• Smart Structures and Systems
• /
• v.24 no.6
• /
• pp.723-732
• /
• 2019

Globally road transport networks are subjected to continuous levels of stress from increasing loading and environmental effects. As the most popular mean of transport in the UK the condition of this civil infrastructure is a key indicator of economic growth and productivity. Structural Health Monitoring (SHM) systems can provide a valuable insight to the true condition of our aging infrastructure. In particular, monitoring of the displacement of a bridge structure under live loading can provide an accurate descriptor of bridge condition. In the past B-WIM systems have been used to collect traffic data and hence provide an indicator of bridge condition, however the use of such systems can be restricted by bridge type, assess issues and cost limitations. This research provides a non-contact low cost AI based solution for vehicle classification and associated bridge displacement using computer vision methods. Convolutional neural networks (CNNs) have been adapted to develop the QUBYOLO vehicle classification method from recorded traffic images. This vehicle classification was then accurately related to the corresponding bridge response obtained under live loading using non-contact methods. The successful identification of multiple vehicle types during field testing has shown that QUBYOLO is suitable for the fine-grained vehicle classification required to identify applied load to a bridge structure. The process of displacement analysis and vehicle classification for the purposes of load identification which was used in this research adds to the body of knowledge on the monitoring of existing bridge structures, particularly long span bridges, and establishes the significant potential of computer vision and Deep Learning to provide dependable results on the real response of our infrastructure to existing and potential increased loading.

• Journal of the Korean Society for information Management
• /
• v.18 no.3
• /
• pp.285-309
• /
• 2001

The industry information grows faster than any other information resources in the Internet age. Unfortunately, however, there is no consensus on the standard of the classification among the information providers of the industry fields. This may a problematic issue not only in building a continuous and systematic development of the industry information, but also in the use of the information among the users. This study aims to propose a well-structured and/or an efficient classification scheme for the industry information to help the users with easy to retrieve the Internet resources. To do this, we analyzed the subject classification scheme of the domestic industry information on the web sites, which is largely adopted the \"Korean Standard for the Industry Classification\". In addition, we suggested the principle of the subject classification and their hierarchial structure derived from the analysis of the knowledge and document classification scheme. As a result, it was suggested an optimized industry classification scheme based on the analysis of the validity test of classification item measured by the quantitative analysis of the industry information, which it currently accessible through the Internet. Internet.

• ETRI Journal
• /
• v.37 no.2
• /
• pp.222-232
• /
• 2015

In this paper, we propose a dual-phase approach to improve the process of heart disease prediction in a mobile environment. Firstly, only the confident frequent rules are extracted from a patient's clinical information. These are then used to foretell the possibility of the presence of heart disease. However, in some cases, subjects cannot describe exactly what has happened to them or they may have a silent disease - in which case it won't be possible to detect any symptoms at this stage. To address these problems, data records collected over a long period of time of a patient's heart rate variability (HRV) are used to predict whether the patient is suffering from heart disease. By analyzing HRV patterns, doctors can determine whether a patient is suffering from heart disease. The task of collecting HRV patterns is done by an online artificial neural network, which as well as learning knew knowledge, is able to store and preserve all previously learned knowledge. An experiment is conducted to evaluate the performance of the proposed heart disease prediction process under different settings. The results show that the process's performance outperforms existing techniques such as that of the self-organizing map and gas neural growing in terms of classification and diagnostic accuracy, and network structure.

• Journal of the Korean Society for information Management
• /
• v.20 no.3
• /
• pp.277-297
• /
• 2003

This study was conducted upon the premise that index terms display the intellectual structure of a specific subject field. In this study, and attempt was made to grasp the intellectual structure of Library and Information. Science by clustering the index terms of the journals of the related academic societies at the Library of National Assembly - such as the Journal of the Korean Society for Information Management, the Journal of the Korean Library and Information Science Society, and the Journal of the Korean Society for Library and Information Science. Through the course of the study, index term clusters were generated based on the linkage of the index terms and the frequency of co-occurrence, and moreover, time periods analysis was conducted along with studies on first-appearing terms, in order to clarify the trend and development process of the Library and Information Science. This study also analysed the difference between two intellectual structure by comparing the structure generated by index term clusters with the existing structure of traditional classification systems.

