• Communications for Statistical Applications and Methods
• /
• v.12 no.3
• /
• pp.713-727
• /
• 2005

Among different regression approaches, nonparametric procedures perform well under different conditions. In practice it is very hard to identify which is the best procedure for the data at hand, thus model combination is of practical importance. In this paper, we focus on one dimensional regression with fixed design. Polynomial regression, local regression, and smoothing spline are considered. The data are split into two parts, one part is used for estimation and the other part is used for prediction. Prediction performances are used to assign weights to different regression procedures. Simulation results show that the combined estimator performs better or similarly compared with the estimator chosen by cross validation. The combined estimator generates a similar risk to the best candidate procedure for the data.

• Journal of Korean Institute of Industrial Engineers
• /
• v.37 no.1
• /
• pp.1-9
• /
• 2011

This paper presents a new method that can solve the integrated problem of combined location routing and inventory problem (CLRIP) efficiently. The CLRIP is used to establish facilities from several candidate depots, to find the optimal set of vehicle routes, and to determine the inventory policy in order to minimize the total system cost. We propose a mathematical model for the CLRIP with budget constrained. Because this model is a nonpolynomial (NP) problem, we propose a endosymbiotic evolutionary algorithm (EEA) which is a kind of symbiotic evolutionary algorithm (SEA). The heuristic method is used to obtaining the initial solutions for the EEA. The experimental results show that EEA perform very well compared to the existing heuristic methods with considering inventory control decisions.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2005.05a
• /
• pp.1020-1025
• /
• 2005

The set covering(SC) problem has many practical application of modeling not only real world problems in civilian but also in military. In this paper we study optimal allocation model for maximizing utility of consolidating old fashioned and new air defense weapon system like Patriot missile and develop the new computational algorithm for the SC problem by using simulated annealing(SA) algorithm. This study examines three different methods: 1) simulated annealing(SA); 2) accelerated simulated annealing(ASA); and 3) selection by effectiveness degree(SED) with SA. The SED is adopted as an enhanced SA algorithm that the neighboring solutions could be generated only in possible optimal feasible region at the PERTURB function. Furthermore, we perform various experiments for both a reduced and an extended scale sized situations depending on the number of customers(protective objective), service(air defense), facilities(air defense artillery), threat, candidate locations, and azimuth angles of Patriot missile. Our experiment shows that the SED obtains the best results than others.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.13 no.2
• /
• pp.9-17
• /
• 1988

This vehicle scheduling problem with multiple depots and multiple vehicle types (VMM) is to determine the optimal vehicle routes to minimize the total travel costs. The object of this paper is to develope an exact algorithm for the VMM. In this paper the VMM is transformed into a mathematical model of the vehicle problem with multiple depots. Then an efficient branch and bound algorithm is developed to obtain an exact solution for this model. In order to enhance the efficiency, this algorithm emphasizes the follows; First, a heuristic algorithm is developed to get a good initial upper bound. Second, an primal-dual approach is used to solve subproblems which are called the quasi-assignment problem, formed by branching strategy is presented to reduce the number of the candidate subproblems.

• Journal of the Korean Magnetic Resonance Society
• /
• v.10 no.1
• /
• pp.96-104
• /
• 2006

The gene coding for APG8a (At4g21980), a protein from Arabidopsis thaliana, is involved in the autophagy process. The protein is an interesting candidate for structure determination by NMR spectroscopy. Toward this end, APG8a has been produced recombinantly in Escherichia coli and typical NMR experiments such as $^{15}N-HSQC$, HNCA, HN(CO)CA, CBCA(CO)NH, HCCH-TOCSY, HNCO were performed. The backbone resonances, HN, N, CA, CB, and C' were sequence-specifically assigned, and the secondary structures including 3 $\alpha$ helices and $4\beta$ strands were deduced based on the assignments. Due to the intrinsic flexibility or the effect of the denaturant, the backbone resonances were not fully observed. Since the structure calculation by NMR data was not possible, the 3-dimensional model was built based on the sequence homology, and compared with the NMR results. The overall structure of the model could explain and complement the NMR derived secondary structures.

• 한국신재생에너지학회:학술대회논문집
• /
• 2009.06a
• /
• pp.569-572
• /
• 2009

In this study, HFC ORCs (Organic Rankine Cycles) are investigated for a low-temperature geothermal power generation by a simulation method. A steady-state simulation model is developed to analyze and optimize cycle's performance. The model contains a turbine, a pump, an expansion valve and heat exchangers. The turbine and pump are modelled by an isentropic efficiency. Simulations were carried out for the given heat source and sink inlet temperatures, and given flow rate that is based on the typical power plant thermal-capacitance-rate ratio. 3 HFC fluids are considered as a candidate for a working fluid of low-temperature ORCs. In this study, all optimized HFC ORCs are shown to yield almost the same performance in terms of power for a low-temperature heat source of about $100^{\circ}C$.

• Bulletin of the Korean Space Science Society
• /
• 1992.10a
• /
• pp.19-22
• /
• 1992

We have computed the model spectra for the novae that formed dust grains shortly after their explosions. And the results are closely compared with recent infrared observational data. The amorphous carbon grains appear to be the major component for the carbon-rich novae. And the silicate grains which reside in Mira variables are found to be the best candidate material for the oxygen-rich novae. In novae, the winds from the central stars are very strong and fast so the emergent spectra are highly dependent on the time scales of dust formation. We find optically thin dustemission for oxgen-rich novae because they have longer time-scales of dust formation and the dust shells with larger radii.

• Proceedings of the Polymer Society of Korea Conference
• /
• 2006.10a
• /
• pp.181-181
• /
• 2006

We developed a novel method to fabricate a nerve guide conduit (NGC) with the porosity of submicron pore sizes (to prevent fibrous tissue infiltration) and hydrophilicity (for effective oxygen and nutrient permeation) using poly(lactic-co-glycolic acid) (PLGA) and Pluronic F127 by a modified immersion precipitation method designed by our laboratory. It was recognized that the hydrophilized PLGA/F127 (3 wt%) tube can be a good candidate as a NGC from the analyses of its morphology, mechanical strength, hydrophilicity, model nutrient permeability and in vivo nerve regeneration behavior using a rat model.

• Journal of Positioning, Navigation, and Timing
• /
• v.8 no.4
• /
• pp.193-200
• /
• 2019

The auto-encoder network which is a good candidate to handle the modeling of the signal strength attenuation is designed for denoising and compensating the distortion of the received data. It provides a non-linear mapping function by iteratively learning the encoder and the decoder. The encoder is the non-linear mapping function, and the decoder demands accurate data reconstruction from the representation generated by the encoder. In addition, the adaptive network width which supports the automatic generation of new hidden nodes and pruning of inconsequential nodes is also implemented in the proposed algorithm for increasing the efficiency of the algorithm. Simulation results show that the proposed method can improve the neural network training surface to achieve the highest possible accuracy of the signal modeling compared with the conventional modeling method.

• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.27-30
• /
• 1999

A spatio-temporal vector channel model is introduced for the position location (PL) estimation problem for CDMA cellular system environment. Two common ways for the PL make use of the AOA (Angle Of Arrival) and TDOA (Time Difference Of Arrival) from a subscriber to the multiple sensors (base stations). In this paper, we applied the derived vector channel to simulate the multipath channel for the angle of the signal arrival in CDMA systems. Cross-correlation method is a good candidate among other direction finding algorithms available in literature, especially in wideband modulation as in the CDMA system. The PL estimation errors are evaluated for different channels, which are obtained as a parameter of scattering radius of the suggested model. We noted that the number of sensors (base-stations) are related to the PL errors in favor of the available data.