• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.23-45
• /
• 2020

Big data is creating in a wide variety of fields such as medical care, manufacturing, logistics, sales site, SNS, and the dataset characteristics are also diverse. In order to secure the competitiveness of companies, it is necessary to improve decision-making capacity using a classification algorithm. However, most of them do not have sufficient knowledge on what kind of classification algorithm is appropriate for a specific problem area. In other words, determining which classification algorithm is appropriate depending on the characteristics of the dataset was has been a task that required expertise and effort. This is because the relationship between the characteristics of datasets (called meta-features) and the performance of classification algorithms has not been fully understood. Moreover, there has been little research on meta-features reflecting the characteristics of multi-class. Therefore, the purpose of this study is to empirically analyze whether meta-features of multi-class datasets have a significant effect on the performance of classification algorithms. In this study, meta-features of multi-class datasets were identified into two factors, (the data structure and the data complexity,) and seven representative meta-features were selected. Among those, we included the Herfindahl-Hirschman Index (HHI), originally a market concentration measurement index, in the meta-features to replace IR(Imbalanced Ratio). Also, we developed a new index called Reverse ReLU Silhouette Score into the meta-feature set. Among the UCI Machine Learning Repository data, six representative datasets (Balance Scale, PageBlocks, Car Evaluation, User Knowledge-Modeling, Wine Quality(red), Contraceptive Method Choice) were selected. The class of each dataset was classified by using the classification algorithms (KNN, Logistic Regression, Nave Bayes, Random Forest, and SVM) selected in the study. For each dataset, we applied 10-fold cross validation method. 10% to 100% oversampling method is applied for each fold and meta-features of the dataset is measured. The meta-features selected are HHI, Number of Classes, Number of Features, Entropy, Reverse ReLU Silhouette Score, Nonlinearity of Linear Classifier, Hub Score. F1-score was selected as the dependent variable. As a result, the results of this study showed that the six meta-features including Reverse ReLU Silhouette Score and HHI proposed in this study have a significant effect on the classification performance. (1) The meta-features HHI proposed in this study was significant in the classification performance. (2) The number of variables has a significant effect on the classification performance, unlike the number of classes, but it has a positive effect. (3) The number of classes has a negative effect on the performance of classification. (4) Entropy has a significant effect on the performance of classification. (5) The Reverse ReLU Silhouette Score also significantly affects the classification performance at a significant level of 0.01. (6) The nonlinearity of linear classifiers has a significant negative effect on classification performance. In addition, the results of the analysis by the classification algorithms were also consistent. In the regression analysis by classification algorithm, Naïve Bayes algorithm does not have a significant effect on the number of variables unlike other classification algorithms. This study has two theoretical contributions: (1) two new meta-features (HHI, Reverse ReLU Silhouette score) was proved to be significant. (2) The effects of data characteristics on the performance of classification were investigated using meta-features. The practical contribution points (1) can be utilized in the development of classification algorithm recommendation system according to the characteristics of datasets. (2) Many data scientists are often testing by adjusting the parameters of the algorithm to find the optimal algorithm for the situation because the characteristics of the data are different. In this process, excessive waste of resources occurs due to hardware, cost, time, and manpower. This study is expected to be useful for machine learning, data mining researchers, practitioners, and machine learning-based system developers. The composition of this study consists of introduction, related research, research model, experiment, conclusion and discussion.

• Journal of Korea Port Economic Association
• /
• v.36 no.2
• /
• pp.19-36
• /
• 2020

