• Economic and Environmental Geology
• /
• v.43 no.4
• /
• pp.381-391
• /
• 2010

Probabilistic prediction methods of landslides which have been developed in recent can be reliable with premise of detailed survey and analysis based on deep and special knowledge. However, landslide susceptibility should also be analyzed with some reliable and simple methods by various people such as government officials and engineering geologists who do not have deep statistical knowledge at the moment of hazards. Therefore, this study suggests an evaluation chart of landslide susceptibility with high reliability drawn by accurate statistical approaches, which the chart can be understood easily and utilized for both specialists and non-specialists. The evaluation chart was developed by a quantification method based on canonical correlation analysis using the data of geology, topography, and soil property of landslides in Korea. This study analyzed field data and laboratory test results and determined influential factors and rating values of each factor. The quantification analysis result shows that slope angle has the highest significance among the factors and elevation, permeability coefficient, porosity, lithology, and dry density are important in descending order. Based on the score assigned to each evaluation factor, an evaluation chart of landslide susceptibility was developed with rating values in each class of a factor. It is possible for an analyst to identify susceptibility degree of a landslide by checking each property of an evaluation factor and calculating sum of the rating values. This result can also be used to draw landslide susceptibility maps based on GIS techniques.

• Journal of Korea Entertainment Industry Association
• /
• v.14 no.8
• /
• pp.467-476
• /
• 2020

The purpose of this study is as a base study for improving the quality of online classes through multilateral analysis that examines the learning outcoms of educational quality and learning emotions on non-face-to-face online classes at Technical Colleges To this study, from March 1, 2020 to August 31, 2020, a survey was conducted on 1,000 students of H Technical Colleges located in the metropolitan area. The collected data were statistically processed using the SPSS Statistics 18.0 program, t-validation were performed to reveal awareness of online class also correlation analysis and multiple regression analysis were performed to reveal the relation and influence of factors related to quality of instruction, learning emotions, learning outcomes. First, there was a statistically significant difference in perception of online classes by gender and grade. Second, there was a positive correlation between the educational quality, learning emotions, and learning outcomes for online classes. Third, among the learning outcomes, the factors that influence the achievement were the educational content and positive emotions, and the factors that influence the satisfaction among the learning outcomes were the educational content and the learning environment.

• Journal of Technology Innovation
• /
• v.29 no.1
• /
• pp.1-38
• /
• 2021

In this paper, an exploratory analysis study was conducted on establishing a strategy to utilize living labs to enhance the innovation of the energy sector. Through the previous research literature, it was possible to confirm the concept, essential components, innovation characteristics of living labs, and types of innovation issues in the energy sector as the theoretical background. Based on this, the case studies of energy living lab (8 overseas, 1 domestic) were analyzed focusing on the possibility of utilizing living lab as an approach to innovation issues in the energy sector, establishing a customized strategy for essential components of living lab and enhancing innovation. It was confirmed that the establishment of a customized strategy for the essential components of the living lab could be a driving force in enhancing innovation, and the Living Lab is effectively used as an approach method for innovation issues(demand management, supply technology, enhance R&D acceptance and promote commercialization, technology policies) in the energy sector. As a result of the case studies, the driving force of each living lab was derived from the viewpoint of contributing to innovation, and strategies for using the living labs for each energy innovation problem were established. This study is an exploratory and descriptive analytical study of the utilization strategy and value of the living lab model as an approach to innovation issues in the energy field, which can provide a living lab strategy framework that has not been tried in the past and enables living lab activation and network formation. It can also be considered to have academic, practical, and policy implications in that it can also contribute.

• The KIPS Transactions:PartD
• /
• v.13D no.6 s.109
• /
• pp.823-832
• /
• 2006

The Purpose of Similarity(Reproduction) Degree Appraisal is to determine the equality or similarity between two programs and it is a system that presents the technical grounds of judgment which is necessary to support the resolution of software intellectual property rights through expert eyes. The most important things in proceeding software appraisal are not to make too much of expert's own subjective judgment and to acquire the accurate-appraisal results. However, up to now standard research and development for its systematic techniques are not properly made out and as different expert as each one could approach in a thousand different ways, even the techniques for software appraisal types have not exactly been presented yet. Moreover, in the analyzing results of all the appraisal cases finished before, through a practical way, we blow that there are some damages on objectivity and accuracy in some parts of the appraisal results owing to the problems of existing appraisal procedures and techniques or lack of expert's professional knowledge. In this paper we present the model for the standardization of software-similarity-appraisal techniques and objective-evaluation methods for decreasing a tolerance that could make different results according to each expert in the same-evaluation points. Especially, it analyzes and evaluates the techniques from various points of view concerning the standard appraisal process, setting a range of appraisal, setting appraisal domains and items in detail, based on unit processes, setting the weight of each object to be appraised, and the degree of logical and physical similarity, based on effective solutions to practical problems of existing appraisal techniques and their objective and quantitative standardization. Consequently, we believe that the model for the standardization of software-similarity-appraisal techniques will minimizes the possibility of mistakes due to an expert's subjective judgment as well as it will offer a tool for improving objectivity and reliability of the appraisal results.