• Journal of Korea Technology Innovation Society
• /
• v.11 no.1
• /
• pp.91-117
• /
• 2008

The relationships between science, technology, and industry are very complicated and vary according to time. Thus, it would be almost impossible to combine the three categories in a single model. However, the linking of science, technology, and industry, which are divided according to their respective classification standards, is a starting point from which to understand how science and technology, technology and industry, and further science, technology, and industry are related to each other. Studies have been carried out to analyze the relationship between science and technology and between technology and industry, whereas no study has been undertaken to get an overall view of science, technology, and industry. Since an appropriate methodology or an analytical model has not been suggested, this paper proposes a model for generally analyzing science, technology, and industry. More specifically, this paper examines the methodology for linking science, technology, and industry. This paper uses citation analysis to analyze knowledge flow such as absorption and utilization of given knowledge, looks at the provision of knowledge to create new knowledge, and examines the use of network analysis to analyze the complicated phenomenon of knowledge flow. This paper proposes an empirical study of trend analysis of technological innovation by looking into a linkage structure of knowledge flow among science, technology, and industry based on the classification linkage and analysis methodology using scientific paper and patents.

• Journal of Korean Biological Nursing Science
• /
• v.2 no.1
• /
• pp.1-19
• /
• 2000

The purpose of this study was to define the content of the requisite knowledge of pathophysiology, clinical microbiology, and mechanisms and effects of drugs needed for clinical knowledge for nursing practice. Contents of knowlege on pathological physiology, clinical microbiology, and mechanisms and effects of drugs were constructed from syllabus of basic nursing subjects in 4 colleges of nursing, and textbooks. The degree of need of 72 items was measured with a 4 point scale. The subjects of this study were college-graduated 136 nurses from seven university hospital in Seoul and three in Chonnam Province, Kyungbook Province, and Inchon. They have been working at internal medicine ward, surgical ward, intensive care unit, obstetrics and gynecology ward, pediatrics ward, opthalmology ward, ear, nose, and throat ward, emergency room, rehabilitation ward, cancer ward, and hospice ward. The results were as follows : 1. The highest scored items of the knowledge of pathophysiology, clinical microbiology, and mechanisms and effects of drugs necessary for nursing practice were side effects of drugs, anticoagulants, mechanisms of drugs, antihypertensive drugs, tolerance and addiction of drugs, interactions among drugs, hospital infection in the order of importance. The lowest scored item was structure of microorganisms. 2. The highest order of need according to unit was repair in tissue injury unit, definition etiology classification of inflammation in inflammation unit, transplantation and immunologic response in alterations in immunity unit, thrombus and thrombosis in disorders of cardiovascular function unit, gene disorders in genetic disorders unit, hospital infection in infection unit, virus in microorganisms unit, side reactions of drugs in introduction unit, anticonvulsants in drugs for central nervous system unit, local anesthesia in anesthesia unit, anticoagulants in drugs for cardiovascular system unit, anti-inflammatory drugs in antibiotics unit, anti-ulcer drugs in drugs for digestive system unit, and bronchodilators in drugs for respiratory system unit. 3. The common content of the knowledge of pathophysiology, clinical microbiology, and mechanisms and effects of drugs needed for all clinical areas in nursing were side effects of drugs, anticoagulants, interactions among drugs, and hospital infection. However, the degree of need of each pathological physiology, clinical microbiology, clinical microbiology, and mechanisms and effects of drugs was different depending on clinical areas. 4. Significant differences in the knowledge of pathophysiology, clinical microbiology, and mechanisms and effects of drugs necessary for nursing practice such as tissue changes due to injurious stimuli, degenerative changes of tissue, alterations in metabolism of carbohydrates, ischemia, hyperemia and congestion, hospital infection, structure of microorganism, classification of microorganism, bacteria, virus, antidepressants, antipsychotic drugs, antiemetic drugs, antiparkinsonism drugs, antianxiety drugs, antibiotics, tuberculostatics, antiviral drugs, antifungal drugs, parasiticides, antiulcer drugs, antidiarrheais, and anti constipation drugs were shown according to the work area. 5. Significant differences in the knowledge of pathophysiology, clinical microbiology, and mechanisms and effects of drugs necessary for nursing practice such as transplantation and immunologic response, alterations in the metabolism of uric acid, structure of microorganism, classification of microorganism, immunosuppressants, drugs for congestive heart failure were demonstrated according to the duration of work. Based on these findings, all the 72 items constructed by Korean Academic Society of Basic Nursing science should be included as contents of the knowledge of pathophysiology, clinical microbiology, and mechanisms and effects of drugs.

