• Journal of the military operations research society of Korea
• /
• v.33 no.2
• /
• pp.101-113
• /
• 2007

The period of military personnel service will be phased down by 2014 according to 'The law of National Defense Reformation' issued by the Ministry of National Defense. For this reason, the ROK army provides discrimination education to 'newly recruited privates' for more effective individual performance in the on-the-job training. For the training to be more effective, it would be essential to predict the degree of achievements by new privates in the training. Thus, we used data mining techniques to develop a classification model which classifies the new privates into one of two achievements groups, so that different skills of education are applied to each group. The target variable for this model is a binary variable, whose value can be either 'a group of general control' or 'a group of special control'. We developed four pure classification models using Neural Network, Decision Tree, Support Vector Machine and Naive Bayesian. We also built four hybrid models, each of which combines k-means clustering algorithm with one of these four mining technique. Experimental results demonstrated that the highest performance model was the hybrid model of k-means and Neural Network. We expect that various military education programs could be supported by these classification models for better educational performance.

• KIPS Transactions on Computer and Communication Systems
• /
• v.5 no.12
• /
• pp.471-480
• /
• 2016

Recently, the damage of cyber attack toward infra-system, national defence and security system is gradually increasing. In this situation, military recognizes the importance of cyber warfare, and they establish a cyber system in preparation, regardless of the existence of threaten. Thus, the study of Intrusion Detection System(IDS) that plays an important role in network defence system is required. IDS is divided into misuse and anomaly detection methods. Recent studies attempt to combine those two methods to maximize advantagesand to minimize disadvantages both of misuse and anomaly. The combination is called Hybrid IDS. Previous studies would not be inappropriate for near real-time network environments because they have computational complexity problems. It leads to the need of the study considering the structure of IDS that have high detection rate and low computational cost. In this paper, we proposed a Hybrid IDS which combines C4.5 decision tree(misuse detection method) and Weighted K-means algorithm (anomaly detection method) hierarchically. It can detect malicious network packets effectively with low complexity by applying mutual information and genetic algorithm based efficient feature selection technique. Also we construct upgraded the the hierarchical structure of IDS reusing feature weights in anomaly detection section. It is validated that proposed Hybrid IDS ensures high detection accuracy (98.68%) and performance at experiment section.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.11
• /
• pp.126-136
• /
• 2018

The purpose of this study was to develop a severity-adjustment model for predicting mortality in acute stroke patients using machine learning. Using the Korean National Hospital Discharge In-depth Injury Survey from 2006 to 2015, the study population with disease code I60-I63 (KCD 7) were extracted for further analysis. Three tools were used for the severity-adjustment of comorbidity: the Charlson Comorbidity Index (CCI), the Elixhauser comorbidity index (ECI), and the Clinical Classification Software (CCS). The severity-adjustment models for mortality prediction in patients with acute stroke were developed using logistic regression, decision tree, neural network, and support vector machine methods. The most common comorbid disease in stroke patients were hypertension, uncomplicated (43.8%) in the ECI, and essential hypertension (43.9%) in the CCS. Among the CCI, ECI, and CCS, CCS had the highest AUC value. CCS was confirmed as the best severity correction tool. In addition, the AUC values for variables of CCS including main diagnosis, gender, age, hospitalization route, and existence of surgery were 0.808 for the logistic regression analysis, 0.785 for the decision tree, 0.809 for the neural network and 0.830 for the support vector machine. Therefore, the best predictive power was achieved by the support vector machine technique. The results of this study can be used in the establishment of health policy in the future.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.6
• /
• pp.1089-1098
• /
• 2020

In this study, we propose a method to detect red tide Cochlodinium Polykrikoide using by machine learning and geostationary marine satellite images. To learn the machine learning model, GOCI Level 2 data were used, and the red tide location data of the National Fisheries Research and Development Institute was used. The machine learning model used logistic regression model, decision tree model, and random forest model. As a result of the performance evaluation, compared to the traditional GOCI image-based red tide detection algorithm without machine learning (Son et al., 2012) (75%), it was confirmed that the accuracy was improved by about 13~22%p (88~98%). In addition, as a result of comparing and analyzing the detection performance between machine learning models, the random forest model (98%) showed the highest detection accuracy.It is believed that this machine learning-based red tide detection algorithm can be used to detect red tide early in the future and track and monitor its movement and spread.

• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.6
• /
• pp.247-252
• /
• 2015

As software has gotten bigger in magnitude and the complexity of software has been increased, the maintenance has gained in-creasing attention for its significant impact on the cost. Identifiers have an impact on more than 90 percent of the readability which accounts for a majority portion of the maintenance activities. For this reason, the existing works focus on domain-specific features based on identifiers. However, their approaches have a limitation when either a class name does not reflect the intention of its context or a class naming is incorrect. Therefore, this paper suggests a series of class name validation process by extracting properties of classes, building learning model by applying a decision tree technique of machine learning, and generating a validation report containing the list of recommendable postfixes of classes to be validated. To evaluate this, four open source projects are selected and indicators such as precision, recall, and ROC curve present the value of this work when it comes to five specific postfixes including functional information on class names.

• Journal of Information Management
• /
• v.39 no.4
• /
• pp.47-66
• /
• 2008

This study introduced the machine learning algorithms to overcome the many different limitations involved with manual classification and to provide the users with faster and more accurate classification service. The experiments objects of the study were consisted of 100 literature titles for each of the eight subject categories in MeSH. The algorithms used to the experiments included Neural network, C5.0, CHAID and KNN. As results, the combination of the neural network and C5.0 technique recorded classification accuracy of 83.75%, which was 2.5% and 3.75% higher than that of the neural network alone and C5.0 alone, respectively. The number represented the highest accuracy rates among the four classification experiments. Thus the use of the neural network and C5.0 technique together will result in higher accuracy rates than the techniques individually.

• Korea Trade Review
• /
• v.46 no.5
• /
• pp.65-81
• /
• 2021

The technological development in the era of the 4th industrial revolution is changing the paradigm of various industries. Various technologies such as big data, cloud, artificial intelligence, virtual reality, and the Internet of Things are used, creating synergy effects with existing industries, creating radical development and value creation. Among them, the logistics sector has been greatly influenced by quantitative data from the past and has been continuously accumulating and managing data, so it is highly likely to be linked with big data analysis and has a high utilization effect. The modern advanced technology has developed together with the data mining technology to discover hidden patterns and new correlations in such big data, and through this, meaningful results are being derived. Therefore, data mining occupies an important part in big data analysis, and this study tried to analyze data mining techniques that can contribute to the logistics field and common logistics using these data mining technologies. Therefore, by using the AHP technique, it was attempted to derive priorities for each type of efficient data mining for logisticalization, and R program and R Studio were used as tools to analyze this. Criteria of AHP method set association analysis, cluster analysis, decision tree method, artificial neural network method, web mining, and opinion mining. For the alternatives, common transport and delivery, common logistics center, common logistics information system, and common logistics partnership were set as factors.

• Journal of Intelligence and Information Systems
• /
• v.16 no.3
• /
• pp.99-120
• /
• 2010

Due to the wide spread of customers' frequent access of non face-to-face services, there have been many attempts to improve customer satisfaction using huge amounts of data accumulated throughnon face-to-face channels. Usually, a call center is regarded to be one of the most representative non-faced channels. Therefore, it is important that a call center has enough agents to offer high level customer satisfaction. However, managing too many agents would increase the operational costs of a call center by increasing labor costs. Therefore, predicting and calculating the appropriate size of human resources of a call center is one of the most critical success factors of call center management. For this reason, most call centers are currently establishing a department of WFM(Work Force Management) to estimate the appropriate number of agents and to direct much effort to predict the volume of inbound calls. In real world applications, inbound call prediction is usually performed based on the intuition and experience of a domain expert. In other words, a domain expert usually predicts the volume of calls by calculating the average call of some periods and adjusting the average according tohis/her subjective estimation. However, this kind of approach has radical limitations in that the result of prediction might be strongly affected by the expert's personal experience and competence. It is often the case that a domain expert may predict inbound calls quite differently from anotherif the two experts have mutually different opinions on selecting influential variables and priorities among the variables. Moreover, it is almost impossible to logically clarify the process of expert's subjective prediction. Currently, to overcome the limitations of subjective call prediction, most call centers are adopting a WFMS(Workforce Management System) package in which expert's best practices are systemized. With WFMS, a user can predict the volume of calls by calculating the average call of each day of the week, excluding some eventful days. However, WFMS costs too much capital during the early stage of system establishment. Moreover, it is hard to reflect new information ontothe system when some factors affecting the amount of calls have been changed. In this paper, we attempt to devise a new model for predicting inbound calls that is not only based on theoretical background but also easily applicable to real world applications. Our model was mainly developed by the interactive decision tree technique, one of the most popular techniques in data mining. Therefore, we expect that our model can predict inbound calls automatically based on historical data, and it can utilize expert's domain knowledge during the process of tree construction. To analyze the accuracy of our model, we performed intensive experiments on a real case of one of the largest car insurance companies in Korea. In the case study, the prediction accuracy of the devised two models and traditional WFMS are analyzed with respect to the various error rates allowable. The experiments reveal that our data mining-based two models outperform WFMS in terms of predicting the amount of accident calls and fault calls in most experimental situations examined.

