• Environmental Mutagens and Carcinogens
• /
• v.23 no.2
• /
• pp.56-62
• /
• 2003

The liver progenitor cells could form a potential target cell population fore both tumor-initiating and -promoting chemicals. Induction of drug-metabolizing and antioxidant enzymes, including AhR-dependent CYP1A1, NQO-1 and AKR1C9, was detected in the rat liver epithelial WB-F344 "stem-like" cells. Additionally, WB-F344 cells express a functional, wild-type form of p53 protein, a biomarker of genotoxic events, and connexin 43, a basic structural unit of gap junctions forming an important type of intercellular communication. In this cellular model, two complementary assays have been established for detection of the modes of action associated with tumor promotion: inhibition of gap junctional intercellular communication (GJIC) and proliferative activity in confluent cells. We found that the PAHs and PCBs, which are AhR agonists, released WB-F344 cells from contact inhibition, increasing both DNA synthesis and cell numbers. Genotoxic effects of some PAHs that lead to apoptosis and cell cycle delay might interfere with the proliferative activity of PAHs. Contrary to that, the nongenotoxic low-molecular-weight PAHs and non-dioxin-like PCB congeners, abundant in the environment, did not significantly affect cell cycle and cell proliferation; however both groups of compounds inhibited GJIC in WB-F344 cells. The release from contact inhibiton by a mechanism that possibly involves the AhR activation, inhibition of GJIC and genotoxic events induced by environmental contaminants are three important modes of action that could play an important role in carcinogenic effects of toxic compounds. The relative potencies to inhibit GJIC, to induce AhR-mediated activity, and to release cells from contact inhibition were determined for a large series of PAHs and PCBs and their metabolites. In vitro bioassays based on detection of events on cellular level (deregulation of GJIC and/or proliferation) or determination of receptor-mediated activities in both ?$stem-like^{\circ}{\times}$ and hepatocyte-like liver cellular models are valuable tools for detection of modes of action of polyaromatic hydrocarbons. They may serve, together with concentration data, as a first step in their risk assessment.

• Smart Media Journal
• /
• v.11 no.2
• /
• pp.31-38
• /
• 2022

Promptly predicting changes in the salinity in rivers is an important task to predict the damage to agriculture and ecosystems caused by salinity infiltration and to establish disaster prevention measures. Because machine learning(ML) methods show much less computation cost than physics-based hydraulic models, they can predict the river salinity in a relatively short time. Due to shorter training time, ML methods have been studied as a complementary technique to physics-based hydraulic model. Many studies on salinity prediction based on machine learning have been studied actively around the world, but there are few studies in South Korea. With a massive number of datasets available publicly, we evaluated the performance of various kinds of machine learning techniques that predict the salinity of the Nakdong River Estuary Basin. As a result, LightGBM algorithm shows average 0.37 in RMSE as prediction performance and 2-20 times faster learning speed than other algorithms. This indicates that machine learning techniques can be applied to predict the salinity of rivers in Korea.

• Journal of Science Education
• /
• v.47 no.1
• /
• pp.37-51
• /
• 2023

This study explored the factors influencing major satisfaction and academic satisfaction of science education major students at the College of Education using machine learning models, random forest, gradient boosting model, and SHAP. Analysis results showed that the performance of the gradient boosting model was better than that of the random forest, but the difference was not large. Factors influencing major satisfaction include 'satisfaction with science teachers in high school corresponding to the subject of one's major', 'motivation for teaching job', and 'age'. Through the SHAP value, the influence of variables was identified, and the results were derived for the group as a whole and for individual analysis. The comprehensive and individual results could be complementary with each other. Based on the research results, implications for ways to support pre-service science teachers' major and academic satisfaction were proposed.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.305-307
• /
• 2021

