• Korean Chemical Engineering Research
• /
• v.61 no.4
• /
• pp.523-541
• /
• 2023

As accessibility to 3D printers increases, there is a growing frequency of exposure to chemicals associated with 3D printing. However, research on the toxicity and harmfulness of chemicals generated by 3D printing is insufficient, and the performance of toxicity prediction using in silico techniques is limited due to missing molecular structure data. In this study, quantitative structure-activity relationship (QSAR) model based on data-centric AI approach was developed to predict the toxicity of new 3D printing materials by imputing missing values in molecular descriptors. First, MissForest algorithm was utilized to impute missing values in molecular descriptors of hazardous 3D printing materials. Then, based on four different machine learning models (decision tree, random forest, XGBoost, SVM), a machine learning (ML)-based QSAR model was developed to predict the bioconcentration factor (Log BCF), octanol-air partition coefficient (Log Koa), and partition coefficient (Log P). Furthermore, the reliability of the data-centric QSAR model was validated through the Tree-SHAP (SHapley Additive exPlanations) method, which is one of explainable artificial intelligence (XAI) techniques. The proposed imputation method based on the MissForest enlarged approximately 2.5 times more molecular structure data compared to the existing data. Based on the imputed dataset of molecular descriptor, the developed data-centric QSAR model achieved approximately 73%, 76% and 92% of prediction performance for Log BCF, Log Koa, and Log P, respectively. Lastly, Tree-SHAP analysis demonstrated that the data-centric-based QSAR model achieved high prediction performance for toxicity information by identifying key molecular descriptors highly correlated with toxicity indices. Therefore, the proposed QSAR model based on the data-centric XAI approach can be extended to predict the toxicity of potential pollutants in emerging printing chemicals, chemical process, semiconductor or display process.

• Journal of Korea Multimedia Society
• /
• v.7 no.2
• /
• pp.283-291
• /
• 2004

Internet Service Subscribers Network has a new role of providing the various multimedia services to the home. However, there exist several types of distributed subscribers network using Asymmetric Digital Subscriber Line (ADSL), Very high-bit rate Digital Subscriber Line (VDSL), and Data Over Cable Service Interface Specifications (DOCSIS). The efficient and concentrated network management of those several distributed subscribers networks with resources require the general information model of network, which has abstract and conceptional managed objects independent of type of network and its equipment to manage the integrated subscriber network. This paper presents the general Internet subscribers network model of the managed object to manage that network in the form of integrated hierarchy This paper adopts the object-oriented development methodology with UML and designs and implements the integrated subscribers NMS of cable data network and VDSL network as examples of the subscriber networks.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.17 no.2
• /
• pp.105-117
• /
• 2004

In each industry field, many engineers have tried to develop integrated environments using information technology. The core technology in building integrated environments is the database based on standardized information. To meet the requirements, this study builds a database with detailed design information as a part of integrating digital information generated from every work of steel bridges. The data model used to build the database was developed based on the international standard, namely ISO/STEP. The data model is classified into geometric and non-geometric parts to represent the design information of steel bridges. The geometric parts are represented by a three dimensional solid model so that they may be able to reuse existing information. Also, the non-geometric parts represent information requirements that are analyzed by the development method of standard data model. To verify the data model, this study validates the syntax of the model on EXPRESS Engine and verifies the validation of the model by applying the design data of Hannam bridge to the database.

• Journal of The Korean Association For Science Education
• /
• v.25 no.6
• /
• pp.698-709
• /
• 2005

When modeling students' conceptual understanding, there are several different frameworks, among which are the alternative conception framework and the mental model framework, which converge to suggest a form of knowledge representation. However, little research has explained how they are different from each other and from memory. The purpose of this study was to develop a new mental model theory that integrates the different terminologies and their background theories, which refer to students' ideas not only in science education, but also in other research areas. For this purpose, at first, we compared different terminologies including alternative conception, p-prim, and mental models, and the underlying theories used for representing students' ideas in learning science. Through such comparison, we tried to find the relationship among them. We reviewed related literature and synthesized the results from both cognitive science (related research areas) and science education approaches, especially, Vosniadou's mental model theory. Based on reviewing previous studies, we have developed a preliminary mental model theory 'an integrated theoretical structure of mental models'. We applied the new mental model theory to interpret data on students' ideas about circular motion from our previous research. We expect our new mental model theory will help us understand how students form their own ideas in science from an integrated perspective.

