• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.30 no.4B
• /
• pp.399-412
• /
• 2010

The goal of this research is to apply the neural networks models for the temporal disaggregation of the yearly pan evaporation (PE) data, Republic of Korea. The neural networks models consist of multilayer perceptron neural networks model (MLP-NNM) and generalized regression neural networks model (GRNNM), respectively. And, for the performances evaluation of the neural networks models, they are composed of training and test performances, respectively. The three types of data such as the historic, the generated, and the mixed data are used for the training performance. The only historic data, however, is used for the testing performance. From this research, we evaluate the application of MLP-NNM and GRNNM for the temporal disaggregation of nonlinear time series data. We should, furthermore, construct the credible monthly PE data from the temporal disaggregation of the yearly PE data, and can suggest the available data for the evaluation of irrigation and drainage networks system.

• Smart Media Journal
• /
• v.11 no.7
• /
• pp.19-27
• /
• 2022

The artificial intelligence software market is expected to grow sixfold from 2020 to 2025. However, the software development process is not standardized and there is no standard for calculating the cost. Accordingly, each AI software development company calculates the input man-hours according to their respective development procedures and presents this as the basis for the development cost. In this study, the development stage of "artificial intelligence-based software" that learns with a large amount of data and derives and applies an algorithm was defined, and the required labor was collected by conducting a survey on the number of man-hours required for each development stage targeting developers. Correlation analysis and regression analysis were performed between the collected man-hours for each development stage, and a model for predicting the man-hours for each development stage was derived. As a result of testing the model, it showed an accuracy of 92% compared to the collected airborne effort. The man-hour prediction model proposed in this study is expected to be a tool that can be used simply for estimating man-hours and costs.

• International Area Studies Review
• /
• v.15 no.1
• /
• pp.135-169
• /
• 2011

This study is for analyzing the management performances of Korean tourism firms, operating as preparing strategically against FTA which is one of the most importantly external environment in international management since in the middle of 1990s. The main purpose is to test empirically some relations between the management performances and the levels of ownership-specifics advantages of Korean tourism ones. To be exact, the dependent variables of management performances are classified with sales, profits and management satisfaction, while the independent ones of the competitive advantages are sorted with the 5 following factors like marketing, product development, service supply, finance and organization culture. The survey of Korean tourism enterprises engaging in management activities in Korea is implemented by collecting questionnaires. And for testing the hypothesis, the analyzing tools are being used for correlation, reliability, validity, multi regression and the path analysis of structural equation modeling. As a result, Marketing is certified as only common factor to influence three dependent variables of sales, profit and management satisfaction positively.

• International Area Studies Review
• /
• v.13 no.1
• /
• pp.265-286
• /
• 2009

The purpose of this research can be said as follows. The close examination of competitive advantages of Korean enterprises who have been participating and dominating the management activities directly in India. And the Analysing of the correlation between the competitive advantages and the management performances of Korean firms there. That is, the factors which exercise their influence over the local management positively can be activated and developed reasonably and systematically while the others which exercise their influence over it negatively have to be eliminated, at least. The factors of competitive advantages on this paper are from ones which could generally be recognized on the basis of the preceding studies, and the management performances are divided by three sub-variables like sales, profits and management satisfaction. As empirically statistical method, Regression coefficient analysis as inferential statistics as well as Pearson's correlation as descriptive is implemented for this paper of testing some hypotheses.

• International conference on construction engineering and project management
• /
• 2013.01a
• /
• pp.133-140
• /
• 2013

The purpose of this study is identifying the relationship among the business strategy, order receiving capability and leverage variables of a construction company using industry characteristic variables, in addition to the explanation variables used in the previous studies. The samples of this study were limited to the construction companies listed in Korean stock market. This study built multiple regression analysis models, which have been frequently used in traditional previous studies, in the explanation of company capital structure. Empirical analysis on Static Trade-off Theory and Pecking Order Theory was done by the built model. The study results suggested that the capital structure determination behavior of a construction company generally follows Static Trade-off Theory; however, profitability was found to follow Pecking Order Theory. The explanation variables used in the previous capital structure studies mostly produced significant results; however, the variables, which this study experimentally used, did not produce significant results. It is believed that it implies that additional studies are required in the selection of variables and study methodology. Consequently, a case that unconditionally supports a particular theory is scarce. It has been also found that a case can support both theories at the same time. Therefore, it is believed that development study methodology or introduction of new study methodology that can identify the dynamic characteristic of construction company capital structure formation is required.

