• 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 the Korean Wood Science and Technology
• /
• v.46 no.1
• /
• pp.48-59
• /
• 2018

This study was conducted to suggest the effective management and recycling processes of coffee waste, which can be easily obtained from coffee shops and coffee-related products industries. Prior to the fabrication of pellets, the potential of coffee waste as a raw material of pellet was investigated through the examination of its chemical compositions and fuel characteristics. Major gradient included in coffee waste was holocellulose, followed by fat/oil and protein. Coffee waste contained a small quantity of ash (0.7%), such as calcium, sodium, potassium and magnesium. Interestingly, coffee waste was easily dried probably due to its porous structure. Pellets fabricated with coffee waste and larch sawdust showed good fuel characteristics, such as moisture content, ash content, density and durability. The pellets exceed greatly the minimum requirements of $1^{st}$-grade wood pellet standard designated by National Institute of Forest Science (NIFOS). Particularly, the high calorific value of coffee waste showed the potential as a raw material of pellet. However, owing to high nitrogen and sulfur contents, coffee waste is like to be used as a raw material of wood pellet for combined heat and power plants equipped with a reduction system of $NO_x$ and $SO_x$ gases. On the other hand, 91 wt% larch sawdust and 9 wt% coffee waste are required to fabricate the $1^{st}$-grade wood pellets designated by NIFOS. Pellets fabricated with the conditions are estimated to have nitrogen content of 0.298% and sulfur content of 0.03%. Lastly, if amounts of coffee waste and sawdust in the production of wood pellets are adequately adjusted according to its purchasing price, the manufacturing cost of pellet can effectively be reduced. In addition, it is expected tp prepare the effective recycling process of waste and to relieve the environmental burden with the reduction of waste from the commercialization of coffee waste/larch pellets.

• Journal of Wetlands Research
• /
• v.18 no.2
• /
• pp.154-165
• /
• 2016

Recently, the frequency of extreme rainfall event has increased due to climate change and impermeable area also has increased due to rapid urbanization. Therefore, we ought to prepare countermeasures for flood reduction to reduce the damage. To consider climate change, the frequency based rainfall was calculated according to the aimed period(reference : 1971~2010, Target period I : 2011~2040, Target period II : 2041~2070, Target period III : 2071~2100) and the flood discharge was also calculated by climate change using HEC-HMS model. Also, the flood elevation was calculated by each alternative through HEC-RAS model, setting 5 sizes of drainage pumps and reservoirs respectively. The flood map was constructed using topographical data and flood elevation, and the economic analysis was conducted for reduction of flood damage using Multi dimension - Flood Damage Analysis, MD-FDA. As a result of the analysis on the flood control effect, a head of drainage pump was reduced by 0.06m up to 0.44m while it was reduced by 0.01m up to 1.86m in the case of a detention pond. The flooded area shrunk by up to 32.64% from 0.3% and inundation depth also dropped. As a result of a comparison of the Benefit/Cost index estimated by the economic analysis, detention pond E in period I and pump D in period II and III were deemed appropriate as an alternative for climate change. The results are expected to be used as good practices when implementing the flood control works considering climate change.

• Membrane Journal
• /
• v.27 no.4
• /
• pp.344-349
• /
• 2017

Alkaline fuel cells using polymer electrolyte membranes are expected to replace proton exchange membrane fuel cells, which have similar system configurations. In particular, in alkaline fuel cells, a low-cost non-platinium catalyst can be used. In this study, to fabricate high performance and high durability anion exchange membranes for alkaline fuel cell systems, two kinds of supports, polybenzoxazole and polyethylene supports, were impregnated with Fumion FAA ionomer, by which we tried to fabricate the support-impregnated membrane which has higher mechanical strength and higher ion conductivity than the Fumion series. Finally, the Pore-filling membranes were successfully fabricated and ionic conductivity and mechanical properties were different depending on the properties of the supports. In the pore-filling membranes with Fumion ionomer on the PE support, excellent mechanical properties were obtained, but ionic conductivity decreased. On the other hand, when the PBO support was impregnated with Fumion ionomer, high ionic conductivity was shown after impregnation due to high basicity of PBO, but the mechanical strength was relatively low as compared with Fumion-PE membrane. As a result, it was concluded that it is necessary to consider the characteristics of the support according to the operating conditions of the alkaline fuel cell during the preparation of the pore-filling membranes.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.21 no.3
• /
• pp.176-188
• /
• 2018

