• The Journal of Engineering Geology
• /
• v.23 no.3
• /
• pp.305-314
• /
• 2013

Recent international and national research trends in landslide hazards were analyzed by performing a literature search of relevant scientific journals. For obtaining data from Korea, we used 'Information for Environmental Geology' (IEG), which covers 17 journals in the field of environmental geology. A total of 54 articles related to landslide hazards were found in 5 journals published in the period 2000-2012. The most common topic was landslide prediction or susceptibility (29 articles), followed by landslide mechanisms. For international information, we analyzed 1,851 articles from the 'Web Of Science' published from 2003 to the present. Researchers in Italy have published the greatest number of papers in this field, while papers from Korea rank first in terms of the citation index.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.12
• /
• pp.203-210
• /
• 2020

Memory-based collaborative filtering is one of the representative types of the recommender system, but it suffers from the inherent problem of data sparsity. Although many works have been devoted to solving this problem, there is still a request for more systematic approaches to the problem. This study exploits distribution of user ratings given to items for computing similarity. All user ratings are utilized in the proposed method, compared to previous ones which use ratings for only common items between users. Moreover, for similarity computation, it takes a global view of ratings for items by reflecting other users' ratings for that item. Performance is evaluated through experiments and compared to that of other relevant methods. The results reveal that the proposed demonstrates superior performance in prediction and rank accuracies. This improvement in prediction accuracy is as high as 2.6 times more than that achieved by the state-of-the-art method over the traditional similarity measures.

• Journal of the Korean Physical Society
• /
• v.80
• /
• pp.247-256
• /
• 2022

Our objective was to investigate radiomics signatures and prediction models defined by four segmentation methods in using 2-[¹⁸F]fluoro-2-deoxy-d-glucose positron emission tomography (¹⁸F-FDG PET) imaging of lung metastases of soft-tissue sarcomas (STSs). For this purpose, three fixed threshold methods using the standardized uptake value (SUV) and gradient-based edge detection (ED) were used for tumor delineation on the PET images of STSs. The Dice coefficients (DCs) of the segmentation methods were compared. The least absolute shrinkage and selection operator (LASSO) regression and Spearman's rank, and Friedman's ANOVA test were used for selection and validation of radiomics features. The developed radiomics models were assessed using ROC (receiver operating characteristics) curve and confusion matrices. According to the results, the DC values showed the biggest difference between SUV40% and other segmentation methods (DC: 0.55 and 0.59). Grey-level run-length matrix_run-length nonuniformity (GLRLM_RLNU) was a common radiomics signature extracted by all segmentation methods. The multivariable logistic regression of ED showed the highest area under the ROC (receiver operating characteristic) curve (AUC), sensitivity, specificity, and accuracy (AUC: 0.88, sensitivity: 0.85, specificity: 0.74, accuracy: 0.81). In our research, the ED method was able to derive a significant model of radiomics. GLRLM_RLNU which was selected from all segmented methods as a meaningful feature was considered the obvious radiomics feature associated with the heterogeneity and the aggressiveness. Our results have apparently showed that radiomics signatures have the potential to uncover tumor characteristics.

• Asian-Australasian Journal of Animal Sciences
• /
• v.19 no.9
• /
• pp.1225-1228
• /
• 2006

A total of 1,367 first lactation records of daughters of 81 sires, having 5 or more progeny were used to evaluate sires by 3 different methods viz., least squares (LS), best linear unbiased prediction (BLUP) and derivative free restricted maximum likelihood (DFREML) method. The highest and lowest overall average breeding value of sires for first lactation 305 days or less milk yield was obtained by BLUP (1,520.72 kg) and LS method (1,502.22 kg), respectively. The accuracy, efficiency and stability of different sire evaluation methods were compared to judge their effectiveness. The error variance of DFREML method was lowest ($191,112kg^2$) and its coefficient of determination of fitting the model was highest (33.39%) revealing that this method of sire evaluation was most efficient and accurate as compared to other methods. However, the BLUP method was most stable amongst all the methods having coefficient of variation (%) very near to unadjusted data (18.72% versus 19.89%). The higher rank correlations (0.7979 to 0.9568) between different sire evaluation methods indicated that there was higher degree of similarity of ranking sires by different methods ranging from about 80 to 96 percent. However, the DFREML method seemed to be the most effective sire evaluation method as compared to other methods for the present set of data.