The bidding phase for logistics outsourcing services is critical for both shippers and logistics companies. According to the logistics bidding phase, the shipper should provide logistics operation information to logistics companies to resolve uncertainty. In addition, the logistics company can win the contract volume that was placed in the bid by expressing their experience and know-how, and proposing to share the risks and benefits of the shipper's logistics operation. Therefore, it is necessary to examine the factors that can be identified during the bidding phase for logistics outsourcing and how these factors affect the satisfaction of logistics outsourcing services. Based on the factors identified in the preceding studies on logistics outsourcing partnership factors and those on logistics outsourcing determinants, a survey was conducted on experts engaged in logistics companies, performing logistics for domestic shippers and analyzed using Smart-PLS. This study presents the following implications. First, in the logistics bidding phase, the shipper should provide its logistics operation information to logistics firms to resolve uncertainties. Details An in-depth explanation of the operation details will be presented via the bidding presentation, and on-site tours of manufacturing plants and logistics centers should also be carried out if necessary. Second, in the bidding phase, logistics companies should appeal through proposals to their competitiveness, such as experience and knowledge of the logistics of the shipper, and also consider alliances with other logistics companies to supplement their insufficient logistics services. Third, logistics companies should make proposals to share profits and risks through logistics outsourcing during the bidding phase, propose accepting risks from environmental uncertainties of the shipper within its capacity to an acceptable extent, and share the benefits of carrying out the shipper's logistics.

• The Korean Journal of Financial Management
• /
• v.24 no.2
• /
• pp.1-40
• /
• 2007

We test a model of investment-cashflow-growth opportunities relationship in order to estimate the sensitivities to investments. In this study, we use a new proxy variable for the value of growth opportunities(hereafter "VGO"), which is based on the seminal papers of M&M(1958:1961:1963) and Lee(2006;2007). The empirical findings on the sensitivities of cashflow and growth opportunities are as follows. First, when the traditional proxy variables for the growth opportunities such as Tobin's Q, MBR and sales growth are included with the new proxy VGO in the estimation, their coefficients are turned out to be insignificant. Second, only the new proxy variable VGO shows a statistically significant positive sensitibity to investment, which can be regarded that the growth opportunities hold the positive influences to investments. Third, the Tobin's Q can be decomposed into three factors such as the value of growth opportunities(VGO), the value of asset-in-place and valuation errors. It turns out that only the VGO shows a statistically significant positive relationship with investment among others. This means that the new variable VGO is a good proxy variable for the growth opportunities in the investment-cashflow sensitivity analysis. In sum, thanks to the above findings in this study, we can say that it will not be proper to choose a proxy variable for the growth opportunities from the traditional set of proxies such as Tobin's Q, MBR, or sales growth rate.

• Investigative Magnetic Resonance Imaging
• /
• v.9 no.2
• /
• pp.109-116
• /
• 2005

Purpose : To determine the usefulness of additional Mn-DPDP MRI for preoperative evaluation of the patients with colorectal cancers by comparison of dual-phase CT scan, Mn-DPDP enhanced MRI and combination of CT and MRI. Materials and Methods : Fifty-three colorectal cancer patients with 92 metastatic nodules underwent dualphase (arterial and portal) helical CT scan and Mn-DPDP MRI prior to surgery. The indication of MRI was presence or suspected of having metastatic lesions at CT scan and/or increased serum carcinoembryonic antigen (CEA) levels (10 ng/mL or more). The diagnosis was established by the combination of findings at surgery, intraoperative ultrasonography, and histopathologic examination. Two radiologists interpreted CT, MRI, and combination of CT-MRI at discrete sessions and evaluated each lesion for location, size, and intrinsic characteristics. The lesions were divided into three groups according to their diameter; 1cm<, 1-2 cm, and >2 cm. Diagnostic accuracy was evaluated using the alternative-free response receiver operating characteristic method. Detection and false positive rate were also evaluated. Results : In the lesions smaller than 1 cm, detection rate of combined CT-MRI was superior to CT or MRI alone (82%, p=0.036). The mean accuracy (Az values) of combined CT and MRI was significantly higher than that of CT in the lesions smaller than 2 cm (1 cm<, p=0.034; 1-2 cm, p=0.045). However, there was no significant difference between MRI and combined CT-MRI. The false positive rate of CT was higher than those of combined CT-MR in the lesions smaller than 1 cm (28%, p=0.023). Conclusion : Additional MRI using Mn-DPDP besides routine CT scan was helpful in differentiating the hepatic lesions (<2 cm) and could improve detection of the small hepatic metastases (<1 cm) from colorectal carcinoma.