• Journal of Intelligence and Information Systems
• /
• v.11 no.1
• /
• pp.65-93
• /
• 2005

Expert system implementation of human expert's diagnosis in art psychotherapy requires extensive knowledge on: (1) characteristics in a drawing; (2) psychological symptoms in a client; (3) relationships between the characteristics and the symptoms; (4) decision process; (5) knowledge elicitation and aquisition methods. Experts from many different fields provide such knowledge, ranging from art therapists who is on the spot, psychiatrists, psychologists, artists to knowledge engineers who know how to implement the decision system to a computer. The problems that make the implementation difficult are the expert's complex decision process and the ambiguity, the inconsistency and even the contradiction in the huge volume of the knowledge. Modeling the expert's decision process, we develope a framework of the system and then analyze and classify the knowledge. With the proposed classification, we present a suitable method of knowledge elicitation and aquisition. Then, we describe the subsets of knowledge in a unified structure using the ontology concept and Protege 2000 as a tool. Finally, we apply the system to a real case to show its usability and suitability.

• 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 Institute of Rural Architecture
• /
• v.16 no.1
• /
• pp.119-127
• /
• 2014

This study suggests institutional and methodological approaches for preservation of South Korea's registered cultural properties of modern architecture. The suggested approaches are as follows. First, in order to improve the current registration and preservation system for cultural properties, we need to employ both structure-based classification and style-based classification. Registration criteria for modern architecture properties need to include more detailed classification in terms of their structure: brick structure, steel concrete structure and post lintel structure. In terms of construction style, the properties need to be further classified into the western style, the traditional style and the Korean-western eclectic style. In addition, protection of registered cultural properties need to be achieved through legislation of a protection system. Second, while the current system sets out six methods for preservation of registered cultural properties of modern architecture, more specific preservation methods types and plans need to be continuously introduced. In particular, as for the method of partial preservation, the method needs to be further classified based on the usage of the relevant structure so as to allow for more diverse options. First, the 'Preservation by Interior Alteration' needs to be added to the category, where the exterior is preserved as it is and the interior is preserved through alteration. Also needs to be added the preservation method where the interior space is preserved as it is and the exterior space is altered, in case the finishing materials of the exterior has deteriorated. Third, if the records on registered cultural properties of modern architecture are to provide the functions of legal evidences regarding management of architectural cultural properties, sources of knowledge required for policy making and implementation and past management record for the future, each phase needs to be closely connected in an organic manner, and we need to establish a management system and plan that go beyond the relevant organizations. Fourth, in order to preserve South Korea's registered cultural properties of modern architecture in its original state, it is imperative to prepare separate criteria for registration of technicians with expertise on modern architecture, and train experts and technicians on modern architecture, which is distinguished from the traditional architecture.

• Journal of Educational Research in Mathematics
• /
• v.22 no.4
• /
• pp.495-515
• /
• 2012

This study is to diversely analyze teachers' Pedagogical Content Knowledge (PCK) regarding to the area of plane figures and discuss the consideration for the materialization of the effective class in learning the area of plane figures by identifying the improvements based on problems indicated in PCK. The subjects of inquiry are what the problems with teachers' PCK regarding to the area of plane figures are and how they can be improved. In which is the first domain of PCK, teachers need to fully understand the concept of the area and the properties and classification of the area and length, recognized the sequence structure as a subject of guidance and improve the direction which naturally connects the flow of measurement by using random units in guidance of the area. In which is the second domain of PCK, teachers need to establish understanding of the concept for the area and understanding of a formula as a subject matter object and improve the activity, discovery and research oriented class for students as a guidance method by escaping from teacher oriented expository class and calculation oriented repetitive learning. They also need to avoid the biased evaluation of using a formula and evenly evaluate whether students understand the concept of the area as a performance evaluation method. In which is the third domain of PCK, teachers need to fully understand the concept of the area rather than explanation oriented correction and fundamentally teach students about errors by suggesting the activity to explore the properties of the area and length. They also need to plan a method to reflect student's affective aspects besides a compliment and encouragement and apply this method to the class. In which is the fourth domain of PCK, teachers need to increase the use of random units by having an independent consciousness about textbooks and supplementing the activity of textbooks and restructure textbooks by suggesting problematic situations in a real life and teaching the sequence structure. Also, class groups will need to be divided into an entire group, individual group, partner group and normal group.