• Geomechanics and Engineering
• /
• v.25 no.1
• /
• pp.1-16
• /
• 2021

Machine learning models have been widely used for landslide susceptibility assessment (LSA) in recent years. The large number of inputs or conditioning factors for these models, however, can reduce the computation efficiency and increase the difficulty in collecting data. Feature selection is a good tool to address this problem by selecting the most important features among all factors to reduce the size of the input variables. However, two important questions need to be solved: (1) how do feature selection methods affect the performance of machine learning models? and (2) which feature selection method is the most suitable for a given machine learning model? This paper aims to address these two questions by comparing the predictive performance of 13 feature selection-based machine learning (FS-ML) models and 5 ordinary machine learning models on LSA. First, five commonly used machine learning models (i.e., logistic regression, support vector machine, artificial neural network, Gaussian process and random forest) and six typical feature selection methods in the literature are adopted to constitute the proposed models. Then, fifteen conditioning factors are chosen as input variables and 1,017 landslides are used as recorded data. Next, feature selection methods are used to obtain the importance of the conditioning factors to create feature subsets, based on which 13 FS-ML models are constructed. For each of the machine learning models, a best optimized FS-ML model is selected according to the area under curve value. Finally, five optimal FS-ML models are obtained and applied to the LSA of the studied area. The predictive abilities of the FS-ML models on LSA are verified and compared through the receive operating characteristic curve and statistical indicators such as sensitivity, specificity and accuracy. The results showed that different feature selection methods have different effects on the performance of LSA machine learning models. FS-ML models generally outperform the ordinary machine learning models. The best FS-ML model is the recursive feature elimination (RFE) optimized RF, and RFE is an optimal method for feature selection.

• Journal of Cardiovascular Imaging
• /
• v.31 no.4
• /
• pp.200-206
• /
• 2023

BACKGROUND: Right ventricular (RV) dysfunction is a significant risk of major adverse cardiac events in patients with acute heart failure (AHF). In this study, we evaluated RV-pulmonary artery (PA) coupling, assessed by tricuspid annular plane systolic excursion (TAPSE)/pulmonary artery systolic pressure (PASP) and assessed its prognostic significance, in AHF patients. METHODS: We measured the TAPSE/PASP ratio and analyzed its correlations with other echocardiographic parameters. Additionally, we assessed its prognostic role in AHF patients. RESULTS: A total of 1147 patients were included in the analysis (575 men, aged 70.81 ± 13.56 years). TAPSE/PASP ratio exhibited significant correlations with left ventricular (LV) ejection fraction(r = 0.243, p < 0.001), left atrial (LA) diameter(r = -0.320, p < 0.001), left atrial global longitudinal strain (LAGLS, r = 0.496, p < 0.001), mitral E/E' ratio(r = -0.337, p < 0.001), and right ventricular fractional area change (RVFAC, r = 0.496, p < 0.001). During the median follow-up duration of 29.0 months, a total of 387 patients (33.7%) died. In the univariate analysis, PASP, TAPSE, and TAPSE/PASP ratio were significant predictors of mortality. After the multivariate analysis, TAPSE/PASP ratio remained a statistically significant parameter for all-cause mortality (hazard ratio [HR], 0.453; p = 0.037) after adjusting for other parameters. In the receiver operating curve analysis, the optimal cut-off level of TAPSE/PASP ratio for predicting mortality was 0.33 (area under the curve = 0.576, p < 0.001), with a sensitivity of 65% and a specificity of 47%. TAPSE/PASP ratio < 0.33 was associated with an increased risk of mortality after adjusting for other variables (HR, 1.306; p = 0.025). CONCLUSIONS: In AHF patients, TAPSE/PASP ratio demonstrated significant associations with RVFAC, LA diameter and LAGLS. Moreover, a decreased TAPSE/PASP ratio < 0.33 was identified as a poor prognostic factor for mortality.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.32 no.E
• /
• pp.1-19
• /
• 1990

Abstract Over the last several decades, crop production in the United States increased largely due to the extensive use of animal waste and fertilizers as plant nutrient supplements, and pesticides for crops pests and weed control. Without the application of animal waste best management, the use of animal waste can result in nonpoint source pollution from agricultural land area. In order to increase nutrient levels and decrease contamination from agricultural lands, nonpoint source pollution is responsible for water quality degradation. Nonpoint source pollutants such as animal waste, ferilizers, and pesticides are transported primarily through runoff from agricultural areas. Nutrients, primarily nitrogen and phosphorus, can be a major water quality problem because they cause eutrophic algae growth. In 1985, it was presented that Watershed/Water Quality Monitoring for Evaluation BMP Effectiveness was implemented for Nomini Creek Watershed, located in Westmoreland County, Virginia. The watershed is predominantly agricultural and has an aerial extent of 1505 ha of land, with 43% under cropland, 54% under woodland, and 3% as homestead and roads. Rainfall data was collected at the watershed from raingages located at sites PNI through PN 7. Streams at stations QN I and QN2 were being measured with V-notch weirs. Water levels at the stream was measured using an FW-l Belfort (Friez FWl). The water quality monitoring system was designed to provide comprehensive assessment of the quality of storm runoff and baseflow as influenced by changes in landuse, agronomic, and cultural practices ill the watershed. As this study was concerned with the Nomini Creek Watershed, the separation of storm runoff and baseflow measured at QNI and QN2 was given by the master depletion curve method, and the loadings of baseflow and storm runoff for TN (Total Nitrogen) and TP (Total Phosphorus) were analyzed from 1987 through 1989. The results were studied for the best management practices to reduce contamination and loss of nutrients, (e.g., total nitrogen and total phosphorus) by nonpoint source pollution from agricultural lands.

