• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2002.05a
• /
• pp.632-638
• /
• 2002

In novelty detection, one attempts to discriminate abnormal patterns from normal ones. Novelty detection is quite difficult since, unlike usual two class classification problems, only normal patterns are available for training. Auto-Associative Multi-Layer Perceptron (AAMLP) has been shown to provide a good performance based upon the property that novel patterns usually have larger auto-associative errors. In this paper, we give a mathematical analysis of 2-layer AAMLP's output characteristics and empirical results of 2-layer and 4-layer AAMLPs. Various activation functions such as linear, saturated linear and sigmoid are compared. The 2-layer AAMLPs cannot identify non-linear boundaries while the 4-layer ones can. When the data distribution is multi-modal, then an ensemble of AAMLPs, each of which is trained with pre-clustered data is required. This paper contributes to understanding of AAMLP networks and leads to practical recommendations regarding its use.

• Journal of the Korean Society of Earth Science Education
• /
• v.1 no.1
• /
• pp.99-110
• /
• 2008

The purpose of this study was to develop an instructional module for creativity(lMC) which was mainly based on a unit ('Sun's family' in the 2nd semester of the 5th grade in the textbook), to verify the effect of this module on Elementary student's creativity and attitudes related to science. The subject in this study was two 5th grade classes from J elementary school located in Busan. One of the group took the lessons which were designed for the IMC, and the other group took the normal classes. The effect of this subject for the experimental group and controlled group was verified by post-test: creativity and attitude related to science. The results of this study are as follows. First, the experimental group showed more creativity than controlled group on the post-test. The IMC was more effective to enhance student's creativity than general class. Second, the IMC was effective to enhance student's creativity without the difference in academic ability level. Third, the IMC was effective to enhance student's creativity without the difference in the gender. Fourth, the IMC was more effective to change student's attitude related to science than general class in the module application.

• Journal of the korean academy of Pediatric Dentistry
• /
• v.30 no.2
• /
• pp.291-297
• /
• 2003

While making diagnosis and the treatment plan for the growing children who visited at Chonnam National University Hospital for orthodontic treatment, authors obtained 8 lateral cephalometric measurements in antero-posterior and vertical relationship such as APDI, WITS, ANB, SN-MP, ODI, PFH/AFH, Y-axis, SUM for children aged 7 to 9 with class III malocclusion and compared them with these of 73 children of elementary school aged 7 to 9 with proper profile and normal occlusion in Gwangju. The results were as follows: 1. Between normal occlusion and class III malocclusion, ANB, SN-MP, ODI, SUM, except PFH/AFH and Y-axis showed statistically significant differences(p<0.05). 2. Between mesurements to describe skeletal disorder of antero-posterior relationship such as APDI, WITS, ANB and skeletal disorder of vertical relationship such as SN-MP, ODI, PFH/AFH, Y-axis, SUM, all of them in both normal occlusion and Class III malocclusion showed significant correlation, except Y-axis, SUM correlation(p<0.01). 3. Wald' statistics of WITS, ANB and APDI expressing skeletal disorder of antero-posterior relationship showed 7.118, 5.148, 0.741, respectively and Wald' statistics of ODI, Y-axis, PFH/AFH, SN-MP, SUM were presented 28.348, 2.238, 1.376, 0.090, 0.089, respectively. Therefore, WITS and ODI could be considered as useful diagnotic measurements for class III malocclusion.

• Journal of radiological science and technology
• /
• v.43 no.5
• /
• pp.397-404
• /
• 2020

Coronavirus disease(COVID-19) is highly infectious disease that directly affects the lungs. To observe the clinical findings from these lungs, the Chest Radiography(CXR) can be used in a fast manner. However, the diagnostic performance via CXR needs to be improved, since the identifying these findings are highly time-consuming and prone to human error. Therefore, Artificial Intelligence(AI) based tool may be useful to aid the diagnosis of COVID-19 via CXR. In this study, we explored various Deep learning(DL) approach to classify COVID-19, other viral pneumonia and normal. For the original dataset and lung-segmented dataset, the pre-trained AlexNet, SqueezeNet, ResNet18, DenseNet201 were transfer-trained and validated for 3 class - COVID-19, viral pneumonia, normal. In the results, AlexNet showed the highest mean accuracy of 99.15±2.69% and fastest training time of 1.61±0.56 min among 4 pre-trained neural networks. In this study, we demonstrated the performance of 4 pre-trained neural networks in COVID-19 diagnosis with CXR images. Further, we plotted the class activation map(CAM) of each network and demonstrated that the lung-segmentation pre-processing improve the performance of COVID-19 classifier with CXR images by excluding background features.