Modern urban problems are increasingly becoming a market mix that can not be solved by the power of a single department and the necessity of establishing a cooperation system based on data communication between departments is increasing. Therefore, this study analyzed Busan metropolitan city's IT projects from 2014 to 2018 in order to understand the utilization and sharing status of departmental data from the viewpoint that cooperation between departments can start from the sharing of data with high common utilization. In addition, based on the results of the FGI(Focus Group Interview) conducted for the officials of the department responsible for the informatization project, we verified the results of data status analysis. At the same time, we figured out the necessity of data link between departments through SNA(Social Network Analysis) and presented data that should be shared first in the future. As a result, most of the information systems currently use limited data only within the department that produced the data. Most of the linked data was concentrated in the information department. Therefore, this study suggested the following solutions. First, in order to prevent overlapping investments caused by the operation of individual departments and share information, it is necessary to build a small platform to tie the departments, which have high connectivity with each other, into small blocks. Second, a local level process is needed to develop data standards as an extension of national standards in order to expand the information to be used in various fields. Third, as another solution, we proposed a system that can integrate various types of information based on address and location information through application of cloud-based GIS platform. The results of this study are expected to contribute to build a cooperation system between departments through expansion of information sharing with cost reduction.

• Management & Information Systems Review
• /
• v.33 no.5
• /
• pp.185-212
• /
• 2014

This study investigated the base of marine leisure facilities and studied the future vision for development of marine industry by conducting a systematic analysis on the category of marine leisure products for development of design and specialization of southeast area of Korea. If the age of $20,000 of per capita national income is called 'the age of my car', $20,000 of per capita national income is called 'the age of my boat'. According to the report of UK-based Marine South East, the scale of world's small boat and personal waterborne equipment reached 277 trillion won in 2010 and domestic market scale is expected to be 11 trillion won. Marine leisure facilities are the new growth engine industry that the government should promote as a nation's strategic and core industry, and the government is pushing ahead with promotion of marine industry actively by announcing Marine Leisure Equipment Industry Activation Plan(June 2009, Ministry of Knowledge Economy), Marine Leisure Activation Plan(July 2010, Ministry of Land, Infrastructure and Transport), The 1st General Plan for Marina Port(January 2010, Ministry of Land, Infrastructure and Transport) etc. The purpose of marine design lies in seeking the status of the country and qualitative value in human life through functional, artistic, industrial and cultural development of design elements for all marine activities made around the sea. Related to all activities made in the ocean and cost, marine design is a sphere of design that includes special conditions centering around water. Considering the condition that 3 sides of land are facing the sea, this study systematically analyzed present condition of equipment possessed by each area, type of facilities, operational status, current status of sectoral use of marine leisure facilities and future prospect of marine leisure products that become the basis of value to raise the statue as an advanced marine power in 2010s through development of the qualitative level of the people, establishment of the direction of national strategy, convergence of industry and culture and specialization of area focusing on the actual condition survey of marine leisure facilities. Especially, this study will be predicting the basis of strategy for strengthening marketability and competitiveness by suggesting role and process of design in developing a promising marine leisure product through an actual condition survey of marine leisure products of southeast area.

• Journal of Family Resource Management and Policy Review
• /
• v.17 no.4
• /
• pp.19-37
• /
• 2013

