Particulate matter is known to have adverse effects on health, making it crucial to accurately gauge its concentration levels. While the recent advent of low-cost air sensors has enabled real-time measurement of particulate matter, discrepancies in concentrations can arise depending on the sensor used, the measuring environment, and the manufacturer. In light of this, we aimed to propose a method to calibrate measurements between low-cost air sensor devices. In our study, we introduced decision tree techniques, commonly used in machine learning for classification and regression problems, to categorize particulate matter concentration intervals. For each interval, both univariate and multivariate multiple linear regression analyses were conducted to derive calibration equations. The concentrations of PM10 and PM2.5 measured indoors and outdoors with two types of LCS equipment and the GRIMM 11-A device were compared and analyzed, confirming the necessity for distinguishing between indoor and outdoor spaces and categorizing concentration intervals. Furthermore, the decision tree calibration method showed greater accuracy than traditional methods. On the other hand, during univariate regression analysis, the proportion exceeding a PM2.5/PM10 ratio of 1 was significantly high. However, using multivariate regression analysis, the exceedance rate decreased to 79.1% for IAQ-C7 and 89.3% for PMM-130, demonstrating that calibration through multivariate regression analysis considering both PM10 and PM2.5 is more effective. The results of this study are expected to contribute to the accurate calibration of particulate matter measurements and have showcased the potential for scientifically and rationally calibrating data using machine learning.

Background: While efforts have been made to differentiate fall risk in older adults using wearable devices and clinical methodologies, technologies are still infancy. We applied a decision tree (DT) algorithm using inertial measurement unit (IMU) sensor data and clinical measurements to generate high performance classification models of fall risk of older adults. Objects: This study aims to develop a classification model of fall risk using IMU data and clinical measurements in older adults. Methods: Twenty-six older adults were assessed and categorized into high and low fall risk groups. IMU sensor data were obtained while walking from each group, and features were extracted to be used for a DT algorithm with the Gini index (DT1) and the Entropy index (DT2), which generated classification models to differentiate high and low fall risk groups. Model’s performance was compared and presented with accuracy, sensitivity, and specificity. Results: Accuracy, sensitivity and specificity were 77.8%, 80.0%, and 66.7%, respectively, for DT1; and 72.2%, 91.7%, and 33.3%, respectively, for DT2. Conclusion: Our results suggest that the fall risk classification using IMU sensor data obtained during gait has potentials to be developed for practical use. Different machine learning techniques involving larger data set should be warranted for future research and development.

It is difficult to optimize the process parameters of directly preparing carbonaceous mesophase (CMs) by solvothermal method using coal tar as raw material. To solve this problem, a Decision Tree model for CMs preparation (DTC) was established based on the relationship between the process parameters and the yields of CMs. Then, the importance of variables in the preparation process for CMs was predicted, the relationship between experimental conditions and yields was revealed, and the preparation process conditions were also optimized by the DTC. The prediction results showed that the importance of the variables was raw material type, solvothermal temperature, solvothermal time, solvent amount, and additive type in order. And the optimized reaction conditions were as follows: coal tar was pretreated by decompress distillation and centrifugation, the solvent amount was 50.0 ml, the solvothermal temperature was 230 °C, and the reaction time was 5 h. These prediction results were consistent with the actual experimental results, and the error between the predicted yields and the actual yields was about − 1.1%. Furthermore, the prediction error of DTC method was within the acceptable range when the data sample sets were reduced to 100 sets. These results proved that the established DTC for chemical process optimization can effectively lessen the experimental workload and has high application value.

