• Journal of KIISE:Information Networking
• /
• v.32 no.3
• /
• pp.301-309
• /
• 2005

Learning program's behavior using machine learning techniques based on system call audit data is an effective intrusion detection method. Rule teaming, neural network, statistical technique, and hidden Markov model are representative methods for intrusion detection. Among them neural networks are known for its good performance in teaming system call sequences. In order to apply it to real world problems successfully, it is important to determine their structure. However, finding appropriate structure requires very long time because there are no formal solutions for determining the structure of networks. In this paper, a novel intrusion detection technique using evolutionary neural networks is proposed. Evolutionary neural networks have the advantage that superior neural networks can be obtained in shorter time than the conventional neural networks because it leams the structure and weights of neural network simultaneously Experimental results against 1999 DARPA IDEVAL data confirm that evolutionary neural networks are effective for intrusion detection.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.43 no.9
• /
• pp.787-798
• /
• 2015

The emergence of mid-to-small satellites has created a need for rapid development with a relatively low cost. However, the development of mid-to-small satellites requires considerable time and cost in early phase, in particular, during the development of mission and system requirements through iterations of conceptual design and mission design. In this research, Spacecraft Conceptual Design Tool(SCDT) which is based on Graphical User Interface(GUI) was developed to reduce the time and cost for early phase development. Furthermore, GUI-based software can make the input values to be editable easily and show users design results in various way. In this paper, the development results of MATLAB GUI-based SCDT are introduced.

• Korean Journal of Ecology and Environment
• /
• v.43 no.1
• /
• pp.161-167
• /
• 2010

In this study, we implemented an experimental approach of ecological model development in order to emphasize the importance of input variable selection with respect to time-delayed arrangement between input and output variables. Time-series modeling requires relevant input variable selection for the prediction of a specific output variable (e.g. density of a species). Inadequate variable utility for input often causes increase of model construction time and low efficiency of developed model when applied to real world representation. Therefore, for future prediction, researchers have to decide number of time-delay (e.g. months, weeks or days; t-n) to predict a certain phenomenon at current time t. We prepared a total of 3,900 equation models produced by Time-Series Optimized Genetic Programming (TSOGP) algorithm, for the prediction of monthly averaged density of a potamic phytoplankton species Stephanodiscus hantzschii, considering future prediction from 0- (no future prediction) to 12-months ahead (interval by 1 month; 300 equations per each month-delay). From the investigation of model structure, input variable selectivity was obviously affected by the time-delay arrangement, and the model predictability was related with the type of input variables. From the results, we can conclude that, although Machine Learning (ML) algorithms which have popularly been used in Ecological Informatics (EI) provide high performance in future prediction of ecological entities, the efficiency of models would be lowered unless relevant input variables are selectively used.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.11 no.4
• /
• pp.109-120
• /
• 2007

In this study, a bridge maintenance system is developed to generate performance-based optimum maintenance strategy by considering the life-cycle cost. A multi-objective combinatorial optimization problem is formulated to generate a tradeoff maintenance scenarios which satisfies the balance among the conflicting objectives such as the performance and cost during the bridge lifetime and a genetic algorithm is applied to the system. By using the developed program, this study proposes a process of optimum maintenance scenario applying to the steel girder bridge of national road. The developed system improves the current methods of establishing the bridge maintenance strategy and can be utilized as an efficient tool to provide the optimum bridge maintenance scenario corresponding to the various constraints and requirements of bridge agency.

• Journal of Drive and Control
• /
• v.17 no.3
• /
• pp.26-32
• /
• 2020

In modern society, the energy-saving problem of industrial vehicles is economically and environmentally critical. Energy savings using the potential energy of forklifts are one of the viable solutions to resolving this problem. The basic concept of this study is to operate the hydraulic motor and recharge the battery using the flow rate from the cylinder when loading heavy objects and lowering the fork. To save energy, the torque and rotational speed of the generator should be optimized according to the load and descent speed to increase efficiency. To this end, we propose a system that optimizes energy saving efficiency by controlling the swashplate angle of the variable hydraulic motor through the GA(Genetic-Algorithm). The results were verified by building and comparing fixed motor models and variable motor models using the AMEsim. The results of the study show that the proposed optimized swashplate angle increases the energy saving efficiency by approximately 6%-8%, depending on the working conditions.

• Journal of Computational Design and Engineering
• /
• v.2 no.3
• /
• pp.157-164
• /
• 2015

This paper discusses an optimization-based approach for the design of a product platform for industrial three-axis linear-type robots, which are widely used for handling objects in manufacturing lines. Since the operational specifications of these robots, such as operation speed, working distance and orientation, weight and shape of loads, etc., will vary for different applications, robotic system vendors must provide various types of robots efficiently and effectively to meet a range of market needs. A promising step toward this goal is the concept of a product platform, in which several key elements are commonly used across a series of products, which can then be customized for individual requirements. However the design of a product platform is more complicated than that of each product, due to the need to optimize the design across many products. This paper proposes an optimization-based fundamental framework toward the design of a product platform for industrial three-axis linear-type robots; this framework allows the solution of a complicated design problem and builds an optimal design method of fundamental features of robot frames that are commonly used for a wide range of robots. In this formulation, some key performance metrics of the robot are estimated by a reducedorder model which is configured with beam theory. A multi-objective optimization problem is formulated to represent the trade-offs among key design parameters using a weighted-sum form for a single product. This formulation is integrated into a mini-max type optimization problem across a series of robots as an optimal design formulation for the product platform. Some case studies of optimal platform design for industrial three-axis linear-type robots are presented to demonstrate the applications of a genetic algorithm to such mathematical models.

