• Psychiatry investigation
• /
• v.15 no.11
• /
• pp.1030-1036
• /
• 2018

Objective In this study, we aimed to develop a model predicting individuals with suicide ideation within a general population using a machine learning algorithm. Methods Among 35,116 individuals aged over 19 years from the Korea National Health & Nutrition Examination Survey, we selected 11,628 individuals via random down-sampling. This included 5,814 suicide ideators and the same number of non-suicide ideators. We randomly assigned the subjects to a training set (n=10,466) and a test set (n=1,162). In the training set, a random forest model was trained with 15 features selected with recursive feature elimination via 10-fold cross validation. Subsequently, the fitted model was used to predict suicide ideators in the test set and among the total of 35,116 subjects. All analyses were conducted in R. Results The prediction model achieved a good performance [area under receiver operating characteristic curve (AUC)=0.85] in the test set and predicted suicide ideators among the total samples with an accuracy of 0.821, sensitivity of 0.836, and specificity of 0.807. Conclusion This study shows the possibility that a machine learning approach can enable screening for suicide risk in the general population. Further work is warranted to increase the accuracy of prediction.

• Fisheries and Aquatic Sciences
• /
• v.9 no.1
• /
• pp.7-13
• /
• 2006

Using biochemical methods, we determined the potential of local female shrimp populations as breeding stock to select the best adult prawns for improving larval production. As condition indexes, we selected total RNA, DNA, their ratio, and trypsin activity. The DNA content in the pleopods of each local population was similar, i.e., between $0.90{\pm}0.06\;and\;1.02{\pm}0.04(SE){\mu}g/mg$. In comparison, the RNA contents differed markedly between $2.00{\pm}0.09$ and $0.96{\pm}0.08\;{\mu}g/mg$. Therefore, the RNA/DNA (R/D) ratio in the pleopod could be used as a condition index because it represents a biochemical characteristic of the population. The mean pleopodal R/D ratio of the Goheung population was the highest at $2.52{\pm}0.19$, which indicated the best condition. Trypsin activity was influenced little by shrimp condition and more by the amount of food ingested. The gonadosomatic index (GSI) and R/D ratio in the gonads provided offsetting information about the instantaneous gonad maturity. The Goheung population had the highest instantaneous GSI, despite some spawning. Based on the condition indexes and time of gonad maturation, the Goheung shrimp population is suitable for use as breeding stock.

• Genomics & Informatics
• /
• v.16 no.4
• /
• pp.31.1-31.7
• /
• 2018

The prevalence of metabolic syndrome (MS) in the nonobese population is not low. However, the identification and risk mitigation of MS are not easy in this population. We aimed to develop an MS prediction model using genetic and clinical factors of nonobese Koreans through machine learning methods. A prediction model for MS was designed for a nonobese population using clinical and genetic polymorphism information with five machine learning algorithms, including naïve Bayes classification (NB). The analysis was performed in two stages (training and test sets). Model A was designed with only clinical information (age, sex, body mass index, smoking status, alcohol consumption status, and exercise status), and for model B, genetic information (for 10 polymorphisms) was added to model A. Of the 7,502 nonobese participants, 647 (8.6%) had MS. In the test set analysis, for the maximum sensitivity criterion, NB showed the highest sensitivity: 0.38 for model A and 0.42 for model B. The specificity of NB was 0.79 for model A and 0.80 for model B. In a comparison of the performances of models A and B by NB, model B (area under the receiver operating characteristic curve [AUC] = 0.69, clinical and genetic information input) showed better performance than model A (AUC = 0.65, clinical information only input). We designed a prediction model for MS in a nonobese population using clinical and genetic information. With this model, we might convince nonobese MS individuals to undergo health checks and adopt behaviors associated with a preventive lifestyle.

• Journal of Cadastre & Land InformatiX
• /
• v.46 no.2
• /
• pp.283-296
• /
• 2016

This paper aims to analyze characteristic by the cities focused on the ratio of new apartment resale that is one of the apartment unit sale market, which has been increased recently. To do so, this study examined characteristics of population, housing, residential, and economical with 162 cities and counties and performed multiple regression analysis with dependent variable, ratio of new apartment resale. As a result. the factors affecting the ratio of new apartment resale are 7variables, regional apartment rate, population increasing rate, a mount of sell in lots, housing rent price (Jeonse price) rate compared to average apartment sale price, single-person households increasing rate, apartment subscription rate and number of buyers in the area. Thus, this study showed that the factors affecting characteristic by the regions are ordered characteristics of residential, population and rate of sale and dealing. Based on this result, this study will be basic data for policy of government and development of apartment sales system and for end user to activate resale in apartment sales market.