• Journal of Food Hygiene and Safety
• /
• v.31 no.1
• /
• pp.15-20
• /
• 2016

Malachite green was measured in 200 freshwater fish collected from local markets in Seoul using HPLC-DAD and LC-MS/MS. LC-MS/MS method was validated by linearity, accuracy, precision and limits of detection and quantification according to the CODEX's recommendation and HPLC-DAD method was applied according to the Food Code. Malachite green levels above the quantification limit of the LC-MS/MS were determined 18.5% (37) but just 1 fish was shown to contain malachite green by HPLC-DAD. Of 83 domestic fish, 21 fish were detected malachite green (25.3%). Of 117 fish from China, just 16 fish were detected malachite green (13.4%). In detection rate by species carp (35.0%), Crucian carp (30.4%), cat fish (28.0%), Korean bull head (23.8%), snake head (20.0%), eel (10.5%) and loach (7.8%) were in order. Especially, fish collected at summer were shown to contain malachite green frequently; the detection rate was 54.8%.

• Food Science of Animal Resources
• /
• v.28 no.2
• /
• pp.232-239
• /
• 2008

The objective of this study is to estimate the shelf-life of Tteokgalbi containing dietary fiber extracted from rice bran by using the predictive microbiology. This Tteokgalbi was made with 0%, 1%, 2%, and 3% dietary fiber. The number of total viable cells, anaerobic, psychrotrophic, and heat-stable bacteria and coliforms was calculated during 15 days of storage under $4{\pm}1^{\circ}C$ and the obtained data was applied to Baranyi function. The evaluation of fitness between predicted and observed data showed that these were matched in a satisfactory way. Heat-stable bacteria was detected lower than <1 log CFU/g and coliforms were not detected during the storage. The changes of total viable cells and psychrotrophic bacteria in Tteokgalbi were increased gradually, but dramatically increased after 3 days of storage. The models of total viable cells and anaerobic bacteria showed very similar growth trends and values of growth parameters each other. The estimated shelf-life of each Tteokgalbi was calculated from the predictive model of total viable cells and the estimated shelf-life was 1.7, 2.3, 2.3, and 2.4 days, respectively. The results suggested that the prediction of bacteria growth could be used to evaluate the microbiological safety and determine the shelf-life of Tteokgalbi as ready-to-eat food in the local market.

• Journal of Korean Society for Geospatial Information Science
• /
• v.8 no.1 s.15
• /
• pp.51-63
• /
• 2000

Dynamic traffic assignment(DTA) has been a topic of substantial research during the past decade. While DTA is gradually maturing, many aspects of DTA still need improvement, especially regarding its formulation and solution algerian Recently, with its promise for In(Intelligent Transportation System) and GIS(Geographic Information System) applications, DTA have received increasing attention. This potential also implies higher requirement for DTA modeling, especially regarding its solution efficiency for real-time implementation. But DTA have many mathematical difficulties in searching process due to the complexity of spatial and temporal variables. Although many solution algorithms have been studied, conventional methods cannot iud the solution in case that objective function or constraints is not convex. In this paper, the genetic algorithm to find the solution of DTA is applied and the Merchant-Nemhauser model is used as DTA model because it has a nonconvex constraint set. To handle the nonconvex constraint set the GENOCOP III system which is a kind of the genetic algorithm is used in this study. Results for the sample network have been compared with the results of conventional method.

