• Steel and Composite Structures
• /
• v.24 no.1
• /
• pp.93-112
• /
• 2017

Metaheuristic algorithms in general make use of uniform random numbers in their search for optimum designs. Levy Flight (LF) is a random walk consisting of a series of consecutive random steps. The use of LF instead of uniform random numbers improves the performance of metaheuristic algorithms. In this study, three discrete optimum design algorithms are developed for steel skeletal structures each of which is based on one of the recent metaheuristic algorithms. These are biogeography-based optimization (BBO), brain storm optimization (BSO), and artificial bee colony optimization (ABC) algorithms. The optimum design problem of steel skeletal structures is formulated considering LRFD-AISC code provisions and W-sections for frames members and pipe sections for truss members are selected from available section lists. The minimum weight of steel structures is taken as the objective function. The number of steel skeletal structures is designed by using the algorithms developed and effect of LF is investigated. It is noticed that use of LF results in up to 14% lighter optimum structures.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.4
• /
• pp.572-578
• /
• 2008

We analyze the search space considered by the previously proposed R-CORE method for learning Bayesian network structures of large scale. Experimental analysis on the search space of the method is also shown. The R-CORE method reduces the search space considered for Bayesian network structures by recursively clustering the random variables and restricting the orders between clusters. We show the R-CORE method has a similar search space with the previous method in the worst case but has a much less search space in the average case. By considering much less search space in the average case, the R-CORE method shows less tendency of overfitting in learning Bayesian network structures compared to the previous method.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.22 no.3
• /
• pp.405-415
• /
• 2012

In many applications a reader needs to determine whether a particular tag exists within a group of tags without a server. This is referred to as serverless RFID tag searching. A few protocols for the serverless RFID searching are proposed but they are the single tag search protocol which can search a tag at one time. In this paper, we propose a multi-tag search protocol based on a hash function and a random number generator which can search some tags at one time. For this study, we introduce a protocol which can resolve the problem of synchronization of seeds when communication error occurs in the S3PR protocol[1], and propose a multi-tag search protocol which can reduce the communication overhead. The proposed protocol is secure against tracking attack, impersonation attack, replay attack and denial-of-service attack. This study will be the basis of research for multi-tag serach protocol.

• Journal of Preventive Medicine and Public Health
• /
• v.32 no.4
• /
• pp.427-434
• /
• 1999

Objectives: This study was conducted to determine, by reviewing the literature, whether treatment of Helicobacter pylori infection in patients with non-ulcer dyspepsia affects symptoms. Methods: We retrieved the literature using MEDLINE search, with nonulcer dyspepsia and Hericobacter pylori and treatment as key words, which were reported from 1984 to 1998, and manual literature search. The criteria for inclusion was as follows; 1) The paper should have confirmed nonulcer dyspepsia as case definition. 2) The paper should have peformed a randomized, blind trial. 3) Confirmation of Helicobacter pylori eradication should be done 4 weeks after treatment. 4) studies with no information on measurement of symptoms after treatment were not accepted. The percentage of patients with symptom improvement after eradication therapy for Helicobacter pylori infection was calculated. Cumulative odds ratio was compared by fixed effect model and random effect model as sensitivity and funnel plot was used to evaluate publication bias. Results: The overall effect size of symptom improvement was calculated by cumulative odds ratio. Cumulative odds ratio of random effect model was 4.16(95% CI: 1.55-11.19). Before integrating each effect sizes into common effect size, the homogeneity test was conducted and random effect model was selected(Cochran's Q=41.08 (d.f=10, p<0.001)). The heterogeneity across studies was evaluated and the different methodological aspects of studies led to differences between study results Conclusions: The results suggest that the eradication of Helicobacter pylori in patients with non-ulcer dyspepsia results more symptom improvement. In studios that shows the opposite results there are methodological aspects explaining the heterogeneity.

• Korean Journal of Remote Sensing
• /
• v.37 no.6_2
• /
• pp.1891-1900
• /
• 2021

Fine particulate matter (FPM; diameter ≤ 2.5 ㎛) is frequently found in metropolitan areas due to activities associated with rapid urbanization and population growth. Many adolescents spend a substantial amount of time at school where, for various reasons, FPM generated outdoors may flow into indoor areas. The aims of this study were to estimate FPM concentrations and categorize types of FPM in schools. Meteorological and chemical variables as well as satellite-based aerosol optical depth were analyzed as input data in a random forest model, which applied 10-fold cross validation and a grid-search method, to estimate school FPM concentrations, with four statistical indicators used to evaluate accuracy. Loose and strict standards were established to categorize types of FPM in schools. Under the former classification scheme, FPM in most schools was classified as type 2 or 3, whereas under strict standards, school FPM was mostly classified as type 3 or 4.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.44 no.4
• /
• pp.12-22
• /
• 2021