• Nuclear Engineering and Technology
• /
• v.42 no.6
• /
• pp.690-703
• /
• 2010

Sampling based uncertainty analysis was carried out to quantify uncertainty in predictions of best estimate code RELAP5/MOD3.2 for a thermal hydraulic test (10% hot leg break LOCA) performed in the Large Scale Test Facility (LSTF) as a part of an IAEA coordinated research project. The nodalisation of the test facility was qualified for both steady state and transient level by systematically applying the procedures led by uncertainty methodology based on accuracy extrapolation (UMAE); uncertainty analysis was carried out using the Latin hypercube sampling (LHS) method to evaluate uncertainty for ten input parameters. Sixteen output parameters were selected for uncertainty evaluation and uncertainty band between $5^{th}$ and $95^{th}$ percentile of the output parameters were evaluated. It was observed that the uncertainty band for the primary pressure during two phase blowdown is larger than that of the remaining period. Similarly, a larger uncertainty band is observed relating to accumulator injection flow during reflood phase. Importance analysis was also carried out and standard rank regression coefficients were computed to quantify the effect of each individual input parameter on output parameters. It was observed that the break discharge coefficient is the most important uncertain parameter relating to the prediction of all the primary side parameters and that the steam generator (SG) relief pressure setting is the most important parameter in predicting the SG secondary pressure.

• Computers and Concrete
• /
• v.32 no.3
• /
• pp.313-326
• /
• 2023

The seismic safety of the shear wall structure can be assessed through seismic fragility analysis, which requires high computational costs in estimating seismic demands. Accordingly, machine learning methods have been applied to such fragility analyses in recent years to reduce the numerical analysis cost, but it still remains a challenging task. Therefore, this study uses the ensemble machine learning method to present an improved framework for developing a more accurate seismic demand model than the existing ones. To this end, a rank-based selection method that enables determining an excellent model among several single machine learning models is presented. In addition, an index that can evaluate the degree of overfitting/underfitting of each model for the selection of an excellent single model is suggested. Furthermore, based on the selected single machine learning model, we propose a method to derive a more accurate ensemble model based on the bagging method. As a result, the seismic demand model for which the proposed framework is applied shows about 3-17% better prediction performance than the existing single machine learning models. Finally, the seismic fragility obtained from the proposed framework shows better accuracy than the existing fragility methods.

• Earthquakes and Structures
• /
• v.27 no.2
• /
• pp.83-95
• /
• 2024

The prediction of seismic behavior of the existing building stock is one of the most impactful and complex problems faced by countries with frequent and intense seismic activities. Human lives can be threatened or lost, the economic life is disrupted and large amounts of monetary reparations can be potentially required. However, authorities at a regional or national level have limited resources at their disposal in order to allocate to preventative measures. Thus, in order to do so, it is essential for them to be able to rank a given population of structures according to their expected degree of damage in an earthquake. In this paper, the authors present a ranking approach, based on Machine Learning (ML) algorithms for pairwise comparisons, coupled with ad hoc ranking rules. The case study employed data from 404 reinforced concrete structures with various degrees of damage from the Athens 1999 earthquake. The two main components of our experiments pertain to the performance of the ML models and the success of the overall ranking process. The former was evaluated using the well-known respective metrics of Precision, Recall, F1-score, Accuracy and Area Under Curve (AUC). The performance of the overall ranking was evaluated using Kendall's tau distance and by viewing the problem as a classification into bins. The obtained results were promising, and were shown to outperform currently employed engineering practices. This demonstrated the capabilities and potential of these models in identifying the most vulnerable structures and, thus, mitigating the effects of earthquakes on society.

• The Journal of Bigdata
• /
• v.5 no.2
• /
• pp.77-84
• /
• 2020

In this study, we conducted a study on the win-loss predicton analysis of korean professional baseball by artificial intelligence models. Based on the model, we predicted the winner as well as each team's final rank in the league. Additionally, we developed a website for viewers' understanding. In each game's first, third, and fifth inning, we analyze to select the best model that performs the highest accuracy and minimizes errors. Based on the result, we generate the rankings. We used the predicted data started from May 5, the season's opening day, to August 30, 2020 to generate the rankings. In the games which Kia Tigers did not play, however, we used actual games' results in the data. KNN and AdaBoost selected the most optimized machine learning model. As a result, we observe a decreasing trend of the predicted results' ranking error as the season progresses. The deep learning model recorded 89% of the model accuracy. It provides the same result of decreasing ranking error trends of the predicted results that we observe in the machine learning model. We estimate that this study's result applies to future KBO predictions as well as other fields. We expect broadcasting enhancements by posting the predicted winning percentage per inning which is generated by AI algorism. We expect this will bring new interest to the KBO fans. Furthermore, the prediction generated at each inning would provide insights to teams so that they can analyze data and come up with successful strategies.