• Journal of Korean Biological Nursing Science
• /
• v.25 no.4
• /
• pp.285-294
• /
• 2023

Purpose: This study aimed to identify the colonization rate of carbapenem-resistant Enterobacteriaceae (CRE), the characteristics of CRE isolates, and risk factors for CRE colonization in patients transferred to the general wards of a small/medium-sized hospital. Methods: This retrospective study was conducted on patients who underwent CRE culture tests within 24 hours of admission among patients transferred to a small/medium-sized hospital. Forty-seven patients confirmed as positive for CRE were classified as belonging to the patient group. For the control group, 235 patients (five times the number of the patient group) were matched by sex, age, and diagnosis, and then selected at random. Data were analyzed using descriptive analysis and multiple logistic regression analysis. Results: The CRE colonization rate was 5% (47 out of 933 patients), and Klebsiella pneumoniae (68.0%) was the most common isolate of CRE. The positivity rate of carbapenemase-producing Enterobacteriaceae was 61.7%. The risk factors for CRE colonization included renal disease (odds ratio [OR]=4.93; 95% confidence interval [CI], 1.49-16.31), heart disease (OR=3.86; 95% CI, 1.35-11.01), indwelling urinary catheters (OR=4.43; 95% CI, 1.59-12.36), and cephalosporin antibiotic use (OR=8.57; 95% CI, 1.23-59.60). Conclusion: Having a comorbid renal or cardiac disease, an indwelling urinary catheter, or a history of exposure to cephalosporin antibiotics could be classified as risk factors for CRE colonization in patients transferred to small and medium-size hospitals. It is necessary to perform active infection control through proactive CRE culture testing of patients with risk factors.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.5
• /
• pp.999-1008
• /
• 2023

Early prediction of chronic diseases such as diabetes is an important issue, and improving the accuracy of diabetes prediction is especially important. Various machine learning and deep learning-based methodologies are being introduced for diabetes prediction, but these technologies require large amounts of data for better performance than other methodologies, and the learning cost is high due to complex data models. In this study, we aim to verify the claim that DNN using the pima dataset and k-fold cross-validation reduces the efficiency of diabetes diagnosis models. Machine learning classification methods such as decision trees, SVM, random forests, logistic regression, KNN, and various ensemble techniques were used to determine which algorithm produces the best prediction results. After training and testing all classification models, the proposed system provided the best results on XGBoost classifier with ADASYN method, with accuracy of 81%, F1 coefficient of 0.81, and AUC of 0.84. Additionally, a domain adaptation method was implemented to demonstrate the versatility of the proposed system. An explainable AI approach using the LIME and SHAP frameworks was implemented to understand how the model predicts the final outcome.

• Animal Bioscience
• /
• v.37 no.5
• /
• pp.918-928
• /
• 2024

Objective: The adulteration of raw beef (BMr) with dog meat (DMr) and pork (PMr) becomes a serious problem because it is associated with halal status, quality, and safety of meats. This research aimed to develop an effective authentication method to detect non-halal meats (dog meat and pork) in beef using metabolomics approach. Methods: Liquid chromatography-high resolution mass spectrometry (LC-HRMS) using untargeted approach combined with chemometrics was applied for analysis non-halal meats in BMr. Results: The untargeted metabolomics approach successfully identified various metabolites in BMr DMr, PMr, and their mixtures. The discrimination and classification between authentic BMr and those adulterated with DMr and PMr were successfully determined using partial least square-discriminant analysis (PLS-DA) with high accuracy. All BMr samples containing non-halal meats could be differentiated from authentic BMr. A number of discriminating metabolites with potential as biomarkers to discriminate BMr in the mixtures with DMr and PMr could be identified from the analysis of variable importance for projection value. Partial least square (PLS) and orthogonal PLS (OPLS) regression using discriminating metabolites showed high accuracy (R² >0.990) and high precision (both RMSEC and RMSEE <5%) in predicting the concentration of DMr and PMr present in beef indicating that the discriminating metabolites were good predictors. The developed untargeted LC-HRMS metabolomics and chemometrics successfully identified non-halal meats adulteration (DMr and PMr) in beef with high sensitivity up to 0.1% (w/w). Conclusion: A combination of LC-HRMS untargeted metabolomic and chemometrics promises to be an effective analytical technique for halal authenticity testing of meats. This method could be further standardized and proposed as a method for halal authentication of meats.

