• The Transactions of the Korea Information Processing Society
• /
• v.7 no.7
• /
• pp.2108-2115
• /
• 2000

The conventional Boolean retrieval systems based on vector spae model can provide the results of retrieval fast, they can't reflect exactly user's retrieval purpose including semantic information. Consequently, the results of retrieval process are very different from those users expected. This fact forces users to waste much time for finding expected documents among retrieved documents. In his paper, we designed a bayesian SOM(Self-Organizing feature Maps) in combination with bayesian statistical method and Kohonen network as a kind of unsupervised learning, then perform classifying documents depending on the semantic similarity to user query in real time. If it is difficult to observe statistical characteristics as there are less than 30 documents for clustering, the number of documents must be increased to at least 50. Also, to give high rank to the documents which is most similar to user query semantically among generalized classifications for generalized clusters, we find the similarity by means of Kohonen centroid of each document classification and adjust the secondary rank depending on the similarity.

• Journal of Power System Engineering
• /
• v.7 no.2
• /
• pp.29-35
• /
• 2003

The monitoring and diagnostics of the rotating machinery have been received considerable attention for many years. The objectives are to classify the machinery condition and to find out the cause of abnormal condition. This paper describes a classification method of diagnosing the small reciprocating compressor for refrigerators using the artificial neural network and the wavelet transform. In order to extract salient features, the wavelet transform are used from primary noise signals. Since the wavelet transform decomposes raw time-waveform signals into two respective parts in the time space and frequency domain, more and better features can be obtained easier than time-waveform analysis. In the training phase for classification, self-organizing feature map(SOFM) and learning vector quantization(LVQ) are applied, and the accuracies of them ate compared with each other. This paper is focused on the development of an advanced signal classifier to automatize the vibration signal pattern recognition. This method is verified by small reciprocating compressors, for refrigerator and normal and abnormal conditions are classified with high flexibility and reliability.

• The Journal of Korean Physical Therapy
• /
• v.24 no.6
• /
• pp.398-404
• /
• 2012

Purpose: This is designed to study the effect of weight-support walking training through motor learning on motor functions of children with cerebral palsy, in particular their activity of daily living and balance. Methods: Thirteen children with spastic cerebral palsy, at gross motor function classification system (GMFCS) levels III~IV, underwent treadmill walking training. It used principles of weight support, 4 times a week for 7 weeks, 10 minutes at a time, before and after neurodevelopmental physical therapy. Everyday functions were measured using Functional Independence Measure for Children (Wee-FIM). The ability to keep their balance was measured using electronic measuring equipment from good balance system and the assessment was made before and after the experiment. Results: There were significant differences (p<0.05) between pre and post experiment levels of functional independence in everyday life, in self-care activities, mobility, locomotion and social cognition. With regard to changes in standing balance, there were significant differences before and after the experiment (p<0.05) in GMFCS level III. There was a reduction in the agitation velocity in the x- and y-axes which measures the left-to-right shaking; in GMFCS level IV, velocity moment was reduced. Conclusion: Walking training using a treadmill can help improve the everyday activity and balance in children with spastic cerebral palsy. It can also be served as a useful purpose as a method of intervention in pediatric care.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.12 no.10
• /
• pp.799-807
• /
• 2002

The vibration signal can give an indication of the condition of rotating machinery, highlighting potential faults such as unbalance, misalignment and bearing defects. The features in the vibration signal provide an important source of information for the faults diagnosis of rotating machinery. When additional training data become available after the initial training is completed, the conventional neural networks (NNs) must be retrained by applying total data including additional training data. This paper proposes the fault diagnostics algorithm using the ART-Kohonen network which does not destroy the initial training and can adapt additional training data that is suitable for the classification of machine condition. The results of the experiments confirm that the proposed algorithm performs better than other NNs as the self-organizing feature maps (SOFM) , learning vector quantization (LYQ) and radial basis function (RBF) NNs with respect to classification quality. The classification success rate for the ART-Kohonen network was 94 o/o and for the SOFM, LYQ and RBF network were 93 %, 93 % and 89 % respectively.

