• Journal of Korea Multimedia Society
• /
• v.16 no.7
• /
• pp.795-801
• /
• 2013

Recently, support vector machine has been widely used in various application fields due to its superiority of classification performance comparing with decision tree and neural network. Since support vector machine is basically designed for the binary classification problem, output coding method to analyze the classification result of multiclass binary classifier is used for the application of support vector machine into the multiclass problem. However, previous feature selection method for output coding based support vector machine found the features to improve the overall classification accuracy instead of improving each classification accuracy of each classifier. In this paper, we propose the novel feature selection method to find the features for maximizing the classification accuracy of each binary classifier in output coding based support vector machine. Experimental result showed that proposed method significantly improved the classification accuracy comparing with previous feature selection method.

• Journal of Korean Society for Quality Management
• /
• v.44 no.4
• /
• pp.883-895
• /
• 2016

Purpose: The demand for ordinary mail services supplied by 'Korea POST' is decreasing due to the opening of mail service market and the growth of alternative communication media such as e-mail and SNS. To overcome this situation it is urgent to introduce new services that can be able to appeal customers and to improve existing services. Methods: A field survey is conducted to corporate customers who send ordinary mails and individual customers who receive these mails, respectively. Quality attributes of ordinary mail services are classified by two-dimensional perspectives in terms of Kano model. Decision tree model is utilized for classifying the quality attributes. Comparative analyses are done whether there are perceived differences on each quality attributes between corporate customers and individual customers. Results: Quality attributes such as 'discount postal charges', 'sending small packages by simply dropping it into a mail box', 'sending a mail of any appearance', 'delivering a mail anywhere', and 'receiving a mail at a preferred time where a customer is located ' are classified differently according to some market segments, while most of the quality attributes are classified as attractive or one-dimensional. Conclusion: Decision tree model has been found to be most effective to classify quality attributes for each market segment especially when trying to classify quality attributes belonging to 'gray areas'. Based on the perceived differences on quality attributes among customers, strategic implications are suggested to obtain potential customers and to have competitive advantages.

• Journal of Korean Critical Care Nursing
• /
• v.11 no.3
• /
• pp.45-57
• /
• 2018

Purpose : This study was performed to identify the influencing factors of unplanned intensive care unit (ICU) readmission. Methods : The study adopted a Rretrospective case control cohort design. Data were collected from the electronic medical records of 844 patients who had been discharged from the ICUs of a university hospital in Incheon from June 2014 to December 2014. Results : The study found the unplanned ICU readmission rate was to be 6.4%(n=54). From the univariate analysis revealed that, major symptoms at $1^{st}$ ICU admission, severity at $1^{st}$ ICU admission (CPSCS and APACHE II), duration of applying ventilator application during $1^{st}$ ICU admission, severity at $1^{st}$ discharge from ICU (CPSCS, APACHE II, and GCS), and application of $FiO_2$ with oxygen therapy, implementation of sputum expectoration methods, and length of stay of ICU at $1^{st}$ ICU discharge were appeared to be significant; further, decision tree model analysis revealed that while only 4 variables (sputum expectoration methods, length of stay of ICU, $FiO_2$ with oxygen therapy at $1^{st}$ ICU discharge, and major symptoms at $1^{st}$ ICU admission) were shown to be significant. Conclusions : Since sputum expectoration method was the most important factor to predictor of unplanned ICU readmission, a assessment tool for the patients' capability of sputum expectoration needs to should be developed and implemented, and standardized ICU discharge criteria, including the factors identified from the by empirical evidences, might should be developed to decrease the unplanned ICU readmission rate.

• Journal of Intelligence and Information Systems
• /
• v.8 no.2
• /
• pp.139-157
• /
• 2002

The rapid growth of e-commerce has made both companies and customers face a new situation. Whereas companies have become to be harder to survive due to more and more competitions, the opportunity for customers to choose among more and more products has increased. So, the recommender systems that recommend suitable products to the customer have an important position in E-commerce. This research introduces collaborative filtering based recommender system which helps customers find the products they would like to purchase by producing a list of top-N recommended products. The suggested methodology is based on decision tree, product taxonomy, and association rule mining. Decision tree is used to select target customers, who have high possibility of purchasing recommended products. We applied the recommender system to a Korean department store. The methodology is evaluated with the analysis of a real department store case and is compared with other methodologies.

• The Journal of the Convergence on Culture Technology
• /
• v.5 no.3
• /
• pp.251-256
• /
• 2019

With the fast development of modern society, the interests concerned about the significance of nature and environment become major issue nowadays. Especially, threats for our health due to severe environmental pollution and fine dusts become serious problem with the fast industrialization of our society, and extra attention is focused on interests about conservation of nature and management of forest resources. Precious forest resources, however, are not properly managed and destroyed vainly due to frequent fire, damage by storms and floods, and unplanned land development. So systematic and scientific construction and management of forest resources are required in order to solve these problems efficiently. Furthermore, implementation of the forest resource information database that contains information of trees, Topography, ecosystem of the forest is urgently needed. In this paper, we design and implement the forest resource information database based on the information of location based forest resources and Topography using forest images taken by a drone, that enables us to manage forest resources efficiently, make decision for logging, and construct a future tree-planting project easily.

• Journal of IKEEE
• /
• v.23 no.3
• /
• pp.883-892
• /
• 2019

This study is the method which is adapted to control ankle joint movement for resolving the problem of gait imbalance in intervals where gait environments are changed and slope walking, as applying terrain-adaptive technique to intelligent above-knee prosthesis. In this development of above-knee prosthesis, to classify the gait modes is essential. For distinguishing the stance phases and the swing phase depending on roads, a machine learning which combines decision tree and random forest from knee angle data and inertial sensor data, is proposed and adapted. By using this method, the ankle movement state of the prosthesis is controlled. This study verifies whether the problem is resolved through butterfly diagram.