• Clinical and Experimental Pediatrics
• /
• v.62 no.9
• /
• pp.353-359
• /
• 2019

Background: Researchers have shown that eosinophil peroxidase (EPO) is a relatively accurate marker of eosinophilia and eosinophil activity. However, its use as a marker of eosinophilic inflammation in nasal secretions is limited because the diagnostic cutoff values of EPO for use as a one-time test for allergic diseases such as allergic rhinitis have not been established. Purpose: To identify the correlation between nasal eosinophil count and EPO in children and adolescents with rhinitis. Methods: We recruited patients <18 years of age with rhinitis for more than 2 weeks or more than 2 episodes a year whose nasal eosinophil and EPO were measured at a single allergy clinic. The eosinophil percentage was calculated by dividing the eosinophil count by the number of total cells under light microscopy at ${\times}1,000$ magnification. EPO and protein were measured from nasal secretions. We retrospectively analyzed the correlation between nasal eosinophils and protein-corrected EPO (EPO/protein) value. Results: Of the 67 patients enrolled, 41 were male (61.2%); the mean age was $8.2{\pm}4.0years$. The median nasal eosinophil count was 1 and percentage was 1%. The median protein-corrected EPO value was $12.5ng/{\mu}g$ (range, $0-31ng/{\mu}g$). There was a statistically significant correlation between eosinophil count and percentage (P<0.001). However, the eosinophil percentage and EPO did not correlate. The eosinophil count and EPO had a statistically significant correlation (P=0.01). The EPO cutoff value examined for nasal eosinophil counts of 2, 5, 10, and 20 was $17.57ng/{\mu}g$ regardless of the reference count. The largest area under the curve value was obtained when the receiver operating characteristic curve was drawn using the eosinophil count of 2. Conclusion: Nasal eosinophil count was significantly associated with protein-corrected EPO.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.11 no.3
• /
• pp.28-38
• /
• 2008

The purpose of this study are to compare existing presence-absence predictive models and to predict suitable habitat for Goral (Nemorhaedus caudatus raddeanus) that is an endangered and protected species in Seoraksan national park using the best model among existing predictive models. The methods of this study are as follows. First, 375 location data and 9 environmental data layers were implemented to build a model. Secondly, 4 existing presence-absence models : Generalized Linear Model (GLM), Generalized Addictive Model (GAM), Classification and Regression Tree (CART), and Artificial Neural Network (ANN) were tested to predict the Goal habitat. Thirdly, ROC (Receiver Operating Characteristic) and Kappa statistics were used to calculate a model performance. Lastly, we verified models and created habitat suitability maps. The ROC AUC (Area Under the Curve) and Kappa values were 0.697/0.266 (GLM), 0.729/0.313 (GAM), 0.776/0.453 (CART), and 0.858/0.559 (ANN). Therefore, ANN was selected as the best model among 4 models. The models showed that elevation, slope, and distance to stream were the significant factors for Goal habitat. The ratio of predicted area of ANN using a threshold was 31.29%, but the area decreased when human effect was considered. We need to investigate the difference of various models to build a suitable wildlife habitat model under a given condition.

• Korean Journal of Remote Sensing
• /
• v.34 no.5
• /
• pp.721-738
• /
• 2018

The purpose of this study is to create landslide vulnerability using frequency ratio (FR) and evidential belief functions (EBF) model which are two methods of probability model and to select appropriate model for each region through comparison of results in Sacheon-myeon and Jumunjin-eup of Gangneung. 762 locations in Sacheon-myeon and 548 landscapes in Jeonju-eup were constructed based on the interpretation of aerial photographs. Half of each landslide point was randomly selected for modeling and remaining landslides were used for verification purposes. Twenty landslide-inducing factors classified into five categories such as topographic elements, hydrological elements, soil maps (1:5,000), forest maps (1:5,000), and geological maps (1:25,000) were considered for the preparation of landslide vulnerability in the study. The relationship between landslide occurrence and landslide inducing factors was analyzed using FR and EBF models. The two models were then verified using the AUC (curve under area) method. According to the results of verification, the FR model (AUC = 81.2%) was more accurate than the EBF model (AUC = 78.9%) at Jeonjun-eup. In the Sacheon-myeon, the EBF model (AUC = 83.6%) was more accurate than the FR model (AUC = 81.6%). Verification results show that FR model and EBF model have high accuracy with accuracy of around 80%.