• Korean Journal of Radiology
• /
• v.25 no.1
• /
• pp.74-85
• /
• 2024

Objective: Idiopathic intracranial hypertension (IIH) is a condition of unknown etiology associated with venous sinus stenosis. This study aimed to develop a magnetic resonance venography (MRV)-based radiomics model for predicting a high trans-stenotic pressure gradient (TPG) in IIH patients diagnosed with venous sinus stenosis. Materials and Methods: This retrospective study included 105 IIH patients (median age [interquartile range], 35 years [27-42 years]; female:male, 82:23) who underwent MRV and catheter venography complemented by venous manometry. Contrast enhanced-MRV was conducted under 1.5 Tesla system, and the images were reconstructed using a standard algorithm. Shape features were derived from MRV images via the PyRadiomics package and selected by utilizing the least absolute shrinkage and selection operator (LASSO) method. A radiomics score for predicting high TPG (≥ 8 mmHg) in IIH patients was formulated using multivariable logistic regression; its discrimination performance was assessed using the area under the receiver operating characteristic curve (AUROC). A nomogram was constructed by incorporating the radiomics scores and clinical features. Results: Data from 105 patients were randomly divided into two distinct datasets for model training (n = 73; 50 and 23 with and without high TPG, respectively) and testing (n = 32; 22 and 10 with and without high TPG, respectively). Three informative shape features were identified in the training datasets: least axis length, sphericity, and maximum three-dimensional diameter. The radiomics score for predicting high TPG in IIH patients demonstrated an AUROC of 0.906 (95% confidence interval, 0.836-0.976) in the training dataset and 0.877 (95% confidence interval, 0.755-0.999) in the test dataset. The nomogram showed good calibration. Conclusion: Our study presents the feasibility of a novel model for predicting high TPG in IIH patients using radiomics analysis of noninvasive MRV-based shape features. This information may aid clinicians in identifying patients who may benefit from stenting.

• International Journal of Computer Science & Network Security
• /
• v.24 no.5
• /
• pp.111-118
• /
• 2024

In general network-based intrusion detection system is designed to detect malicious behavior directed at a network or its resources. The key goal of this paper is to look at network data and identify whether it is normal traffic data or anomaly traffic data specifically for accounting information systems. In today's world, there are a variety of principles for detecting various forms of network-based intrusion. In this paper, we are using supervised machine learning techniques. Classification models are used to train and validate data. Using these algorithms we are training the system using a training dataset then we use this trained system to detect intrusion from the testing dataset. In our proposed method, we will detect whether the network data is normal or an anomaly. Using this method we can avoid unauthorized activity on the network and systems under that network. The Decision Tree and K-Nearest Neighbor are applied to the proposed model to classify abnormal to normal behaviors of network traffic data. In addition to that, Logistic Regression Classifier and Support Vector Classification algorithms are used in our model to support proposed concepts. Furthermore, a feature selection method is used to collect valuable information from the dataset to enhance the efficiency of the proposed approach. Random Forest machine learning algorithm is used, which assists the system to identify crucial aspects and focus on them rather than all the features them. The experimental findings revealed that the suggested method for network intrusion detection has a neglected false alarm rate, with the accuracy of the result expected to be between 95% and 100%. As a result of the high precision rate, this concept can be used to detect network data intrusion and prevent vulnerabilities on the network.