• Journal of Institute of Control, Robotics and Systems
• /
• v.12 no.4
• /
• pp.328-338
• /
• 2006

A new evolutionary computation technique, called particle swarm optimization(PSO), has been proposed and introduced recently. PSO has been inspired by the social behavior of flocking organisms, such as swarms of birds and fish schools and PSO is an algorithm that follows a collaborative population-based search model. Each particle of swarm flies around in a multidimensional search space looking for the optimal solution. Then, Particles adjust their position according to their own and their neighboring-particles experience. In this paper, characteristics of PSO such as mentioned are reviewed and compared with GA which is based on the evolutionary mechanism in natural selection. Also dimensionalities of PSO and GA are compared throughout numeric experimental studies. The comparative studies demonstrate that PSO is characterized as simple in concept, easy to implement, and computationally efficient and can generate a high-quality solution and stable convergence characteristic than GA.

• Journal of Environmental Science International
• /
• v.8 no.3
• /
• pp.331-336
• /
• 1999

The monthly water quality data measured at 14 stations located in the Geum-River watershed were clustered into 2 to 7 clusters. Furthermore, factor analyses were conducted on Gabcheon and Yugucheon to characterize the water qualtiy, based on the information obtained from the results of culster analysis. The results of cluster analysis show that the water quality charactersitic of main stream of the Geum-River is somewhat different from that of substream of the Geum-River. Furthermore, the water quality characteristic of Gabcheon which is expected to have the most serious water quality problems in the Geum-River watershed shows the most different water quality characteristic from Yugucheon. Based ont he factor loadings in each factor, Gabcheon and Yugucheon have their own water quality characteristics. This is mainly because of composite factors such as different population density, industrial activities, and land use conditions in Gabcheon and Yugucheon subwatersheds.

• Research in Mathematical Education
• /
• v.7 no.4
• /
• pp.247-270
• /
• 2003

The purpose of this study is to build a model that explains the relationship between and among five variables that are student background, teacher background, home environment, school characteristic, and student mathematics achievement, using structural equation modeling. Another purpose of this study is to compare the relationships of these variables between the United States and Korea in 7th and 8th grades mathematics. Student, teacher, and school background files from population 2 in the TIMSS were selected for this study. The result of the study provides practical information for teachers, parents, school principals, and other people who are interested in improving student achievement, and also provides the information that may explain differences and similarities between the US and Korea in mathematics achievement.

• Journal of Electrical Engineering and Technology
• /
• v.10 no.4
• /
• pp.1415-1421
• /
• 2015

This paper presents a new algorithm called Quantum-behaved Electromagnetism-like Mechanism Algorithm which is used to solve economic load dispatch of power system. Electromagnetism-like mechanism algorithm simulates attraction and repulsion mechanism for particles in the electromagnetic field. Every solution is a charged particle, and it move to optimum solution according to certain criteria. Quantum-behaved electromagnetism-like mechanism algorithm merges quantum computing theory with electromagnetism-like mechanism algorithm. Superposition characteristic of quantum methodology can make a single particle present several states, and the characteristic potentially increases population diversity. Probability representation of quantum methodology is to make particle state be presented according to a certain probability. And the quantum rotation gates are used to realize update operation of particles. The algorithm is tested for 13-generator system and 40-generator system, which validates it can effectively solve economic load dispatch problem. Through performance comparison, it is obvious the solution is superior to other optimization algorithm.

• Journal of the Korean Institute of Rural Architecture
• /
• v.14 no.3
• /
• pp.33-40
• /
• 2012

This study is to clarify the actual conditions of small elementary school facilities in depopulation areas. The aim of this thesis is to present the directions for Reorganization of small school facilities. Research area was kumi and uiseong, the number of students decreased rapidly. And small elementary school facilities were surveyed. The results are as the follows; 1)After consider living zone, commuting distance, opinions of residents, it is advisable that the small size school(the number of students under 60) will be combined stronghold school. 2)In the case of relocation, first of all, should consider the characteristic of living zone, exchanging training programs between elementary schools. 3)The closed school facilities will be used consistently as public facilities with priority consideration of environmental characteristic and users' demand.

• Korean Journal of Environment and Ecology
• /
• v.25 no.1
• /
• pp.10-16
• /
• 2011

This study was carried out to analyze the vegetation and soil characteristic, and ordination of the Ilex cornuta population, in the Yongsu Reservoir of Jeju Island. The Ilex cornuta population was classified into Cudrania tricuspidata dominant population, Sageretia theezans dominant population, and Mallotus japonicus dominant population. In the study sites, soil organic matter(O.M.), total nitrogen(T.N.), available phosphorus($P_2O_5$), changeable potassium, changeable calcium, changeable magnesium and soil pH were 14.62~17.35%, 0.39~0.51%, 8.83~20.15mg/kg, 0.44~0.64cmol+/kg, 5.79~6.87cmol+/kg, 3.43~4.19cmol+/kg and 5.41~5.80, respectively. The Mallotus japonicus dominant population was mainly found in the high percentage of available phosphorus, organic matter. It was also showed the lowest concentration of exchangeable K, and Mg. Cudrania tricuspidata dominant population and Sageretia theezans dominant population were found in the low percentage of available phosphorus, organic matter and there were also showed the highest concentration of exchangeable K, and Mg. It is one of the evidence that Ilex cornuta community indicated an intensive site management likes clearance of creeper is proper habitat management protocol. Thus, further researches should be followed to determine the other disturbance factors as management techniques.