• Title/Summary/Keyword: Index Selection

Search Result 903, Processing Time 0.034 seconds

A Study on the prediction of BMI(Benthic Macroinvertebrate Index) using Machine Learning Based CFS(Correlation-based Feature Selection) and Random Forest Model (머신러닝 기반 CFS(Correlation-based Feature Selection)기법과 Random Forest모델을 활용한 BMI(Benthic Macroinvertebrate Index) 예측에 관한 연구)

  • Go, Woo-Seok;Yoon, Chun Gyeong;Rhee, Han-Pil;Hwang, Soon-Jin;Lee, Sang-Woo
    • Journal of Korean Society on Water Environment
    • /
    • v.35 no.5
    • /
    • pp.425-431
    • /
    • 2019
  • Recently, people have been attracting attention to the good quality of water resources as well as water welfare. to improve the quality of life. This study is a papers on the prediction of benthic macroinvertebrate index (BMI), which is a aquatic ecological health, using the machine learning based CFS (Correlation-based Feature Selection) method and the random forest model to compare the measured and predicted values of the BMI. The data collected from the Han River's branch for 10 years are extracted and utilized in 1312 data. Through the utilized data, Pearson correlation analysis showed a lack of correlation between single factor and BMI. The CFS method for multiple regression analysis was introduced. This study calculated 10 factors(water temperature, DO, electrical conductivity, turbidity, BOD, $NH_3-N$, T-N, $PO_4-P$, T-P, Average flow rate) that are considered to be related to the BMI. The random forest model was used based on the ten factors. In order to prove the validity of the model, $R^2$, %Difference, NSE (Nash-Sutcliffe Efficiency) and RMSE (Root Mean Square Error) were used. Each factor was 0.9438, -0.997, and 0,992, and accuracy rate was 71.6% level. As a result, These results can suggest the future direction of water resource management and Pre-review function for water ecological prediction.

Development of Evaluation Index for Foreign Weapon System Purchase using DEMATEL and ANP (DEMATEL과 ANP를 이용한 해외구매 무기체계의 평가지표 개발)

  • Cho, Hyun-Ki;Kim, Woo-Je
    • Journal of the Korean Operations Research and Management Science Society
    • /
    • v.37 no.2
    • /
    • pp.73-88
    • /
    • 2012
  • Even though the final source selection of foreign weapon system purchase project in defense area is the most important phase, the standard evaluation index has not been developed. This paper provides an appropriate evaluation index using DEMATEL and ANP methods. First, the all possible evaluation criteria applied to the relevant previous literatures in domestic and overseas researches are derived and classified into groups. Second, DEMATEL method is used to determine the network structure representing the relations of cause and effect between groups and their sub-criteria. If isolated factors, not connected with other factors, are existed in the network structure, all factors except for the isolated ones are grouped as one large factor so that the independency between those ones is maintained. The weights of criteria are determined using AHP method if the criteria are independent relation and ANP method if the criteria are networked. The weights of higher and lower level criteria are then integrated and distributed as a point with respect to the decision making purpose. The developed evaluation index can be used as a standard one in various foreign weapon system purchase projects in defense area.

Estimation of Heritabilities and Genetic Correlations on Preweaning Body Weights and Postweaning Traits in Swine (돼지의 이유전체중(離乳前體重)과 이유후형질(離乳後形質)에 대한 유전력(遺傳力)과 유전상관(遺傳相關)의 추정(推定))

  • Han, Sung Wook;Sang, Byung Chan;Lee, Han Ok
    • Korean Journal of Agricultural Science
    • /
    • v.14 no.1
    • /
    • pp.51-60
    • /
    • 1987
  • The study was conducted to estimate the heritabilities, genetic and phenotypic correlations on preweaning body weight and postweaning traits. The data analysis were the record of 253 male pigs produced from 54 boars of Landrace, Hampshire, Large Yorkshire and Duroc purebreds raised at National Animal Breeding Institute from 1978 to 1983. The results obtained in this study are summarized as follows. 1. The heritabilities of body weight at birth, 21days and 56days were $0.233{\pm}0.160$, $0.485{\pm}0.185$ and $0.758{\pm}0.214$, respectively, and the heritabilities estimated on postweaning traits were $0.270{\pm}0.164$ for average daily gain, $0.350{\pm}0.174$ for feed requirement, $0.272{\pm}0.165$ for backfat thickness, $0.887{\pm}0.221$ for days to 90Kg and $0.565{\pm}0.195$ for selection index. 2. Genetic correlations of body weight at birth with 21 days and 56 days were 0.349 and 0.19& and body weight at 21 days with 56 days was 0.907, and daily gain with feed requirement, backfat thickness, days to 90 Kg and selection index were -0.552, 0.107, -0.903 and 0.716, and feed requirement with backfat thickness, days to 90Kg and selection index were -0.058, 0.699 and -0.942, and backfat thickness with days to 90 Kg and selection index were -0.237 and -0.025, respectively. 3. Phenotypic correlations of body weight at birth with 21 days and 56 days were 0.342 and 0.287, and body weight at 21 days with 56 days was 0.893 and daily gain with feed requirement, backfat thickness, days to 90Kg and selection index were -0.062, 0.093, -0.651 and 0.540, and feed requirement with backfat thickness, days to 90Kg and selection index were 0.105, 0.601 and -0.613, and backfat thickness with days to 90Kg and selection index were -0.040, -0.416, respectively.