This paper analyzed the correlation between injection molding factors through correlation analysis. In addition, the decision-tree model, which is a white box model with excellent explanatory power, was used to obtain optimal molding conditions that satisfy multiple constraint conditions. First, 243 data to be used in the experiment were created through a full factorial design. Second, a correlation analysis was conducted to understand the correlation. Third, to verify the decision-tree model, the prediction performance was evaluated using RMSE. As a result, good prediction performance was confirmed. A decision-tree experiment analysis was conducted. As a result of the progress, the same results as the correlation analysis were derived. Based on the previous analysis results, optimal molding conditions were applied to CAE. As a result, the amount of deformation in the multi-cavity could be improved by about 1.1% and 2.72% while satisfying the constraint.

Most of the open-source decision tree algorithms are based on three splitting criteria (Entropy, Gini Index, and Gain Ratio). Therefore, the advantages and disadvantages of these three popular algorithms need to be studied more thoroughly. Comparisons of the three algorithms were mainly performed with respect to the predictive performance. In this work, we conducted a comparative experiment on the splitting criteria of three decision trees, focusing on their interpretability. Depth, homogeneity, coverage, lift, and stability were used as indicators for measuring interpretability. To measure the stability of decision trees, we present a measure of the stability of the root node and the stability of the dominating rules based on a measure of the similarity of trees. Based on 10 data collected from UCI and Kaggle, we compare the interpretability of DT (Decision Tree) algorithms based on three splitting criteria. The results show that the GR (Gain Ratio) branch-based DT algorithm performs well in terms of lift and homogeneity, while the GINI (Gini Index) and ENT (Entropy) branch-based DT algorithms performs well in terms of coverage. With respect to stability, considering both the similarity of the dominating rule or the similarity of the root node, the DT algorithm according to the ENT splitting criterion shows the best results.

본 연구는 데이터 마이닝 기반 의사결정 나무 분석을 적용해 Z세대 스포츠 소비 스타일을 탐색 하여 Z세대가 주도할 스포츠 소비 시장을 예측하기 위한 기초자료를 제공하고자 했다. 따라서 Z세대 중 만 19세 이상 남성 및 여성을 표본으로 선정해 본 조사를 실시했으며, 총 429명의 자료를 최종 분석에 사용했다. 자료처리는 SPSS statistics(ver. 21.0) 프로그램을 이용하여 빈도분석, 탐색적 요인분석, 재검사 신 뢰도 및 신뢰도 분석, 의사결정 나무 분석을 실시했다. 본 연구의 주요 결과는 다음과 같다. 첫째, 합리 효율성 지수가 높고, 심미적 소비 지수가 낮을 경우 여성 집단으로 분류될 확률이 96.8%로 나타났다. 반면에 합리 효율성과 가격 지향 지수가 낮을 경우 남성 집단으로 분류될 확률이 100%로 나타났다. 둘째, 브랜드 지향, 가격 지향, 합리 효율성 지수가 높을 경우 수도권 집단으로 분류될 확률이 97.3%로 나타났다. 앞서 제시한 결과와는 상반적으로 브랜드 지향, 기념 의례, 지위 상징 지수가 낮을 경우 이외 지역 집단으로 분 류될 확률이 82.1%로 나타났다. 셋째, 지위 상징, 유행 지향 지수가 높으며, 기능성 지수가 낮을 경우 일상 생활 및 패션 집단으로 분류될 확률이 77.6%로 나타났다. 이와 반대로 지위 상징 지수가 낮고, 소속감 유지, 소비 향유 지수가 높을 경우 운동 및 경기 집단으로 분류될 확률이 81.0%로 나타났다.