• Journal of Positioning, Navigation, and Timing
• /
• v.5 no.3
• /
• pp.119-129
• /
• 2016

This paper presents an integrated navigation system for accurate navigation solution-based safety and convenience services in the vehicular augmented reality (AR)-head up display (HUD) system. For lane-level guidance service, especially, an accurate navigation system is essential. To achieve this, an inertial navigation system (INS)/global positioning system (GPS)/vision/digital map (IGVM) integrated navigation system has been developing. In this paper, the concept of the integrated navigation system is introduced and is implemented based on a multi-model switching filter and vehicle status decided by using the GPS data and inertial measurement unit (IMU) measurements. The performance of the implemented navigation system is verified experimentally.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.19 no.40
• /
• pp.1-14
• /
• 1996

We develop a dynamic demand forecasting model compared to regression analysis model and AutoRegressive Integrated Moving Average(ARIMA) model. The dynamic model can apply to the current dynamic data to forecasts through introducing state equation. A multiple regression model and ARIMA model using given data are designed via the model analysis. The forecasting fitness evaluation between the designed models and the dynamic model is compared with the criterion of sum of squared error.

• Communications for Statistical Applications and Methods
• /
• v.8 no.2
• /
• pp.543-556
• /
• 2001

This study suggests integrated neural network modes for he stock price index forecasting using change-point detection. The basic concept of this proposed model is to obtain significant intervals occurred by change points, identify them as change-point groups, and reflect them in stock price index forecasting. The model is composed of three phases. The first phase is to detect successive structural changes in stock price index dataset. The second phase is to forecast change-point group with various data mining classifiers. The final phase is to forecast the stock price index with backpropagation neural networks. The proposed model is applied to the stock price index forecasting. This study then examines the predictability of integrated neural network models and compares the performance of data mining classifiers.

• Journal of the Korean Society for information Management
• /
• v.23 no.4 s.62
• /
• pp.165-177
• /
• 2006

National Knowledge and Information Resources of KADO(Korea Agency for Digital Opportunity and Promotion) were distributed to the several data centers. The metadata for the resources was the conceptual level recommended standard. It was not for the integration, but the retrieval. So it is not easy to integrate to the central metadata DB or connect metadata among the data centers. In this paper, we analysed the metadata of the several data centers and provided the integrated standard model for the central metadata DB.

• Journal of the Korean Institute of Educational Facilities
• /
• v.15 no.6
• /
• pp.39-46
• /
• 2008

The main purpose of this study is to find out the strengths and weaknesses of the application of BIM to the educational facilities. All the data information is drawn from the integrated design process which links various fields such as energy simulation, structure analyzation, and etc, and it is applied to the project combined as one data set. Moreover, we analyze the possible problems of the data exchange that can happen as collaborating with various fields while working on the project, and we present its solutions and the futher studies on this matter of a project.

• Proceedings of the Korean Society of Agricultural Engineers Conference
• /
• 1998.10a
• /
• pp.344-348
• /
• 1998

FEM numerical models have been known to provide an extensive applicability to the field of water resources development. However, some of restrictions such as requiring considerable number of input data and numerous subprocess were the problem of using such FEM numerical models. Especially, where the model is applied to the complex coastal area, difficulties will be intensified. Therefore it is necessary that the profitable user interface, data optimization, and structured system should be developed if the models could be used effectively. In this study, it is intended that development of integrated system for simulations of FEM numerical models to give better applicability in the field of water resources development. By using integrated system which was developed in this study, it would be concluded that the efforts to need some treatments for subprocesses of the FEM numerical model were decreased and GUI environment proved to be convinient for use for the on-the-job users.