  • PDF

An Empirical Study on the Evaluation of Supplier Selection Factors according to the Product Standardization - Focused on the Stationery and Office Machine Suppliers - (제품 표준화 수준에 따른 공급업체 선정 요인별 중요도 평가에 관한 실증적 연구 - 사무용품 및 사무기기 공급업체를 대상으로 -)

  • Kim, Shin-Joong;Lee, Jung-Sae
    • Journal of the Korea Society of Computer and Information
    • /
    • v.13 no.1
    • /
    • pp.261-272
    • /
    • 2008
  • The primary research objects of this study is to evaluate an importance of supplier selection factors as an index according the level of product standardization and to present the evaluation model for supplier selection. For this purpose, this study adopts the AHP method to calculate the importance of supplier selection factors. In this study 16 factors which affect on the supplier selection decision making are classified into three factors-product supply related factor, product related factor, management ability related factor. Results also indicate that standardized products are much more dealt by means of on-line compare to customized products. It means the buyer opportunities is potentially an increase in the amount of current supplier re-evaluation, which may lead to new suppliers being considered more often.

  • PDF

Evaluation of calving interval and selection indices in Korean native cows

  • Choi, Inchul;Lee, Dooho;Lee, Jong-Gwan;Lee, Seung-Hwan;Ryoo, Seung-Heui
    • Korean Journal of Agricultural Science
    • /
    • v.47 no.3
    • /
    • pp.667-672
    • /
    • 2020
  • It is well known that intensive selection caused a decline in reproductive performance in dairy cattle. Interestingly, the reproductive performances including fertility and calving interval of Korean native beef cattle have declined in the last 20 years, suggesting that a breeding program focusing on carcass weight and intramuscular fat may affect the reproductive physiology in Korean native beef cattle, too. In this study, we analyzed the calving interval (CI) and selection index (SI) based on genome-wide association studies (GWAS) of Hanwoo cows for seven years (2013 - 2019). Multiparous cows (4.5 ± 0.11) were analyzed, which were bred by artificial insemination (AI). We first examined the distribution of the AIs and calving dates. About 40% of the AIs were carried out in May to June and October to December; subsequently, calving was observed from March to April and August to October, respectively, indicating the cows were seasonally bred. No correlation between CI and SI was found (y = 0.0459x - 17.64; R2 = 0.0356), but the ratio of cows with a positive SI was higher in the longer CI group compared to the shorter group, suggesting that the selection for meat quality and quantity may affect the reproductive performances. In addition, the average value of SI was - 3.42 in the CI < 400 while + 5.79 in the CI > 400 although the values were not statistically significant. However, our results suggest that reproductive indices such as fertility and CI should be considered for sustainability in the Hanwoo breeding selection program.

The Relationship between Win-Win Growth Effort and Financial Performance with Time-lag : Development of Win-Win Growth Index using Ordered Probit Model (기업의 동반성장 노력과 재무성과의 선후행 관계 : 순위 프로빗 모형을 이용한 계량적 동반성장지수의 산출)

  • Min, Jae H.;Kim, Bumseok
    • Journal of the Korean Operations Research and Management Science Society
    • /
    • v.39 no.2
    • /
    • pp.67-82
    • /
    • 2014
  • The purpose of this study is two-fold : the one is to examine the causal relationship between domestic large firms' win-win growth effort and their financial performance by fiscal years; and the other is to develop a quantitative win-win growth index to overcome the limitation of the current one mainly using a survey method developed by NCCP (National Commission for Corporate Partnership). To serve the first purpose, we take a sample of 128 large companies whose win-win growth indices as of year 2011 and 2012 were evaluated by NCCP. We use their respective fiscal year's financial data to select 62 candidate financial ratios, which are then used in subsequent empirical tests. For the tests, we employ ordered probit model with stepwise selection method and two-way ANOVA with randomized block design to identify which of the 62 financial ratios are statistically significant ones to affect the firms' win-win growth index as well as to determine if the firms' win-win growth effort would cause their financial performance positively. To serve the second purpose, we devise a model using the 123 firms' 45 financial ratios, which employs ordered probit model with stepwise selection, and the validation of the model follows. We claim that the model suggested in this study serve as an alternative complementing the current one as it can produce the index in a more objective and swift manner using the firms' publicized financial statements.