Alzheimer's Disease (AD) is a cognitive disorder characterized by memory impairment that can be assessed at early stages based on administering clinical tests. However, the AD pathophysiological mechanism is still poorly understood due to the difficulty of distinguishing different levels of AD severity, even using a variety of brain modalities. Therefore, in this study, we present a hybrid EEG-fNIRS modalities to compensate for each other's weaknesses with the help of Machine Learning (ML) techniques for classifying four subject groups, including healthy controls (HC) and three distinguishable groups of AD levels. A concurrent EEF-fNIRS setup was used to record the data from 41 subjects during Oddball and 1-back tasks. We employed both a traditional neural network (NN) and a CNN-LSTM hybrid model for fNIRS and EEG, respectively. The final prediction was then obtained by using majority voting of those models. Classification results indicated that the hybrid EEG-fNIRS feature set achieved a higher accuracy (71.4%) by combining their complementary properties, compared to using EEG (67.9%) or fNIRS alone (68.9%). These findings demonstrate the potential of an EEG-fNIRS hybridization technique coupled with ML-based approaches for further AD studies.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.7
• /
• pp.1773-1793
• /
• 2023

Automated machine learning, often referred to as "AutoML," is the process of automating the time-consuming and iterative procedures that are associated with the building of machine learning models. There have been significant contributions in this area across a number of different stages of accomplishing a data-mining task, including model selection, hyper-parameter optimization, and preprocessing method selection. Among them, preprocessing method selection is a relatively new and fast growing research area. The current work is focused on the recommendation of preprocessing methods, i.e., feature subset selection (FSS) algorithms. One limitation in the existing studies regarding FSS algorithm recommendation is the use of a single learner for meta-modeling, which restricts its capabilities in the metamodeling. Moreover, the meta-modeling in the existing studies is typically based on a single group of data characterization measures (DCMs). Nonetheless, there are a number of complementary DCM groups, and their combination will allow them to leverage their diversity, resulting in improved meta-modeling. This study aims to address these limitations by proposing an architecture for preprocess method selection that uses ensemble learning for meta-modeling, namely AutoFE-Sel. To evaluate the proposed method, we performed an extensive experimental evaluation involving 8 FSS algorithms, 3 groups of DCMs, and 125 datasets. Results show that the proposed method achieves better performance compared to three baseline methods. The proposed architecture can also be easily extended to other preprocessing method selections, e.g., noise-filter selection and imbalance handling method selection.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.21
• /
• pp.9347-9353
• /
• 2014

Background: Excision repair crossing-complementing group 2 (ERCC2), also called xeroderma pigmentosum complementary group D (XPD), plays a crucial role in the nucleotide excision repair (NER) pathway. Previous epidemiological studies have reported associations between ERCC2 polymorphisms and non-Hodgkin lymphoma (NHL) risk, but the results have remained controversial. Materials and Methods: We conducted this meta-analysis based on eligible case-control studies to investigate the role of two ERCC2 polymorphisms (Lys751Gln and Asp312Asn) in determining susceptibility to NHL. Ten case-control studies from several electronic databases were included in our study up to August 14, 2014. Pooled odds ratios (ORs) and 95% confidence intervals (CIs) were calculated using fixed- or random-effects models to estimate the association strength. Results: The combined results based on all studies did not show any association between Lys751Gln/Asp312Asn polymorphisms and NHL risk for all genetic models. Stratified analyses by histological subtype and ethnicity did not indicate any significant association between Lys751Gln polymorphism and NHL risk. However, a significant reduced risk of NHL was found among population-based studies (Lys/Gln versus Lys/Lys: OR=0.87, 95% CI=0.77-0.99, P=0.037) but not hospital-based studies. As for Asp312Asn polymorphism, there was no evidence for the association between this polymorphism and the risk of NHL in all subgroup analyses. Conclusions: This meta-analysis suggests that there may be no association between Lys751Gln/Asp312Asn polymorphism and the risk of NHL and its two subtypes, whereas ERCC2 Lys751Gln heterozygote genotype may provide protective effects against the risk of NHL in population-based studies. Therefore, large-scale and well-designed studies are needed to clarify the effects of haplotypes, gene-gene, and gene-environment interactions on these polymorphisms and the risk of NHL and its different histological subtypes in an ethnicity specific population.