Background: Scapular winging (SW) could be caused by tightness or weakness of the periscapular muscles. Although data mining techniques are useful in classifying or predicting risk of musculoskeletal disorder, predictive models for risk of musculoskeletal disorder using the results of clinical test or quantitative data are scarce. Objects: This study aimed to (1) investigate the difference between young women with and without SW, (2) establish a predictive model for presence of SW, and (3) determine the cutoff value of each variable for predicting the risk of SW using the decision tree method. Methods: Fifty young female subjects participated in this study. To classify the presence of SW as the outcome variable, scapular protractor strength, elbow flexor strength, shoulder internal rotation, and whether the scapula is in the dominant or nondominant side were determined. Results: The classification tree selected scapular protractor strength, shoulder internal rotation range of motion, and whether the scapula is in the dominant or nondominant side as predictor variables. The classification tree model correctly classified 78.79% (p = 0.02) of the training data set. The accuracy obtained by the classification tree on the test data set was 82.35% (p = 0.04). Conclusion: The classification tree showed acceptable accuracy (82.35%) and high specificity (95.65%) but low sensitivity (54.55%). Based on the predictive model in this study, we suggested that 20% of body weight in scapular protractor strength is a meaningful cutoff value for presence of SW.

PURPOSES : The objective of this study is to develop a pavement rehabilitation decision tree considering current pavement condition by evaluating severity and distress types such as roughness, cracking and rutting. METHODS: To improve the proposed overall rehabilitation decision tree, current decision tree from Korea and decision trees from other countries were summarized and investigated. The problem when applying the current rehabilitation method obtained from the decision tree applied in Seoul was further analyzed. It was found that the current decision trees do not consider different distress characteristics such as crack type, road types and functions. Because of this, different distress values for IRI, crack rate and plastic deformation was added to the proposed decision tree to properly recommend appropriate pavement rehabilitation. Utilizing the 2017 Seoul pavement management system data and considering all factors as discussed, the proposed overall decision tree was revised and improved. RESULTS: In this study, the type of crack was included to the decision tree. Meanwhile current design thickness and special asphalt mixture were studied and improved to be applied on different pavement condition. In addition, the improved decision tree was incorporated with the Seoul asphalt overlay design program. In the case of Seoul's rehabilitation budget, rehabilitation budget can be optimized if a 25mm milling and overlay thickness is used. CONCLUSIONS: A practical and theoretical evaluation tool in pavement rehabilitation design was presented and proposed for Seoul City.

For game design planning education, we researched step by step learning method from storyline setting to game content evaluation. In this process, we developed 'Content Generated Tree' educational model applying the segmentation, classification, and prediction process of decision tree theory. This model is divided into the trunk stage as a story setting, the node generation stage as a content branch, and the conformity assessment. In the node generation stage, there are 'Game Theme' stage for determining the overall direction of the game, 'Interest Element' stage for finding the unique joy of the development game, and 'Game Format' stage for setting the visualization direction. The learner creates several game content combinations through content branching, and evaluates each content combination value. The education model was applied to 19 teams, and the efficiency of the step by step learning process was confirmed.

As a non-parametric data mining method, decision tree classification has performed well in many applications. The complexity of the model increases as the decision tree algorithm proceeds to grow the decision tree as the rule of decision making. While the increase of the complexity enhances the accuracy, it degrades the generalization which predicts the unseen data. This phenomenon is called as overfitting. To avoid the overfitting, pruning has been introduced. Pruning enables to make the generalization better, reduces the complexity, and avoids the overfitting. Although various pruning methods have been proposed, selecting the best pruning methods or making balance between complexity and generalization with pruning is not a simple problem. In this paper, we explore the methods of pruning and analyze them to suggest the optimal approach for applications.

PURPOSES: This study was initiated to analyze the characteristics of bus traffic accidents, by bus types, using the decision tree in order to establish customized safety alternatives by bus types, including the intra-city bus, rural area bus, and inter-city bus. METHODS: In this study, the major elements involved in bus traffic accidents were identified using decision trees and CHAID algorithm. The decision tree was used to identify the characteristics of major elements influencing bus traffic accidents. In addition, the CHAID algorithm was applied to branch the decision trees. RESULTS : The number of casualties and severe injuries are high in bus accidents involving pedestrians, bicycles, motorcycles, etc. In the case of light injury caused by bus accidents, different results are found. In the case of intra-city bus accidents, the probability of light injury is of 77.2% when boarding a non-owned car and breaching of duty to drive safely are involved. In the case of rural area bus accidents, the elements showing the highest probability of light injury are boarding an owned car, vehicle-to-vehicle accidents, and breaching of duty to drive safely. In the case of intra-city bus accidents, boarding owned car, streets, and vehicle-to-vehicle accidents work as the critical elements. CONCLUSIONS: In this study, the bus accident data were categorized by bus types, and then the influential elements were identified using decision trees. As a result, the characteristics of bus accidents were found to be different depending on bus types. The findings in this study are expected to be utilized in establishing effective alternatives to reduce bus accidents.