• Information Systems Review
• /
• v.26 no.1
• /
• pp.367-383
• /
• 2024

Korea faces challenges in securing technical talent due to low birth rates and an aging population. To bridge labor market gaps, tailored education programs through universities are crucial. Although Program for Industrial needs-Matched Education (PRIME) encouraged developing industrial-university education courses, a few universities have the opportunities and the courses development is often depending on capability of a professor. Furthermore, administrative issues hinder progress. This study proposes streamlining administrative processes and leveraging technology to meet industry demands. Active collaboration between academia and industry can enhance education and benefit both employees and students.

• Information Systems Review
• /
• v.26 no.2
• /
• pp.45-57
• /
• 2024

This study develops a deep learning-based methodology for predicting Crude Palm Oil (CPO) prices. Palm oil is an essential resource across various industries due to its yield and economic efficiency, leading to increased industrial interest in its price volatility. While numerous studies have been conducted on palm oil price prediction, most rely on time series forecasting, which has inherent accuracy limitations. To address the main limitation of traditional methods-the absence of stationarity-this research introduces a novel model that uses the ratio of future prices to current prices as the dependent variable. This approach, inspired by return modeling in stock price predictions, demonstrates superior performance over simple price prediction. Additionally, the methodology incorporates the consideration of lag values of independent variables, a critical factor in multivariate time series forecasting, to eliminate unnecessary noise and enhance the stability of the prediction model. This research not only significantly improves the accuracy of palm oil price prediction but also offers an applicable approach for other economic forecasting issues where time series data is crucial, providing substantial value to the industry.

• Journal of Intelligence and Information Systems
• /
• v.28 no.3
• /
• pp.185-207
• /
• 2022

Recently, with the development of deep learning technology, researches to apply a deep learning algorithm to analyze unstructured data such as text and images are being actively conducted. Text classification has been studied for a long time in academia and industry, and various attempts are being performed to utilize data characteristics to improve classification performance. In particular, a hierarchical relationship of labels has been utilized for hierarchical classification. However, the top-down approach mainly used for hierarchical classification has a limitation that misclassification at a higher level blocks the opportunity for correct classification at a lower level. Therefore, in this study, we propose a methodology for classifying hierarchical data using the autoencoder-based deeply supervised network that high-level classification does not block the low-level classification while considering the hierarchical relationship of labels. The proposed methodology adds a main classifier that predicts a low-level label to the autoencoder's latent variable and an auxiliary classifier that predicts a high-level label to the hidden layer of the autoencoder. As a result of experiments on 22,512 academic papers to evaluate the performance of the proposed methodology, it was confirmed that the proposed model showed superior classification accuracy and F1-score compared to the traditional supervised autoencoder and DNN model.

• Journal of Digital Convergence
• /
• v.17 no.2
• /
• pp.355-361
• /
• 2019

The purpose of this study is to analyze how brands are perceived to be most positive when they are presented to users in brand experience design, and to help them communicate more effectively. Originally, brands changed their logos periodically with the aim of communicating anniversaries. These days, not only this information but also emotional communication with users. As a research method, two major portal sites were selected for use in Korea, and a preference survey and in-depth interview were conducted based on the case of the event logos. From the results of the study, we were able to obtain results that the event logos act as a more positive factor when they provide users with various emotional motivations. In the future, we anticipate that users will be given higher value if they have a design approach that will elicit more diverse emotions from the brand experience.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.22 no.3
• /
• pp.637-644
• /
• 2012

In our current information focused society, information is regarded as a core asset and the leakage of customers' information has emerged as a critical issue, especially in financial companies. It is very likely that the technology that safeguards which is currently in commercial use is not focused at an enterprise level but is fragmented by function or by only guards portions of a customer's personal information. Therefore, It is necessary to study the systems which monitor the indicators of access at an enterprise level in order to preemptively prevent the compromise of such data. This study takes an enterprise perspective on such systems for a financial company. I will focus on examination of the methods of implementation of the monitoring system, the application of pattern analysis and examination of Security Risk Indicators (SRI). A trial of the monitoring system provided security managers and related departments with proper screening capabilities of information. Therefore, it is possible to establish a systemic counter-plans based on detectable patterns.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.285-301
• /
• 2023

Due to the increasing demand and importance of non-face-to-face education, open online learning platforms are getting interests both domestically and internationally. These platforms exhibit different characteristics from online courses by universities and other educational institutions. In particular, students engaged in these platforms can receive more learner autonomy, and the development of tools to assist learning is required. From the past, researchers have attempted to utilize process mining to understand realistic study behaviors and derive learning patterns. However, it has a deficiency to employ it to the open online learning platforms. Moreover, existing research has primarily focused on the process model perspective, including process model discovery, but lacks a method for the process pattern and instance perspectives. In this study, we propose a method to identify learning patterns within an open online learning platform using process mining techniques. To achieve this, we suggest three different viewpoints, e.g., model-level, variant-level, and instance-level, to comprehend the learning patterns, and various techniques are employed, such as process discovery, conformance checking, autoencoder-based clustering, and predictive approaches. To validate this method, we collected a learning log of machine learning-related courses on a domestic open education platform. The results unveiled a spaghetti-like process model that can be differentiated into a standard learning pattern and three abnormal patterns. Furthermore, as a result of deriving a pattern classification model, our model achieved a high accuracy of 0.86 when predicting the pattern of instances based on the initial 30% of the entire flow. This study contributes to systematically analyze learners' patterns using process mining.