• Geophysics and Geophysical Exploration
• /
• v.9 no.1
• /
• pp.1-9
• /
• 2006

Geological storage of captured $CO_2$ is a new way of reducing greenhouse gas emissions to protect the climate, but is based on the established technology associated with injection of fluids underground. The geological formations of interest for this technique include operational and depleted oil and gas fields, and deep saline aquifers. Prediction of storage performance will depend on models of the behaviour of $CO_2$ in geological formations; these need to be refined and verified, and methods of monitoring developed and proved. These needs can be met through monitored demonstration and research projects. Current commercial projects that are demonstrating $CO_2$ storage include Sleipner, Weyburn, ORC, and In Salah; research projects include West Pearl Queen, Nagaoka, and Frio. In this paper, some of the monitored injection projects are described. The reservoirs employed for storing $CO_2$, and the associated monitoring techniques, are briefly reviewed. It is argued that small-scale research projects, used to develop techniques and prove models, are complementary to the large-scale monitored injections that will establish the viability of this technique for mitigating climate change.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.15 no.4
• /
• pp.1-11
• /
• 2016

The purpose of this study is to analyze the effect of public transit accessibility on the Carsharing use demand. By utilizing the rental historical DB of Greencar which is operated in Suwon city and public transit GIS DB, the use demand models for Carsharing by rental offices are built and analyzed in accordance with public transit accessibility. The result indicates 73% of walking as a majority, 3% cycling, and 20% using buses and urban railways to access Carsharing rental offices. The goodness of fit of Carsharing use models reflecting accessibility to buses and railways is verified as 0.818 which proves that public transit accessibility is a significant variable. Therefore, it is verified that installing Carsharing rental offices where public transit transfer is convenient can possibly increase the use demand. Especially, while accessibility to buses is verified as a significant variable out of other public transit means, the accessibility to urban railways is verified as not significant. This suggests that a variety of complementary policies such as transfer discount policy and one-way transfer return policy are necessary in between urban railways and Carsharing in order to promote mutual use demand in accordance with the other public transit means. This study result is yet the basic research on Carsharing, however it is expected to contribute to improvement of transfer demand in between different public transit means.

• Journal of Technology Innovation
• /
• v.23 no.1
• /
• pp.61-86
• /
• 2015

This study provides an empirical analysis based on 2012 Korea Innovation Survey (STEPI) to investigate the relation between R&D cooperation and in-house R&D investment. The study further analyzes the effect of the R&D cooperation and in-house R&D investment on technical innovation. First, the relation between company's in-house R&D investment and R&D cooperations is estimated with the two equations using SUR models. Second, the effect of in-house R&D investment and R&D cooperation on the company's technical innovation is estimated using Probit model. This study differs from other existing R&D studies using Korean data in that empirical models are based on structural relationships among in-house R&D, R&D cooperation, and technical innovation. The results can be summarized as follows; the R&D cooperation expands the in-house R&D investment and the in-house R&D strengthen the R&D cooperation. Furthermore, In-house R&D investment increases the chances of success in innovation. As we obtain evidence of complementary relation between R&D cooperation and in-house R&D investment, it is necessary to develop environment conducive to this complementarity in order to have more efficient R&D system.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.4
• /
• pp.232-241
• /
• 2019

This study examines one of the conventional and controversial issues in modern finance. Specifically, this study identifies financial determinants of corporate R&D intensity for firms belonging to Korean Chaebols. Empirical estimation procedures are applied to derive more robust results of each hypothesis test. Static panel data, Tobit regression and stepwise regression models are employed to obtain significant financial factors of R&D expenditures, while logit, probit and complementary log-log regression models are used to detect financial differences between Chaebol firms and their counterparts not classified as Chaebols. Study results found the level of R&D intensity in the prior fiscal year, market-value based leverage ratio and firm size empirically showed their significance to account for corporate R&D intensity in the first hypothesis test, whereas the majority of explanatory variables had important power on a relative basis. Assuming that the current circumstances in the domestic capital market may necessitate gradual changes of Korean Chaebols in terms of their socio-economic function, the results of this study are expected to contribute to identifying financial antecedents that can be beneficial to attain optimal level of corporate R&D expenditures for Chaebol firms on a virtuous cycle.