A Study on the Development of an Ecological Park Planning Model to Enhance the Functions of Habitats and Ecological Corridors in Green Belt Areas (개발제한구역 내 생태공원 조성방안에 관한 연구 - 서식처 및 생태통로로서의 기능강화를 중심으로 -)

  • Kim, Dae-Heui;Choi, Hee-Sun;Kim, Hyun-Ae;Kim, Kwi-Gon
    • Journal of Environmental Impact Assessment
    • /
    • v.20 no.3
    • /
    • pp.367-379
    • /
    • 2011
  • This study was conducted to develop an ecological park planning model to enhance the functions of habitats and ecological corridors in Green Belt Areas, because changing policies have resulted in the degredation of the Green Belts due to progressive fragmentation of ecosystems. The principal outcome of the study is to plan an ecological park model through the restoration of habitats. In order to evaluate the capacity of the model to enhance the ecological functions of habitats and ecological corridors in Green Belt Areas, a simulation of habitats was carried out in the Sungnam-Yusoo region. The model was developed via following steps: 1. Selection of candidate sites and selection of the study site by analyzing development factors; 2. Selection of target species that can represent the habitat at the site; 3. Analysis of the site's suitability index for the target species; 4. Establishment of a conceptual plan to enhance and expand the currently produced suitability index; 5. Creation of a master plan based on the conceptual plan; and 6. Evaluation of the enhanced and expanded suitability index of the site. The study showed that the Habitat Unit (HU) of Rana coreana, which was selected as the target species of the study, increased from $28,044m^2$(3.6%) to $224,352m^2$(28.8%), and the HU of the site as the ecological corridor for wild animals increased from $4,674m^2$(0.6%) to $152,684m^2$(19.6%). The study results show that the ecological deficits of the Green Belt Area can be overcome by enhancing the ecological functions of the region, which should be beneficial. The model could be utilized for effective enhancement and management of other Green Belt Areas.

Trust-based Relay Selection in Relay-based Networks

  • Wu, Di;Zhu, Gang;Zhu, Li;Ai, Bo
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • v.6 no.10
    • /
    • pp.2587-2600
    • /
    • 2012
  • It has been demonstrated that choosing an appropriate relay node can improve the transmission rate for the system. However, such system improvement brought by the relay selection may be degraded with the presence of the malicious relay nodes, which are selected but refuse to cooperate for transmissions deliberately. In this paper, we formulate the relay selection issue as a restless bandit problem with the objective to maximize the average rate, while considering the credibility of each relay node, which may be different at each time instant. Then the optimization problem is solved by using the priority-index heuristic method effectively. Furthermore, a low complexity algorithm is offered in order to facilitate the practical implementations. Simulation results are conducted to demonstrate the effectiveness of the proposed trust-based relay selection scheme.

Variable Selection and Outlier Detection for Automated K-means Clustering

  • Kim, Sung-Soo
    • Communications for Statistical Applications and Methods
    • /
    • v.22 no.1
    • /
    • pp.55-67
    • /
    • 2015
  • An important problem in cluster analysis is the selection of variables that define cluster structure that also eliminate noisy variables that mask cluster structure; in addition, outlier detection is a fundamental task for cluster analysis. Here we provide an automated K-means clustering process combined with variable selection and outlier identification. The Automated K-means clustering procedure consists of three processes: (i) automatically calculating the cluster number and initial cluster center whenever a new variable is added, (ii) identifying outliers for each cluster depending on used variables, (iii) selecting variables defining cluster structure in a forward manner. To select variables, we applied VS-KM (variable-selection heuristic for K-means clustering) procedure (Brusco and Cradit, 2001). To identify outliers, we used a hybrid approach combining a clustering based approach and distance based approach. Simulation results indicate that the proposed automated K-means clustering procedure is effective to select variables and identify outliers. The implemented R program can be obtained at http://www.knou.ac.kr/~sskim/SVOKmeans.r.

Investigation of SCI Journal Selection Process for the Journals of Korean Traditional Medicine (한국한의학 관련학회지의 SCI등재를 위한 준비과정에 관한 고찰)

  • Kim, Hyun-Do;Kang, Tae-Sik;Kwon, Ki-Rok
    • Journal of Pharmacopuncture
    • /
    • v.6 no.3
    • /
    • pp.87-90
    • /
    • 2003
  • The purpose of this study is to investigate and analyze the selection process of the Science Citation Index(SCI). SCI has been the benchmarking medium of scientific journals for over 40 years by reviewing thousands of journals published each year. The discipline of Traditional Oriental Medicine has been gaining global interest in recent years, yet the number of related journals indexed by SCI has been minimal. Korean Medicine has been producing number of quality journals for decades, but lack of journals in the English language and other problems has hindered consideration for registering with SCI. This paper will focus on the journal selection process at ISI and recommend the criteria needed for a journal to be considered for SCI selection.