• Journal of the Korea Society for Simulation
• /
• v.20 no.2
• /
• pp.77-85
• /
• 2011

It is believed that the anomalies or diseases of human organs are identified by the analysis of the patterns. This paper proposes a new classification technique for the identification of cancer disease using the proteome patterns obtained from two-dimensional polyacrylamide gel electrophoresis(2-D PAGE). In the new classification method, three different classification methods such as support vector machine(SVM), multi-layer perceptron(MLP) and k-nearest neighbor(k-NN) are extended by multi-boosting method in an array of subclassifiers and the results of each subclassifier are merged by ensemble method. Genetic algorithm was applied to obtain optimal feature set in each subclassifier. We applied our method to empirical data set from cancer research and the method showed the better accuracy and more stable performance than single classifier.

• International Journal of Control, Automation, and Systems
• /
• v.2 no.4
• /
• pp.423-434
• /
• 2004

In this paper, we introduce a new topology of Self-Organizing Polynomial Neural Networks (SOPNN) based on genetically optimized Multi-Layer Perceptron (MLP) and discuss its comprehensive design methodology involving mechanisms of genetic optimization. Let us recall that the design of the 'conventional' SOPNN uses the extended Group Method of Data Handling (GMDH) technique to exploit polynomials as well as to consider a fixed number of input nodes at polynomial neurons (or nodes) located in each layer. However, this design process does not guarantee that the conventional SOPNN generated through learning results in optimal network architecture. The design procedure applied in the construction of each layer of the SOPNN deals with its structural optimization involving the selection of preferred nodes (or PNs) with specific local characteristics (such as the number of input variables, the order of the polynomials, and input variables) and addresses specific aspects of parametric optimization. An aggregate performance index with a weighting factor is proposed in order to achieve a sound balance between the approximation and generalization (predictive) abilities of the model. To evaluate the performance of the GA-based SOPNN, the model is experimented using pH neutralization process data as well as sewage treatment process data. A comparative analysis indicates that the proposed SOPNN is the model having higher accuracy as well as more superb predictive capability than other intelligent models presented previously.reviously.

• Journal of ILASS-Korea
• /
• v.5 no.3
• /
• pp.17-26
• /
• 2000

The main parameter commonly used to evaluate spray distribution is spray angle. Spray angle is important because it influences the axial and radial distribution of the fuel. Spray angles were measured and compared for the two non-air assisted injectors such as 2hole-2stream 4hole-1stream injectors used for port fuel injection gasoline engines with n-heptane as a fuel by three different measuring techniques, i.e., digital image processing, shadowgraphy, and spray patternator, respectively. Fuel was injected with the injection pressures of 0.2-0.35 MPa into the room temperature and atmospheric pressure environment. In digital image processing approach, the selection of the transmittance level is critical to obtain the edge of spray and hence to measure the spray angle. From the measurement results by the shadowgraphy technique, it is dear that the spray angle is varied during the spray injection period. The measurement results from spray patternator show that the different spray angles exist in different region. Spray angle increases with the increase in the injection pressure. it is suggested that the spray angle and stream separated angle should be specified when spray is characterized for 2hole-2stream injector, because spray angle is much different though stream separated angle is same. It was also considerably affected by the measurement techniques introduced in this experimental work. However, the optimal axial distance for measuring the spray angle seems to be at least 60-80 mm from the injector tip for two non-air assisted injectors.

• Journal of Digital Convergence
• /
• v.8 no.1
• /
• pp.93-107
• /
• 2010

Performance of software development is measured by two major criteria - roductivity and quality. Although the criteria is empirically tested in software engineering research, they often present with a limited way under consideration of a few factors or contexts for developers to focus on the either productivity facets or quality facets. Analyzing data on software development performance collected over a 13-year period from 20 countries, we investigated how major software development factors - development type, development platform, development technique, language type, DBMS, methodology, methodology acquisition, CASE,, summary of work effort, resource level, max team size, affect the performance of software development. The results suggest that productivity and quality of software development are affected by different factors and context: function points, line of code, extreme defects, major defects, or minor defects. This research provides the empirical evidence that the two performance criteria require for software developer to have careful attention to find the optimal balance between the two performance criteria.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.9 no.2 s.42
• /
• pp.17-27
• /
• 2005

This paper presents an integrated optimum design and a cost effectiveness evaluation method of a viscoelastically damped structural system. The criterion selected for the optimization is the minimization of the life?cycle cost which is a function of structural sizing variables and the amount of the viscoelastic damper. A genetic algorithm is used as a numerical searching technique in order to simultaneously find the optimum parameters of the integrated system. Optimal distributions of design variables according to various seismic characteristics are investigated by applying the proposed design method to a numerical example of a 10?story building structure. The cost effectiveness of viscoelastically damped structural system is also evaluated by comparing the life-cycle cost of the structure without viscoelastic dampers. The results show that the viscoelastic damper is effective in a region of low to moderate seismicity.

