• Journal of Korea Society of Digital Industry and Information Management
• /
• v.13 no.4
• /
• pp.91-98
• /
• 2017

Previous works for detecting arrhythmia have mostly used nonlinear method such as artificial neural network, fuzzy theory, support vector machine to increase classification accuracy. Most methods require higher computational cost and larger processing time. Therefore it is necessary to design efficient algorithm that classifies PVC(premature ventricular contraction) and decreases computational cost by accurately detecting minimal feature point based on only R peak through optimal R wave. We propose an optimal R wave detection and PVC classification method through extracting minimal feature point in IoT environment. For this purpose, we detected R wave through optimal threshold value and extracted RR interval and R peak pattern from noise-free ECG signal through the preprocessing method. Also, we classified PVC in realtime through RR interval and R peak pattern. The performance of R wave detection and PVC classification is evaluated by using record of MIT-BIH arrhythmia database. The achieved scores indicate the average of 99.758% in R wave detection and the rate of 93.94% in PVC classification.

• Journal of KIISE:Computing Practices and Letters
• /
• v.9 no.3
• /
• pp.301-310
• /
• 2003

In this paper, we design and Implement the supervised classification systems for high resolution satellite images. The systems support various interfaces and statistical data of training samples so that we can select the m()st effective training data. In addition, the efficient extension of new classification algorithms and satellite image formats are applied easily through the modularized systems. The classifiers are considered the characteristics of spectral bands from the selected training data. They provide various supervised classification algorithms which include Parallelepiped, Minimum distance, Mahalanobis distance, Maximum likelihood and Fuzzy theory. We used IKONOS images for the input and verified the systems for the classification of high resolution satellite images.

• The Journal of the Society of Korean Medicine Diagnostics
• /
• v.12 no.2
• /
• pp.27-40
• /
• 2008

Background : In spite of the predominant of the theory of Pathogenesis, the method of Pathogenesis classification is depending on the doctor's clinical trials because od the lack of the objective test criteria. Methods and Results : This study is trying to improve the objectiveness of classification using a new statistical method, decision tree. Decision tree method -a classification technique in the statistical analysis- was used to analyze the result of pathogenesis questionnaire instead of using discriminant analysis. As a result, 10 among 38 pathogenesis questionnaire was selected as important questions and 12 terminal nodes was built to classify the pathogenesis. Conclusions : Using only 10 questions shown in the result of decision tree, we can classify and interpret the pathogenesis easily and effectively.

• Journal of the Korean Society for Library and Information Science
• /
• v.14
• /
• pp.19-65
• /
• 1987

Library classification schedule IS based on the classification theory, principle and the system of the classification of science. It should be consisted of the basic principle of library classification which should use the library materials effectively. Continuous study and research on the each subject field of the discipline are essential for keeping up with the transformation of each learning field and the change of modern society. In this paper, I studied comparatively the sections and subsections of the management in KDC, DDC and NDC and reviewed the academic systems of each subject area in the management. I tried to compare the relationship beween the structure of library classifications and academic systems for the more specialized subsections of the management. KDC is influenced by the principle and structure of DDC, but I found that KDC is more similar to NDC than DDC in the sections and subsections of the management. Being un sufficient of subsections of KDC and NDC, they are not enough for the expansion and specialization of the subsections in the management. DDC is necessary to re-schedule for the proper expansion of 650 and 658 with reflection of the importance of that sections and academic systems. In this study, I adoped 9 sections of management, (1) Management policy (2) Administrative organization (3) Personnel (4) Office management and business information management (5) Marketing (6) Financial management (7) Production management (8) Accounting (9) International management. It would be necessary for us to study continuously about the specilized subsubsections of the management for the more professional classification.

• Geotechnical Engineering
• /
• v.11 no.2
• /
• pp.71-78
• /
• 1995

In this paper, a study was performed on classifying a rock mass into multiple classes as in rock mass classification systems, such as RMR system and Q system etc. In a situation with only limited quantitative data available, it was sought to employ a way of incorporating qualitative data in a systematical and reasonable manner. It is based on the realm of Geostatistics. In particular, indicator kriging technique, which is one of non-parametric approaches, was used. As a selection criterion for an optimal classification, the cost of errors was adopted. As a result, the binary rock classification method developed before was extended and generalized for multiple rock classification with its total number of classes unlimited.

• The KIPS Transactions:PartB
• /
• v.19B no.4
• /
• pp.231-236
• /
• 2012

According to consumer behavior theory, human propensity can be divided into two regulatory focus types: promotion and prevention. These two types have much influence on the consumer's decision in many diverse areas. In this research, we apply regulatory focus theory to personalized recommendation to minimize the cold start problem and to improve the performance of recommendation algorithms. To achieve this goal, we extract the consumer behavior variables and information exploration activity index from web shopping logs. We then use them for classifying regulatory focus of the consumer. This research has the contribution to show the possibility of systematization of consumer behavior theory as an interdisciplinary research tool of social science and information technology. Based on this attempt, we will extend the research to IT services adapting theories on other areas.