From the perspective of labor welfare, forty-hour-a-week working system:(FWS) has been an important goal throughout world, and in fact, advanced countries implemented this a long time ago. However, there are differences in opinions concerning FWS; some people emphasizes the improvement in life quality, while others point out that this measure increases the cost of wages and has limited effectiveness. Thus, discussions about the success of FWS have emerged from diverse perspectives; One thing that should be made clear before debating FWS is that reducing laborers' working hours is already a global trend, and Korea, also intends to extend it. Therefore, in order to maximize the benefits resulting from the execution of the system and to identify measures that can be used to solve the problems related to FWS, it is necessary to consider actual laborers' use of leisure resources and whether they have increased or decreased as a result of FWS. It is also necessary to look at the differences in workers' leisure activity with and without the system. To evaluate and diagnose FWS's political effect from the perspective of laborers' leisure satisfaction and improvements in life quality, this study examines differences in leisure expenses, leisure hours, use of and demand for leisure resources such as leisure space, and types of leisure activity, according to the execution of FWS, This research is based on the "2012 Survey on National Leisure Activity" conducted by the Ministry of Culture, Sports and Tourism. In addition, through analysis of the differences in leisure satisfaction and happiness levels, the study intends to confirm the necessity of executing FWS and ensuring that the system is in use. The study results can be briefly summed up as followa:: First, regarding the general findings of the study, a significant result was shown in terms of the execution of FWS according to income level. The finding that the execution of FWS works differently according to the working environment or life quality reassures us of the common notion in society that working environment or life quality may differ in relation to social characteristics. The utility of weekday leisure hours did not indicate a statistically significant difference, but in terms of weekend leisure hours, laborers practicing FWS had an additional 30 minutes of leisure time than those who did not. Furthermore, regarding leisure expenses, laborers practicing FWS indicated more monthly average leisure expenses or expected leisure expenses. In relation to leisure activity, those working at a company executing FWS engaged in culture and art activities more frequently than those working at the companies that did not. On the other hand, those working at companies without FWS indicated more hobbies, amusement activities, rest, and other activities than those working at the companies with FWS. In terms of vacation experience, those working at companies with FWS had more vacation time than those working at companies without it; on average, they had longer vacations by 1.64 days. Regarding their leisure life satisfaction and happiness level, those working at companies with FWS indicated higher satisfaction and greater happiness than those working at companies without it. The findings mentioned above represent the preliminary results of this paper, and the remainder of the research will provide more detailed analysis results and suggestions corresponding to them.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.243-264
• /
• 2018

Although the worldwide battery market is recently spurring the development of lithium secondary battery, lead acid batteries (rechargeable batteries) which have good-performance and can be reused are consumed in a wide range of industry fields. However, lead-acid batteries have a serious problem in that deterioration of a battery makes progress quickly in the presence of that degradation of only one cell among several cells which is packed in a battery begins. To overcome this problem, previous researches have attempted to identify the mechanism of deterioration of a battery in many ways. However, most of previous researches have used data obtained in a laboratory to analyze the mechanism of deterioration of a battery but not used data obtained in a real world. The usage of real data can increase the feasibility and the applicability of the findings of a research. Therefore, this study aims to develop a model which predicts the battery deterioration using data obtained in real world. To this end, we collected data which presents change of battery state by attaching sensors enabling to monitor the battery condition in real time to dozens of golf carts operated in the real golf field. As a result, total 16,883 samples were obtained. And then, we developed a model which predicts a precursor phenomenon representing deterioration of a battery by analyzing the data collected from the sensors using machine learning techniques. As initial independent variables, we used 1) inbound time of a cart, 2) outbound time of a cart, 3) duration(from outbound time to charge time), 4) charge amount, 5) used amount, 6) charge efficiency, 7) lowest temperature of battery cell 1 to 6, 8) lowest voltage of battery cell 1 to 6, 9) highest voltage of battery cell 1 to 6, 10) voltage of battery cell 1 to 6 at the beginning of operation, 11) voltage of battery cell 1 to 6 at the end of charge, 12) used amount of battery cell 1 to 6 during operation, 13) used amount of battery during operation(Max-Min), 14) duration of battery use, and 15) highest current during operation. Since the values of the independent variables, lowest temperature of battery cell 1 to 6, lowest voltage of battery cell 1 to 6, highest voltage of battery cell 1 to 6, voltage of battery cell 1 to 6 at the beginning of operation, voltage of battery cell 1 to 6 at the end of charge, and used amount of battery cell 1 to 6 during operation are similar to that of each battery cell, we conducted principal component analysis using verimax orthogonal rotation in order to mitigate the multiple collinearity problem. According to the results, we made new variables by averaging the values of independent variables clustered together, and used them as final independent variables instead of origin variables, thereby reducing the dimension. We used decision tree, logistic regression, Bayesian network as algorithms for building prediction models. And also, we built prediction models using the bagging of each of them, the boosting of each of them, and RandomForest. Experimental results show that the prediction model using the bagging of decision tree yields the best accuracy of 89.3923%. This study has some limitations in that the additional variables which affect the deterioration of battery such as weather (temperature, humidity) and driving habits, did not considered, therefore, we would like to consider the them in the future research. However, the battery deterioration prediction model proposed in the present study is expected to enable effective and efficient management of battery used in the real filed by dramatically and to reduce the cost caused by not detecting battery deterioration accordingly.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.39 no.6
• /
• pp.98-109
• /
• 2011

