• Biomolecules & Therapeutics
• /
• v.5 no.2
• /
• pp.215-221
• /
• 1997

In an effort to screen new selective antitumor agents from the broth of soil microorganism, cytotoxicity oriented screening was performed against tumor cells and 3 compounds (Compound 1, 2 and 3) were isolated from Sreptomyces parvullus ISP 5048 and their chemical structures were determined. Among these compounds, Compound 2 showed the highest cytotoxicity against P388Dl and L1210. While the $IC_{50}$/ values of compound 2 against P388Dl and L1210 were 0.073$\mu$g/ml and 0.07$\mu$g/ml, respectively, and the $IC_{50}$/ value of Compound 3 was 0.17$\mu$g/ml against human lung cancer cells, A549, the cytotoxicity of Compound 2 and 3 against normal cell line, Vero E6 cell was about 4- and 8-fold lower than that of adriamycin. Based on the chemical analysis data, Compound 3 was octacosamicine A, a known antibiotic, which was reported by Dobasih et al. (1988). Taken together the results demonstrated that Compound 2 and Compound 3 has the possibility to be developed as antitumor agent because of its potent cytotoxicity as well as high selectivity against various cancer cell lines.

• Journal of The Korean Association of Information Education
• /
• v.24 no.1
• /
• pp.49-57
• /
• 2020

The society we are living in has being changed to the age of the intelligent information society after passing through the knowledge-based information society in the early 21st century. In this study, we have developed the instructional model for software education based on the machine learning which is a field of artificial intelligence(AI) to enhance the core competencies of learners required in the intelligent information society. This model is focusing on enhancing the core competencies through the process of problem-solving as well as reducing the burden of learning about AI itself. The specific stages of the developed model are consisted of seven levels which are 'Problem Recognition and Analysis', 'Data Collection', 'Data Processing and Feature Extraction', 'ML Model Training and Evaluation', 'ML Programming', 'Application and Problem Solving', and 'Share and Feedback'. As a result of applying the developed model in this study, we were able to observe the positive response about learning from the students and parents. We hope that this research could suggest the future direction of not only the instructional design but also operation of software education program based on machine learning.

• The Korean Journal of Applied Statistics
• /
• v.27 no.6
• /
• pp.1003-1016
• /
• 2014

Proper missing data imputation is an important procedure to obtain superior results for data analysis based on survey data. This paper deals with both a model based imputation method and model estimation method. We utilized a Bayesian method to solve a boundary solution problem in which we applied a maximum likelihood estimation method. We also deal with a missing mechanism model selection problem using forecasting results and a comparison between model accuracies. We utilized MWPE(modified within precinct error) (Bautista et al., 2007) to measure prediction correctness. We applied proposed ML and Bayesian methods to the Korean presidential election exit poll data of 2012. Based on the analysis, the results under the missing at random mechanism showed superior prediction results than under the missing not at random mechanism.

• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.337-340
• /
• 2005

Context-awareness techniques in ubiquitous computing environment provide various services to users who need to get information via the analysis of collected information from sensors in a spatial area. Context-awareness has been increased in ubiquitous computing and is applied to many different applications such as disaster management system, intelligent robot system, transportation management system, shopping management system, and digital home service. Many researches have recently focused on services that provide the appropriate information, which are collected from Internet by different kinds of sensors, to users according to context of their surrounding environment. In this paper, we propose an abstraction model to manage the large-scale contextual information and their metadata which are collected from different kinds of in-situ sensors in a spatial area and are presented them on the web. This model is composed of the modules expressing functional elements of sensors using sensorML(Sensor Model Language) based on XML language and the modules managing contextual information, which is transmitted from the sensors.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.11
• /
• pp.19-27
• /
• 2022

In this study, we propose a language and platform to describe and manage the MLOps(Machine Learning Operations) workflow for time series data anomaly detection. Time series data is collected in many fields, such as IoT sensors, system performance indicators, and user access. In addition, it is used in many applications such as system monitoring and anomaly detection. In order to perform prediction and anomaly detection of time series data, the MLOps platform that can quickly and flexibly apply the analyzed model to the production environment is required. Thus, we developed Python-based AI/ML Modeling Language (AMML) to easily configure and execute MLOps workflows. Python is widely used in data analysis. The proposed MLOps platform can extract and preprocess time series data from various data sources (R-DB, NoSql DB, Log File, etc.) using AMML and predict it through a deep learning model. To verify the applicability of AMML, the workflow for generating a transformer oil temperature prediction deep learning model was configured with AMML and it was confirmed that the training was performed normally.

• The KIPS Transactions:PartD
• /
• v.12D no.5 s.101
• /
• pp.755-764
• /
• 2005

Recently, as it is considered more important to identify the function of ail unknown genes in living things, many tools for gene prediction have been developed to identify genes in the DNA sequences. Unfortunately, most of those tools use their own schemes to represent their programs results, requiring researchers to make additional efforts to understand the result generated by them So, it is desirable to provide a standardized method of representing predicted gene information, which makes it possible to automatically produce the predicted results for a given set of gene data In this paper, we describe an effective U representation for various predicted gene information, and present an XML-based analysis tool for gene predication results based on this representation. The developed system helps users of gene prediction tools to conveniently analyze the predicted results and to automatically produce the statistical results of the prediction. To show the usefulness of the tool, we applied our programs to the results generated by GenScan and GeneID, which are widely used gene prediction systems.