• The Journal of Society for e-Business Studies
• /
• v.26 no.3
• /
• pp.97-117
• /
• 2021

Predicting term deposit subscriptions is one of representative financial marketing in banks, and banks can build a prediction model using various customer information. In order to improve the classification accuracy for term deposit subscriptions, many studies have been conducted based on machine learning techniques. However, even if these models can achieve satisfactory performance, utilizing them is not an easy task in the industry when their decision-making process is not adequately explained. To address this issue, this paper proposes an explainable scheme for term deposit subscription forecasting. For this, we first construct several classification models using decision tree-based ensemble learning methods, which yield excellent performance in tabular data, such as random forest, gradient boosting machine (GBM), extreme gradient boosting (XGB), and light gradient boosting machine (LightGBM). We then analyze their classification performance in depth through 10-fold cross-validation. After that, we provide the rationale for interpreting the influence of customer information and the decision-making process by applying Shapley additive explanation (SHAP), an explainable artificial intelligence technique, to the best classification model. To verify the practicality and validity of our scheme, experiments were conducted with the bank marketing dataset provided by Kaggle; we applied the SHAP to the GBM and LightGBM models, respectively, according to different dataset configurations and then performed their analysis and visualization for explainable term deposit subscriptions.

• Journal of Intelligence and Information Systems
• /
• v.19 no.2
• /
• pp.125-140
• /
• 2013

We call a data set in which the number of records belonging to a certain class far outnumbers the number of records belonging to the other class, 'imbalanced data set'. Most of the classification techniques perform poorly on imbalanced data sets. When we evaluate the performance of a certain classification technique, we need to measure not only 'accuracy' but also 'sensitivity' and 'specificity'. In a customer churn prediction problem, 'retention' records account for the majority class, and 'churn' records account for the minority class. Sensitivity measures the proportion of actual retentions which are correctly identified as such. Specificity measures the proportion of churns which are correctly identified as such. The poor performance of the classification techniques on imbalanced data sets is due to the low value of specificity. Many previous researches on imbalanced data sets employed 'oversampling' technique where members of the minority class are sampled more than those of the majority class in order to make a relatively balanced data set. When a classification model is constructed using this oversampled balanced data set, specificity can be improved but sensitivity will be decreased. In this research, we developed a hybrid model of support vector machine (SVM), artificial neural network (ANN) and decision tree, that improves specificity while maintaining sensitivity. We named this hybrid model 'hybrid SVM model.' The process of construction and prediction of our hybrid SVM model is as follows. By oversampling from the original imbalanced data set, a balanced data set is prepared. SVM_I model and ANN_I model are constructed using the imbalanced data set, and SVM_B model is constructed using the balanced data set. SVM_I model is superior in sensitivity and SVM_B model is superior in specificity. For a record on which both SVM_I model and SVM_B model make the same prediction, that prediction becomes the final solution. If they make different prediction, the final solution is determined by the discrimination rules obtained by ANN and decision tree. For a record on which SVM_I model and SVM_B model make different predictions, a decision tree model is constructed using ANN_I output value as input and actual retention or churn as target. We obtained the following two discrimination rules: 'IF ANN_I output value <0.285, THEN Final Solution = Retention' and 'IF ANN_I output value ${\geq}0.285$, THEN Final Solution = Churn.' The threshold 0.285 is the value optimized for the data used in this research. The result we present in this research is the structure or framework of our hybrid SVM model, not a specific threshold value such as 0.285. Therefore, the threshold value in the above discrimination rules can be changed to any value depending on the data. In order to evaluate the performance of our hybrid SVM model, we used the 'churn data set' in UCI Machine Learning Repository, that consists of 85% retention customers and 15% churn customers. Accuracy of the hybrid SVM model is 91.08% that is better than that of SVM_I model or SVM_B model. The points worth noticing here are its sensitivity, 95.02%, and specificity, 69.24%. The sensitivity of SVM_I model is 94.65%, and the specificity of SVM_B model is 67.00%. Therefore the hybrid SVM model developed in this research improves the specificity of SVM_B model while maintaining the sensitivity of SVM_I model.