Habitat restoration initiative is an important factor for the on-site preservation of butterflies. A new habitat necessitates the investigation of the ecology of the butterfly, the landscape of the habitat, the work process, and a cost analysis. In this study, these factors were analyzed through1) re-consideration of the secured results from three years of field work, and 2) a habitat area estimation conducted according to the presence or absence of larvae and adults via a Parnassius bremeri Bremer survey. The investigation of the natural habitat, done for both larvae and adult butterflies found in South Korea, suggested that multiple patches with a minimum size exceeding $300m^2$ and with an average size of about $1,600m^2$were required for survival of this butterfly. Therefore, more than five patches should be considered for butterfly habitat and patches should have similarity to the present habitat environment with transplantation plans for diet plants and honeydew plants. In addition, to activate the migration of the butterfly, cutting down trees that are obstacles to migration, minimizing the distance between patches and the addition of a stepping patch are also required. A patch connectivity analysis showed that patches should be located within 300m of neighboring patches, as the migration of the butterfly will fail if it is more than 600m. Additionally, more than $10,000m^2$ for a single patch or a patch network composed more than five patches over $1,600m^2$ in size were recommended, with a total patch size of $8,000m^2$. Additionally, neighboring multiple patch networks are more desirable than a single habitat in the event a cyclic habitat pattern arises. In this study, we suggest a habitat restoration and optimal prerequisites for a butterfly habitat. It is expected that this research will lead to the creation of a good model for the restoration of butterfly species.

• Tuberculosis and Respiratory Diseases
• /
• v.55 no.1
• /
• pp.59-68
• /
• 2003

Background : In intubated patients, cultures of endotracheal aspirates (EA) are apt to contamination throughout the endotracheal tube. Therefore, the identification of etiologic agents via conventional EA cultures is not always reliable. In order to differentiate a pulmonary infection from a non-infectious disease, and to identify the true etiologic agent of acute pulmonary infection, blinded protected specimen brushing (PSB) was used, and its efficacy evaluated. Methods : In 51 intubated patients, with suspected pneumonia, blind PSB were performed, and the results compared with blood and EA cultures. A protected specimen brush was introduced through the endotracheal tube, and settled at the affected large bronchus. A specimen brush was introduced to the expected region using the blind method. The tip of the brush was introduced with an aseptic technique after vigorously mixed for 1 minute in $1cm^3$ of Ringer's lactate solution. The specimens were submitted for quantitative culture within 15 minutes, with a culture being regarded as positive if the colony forming units were above $10^3/ml$. Results : Of the 51 patients, 15 (29.4%) had community-acquired pneumonia (CAP), 27 (52.9%) hospital-acquired pneumonia (HAP) and 9 (17.6%) non-infectious diseases. The sensitivity and specificity of the quantitative PSB culture for the diagnosis of pneumonia were 52.4 and 88.9%, respectively. The sensitivity and specificity of EA were 78.6 and 77.8%, respectively. The blind PSB was superior to the EA for the identification of true etiologic agents. Of 53 episodes of 27 HAP patients, MRSA (Methicillin-resistant staphylococcus aureus) (41.5%) was the most common causative agent followed by Pseudomonas aeruginosa (15.1%), Klebsiella sp. (7.5%) and Acinetobacter sp. (7.5%). Conclusions : As a simple, non-invasive diagnostic modality, the blind PSB is a useful method for the differentiation of a pulmonary infection from non-infectious diseases and to identify the etiologic agents in intubated patients. A blind PSB can be performed without bronchoscopy, so is safer, more convenient and cost-effectiveness for patients where bronchoscopy can not be performed.