in TCS. Therefore, this study was initiated to systematically determine the appropriate PCE values of TCS vehicle types for the travel demand model. METHODS : To search for the appropriate PCE values of TCS vehicle types, a traffic demand model based on TCS-based OD matrices and the expressway network was developed. Using the traffic demand model and a genetic algorithm, the appropriate PCE values were optimized through an approach that minimizes errors between actual link counts and estimated link volumes. RESULTS : As a result of the optimization, the optimal PCE values of TCS vehicle types 1 and 5 were determined to be 1 and 3.7, respectively. Those of TCS vehicle types 2 through 4 are found in the manual for the preliminary feasibility study. CONCLUSIONS : Based on the given vehicle delay functions and network properties (i.e., speeds and capacities), the travel demand model with the optimized PCE values produced a MAPE value of 37.7%, RMSE value of 17124.14, and correlation coefficient of 0.9506. Conclusively, the optimized PCE values were revealed to produce estimates of expressway link volumes sufficiently close to actual link counts.

• Journal of Institute of Control, Robotics and Systems
• /
• v.10 no.12
• /
• pp.1210-1216
• /
• 2004

This paper deals with a human-like gait generation of a biped robot with a balancing weight of an inverted pendulum type by using genetic algorithm. The ZMP (Zero Moment Point) is the most important index in a biped robot's dynamic walking stability. To perform a stable walking of a biped robot, a balancing motion is required according to legs' trajectories and a desired ZMP trajectory. A dynamic equation of the balancing motion is nonlinear due to an inverted pendulum type's balancing weight. To solve the nonlinear equation by the FDM (Finite Difference Method), a linearized model of equation is proposed. And GA (Genetic Algorithm) is applied to optimize a human-like balancing motion of a biped robot. By genetic algorithm, the index of the balancing motion is efficiently optimized, and a dynamic walking stability is verified by the ZMP verification equation. These balancing motion are simulated and experimented with a real biped robot IWR-IV. This human-like gait generation will be applied to a humanoid robot, at future work.

• Journal of the Institute of Convergence Signal Processing
• /
• v.2 no.4
• /
• pp.97-102
• /
• 2001

In computer-aided design, partitioning is task of clustering objects into groups to that a given objection function is optimized It is used at the layout level to fin strongly connected components that can be placed together in order to minimize the layout area and propagation delay. Partitioning can also be used to cluster variables and operation into groups for scheduling and unit selection in high-level synthesis. The most popular algorithms partitioning include the Kernighan-Lin algorithm Fiduccia-Mattheyses heuristic and simulated annealing In this paper we propose a genetic algorithm searching solution space for the circuit partitioning problem. and then compare it with simulated annealing by analyzing the results of implementation.

• Wind and Structures
• /
• v.20 no.3
• /
• pp.363-388
• /
• 2015

For controlling the vibration of specific building structure with large span, a practical method for the design of MTMD was developed according to the characteristics of structures subjected to wind loads. Based on the model of analyzing wind-induced response of large-span structure with MTMD, the optimization method of multiple tuned mass dampers for large-span roof structures subjected to wind loads was established, in which the applicable requirements for strength and fatigue life of TMD spring were considered. According to the method, the controlled modes and placements of TMDs in MTMD were determined through the quantitative analysis on modal contribution to the wind-induced dynamic response of structure. To explore the characteristics of MTMD, the parametric analysis on the effects of mass ratio, damping ratio, central tuning frequency ratio and frequency range of MTMD, was performed in the study. Then the parameters of MTMD were optimized through genetic algorithm and the optimized MTMD showed good dynamic characteristics. The robustness of the optimized MTMD was also investigated.

• Journal of Power Electronics
• /
• v.15 no.2
• /
• pp.479-486
• /
• 2015

The application of soft-switching techniques is increasing in the DC/DC converter area. It is important to design soft-switching parameters to ensure the converter operates properly and efficiently. An optimized design method is presented in this paper. The objective function is the total power loss of a converter, while the variables are soft-switching parameters and the constraints are the electrical requirements for soft-switching. Firstly, a response surface methodology (RSM) model with a high precision is built, and the rough optimized parameters can be obtained with the help of a genetic algorithm (GA) in the solution space determined by the constraints. Secondly, a re-optimization is conducted with a SPICE model and a GA, and accurate optimized parameters can be obtained. Simulation and experiment results show that the proposed method performs well in terms of a wide adaptability, efficiency, and global optimization.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.15 no.1
• /
• pp.12-19
• /
• 2015

In order to guide the robots move along a collision-free path efficiently and reach the goal position quickly in the unknown multi-obstacle environment, this paper presented the navigation problem of a wheel mobile robot based on proximity sensors by fuzzy logic controller. Then a genetic algorithm was applied to optimize the membership function of input and output variables and the rule base of the fuzzy controller. Here the environment is unknown for the robot and contains various types of obstacles. The robot should detect the surrounding information by its own sensors only. For the special condition of path deadlock problem, a wall following method named angle compensation method was also developed here. The simulation results showed a good performance for navigation problem of mobile robots.

• Proceedings of the Korea Society of Information Technology Applications Conference
• /
• 2005.11a
• /
• pp.263-266
• /
• 2005

An UHF ($860{\sim}960MHz$) RFID tag antenna is optimized and designed using a genetic algorithm (GA). The tag antenna impedance should be matched to the conjugate of the impedance of the tag IC Chip. The chip impedance has real and capacitive imaginary parts due to the parasitic capacitance of the RFID chip. A GA linked with a commercially available antenna simulation program optimizes the UHF $860{\sim}960\;MHz$ tag antenna to match a commercially available RFID chip. This method shows that any RFID antenna can be designed for any commercial RFID chip with any impedance.