In the manufacturing industry fields, thousands of quality characteristics are measured in a day because the systems of process have been automated through the development of computer and improvement of techniques. Also, the process has been monitored in database in real time. Particularly, the data in the design step of the process have contributed to the product that customers have required through getting useful information from the data and reflecting them to the design of product. In this study, first, characteristics and variables affecting to them in the data of the design step of the process were analyzed by decision tree to find out the relation between explanatory and target variables. Second, the tolerance of continuous variables influencing on the target variable primarily was shown by the application of algorithm of decision tree, C4.5. Finally, the target variable, loss, was calculated by a loss function of Taguchi and analyzed. In this paper, the general method that the value of continuous explanatory variables has been used intactly not to be transformed to the discrete value and new method that the value of continuous explanatory variables was divided into 3 categories were compared. As a result, first, the tolerance obtained from the new method was more effective in decreasing the target variable, loss, than general method. In addition, the tolerance levels for the continuous explanatory variables to be chosen of the major variables were calculated. In further research, a systematic method using decision tree of data mining needs to be developed in order to categorize continuous variables under various scenarios of loss function.

Self-efficacy (one's perceptions of their capability to perform a task) plays an important role in work-related performance and motivation. For example, self-efficacy is known to have much influence on job performance, job satisfaction, motivation, etc. As such it is important to know what factors collectively enhance the selfefficacy of employees, so that injured workers contribute to the organization they belong to after they come back to their workplace. The aim of this study is to identify such industrial accident-related factors and extract rules among the factors in order to establish self-efficacy enhancement strategies for injured workers. In this study, a binary decision tree model for self-efficacy prediction was built using a panel data provided from Korea Workers’ Compensation & Welfare Service. As a result, eight variables with the largest influence on self-efficacy were selected in the prediction model, and it correctly classified 70.1% of instances. The result suggests social support during the treatment period and offering paid time off such as vacation leave, sick leave and bereavement leave are important factors to enhance self-efficacy that will improve the work performance of injured workers.

Decision Tree is one of analysis techniques which conducts grouping and prediction into several sub-groups from interested groups. Researcher can easily understand this progress and explain than other techniques. Because Decision Tree is easy technique to see results. This paper uses CART algorithm which is one of data mining technique. It used 273 variables and 70094 data(2010-2011) of working environment survey conducted by Korea Occupational Safety and Health Agency(KOSHA). And then refines this data, uses final 12 variables and 35447 data. To find satisfaction factor in working environment, this page has grouped employee to 3 types (under 30 age, 30 ~ 49age, over 50 age) and analyzed factor. Using CART algorithm, finds the best grouping variables in 155 data. It appeared that ‘comfortable in organization’ and ‘proper reward’ is the best grouping factor.

This paper deals with the economic value analysis of meteorological forecasts for a hypothetical inventory decision-making situation in the pharmaceutical industry. The value of Asian dust (AD) forecasts is assessed in terms of the expected value of profits by using a decision tree, which is transformed from the specific payoff structure. The forecast user is assumed to determine the inventory level by considering base profit, inventory cost, and lost sales cost. We estimate the information value of AD forecasts by comparing the two cases of decision-making with or without the AD forecast. The proposed method is verified for the real data of AD forecasts and events in Seoul during the period 2004~2008. The results indicate that AD forecasts can provide the forecast users with benefits, which have various ranges of values according to the relative rate of inventory and lost sales cost.