• Journal of the Korean Society of Radiology
• /
• v.11 no.3
• /
• pp.131-137
• /
• 2017

This study investigated the risk factor of Gallbladder stone in Busan and Kyungnam area. The subjects of the experiment was performed with patients by abdominal ultrasonography among the patients who came to the P hospital from June 2016 to December 2016. Among them, risk factors were analyzed on 353 people at the same time when abdominal ultrasonography and hematological test. The statistical analysis of risk factors related to the Gallbladder stone was performed by independent t-test and chi-square test. In consider of difference verification result for calculations odds ratio about independent variables, multiple logistic regression analysis to conduct verify adequacy by calculating forecasting model from variable. As a result, Gallbladder stone risk factors have relevance to age ${\gamma}GTP$ with probability model and values to calculated. Age was showed sensitivity 49.7%, specificity 82.2%, receiver operating characteristic area under curve 0.724. Forecasting probability sensitivity 69.3%, specificity 62.4%, receiver operating characteristic area under curve 0.699 showed, ${\gamma}GTP$ confirmed validity of forecasting model.

• Journal of Korean Medicine Rehabilitation
• /
• v.18 no.4
• /
• pp.13-24
• /
• 2008

Objectives : The purpose of this study was to investigate the effect of Poncirus Trifoliata(PT) on improvement of fecal impaction in spinal cord injured(SCI) rats. Methods : Fifteen adult Sprague-Dawley female rats were used weighing 200~250 g. A complete spinal cord transection was performed surgically at the T10 cord level. Experimental groups were assigned into 3 groups: Control(n=5), SCI+vehicle(n=5) and SCI+PT(n=5). PT was administered 100mg/kg in 0.5ml every 24 hours from 1st operation day to 7th day. We measured the body weight and food intake as well as the number and the weight of fecal pellet every morning. After 1 week of operation, whole colon was divided into proximal and distal segments under anesthesia. Each segment of colon was mounted with longitudinal direction in a organ bath. We measured spontaneous contraction and compared the area under the curve in each segments. Enhanced responses were observed by acetylcholine($10^{-6}M$), 40 mM KCl solution, L-NAME($10^{-4}M$). Results : The fecal number and weights were significantly higher in the group of SCI+PT than SCI+vehicle group(p<0.05). In organ bath study, area under the curves of the spontaneous contraction in SCI+vehicle and SCI+PT groups were significantly increased compared to control group. Contractility of distal colon in response to acetylcholine or KCl in SCI+vehicle group was significantly decreased compared to other groups(p<0.05). Conclusions : These results suggest that PT might be useful to promote bowel emptying in spinal cord injured rats.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.31 no.1
• /
• pp.49-55
• /
• 2013

In this paper, we proposed a good classifier to match different spatial data sets by applying evaluation of classifiers performance in data mining and biometrics. For this, we calculated distances between a pair of candidate features for matching criteria, and normalized the distances by Min-Max method and Tanh (TH) method. We defined classifiers that shape similarity is derived from fusion of these similarities by CRiteria Importance Through Intercriteria correlation (CRITIC) method, Matcher Weighting method and Simple Sum (SS) method. As results of evaluation of classifiers performance by Precision-Recall (PR) curve and area under the PR curve (AUC-PR), we confirmed that value of AUC-PR in a classifier of TH normalization and SS method is 0.893 and the value is the highest. Therefore, to match different spatial data sets, we thought that it is appropriate to a classifier that distances of matching criteria are normalized by TH method and shape similarity is calculated by SS method.

• Asian Pacific Journal of Cancer Prevention
• /
• v.13 no.11
• /
• pp.5517-5523
• /
• 2012

Purpose: To evaluate the diagnostic accuracy of ultrasonograph and fine-needle aspiration cytologic examination (USG-FNAC) in the staging of axillary lymph node metastasis in breast cancer patients.Methods: We conducted an electronic search of the literature addressing the performance of USG-FNAC in diagnosis of axillary lymph node metastasis in databases such as Pubmed, Medline, Embase, Ovid and Cochrane library. We introduced a series of diagnostic test indices to evaluate the performance of USG-FNAC by the random effect model (REM), including sensitivity, specificity, likelihood ratios, and diagnostic odds ratios and area under the curve (AUC). Results: A total of 20 studies including 1371 cases and 1289 controls were identified. The pooled sensitivity was determined to be 0.66 (95% CI 0.64-0.69), specificity 0.98 (95% CI 0.98-0.99), positive likelihood ratio 22.7 (95% CI 15.0-34.49), negative likelihood ratio 0.32 (95% CI 0.25-0.41), diagnostic OR 84.2 (95% CI 53.3-133.0). Due to the marginal threshold effect found in some indices of diagnostic validity, we used a summary SROC curve to aggregate data, and obtained a symmetrical curve with an AUC of 0.942. Conclusion: The results of this meta-analysis indicated that the USG-FNAC techniques have acceptable diagnostic validity indices and can be used for early staging of axillary lymph node in breast cancer patients.