This article suggests the machine learning model, i.e., classifier, for predicting the production quality of free-machining 303-series stainless steel(STS303) small rolling wire rods according to the operating condition of the manufacturing process. For the development of the classifier, manufacturing data for 37 operating variables were collected from the manufacturing execution system(MES) of Company S, and the 12 types of derived variables were generated based on literature review and interviews with field experts. This research was performed with data preprocessing, exploratory data analysis, feature selection, machine learning modeling, and the evaluation of alternative models. In the preprocessing stage, missing values and outliers are removed, and oversampling using SMOTE(Synthetic oversampling technique) to resolve data imbalance. Features are selected by variable importance of LASSO(Least absolute shrinkage and selection operator) regression, extreme gradient boosting(XGBoost), and random forest models. Finally, logistic regression, support vector machine(SVM), random forest, and XGBoost are developed as a classifier to predict the adequate or defective products with new operating conditions. The optimal hyper-parameters for each model are investigated by the grid search and random search methods based on k-fold cross-validation. As a result of the experiment, XGBoost showed relatively high predictive performance compared to other models with an accuracy of 0.9929, specificity of 0.9372, F₁-score of 0.9963, and logarithmic loss of 0.0209. The classifier developed in this study is expected to improve productivity by enabling effective management of the manufacturing process for the STS303 small rolling wire rods.

• Proceedings of the KIEE Conference
• /
• summer
• /
• pp.36-38
• /
• 2004

This paper presents an application of parallel hybrid Genetic Algorithm-Tabu Search (GA-TS) algorithm to search an optimal solution of a recokiguration in distribution system. In parallel hybrid CA-TS, after CA operations, stings which are not emerged in the past population are selected in the reproduction procedure. After reproduction operation, if there are many strings which are in the past population, we add new random strings into the population, if there's no improvement for the predetermined iteration, local search procedure is executed by TS for the strings with high fitness function value. To show the usefulness of the proposed method, developed algorithm has been tested and compared on a distribution system in the reference paper.

• Proceedings of the KIEE Conference
• /
• summer
• /
• pp.446-448
• /
• 2004

This paper presents an application of parallel hybrid Genetic Algorithm-Tabu Search (GA-TS) algorithm to search an optimal solution of a service restoration in distribution system. In parallel hybrid GA-TS, after GA operations, strings which are not emerged in the past population are selected in the reproduction procedure. After reproduction operation, if there are many strings which are in the past population, we add new random strings into the population. If there's no improvement for the predetermined iteration, local search procedure is executed by f for the strings with high fitness function value. To show the usefulness of the proposed method, developed algorithm has been tested and compared on a practical distribution system in Korea.

• Journal of Distribution Science
• /
• v.19 no.7
• /
• pp.5-17
• /
• 2021

Purpose: The distribution of goods and the flow of information, determined by consumer behavior toward online shopping, is drastically popular worldwide. This study examines some factors such as brand trust, online sales promotion, consumer personality, delivery service, quality assurance, information search, and online consumer satisfaction influence online shopping behavior. Research design, data, and methodology: A constructed questionnaire in an online survey was conducted with 241 random cluster respondents in the greater Jakarta Area. Structure equation model was utilized to analyze and verify all the data. Results: Research finding indicates online sales promotion, delivery service, quality assurance, and online consumer satisfaction positively influence information search. Meanwhile, brand trust, quality assurance, and information search positively influence online shopping behavior. However, the result illustrates that consumer personality negatively influences both information search and online shopping behavior. Conclusions: To influence online shopping behavior, the most important factors that need to be considered by marketplaces are quality assurance. It positively motivates Indonesia's citizens to collect information and make unplanned purchases. The study finding can be a reference for brands to maintain and build outstanding product quality, an informational website, and an excellent marketing strategy so that customers can meet their expectations. Besides, it also broadens both companies' and individuals' knowledge about the digital revolution on consumer behavior.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.4
• /
• pp.843-859
• /
• 2024

The university course scheduling problem (UCSP) aims at optimally arranging courses to corresponding rooms, faculties, students, and timeslots with constraints. Previously, the university staff solved this thorny problem by hand, which is very time-consuming and makes it easy to fall into chaos. Even some meta-heuristic algorithms are proposed to solve UCSP automatically, while most only utilize one single algorithm, so the scheduling results still need improvement. Besides, they lack an in-depth analysis of the inner algorithms. Therefore, this paper presents a novel and practical approach based on Tabu search and simulated annealing algorithms for solving USCP. Firstly, the initial solution of the UCSP instance is generated by one construction heuristic algorithm, the first fit algorithm. Secondly, we defined one union move selector to control the moves and provide diverse solutions from initial solutions, consisting of two changing move selectors. Thirdly, Tabu search and simulated annealing (SA) are combined to filter out unacceptable moves in a parallel mode. Then, the acceptable moves are selected by one adaptive decision algorithm, which is used as the next step to construct the final solving path. Benefits from the excellent design of the union move selector, parallel tabu search and SA, and adaptive decision algorithm, the proposed method could effectively solve UCSP since it fully uses Tabu and SA. We designed and tested the proposed algorithm in one real-world (PKNU-UCSP) and ten random UCSP instances. The experimental results confirmed its effectiveness. Besides, the in-depth analysis confirmed each component's effectiveness for solving UCSP.