• The Journal of Churna Manual Medicine for Spine and Nerves
• /
• v.4 no.2
• /
• pp.211-223
• /
• 2009

Objectives : The aim of this research is to analyze the current trend of the studies about eridian muscle and to provide background for further studies. Methods : Reviewing 33 domestic oriental medical studies about meridian muscle, and comparative analysis was made. These studies were classified by method, theme and subtitle. Results : 1. According to the classification by study method, number of literary studies are 22(67%), which is more than half, number of experimental studies are 5(15%) and clinical studies are 6(18%). 2. According to the classification by study theme in literary study, percentage of 'Structure amp; Movement of Meridian Muscle' took 64%, Theory study of Meridian Muscle' took 14%, 'Application of Concept of Meridian Muscle' took 14%, 'Treatment of Meridian Muscle disorder' took 9% arranged in order. 3. In 'Theory study of Meridian Muscle', there were not only literary approaches but also Deficiency-Excessiveness(虛實) and historical approaches. Study about 'Structure & Movement of Meridian Muscle' includes analysis of muscle and Myofascial pain syndrome. On this background, it is necessary to recognize the linkage and motion analysis of Meridian Muscle. Therefore, studies were changed into interpretation about Anatomy trains, analysis of motion. The study about 'Treatment of Meridian Muscle disorder' provided the various treatment method-Acupuncture, Manual therapy, Ashi(阿是)-point therapy, CHUNA therapy etc.- in literary study. The study about the 'Application of Concept of Meridian Muscle' has been performed in relation to Embedding Therapy, Kyungkuen chuna, Ki-gong therapy. 4. Experimental Studies were all Anatomical Studies. Studies were done in trial of discovering the actual existence, but revealed problem in interpretating the meaning of Meridian Muscle. 5. Clinical Studies based on Ashi(阿是)-point therapy CHUNA Muscles Along Meridians Release Therapy etc, were performed. Experimental studies about Meridian Muscle were assessed as low grade according to Jadad Scale. There were no studies which were based on well-organized Meridian Muscle theory. Conclusions : There needs to be more discussion about concept of Meridian Muscle and proceed more reliable experimental studies with organized Meridian Muscle theory. Further objective studies about treatment of Meridian Muscle should be done.

• The Journal of the Korea Contents Association
• /
• v.17 no.9
• /
• pp.650-660
• /
• 2017

This study is to suggest a new method of analyzing personality types of characters in narrative. First, we examined the history of the taxonomy of character types that existed in narrative theories so far. Until now, the classification of character types in narrative theory consisted largely of a formal classification based on roles in narrative, a content classification based on human internal qualities, and a complementary classification in which the two classification criteria are united. The problem with the existing character classification type is difficult to categorize it in spite of the usefulness of the content classification based on human internal qualities. On the other hand, the classification based on the role of the character in the narrative does not help as much as a practical analysis methodology because the classification is formal. In this study, we try to solve this problem by introducing Shalom Schwartz's human value type, and to make human character's value type and human role correlated with each other as a new character analysis methodology. Schwartz's study of value type is a very effective method to grasp the motivation of human behavior, and it seems to be very meaningful in analyzing the directivity of characters.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.20 no.1
• /
• pp.21-31
• /
• 2002

This study applied each Neural Networks theory and Fuzzy Set theory to improve accuracy in remotely sensed images. Remotely sensed data have been used to map land cover. The accuracy is dependent on a range of factors related to the data set and methods used. Thus, the accuracy of maps derived from conventional supervised image classification techniques is a function of factors related to the training, allocation, and testing stages of the classification. Conventional image classification techniques assume that all the pixels within the image are pure. That is, that they represent an area of homogeneous cover of a single land-cover class. But, this assumption is often untenable with pixels of mixed land-cover composition abundant in an image. Mixed pixels are a major problem in land-cover mapping applications. For each pixel, the strengths of class membership derived in the classification may be related to its land-cover composition. Fuzzy classification techniques are the concept of a pixel having a degree of membership to all classes is fundamental to fuzzy-sets-based techniques. A major problem with the fuzzy-sets and probabilistic methods is that they are slow and computational demanding. For analyzing large data sets and rapid processing, alterative techniques are required. One particularly attractive approach is the use of artificial neural networks. These are non-parametric techniques which have been shown to generally be capable of classifying data as or more accurately than conventional classifiers. An artificial neural networks, once trained, may classify data extremely rapidly as the classification process may be reduced to the solution of a large number of extremely simple calculations which may be performed in parallel.

• Proceedings of the Korean Society for Bioinformatics Conference
• /
• 2005.09a
• /
• pp.85-90
• /
• 2005

In this paper, firstly we report experimental results on applying information extraction (IE) methodology to the task of summarizing clinical trial design information in focus on ‘Compared Treatment’, ‘Endpoint’ and ‘Patient Population’ from clinical trial MEDLINE abstracts. From these results, we have come to see this problem as one that can be decomposed into a sentence classification subtask and an IE subtask. By classifying sentences from clinical trial abstracts and only performing IE on sentences that are most likely to contain relevant information, we hypothesize that the accuracy of information extracted from the abstracts can be increased. As preparation for testing this theory in the next stage, we conducted an experiment applying state-of-the-art sentence classification techniques to the clinical trial abstracts and evaluated its potential in the original task of the summarization of clinical trial design information.