• Journal of Internet Computing and Services
• /
• v.3 no.4
• /
• pp.27-36
• /
• 2002

The purpose of this study is to develop editor applied to vector image for the distance learning system(FVU), which enables teachers effectively to construct self-page on the screen, to reduce the size of file for teaching, and to correct many different kinds of event which was already made in the previous, The design of the editor is used UML and the editor is named VUEditor. The first page which is needed in class can be constructed by using VUEditor. The contents using VUEditor ore exported into VUAuthor through Vector-transformation. Through this procedure, the size of image file comes to be reduced, it has a low bond width. In conclusion, this VUEditor enables user to construct the first page. even without using such applied program as Image Tool and Power Point, to solve the problem of network traffic for reducing size of the file.

• Journal of Korean Library and Information Science Society
• /
• v.38 no.4
• /
• pp.87-116
• /
• 2007

The School Library Instruction(SLI) is one of the tool subjects for information literacy. Therefore, the connection with school curricula Is the activation strategy of SLI. The school library Integrated curriculum is Integrating a thinking strategy of SLI and subjects of subject education curricula. The purpose of the school library Integrated curriculum is to strengthen the educational role of teacher-librarian and self-directed learning. In this study, a presented example of the school library Integrated curriculum for the 10th students is based on the cross-curriculum subjects as a strategy of connection and integration.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.33 no.1
• /
• pp.131-148
• /
• 2008

Today, it is not difficult to use information technology (IT), especially, Internet based ones. Many people can not only access IT without learning how to use it but also find and develop new techniques and usages which couldn't be expected by system engineers or designers. This is owing to social interactions among users as well as advancement of IT. Theoretically, such social interactions in using IT can be well explained by adaptive structuration theory (AST) which has been considered as one of trying to capture the change of using IT due to social interactions between users and system. This study is to analyze the relationship between social interactions and motivation in using IT which can determine attitude and intention of using IT. For this purpose we provide a research model, in which two AST related variables, faithfulness of appropriation and consensus on appropriation, are independent variables and three beliefs for using IT, usefulness, ease of use and playfulness, are dependent ones. Additionally, for reflection of changing uses, usefulness is formed as second order factor by two first order factors-usefulness of self-expression and communication. An empirical test of our model for blog users which is analyzed by Partial Least Square method shows supporting most of hypotheses except one, consensus-ease of use.

• The Journal of the Korea Contents Association
• /
• v.7 no.10
• /
• pp.44-58
• /
• 2007

E-homestudy refers to e-Learning after school. This concept has been introduced by Korean Government as a substitute for expensive private tutoring. The purpose of this research is to explore the perceptions and relationships among determinants affecting the attitude and satisfaction level in e-homestudy. Such factors as subjective norms, visibility, perceived usefulness, quality of contents, facilitating conditions, interactions are introduced into the model. The survey results show that the attitude and the self-directed teaming level influence the satisfaction level in e-homestudy; the subjective norms, visibility, and perceived usefulness are the major determinant affecting the attitude; the quality of contents as well as interactions have positive impact on the perceived usefulness.

• Journal of the Korea Computer Industry Society
• /
• v.2 no.3
• /
• pp.377-388
• /
• 2001

Software metrics provide effective methods for characterizing software. Metrics have traditionally been composed through the definition of an equation, but this approach restricted within a full understanding of every interrelationships among the parameters. This paper use fuzzy logic system that is capable of uniformly approximating any nonlinear function and applying cognitive psychology theory. First of all, we extract multiple regression equation from the factors of 12 software complexity metrics collected from Java programs. We apply cognitive psychology theory in program volume factor, and then measure program volume complexity to execute fuzzy learning. This approach is sound, thus serving as the groundwork for further exploration into the analysis and design of software metrics.

• Journal of Power Electronics
• /
• v.15 no.6
• /
• pp.1567-1576
• /
• 2015

Offline inductance identification of a permanent magnet synchronous motor (PMSM) is essential for the design of the closed-loop controller and position observer in sensorless vector controlled drives. On the base of the offline inductance identification method combining direct current (DC) offset and high frequency (HF) voltage injection which is fulfilled at standstill, this paper investigates the inverter nonlinearity effects on the inductance identification while considering harmonics in the induced HF current. The negative effects on d-q axis inductance identifications using HF signal injection are analyzed after self-learning of the inverter nonlinearity characteristics. Then, both the voltage error and the harmonic current can be described. In addition, different cases of voltage error distribution with different injection conditions are classified. The effects of inverter nonlinearities on the offline inductance identification using HF injection are validated on a 2.2 kW interior PMSM drive.