• Journal of The Korean Association For Science Education
• /
• v.41 no.3
• /
• pp.203-220
• /
• 2021

We explored the performance improvement method of automated scoring for scientific argumentation. We analyzed the pattern of argumentation using automated scoring models. For this purpose, we assessed the level of argumentation for student's scientific discourses in classrooms. The dataset consists of four units of argumentation features and argumentation levels for episodes. We utilized argumentation clusters and n-gram to enhance automated scoring accuracy. We used the three supervised learning algorithms resulting in 33 automatic scoring models. As a result of automated scoring, we got a good scoring accuracy of 77.59% on average and up to 85.37%. In this process, we found that argumentation cluster patterns could enhance automated scoring performance accuracy. Then, we analyzed argumentation patterns using the model of decision tree and random forest. Our results were consistent with the previous research in which justification in coordination with claim and evidence determines scientific argumentation quality. Our research method suggests a novel approach for analyzing the quality of scientific argumentation in classrooms.

• Journal of the Korean Applied Science and Technology
• /
• v.40 no.1
• /
• pp.24-34
• /
• 2023

This study sought to explore the online consumption propensity of sports goods by generation of the productive population and to provide basic data to predict the future consumption market by segmenting online consumers in the sports 4.0 market. Therefore, this survey was conducted on those who consumed sports goods among the generation-specific groups (Generation Y and above, Z) of the productive population, and a total of 478 people's data were applied to the final analysis. Data processing was conducted with SPSS statistics (ver.21.0), frequency analysis, exploratory factor analysis, correlation analysis of re-examination reliability, reliability analysis, and decision tree analysis. According to the online consumption propensity of sports goods by generation of the productive population, there is a high probability of being classified as Generation Z group if the factors of leisure, joy, and environment are high. In addition, the classification accuracy of such a model was 69.7%.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.248-248
• /
• 2020

토양수분은 증발산, 유출, 침투 등 물수지 요소들과 밀접한 연관이 있는 주요한 변수 중에 하나이다. 토양수분의 정도는 토양의 특성, 토지이용 형태, 기상 상태 등에 따라 공간적으로 상이하며, 특히 기상 상태에 따라 시간적 변동성을 보이고 있다. 기존 토양수분 측정은 토양시료 채취를 통한 실내 실험 측정과 측정 장비를 통한 현장 조사 방법이 있으나 시간적, 경제적 한계점이 있으며, 원격탐사 기법은 공간적으로 넓은 범위를 포함하지만 시간 해상도가 낮은 단점이 있다. 또한, 모델링을 통한 토양수분 예측 기술은 전문적인 지식이 요구되며, 복잡한 입력자료의 구축이 요구된다. 최근 머신러닝 기법은 수많은 자료 학습을 통해 사용자가 원하는 출력값을 도출하는데 널리 활용되고 있다. 이에 본 연구에서는 토양수분과 연관된 다양한 기상 인자들(강수량, 풍속, 습도 등)을 활용하여 머신러닝기법의 반복학습을 통한 토양수분의 예측 가능성을 분석하고자 한다. 이를 위해 시공간적으로 토양수분 실측 자료가 잘 구축되어 있는 청미천과 설마천 유역을 대상으로 머신러닝 기법을 적용하였다. 두 대상지에서 2008년~2012년 수문자료를 확보하였으며, 기상자료는 기상자료개방포털과 WAMIS를 통해 자료를 확보하였다. 토양수분 자료와 기상자료를 머신러닝 알고리즘을 통해 학습하고 2012년 기상 자료를 바탕으로 토양수분을 예측하였다. 사용되는 머신러닝 기법은 의사결정 나무(Decision Tree), 신경망(Multi Layer Perceptron, MLP), K-최근접 이웃(K-Nearest Neighbors, KNN), 서포트 벡터 머신(Support Vector Machine, SVM), 랜덤 포레스트(Random Forest), 그래디언트 부스팅 (Gradient Boosting)이다. 토양수분과 기상인자 간의 상관관계를 분석하기 위해 히트맵(Heat Map)을 이용하였다. 히트맵 분석 결과 토양수분의 시간적 변동은 다양한 기상 자료 중 강수량과 상대습도가 가장 큰 영향력을 보여주었다. 또한 다양한 기상 인자 기반 머신러닝 기법 적용 결과에서는 두 지역 모두 신경망(MLP) 기법을 제외한 모든 기법이 전반적으로 실측값과 유사한 형태를 보였으며 비교 그래프에서도 실측값과 예측 값이 유사한 추세를 나타냈다. 따라서 상관관계있는 과거 기상자료를 통해 머신러닝 기법 기반 토양수분의 시간적 변동 예측이 가능할 것으로 판단된다.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.4
• /
• pp.707-715
• /
• 2023

This study utilized CART algorithm, a decision tree analysis method, to comparatively analyze factors affecting housing and residential environment satisfaction by region using data from Ministry of Land, Infrastructure and Transport's housing survey in 2020. First, in terms of residential environment satisfaction, accessibility to medical facilities and school district showed higher importance in metropolitan cities and areas compared to other regions, whereas safety from accident showed the opposite trait, showing difference between region. Second, housing characteristics were important in housing satisfaction, indoor environment level satisfaction and indoor safety and hygiene being important in almost all regions, while residential environment characteristics were more important in residential environment satisfaction and influencing factors were relatively evenly distributed. In order to generalize these regional characteristics, research using time series data needs to be conducted later.