• Korean journal of applied entomology
• /
• v.43 no.1
• /
• pp.27-34
• /
• 2004

This study was conducted to develop optimal control tactics of the northern root-knot nematode, Meloidogyne hapla, using cultural method and biological agents ｛Bacillus thuringiensis (Bt), Paecilomyces lilacinus and plant extract (Huhjunl)｝ in the fields of Codonopsis lanceolata. Germination of C. lanceolata was susceptible to fosthiazate, but not to Bt or a plant extract. In pot assay, the inhibitory effect of two microbial agents, Bt and Paecilomyces lilacinus, on M. hapla were significant, but less than that of fosthiazate. The plant extract also had significantly inhibitory effect on M. hapla. In field assay, treatments of P lilacinus and fosthiazate resulted in maximal yields and qualities of C. lanceolata. The effect of the plant extract on the yields of C. lanceolata was also better than no treatment. The nematode-occurring condition of the fields before transplanting had significant effect on development of C. lanceolata; nematode-occurring field type gave less yields than nematode-free field type. These results suggest that a cultural control technique using paddy field, microbial pesticides using Bt or P lilacinus, and the plant extract are the promising control tactics against M. hapla in C. lanceolata fields. As a field manual to decrease economical damage of C. lanceolata due to M. hapla, this study suggests that C. lanceolata can be cultured directly in paddy field or in upland field after nematode control using microbial agents or the plant extract.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.49 no.7
• /
• pp.23-31
• /
• 2012

Resource allocation, such as joint rate control and scheduling, is an important issue in cognitive radio networks. However, it is difficult to jointly consider the rate control and scheduling problem due to the stochastic behavior of channel availability in cognitive radio networks. In this paper, we propose an asymmetric joint rate control and scheduling technique under reliability constraints in cognitive radio networks. The joint rate control and scheduling problem is formulated as a convex optimization problem and substantially decomposed into several sub-problems using a dual decomposition method. An algorithm for secondary users to locally update their rate that maximizes the utility of the overall system is also proposed. The results of simulations revealed that the proposed algorithm converges to a globally optimal solution.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.44 no.1
• /
• pp.24-31
• /
• 2007

DVB-T (Digital Video Broadcasting-Terrestrial) is an important multimedia broadcasting technology capable of high data-rate transmission and adopted by Europe. OFDM (Orthogonal Frequency Division Multiplexing) is the backbone technique employed in DVB-T to support multimedia services that have various bandwidths. Unfortunately, an OFDM signal has a large PAPR (Peak-to-Average Power Ratio). In this paper, we investigate the performance of a simple PAPR reduction scheme for the DVB-T system, which requires no change of a receiver structure or no additional information transmission. The approach we employed is clipping in the time and frequency domains. The time-domain clipping is carried out with a predetermined clipping level while the frequency-domain clipping is done within EVM (Error Vector Magnitude). This approach is suboptimal with lower computational complexity compared to the optimal method. The simulation results demonstrate that the proposed one is getting more effective at lower modulation levels and with more allowed constellation error.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.40 no.4
• /
• pp.253-259
• /
• 2017

Recent development in science and technology has modernized the weapon system of ROKN (Republic Of Korea Navy). Although the cost of purchasing, operating and maintaining the cutting-edge weapon systems has been increased significantly, the national defense expenditure is under a tight budget constraint. In order to maintain the availability of ships with low cost, we need accurate demand forecasts for spare parts. We attempted to find consumption pattern using data mining techniques. First we gathered a large amount of component consumption data through the DELIIS (Defense Logistics Intergrated Information System). Through data collection, we obtained 42 variables such as annual consumption quantity, ASL selection quantity, order-relase ratio. The objective variable is the quantity of spare parts purchased in f-year and MSE (Mean squared error) is used as the predictive power measure. To construct an optimal demand forecasting model, regression tree model, randomforest model, neural network model, and linear regression model were used as data mining techniques. The open software R was used for model construction. The results show that randomforest model is the best value of MSE. The important variables utilized in all models are consumption quantity, ASL selection quantity and order-release rate. The data related to the demand forecast of spare parts in the DELIIS was collected and the demand for the spare parts was estimated by using the data mining technique. Our approach shows improved performance in demand forecasting with higher accuracy then previous work. Also data mining can be used to identify variables that are related to demand forecasting.

• Advanced Composite Materials
• /
• v.17 no.3
• /
• pp.259-275
• /
• 2008

This study aims to optimize the mechanical and electrical properties of electrically conductive polymer composites (CPCs) for use as a material of bipolar plates for PEM fuel cells. The thin CPCs consisting of conductive fillers and polymer resin were fabricated by a preform molding technique. Expanded graphite (EG), flake-type graphite (FG) and carbon fiber (CF) were used as conductive fillers. This study tested two types of CPCs, EG/FG filled CPCs and EG/CF filled CPCs, to optimize the material properties. First, the characteristics of EG/FG filled CPCs were investigated according to the FG ratio for 7 and $100{\mu}m$ sized FG. CPCs using $100{\mu}m$ FG showed optimal material properties at 60 wt% FG ratio, which were an electrical conductivity of 390 S/cm and flexural strength of 51 MPa. The particle size was an important parameter to change the mechanical and electrical behaviors. The flexural strength was sensitive to the particle size due to the different levels of densification. The electrical conductivity also showed size-dependent behavior because of the different contributions to the conductive network. Meanwhile, the material properties of EG/CF filled CPCs was also optimized according to the CF ratio, and the optimized electrical conductivity and flexural strength were 290 S/cm and 58 MPa, respectively. The electrical conductivity of this case decreased similarly to the EG/FG filled case. On the other hand, the behavior of the flexural strength was more complicated than the EG/FG filled case, and the reason was attributed to the interaction between the strengthening effect of CF and the deterioration of voids.