• Journal of Biomedical Engineering Research
• /
• v.36 no.5
• /
• pp.228-234
• /
• 2015

The balance ability significantly decreased in the elderly because of deterioration of the neural musculature regulatory mechanisms. Several studies have investigated methods of improving balance ability using real-time systems, but it is limited by the expensive test equipment and specialized resources. Recently, Kinect system based on depth data has been applied to address these limitations. Little information about accuracy/inaccuracy of Kinect system is, however, available, particular in motion analysis for evaluation of effectiveness in rehabilitation training. Therefore, the aim of the current study was to evaluate accuracy/inaccuracy of Kinect system in specific rotational movement for balance rehabilitation training. Six healthy male adults with no musculoskeletal disorder were selected to participate in the experiment. Movements of the participants were induced by controlling the base plane of the balance training equipment in directions of AP (anterior-posterior), ML (medial-lateral), right and left diagonal direction. The dynamic motions of the subjects were measured using two Kinect depth sensor systems and a three-dimensional motion capture system with eight infrared cameras for comparative evaluation. The results of the error rate for hip and knee joint alteration of Kinect system comparison with infrared camera based motion capture system occurred smaller values in the ML direction (Hip joint: 10.9~57.3%, Knee joint: 26.0~74.8%). Therefore, the accuracy of Kinect system for measuring balance rehabilitation traning could improve by using adapted algorithm which is based on hip joint movement in medial-lateral direction.

• The Journal of Engineering Geology
• /
• v.30 no.3
• /
• pp.315-325
• /
• 2020

This study was performed to develop a model to predict landslides and determine the variable importance of landslides susceptibility factors based on the probabilistic prediction of landslides occurring on slopes along the road. Field survey data of 30,615 slopes from 2007 to 2020 in Korea were analyzed to develop a landslide prediction model. Of the total 131 variable factors, 17 topographic factors and 114 geological factors (including 89 bedrocks) were used to predict landslides. Automated machine learning (AutoML) was used to classify landslides and non-landslides. The verification results revealed that the best model, an extremely randomized tree (XRT) with excellent predictive performance, yielded 83.977% of prediction rates on test data. As a result of the analysis to determine the variable importance of the landslide susceptibility factors, it was composed of 10 topographic factors and 9 geological factors, which was presented as a percentage for each factor. This model was evaluated probabilistically and quantitatively for the likelihood of landslide occurrence by deriving the ranking of variable importance using only on-site survey data. It is considered that this model can provide a reliable basis for slope safety assessment through field surveys to decision-makers in the future.

• Journal of Veterinary Clinics
• /
• v.32 no.6
• /
• pp.486-490
• /
• 2015

Two-demensional echocardiography is routinely used for evaluation of cardiac function. Visualization of the endocardial border is essential for the assessment of global and regional left ventricular with cardiac disease. SonoVue$^{TM}$ is a microbubble contrast agent that consists of sulfur hexafluoride-filled microbubbles in a phospholipid shell. There were many studies about contrast echocardiographic examination using SonoVue$^{TM}$ contrast agent, and various doses of SonoVue$^{TM}$ were used. To our knowledge, in published veterinary medicine, there was not reported for diagnostic efficient dose of SonoVue$^{TM}$ to evaluate contrast enhanced left ventricular endocardial border delineation (LVEBD). The purpose of this study is to compare the visualization time of LVEBD and find efficient dose of SonoVue$^{TM}$ for using various doses in dogs. Ten healthy Beagles were recruited to the study. Three different doses (0.03 ml/kg, 0.05 ml/kg and 0.1 ml/kg) of SonoVue$^{TM}$ were injected. Endocardial segments were assigned based on previously established methodology, where by the four-chamber views of the LV were divided into 6 segments. In this study, Contrast enhancement of the LVEBD after each injection was evaluated visually at the time point of overall contrast enhancement (Segmental scoring 5+) in the LV by three investigators in a blind manner. Statistical analysis was performed with SPSS version 14.0. All data were analyzed using one-way ANOVA, the multiple comparison Scheffe test. When data for the three offsite readers were combined, mean durations of useful contrast were $3.54({\pm}2.14)$, $6.15({\pm}2.61)$, and $24.39({\pm}11.10)$ seconds for the 0.03 ml/kg, 0.05 ml/kg, and 0.1 ml/kg SonoVue$^{TM}$ doses, respectively. After injection of contrast agent, there were no significant change in side effects such as urticaria, angioedema, hypersensitivity reactions, and digestive system disorders. This study suggests that efficient dose of SonoVue$^{TM}$ contrast agent for improvement of the left ventricle visualization is 0.1 ml/kg. The duration of useful enhancement of LVEBD and the reproducibility were also the highest at the 0.1 ml/kg dosage.

• Journal of Korea Water Resources Association
• /
• v.32 no.3
• /
• pp.247-254
• /
• 1999

The frequency analyses of annual maximum rainfall data for 22 rainfall gauging stations is Korea were performed. The method of moments (MOM), maximum likelihood (ML), and probability weighted moments (PWM) were used in parameter estimation. The GEV distribution was selected as an appropriate model for annual maximum rainfall data based on parameter validity condition, graphical analysis, separation effect, and goodness of fit tests. For the selected GEV model, spatial analysis was performed and rainfall intensity-duration-frequency equation was derived by using linearization technique. The derived rainfall intensity-duration-frequency equation can be used for estimating rainfall quantiles of the selected stations with convenience and reliability in practice.