• Korean Journal of Radiology
• /
• v.21 no.9
• /
• pp.1055-1064
• /
• 2020

Objective: To assess the incremental prognostic value of coronary computed tomography angiography (CCTA) in comparison to a clinical risk model (Framingham risk score, FRS) and coronary artery calcium score (CACS) for future cardiac events in ischemic stroke patients without chest pain. Materials and Methods: This retrospective study included 1418 patients with acute stroke who had no previous cardiac disease and underwent CCTA, including CACS. Stenosis degree and plaque types (high-risk, non-calcified, mixed, or calcified plaques) were assessed as CCTA variables. High-risk plaque was defined when at least two of the following characteristics were observed: low-density plaque, positive remodeling, spotty calcification, or napkin-ring sign. We compared the incremental prognostic value of CCTA for major adverse cardiovascular events (MACE) over CACS and FRS. Results: The prevalence of any plaque and obstructive coronary artery disease (CAD) (stenosis ≥ 50%) were 70.7% and 30.2%, respectively. During the median follow-up period of 48 months, 108 patients (7.6%) experienced MACE. Increasing FRS, CACS, and stenosis degree were positively associated with MACE (all p < 0.05). Patients with high-risk plaque type showed the highest incidence of MACE, followed by non-calcified, mixed, and calcified plaque, respectively (log-rank p < 0.001). Among the prediction models for MACE, adding stenosis degree to FRS showed better discrimination and risk reclassification compared to FRS or the FRS + CACS model (all p < 0.05). Furthermore, incorporating plaque type in the prediction model significantly improved reclassification (integrated discrimination improvement, 0.08; p = 0.023) and showed the highest discrimination index (C-statistics, 0.85). However, the addition of CACS on CCTA with FRS did not add to the prediction ability for MACE (p > 0.05). Conclusion: Assessment of stenosis degree and plaque type using CCTA provided additional prognostic value over CACS and FRS to risk stratify stroke patients without prior history of CAD better.

• Proceedings of the Korean Society for Bioinformatics Conference
• /
• 2003.10a
• /
• pp.26-51
• /
• 2003

Large scale protein interaction maps provide a new, global perspective with which to analyse protein function. PSIMAP, the Protein Structural Interactome Map, is a database of all the structurally observed interactions between superfamilies of protein domains with known three-dimensional structure in thePDB. PSIMAP incorporates both functional and evolutionary information into a single network. It makes it possible to age protein domains in terms of taxonomic diversity, interaction and function. One consequence of it is to predict the most important protein domain structure in evolution. We present a global analysis of PSIMAP using several distinct network measures relating to centrality, interactivity, fault-tolerance, and taxonomic diversity. We found the following results: ${\bullet}$ Centrality: we show that the center and barycenter of PSIMAP do not coincide, and that the superfamilies forming the barycenter relate to very general functions, while those constituting the center relate to enzymatic activity. ${\bullet}$ Interactivity: we identify the P-loop and immunoglobulin superfamilies as the most highly interactive. We successfully use connectivity and cluster index, which characterise the connectivity of a superfamily's neighbourhood, to discover superfamilies of complex I and II. This is particularly significant as the structure of complex I is not yet solved. ${\bullet}$ Taxonomic diversity: we found that highly interactive superfamilies are in general taxonomically very diverse and are thus amongst the oldest. This led to the prediction of the oldest and most important protein domain in evolution of lift. ${\bullet}$ Fault-tolerance: we found that the network is very robust as for the majority of superfamilies removal from the network will not break up the network. Overall, we can single out the P-loop containing nucleotide triphosphate hydrolases superfamily as it is the most highly connected and has the highest taxonomic diversity. In addition, this superfamily has the highest interaction rank, is the barycenter of the network (it has the shortest average path to every other superfamily in the network), and is an articulation vertex, whose removal will disconnect the network. More generally, we conclude that the graph-theoretic and taxonomic analysis of PSIMAP is an important step towards the understanding of protein function and could be an important tool for tracing the evolution of life at the molecular level.