Currently, R&D investment of government is increased dramatically. However, the budget of the government is different depend- ing on the size of ministry and priorities, and then it is difficult to obtain consensus on the budget. They did not establish decision support systems to evaluate and execute R&D budget. In this paper, we analyze factors affecting research funds by linear regression and decision tree analysis in order to increase investment efficiency in national research project. Moreover, we suggested strategies that budget is estimated reasonably.

Cost estimating is essential in decision-making for conducting project management on early design stage. The cost estimating method for each stage varies according to level of design detail. Therefore, in the cost estimating method for each stage, it must distinguish quantity items that can be directly measured from quantity items that should be predicted. The parametric estimating method is able to support cost planning for various design attributes as it is possible to set impact factors related to design features as parameters. This study suggests a prediction method for quantity information that is required to estimate the final cost during the early design stage. The case study suggests an predicting method for the steel (rebar) ratio of office buildings. The suggested parametric cost estimating model enables users to predict the steel (rebar) quantity for various design alternatives according to design features. During quantity predictions, IG(Information gain) measurements for the design attributes were analyzed, by setting the ratio of steel-rebar quantity(Ratio: ton/Concrete_㎥) as the dependent variable.

Proteomics may help to detect subtle pollution-related changes, such as responses to mixture pollution at low concentrations, where clear signs of toxicity are absent. Also proteomics provide potential in the discovery of new sensitive biomarkers for environmental pollution. We utilized SELDI-TOF MS (surface enhanced laser desorption. / ionization time-of-flight mass spectrometry) to analyze the proteomic profile of Heterocypris incongruens exposed to several heavy metals (lead, mercury, copper, cadmium and chromium) and pesticides (emamectin benzoate, endosulfan, cypermethrin, mancozeb and paraquat dichloride). Several highly significant biomarkers were selected to make a model of classification analysis. data sets obtained from H. incongruens exposed to pollutants were investigated for differential protein expression by SELDI-TOF MS and decision tree classification. Decision tree model was developed with training set, and then validated with test set from profiling data of H. incongruens. Machine learning techniques provide a promising approach to process the information from mass spectrometry data. Even thought the identification of protein would be ideal, class discrimination does not need it. In the future, this decision tree model would be validated with various levels of pollutants to apply field samples.

본 연구는 불특정 다수의 도로이용자들이 경로우회 시 갖는 의사결정과정속에 내포된 비선형성과 불확실성을 고려한 정도 있는 모형구축으로 주요 우회결정요인을 분석하는 것이 주요 목적이다. 이를 위하여 고속도로 및 국도를 이용하는 운전자를 대상으로 우회여부에 관련된 SP조사를 실시하였고, 조사결과에 대하여 의사결정나무와 신경망이론의 결합된 모형을 구축하여 운전자 우회결정요인을 분석하였다. 분석결과 운전자 우회여부결정에 영향을 미치는 요인은 우회도로 인지여부, 교통정보 신뢰도 및 이용빈도, 경로전환빈도, 나이순으로 나타났다. 또한 오분류표를 통한 기존 모형과의 예측력의 비교결과 결합된 모형의 오분류율이 8.7%로 기존 모형인 로짓모형 12.8%, 의사결정나무 단독 모형 13.8%와 비교했을 때 가장 예측력이 높은 것으로 나타나 운전자 우회결정요인 분석에 관한 모형의 적용 타당성을 확인할 수 있었다. 본 연구의 결과는 향후 교통량 분산효과와 도로망 효율 증대를 위한 효과적인 우회관리전략 수립 시 기초 자료로 활용가능하리라 사료된다.

This paper proposes a methodology to measure the risk level in real-time for Business Activity Monitoring (BAM). A decision-tree methodology was employed to analyze the effect of process attributes on the result of the process execution. In the course of