• Journal of Life Science
• /
• v.23 no.4
• /
• pp.595-601
• /
• 2013

The clusters of orthologous groups of proteins (COG) algorithm was applied to identify essential proteins in eukaryotes and to measure the degree of conservation. Sixty-three orthologous groups, which were conserved in 66 microbial genomes, enlarged to 104 eukaryotic orthologous groups (KOGs) and 71 KOGs were conserved at the nuclear genome of 7 eucaryotes. Fifty-four of 71 translation-related genes were conserved, highlighting the importance of proteins in modern organisms. Translation initiation factors (KOG0343, KOG3271) and prolyl-tRNA synthetase (KOG4163) showed high conservation based on the distance value analysis. The genes of Caenorhabditis elegans appear to harbor high genetic variation because the genome showed the highest variation at 71 conserved proteins among 7 genomes. The 71 conserved genes will be valuable in basic and applied research, for example, targeting for antibiotic development.

• Korean Journal of Construction Engineering and Management
• /
• v.14 no.5
• /
• pp.74-83
• /
• 2013

Most current BIM systems are focused on the visual information of work status in the design and construction stages. In a passive BIM system, 3D CAD tool can visualize the interference elements of design drawings, however, it cannot suggest a solution to solve the interference status. And 4D CAD tool in the construction stage can simulate the appearance of each activity by construction schedule, however, it cannot suggest an optimized schedule plan considering specified schedule condition of the project. Recently, many organizations need BIM solutions that can improve the work status beyond the level of simple visual information from BIM system. Active BIM system can provide the solutions to the project manager. This study suggests active BIM functions for the solutions and attempts to develop a 4D CAD engine to validate the usability of the functions.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2002.05a
• /
• pp.449-455
• /
• 2002

This paper considers that advanced planning and scheduling (APS) in manufacturing and the efficient purchasing where each customer order has its due date and multi-suppliers exit We present a Make-To­Order Supply Chan (MTOSC) model of efficient purchasing process from multi-suppliers and APS with outsourcing in a supply chain, which requires the absolute due date and minimized total cost. Our research has included two states. One is for efficient purchasing from suppliers: (a) selection of suppliers for required parts; (b) optimum part lead­time of selected suppliers. Supplier selection process has received considerable attention in the business­management literature. Determining suitable suppliers in the supply chain has become a key strategic consideration. However, the nature of these decisions usually is complex and unstructured. These influence factors can be divided into quantitative and qualitative factors. In the first level, linguistic values are used to assess the ratings for the qualitative factors such as profitability, relationship closeness and quality. In the second level a MTOSC model determines the solutions (supplier selection and order quantity) by considering quantitative factors such as part unit price, supplier's lead-time, and storage cost, etc. The other is for APS: (a) selection of the best machine for each operation; (b) deciding sequence of operations; (c) picking out the operations to be outsourcing; and (d) minimizing makespan under the due date of each customer's order. To solve the model, a genetic algorithm (GA)-based heuristic approach is developed. From the numerical experiments, GA­based approach could efficiently solve the proposed model, and show the best process plan and schedule for all customers' orders.

• Journal of Pharmaceutical Investigation
• /
• v.38 no.6
• /
• pp.365-372
• /
• 2008

The aim of this study was to investigate the frequency of the SNPs on MDR1 exon 12, 21 and 26 in Korean population and to analyze haplotype frequency on MDR1 exon 12, 21 and 26 in Korean population. A total of 426 healthy subjects was genotyped for MDR1, using polymerase chain reaction-based diagnostic tests. Haplotype was statistically inferred using an algorithm based on the expectation-maximization (EM). MDR1 C1236T genotyping revealed that the frequency for homozygous wild-type (C/C), heterozygous (C/T) and for homozygous mutant-type (T/T) was 20.19%, 46.48% and 33.33%, respectively. MDR1 G2677T/A genotyping revealed that the frequency for homozygous G/G, heterozygous G/T, homozygous T/T, heterozygous G/A, heterozygous T/A and for homozygous A/A type was 30.75%, 42.26%, 9.86%, 7.51 %, 7.04% and 2.58%, respectively. MDR1 C3435T genotyping revealed that the frequency for homozygous wild-type (C/C), heterozygous (C/T) and for homozygous mutant-type (T/T) was 38.73%, 50.24% and 11.03%, respectively. Twelve haplotypes were observed. Of the three major haplotypes identified (CGC, TTT and TGC), the CGC haplotype were mainly predominant in the Korean populations and accounted for 29.96% of total haplotype in Korean.