• Tuberculosis and Respiratory Diseases
• /
• v.45 no.4
• /
• pp.766-775
• /
• 1998

Background : The prognosis of patients with lung cancer is still poor. Lung cancer exhibits a variable clinical outcome, even in those patients with same stage. Numerous reports suggest that oncogene expression might playa role in explaining the variability of response and survival But many of these reports are still under debate. So we studied the clinical relevance of oncogene expression in Korean lung cancer patients. Immunohistochemistry of p53, erbB-2, CEA expression was performed. Method: From March, 1992 until March, 1997, 120 patients with lung cancer were reviewed. p53, erbB-2, and CEA expression were detected on paraffin-embedded tumor blocks with the use of monoclonal antibodies. The survival and response has correlated with the expressibility of p53, erbB-2, and CEA oncoprotein Results: Overall, the expression rates of p53, erbB-2, and CEA were 33.7%, 59.3%, and 32.6% respectively. Expression rates were not correlated to cell type or stage. Compared with response to chemotherapy, no correlation was found. The expression of p53, erbB-2, or CEA was not correlated with 2-year survival. With simultaneous applications of p53, erbB-2, and CEA, patients with 2 or more expressions also did not show poor response to chemotherapy. Conclusion: We conclude the p53, erbB-2, and CEA expression are clinically less useful in predicting response to chemotherapy or survival.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.29 no.2
• /
• pp.109-120
• /
• 2017

A discounted cost model for preventive maintenance of armor units of rubble-mound breakwaters is mathematically derived by combining the deterioration model based on a discrete-time stochastic process of shock occurrence with the cost model of renewal process together. The discounted cost model of condition-based maintenance proposed in this paper can take into account the nonlinearity of cumulative damage process as well as the discounting effect of cost. By comparing the present results with the previous other results, the verification is carried out satisfactorily. In addition, it is known from the sensitivity analysis on variables related to the model that the more often preventive maintenance should be implemented, the more crucial the level of importance of system is. However, the tendency is shown in reverse as the interest rate is increased. Meanwhile, the present model has been applied to the armor units of rubble-mound breakwaters. The parameters of damage intensity function have been estimated through the time-dependent prediction of the expected cumulative damage level obtained from the sample path method. In particular, it is confirmed that the shock occurrences can be considered to be a discrete-time stochastic process by investigating the effects of uncertainty of the shock occurrences on the expected cumulative damage level with homogeneous Poisson process and doubly stochastic Poisson process that are the continuous-time stochastic processes. It can be also seen that the stochastic process of cumulative damage would depend directly on the design conditions, thus the preventive maintenance would be varied due to those. Finally, the optimal periods and scale for the preventive maintenance of armor units of rubble-mound breakwaters can be quantitatively determined with the failure limits, the levels of importance of structure, and the interest rates.

• Korean Journal of Heritage: History & Science
• /
• v.54 no.4
• /
• pp.260-285
• /
• 2021

This article deals with the current status of investigation of the royal tombs of Baekje (Gongju Songsan-ri Tomb, Buyeo Neungsan-ri Tomb, Iksan Ssangneung) from the Japanese colonial period to the present. A review of the maintenance status is also conducted to see if the survey content was actually reflected in the restoration maintenance of the ruins. First, the structure scale and characteristics of the royal tombs of Baekje during the Woongjin and Sabi periods were identified by examining the survey content organized by period and feature. Through the recent re-excavation survey, it was confirmed that the results of the research during the Japanese colonial period were being verified. Next, before examining the maintenance status of the Baekje royal tombs, related content about maintenance of laws and regulations were extracted to establish the maintenance standards. It was confirmed that the most importance part of maintenance is 'maintenance of the original form' without compromising the authenticity of cultural properties. Based on these criteria, the maintenance status was reviewed. The main part of the burial tomb is located underground, so maintenance is mainly made around the tomb, which is the upper structure. However, most of the original burial mounds have been lost or damaged, so it is difficult to determine their original form. In fact, constant changes in the size and location of tombs from the Japanese colonial period to the present were confirmed in the Songsan-ri and Neungsan-ri tombs, meaning that the current maintenance status is problematic. On the other hand, in the case of Ssangneung, not only are the tombs relatively intact, but there are also few changes in the records, so it seems that maintenance was carried out that preserved the original form of the tombs. Therefore, the maintenance of tombs in the future should be based on 'maintaining the original form', but it is recommended that the 'education and utilization' plan be prepared after determining whether or not to restore the tomb and the degree of restoration.