• Journal of Periodontal and Implant Science
• /
• v.46 no.2
• /
• pp.96-106
• /
• 2016

Purpose: Stress distribution and mandible distortion during lateral movements are known to be closely linked to bruxism, dental implant placement, and temporomandibular joint disorder. The present study was performed to determine stress distribution and distortion patterns of the mandible during lateral movements in Class I, II, and III relationships. Methods: Five Korean volunteers (one normal, two Class II, and two Class III occlusion cases) were selected. Finite element (FE) modeling was performed using information from cone-beam computed tomographic (CBCT) scans of the subjects' skulls, scanned images of dental casts, and incisor movement captured by an optical motion-capture system. Results: In the Class I and II cases, maximum stress load occurred at the condyle of the balancing side, but, in the Class III cases, the maximum stress was loaded on the condyle of the working side. Maximum distortion was observed on the menton at the midline in every case, regardless of loading force. The distortion was greatest in Class III cases and smallest in Class II cases. Conclusions: The stress distribution along and accompanying distortion of a mandible seems to be affected by the anteroposterior position of the mandible. Additionally, 3-D modeling of the craniofacial skeleton using CBCT and an optical laser scanner and reproduction of mandibular movement by way of the optical motion-capture technique used in this study are reliable techniques for investigating the masticatory system.

• Journal of the Korea Convergence Society
• /
• v.9 no.11
• /
• pp.15-21
• /
• 2018

In this study, we try to detect anomalies on the network intrusion detection system by learning only one class. We use KDD CUP 1999 dataset, an intrusion detection dataset, which is used to evaluate classification performance. One class classification is one of unsupervised learning methods that classifies attack class by learning only normal class. When using unsupervised learning, it difficult to achieve relatively high classification efficiency because it does not use negative instances for learning. However, unsupervised learning has the advantage for classifying unlabeled data. In this study, we use one class classifiers based on support vector machines and density estimation to detect new unknown attacks. The test using the classifier based on density estimation has shown relatively better performance and has a detection rate of about 96% while maintaining a low FPR for the new attacks.

• Journal of the Korean Society of Earth Science Education
• /
• v.7 no.2
• /
• pp.192-202
• /
• 2014

The purpose of this study was to examine the effects of science lessons using mind mapping on creativity and academic achievement in science. The subjects of this study were fifth-grade students selected from four classes of an elementary school located in Busan. For ten weeks, the experimental group of 40 students were taught using the mind mapping technique. The comparative group, also of 40 students, was taught in normal classes which used a standard text-book. Children were given a test on science processing skills and academic achievement in science to measure the effects of mind mapping. The Likert scales were used to gather student's feedback on creativity and academic achievement in science. Through these procedures, the following results were obtained: First, mind mapping had a greater effect on science processing skills than the normal classes, where a text-book was used. Second, mind mapping was effective in improving the student's academic achievements in science at a greater level than the normal classes where a text-book was used. Third, after viewing results of the Student Recognition Investigation, we found that the students showed a higher level of interest in science lessons that used mind mapping, and were better able to understand the scientific theories. As a result, the elementary science class with mind mapping developed greater science processing skills and saw higher academic achievement in science. We conclude that science classes that use mind mapping have the potential to develop better science processing skills and improve academic achievement in science.

• Proceedings of the IEEK Conference
• /
• 2000.07a
• /
• pp.229-232
• /
• 2000

AAL2 has been adopted for bandwidth-efficient trans-mission of low bit tate traffic over ATM networks in ITUT and ATM Forum. Since ATM/AAL2 is expected to be used as a switching technology in third-generation mobile access networks and mobile data traffic is expected to increase rapidly in near future, there must be a need for efficient scheduling scheme satisfying the QoS requirement of ow bit rate voice as well as the one of high bit rate data. In this paper, we propose a new class-scheduling scheme to improve data packet loss probability, while Qos of voice traffic is guaranteed, when data traffic is multiplexed together with mobile voice traffic into a single ATM VCC. The proposed scheme can efficiently support data traffic by assigning a time threshold value to voice traffic. Through simulation study, we show that the proposed scheme does not only achieve better efficiency for providing both mobile voice and data services than HOL class-scheduling scheme and normal FIFO scheme, but also guarantees mean voice packet delay under a certain criteria.

• Journal of Korean Academy of Nursing
• /
• v.3 no.2
• /
• pp.91-100
• /
• 1973

I. Objectives of the study This study attempted In examine, from a pedagogical point of view, how socially-handicapped children differ from normal ones in their family backgrounds, personality-traits. adaptability to school life, and their peer relationship. This study was made under the following hypothesis; 1. The family background of socially-handicapped children is less desirable than that of normal ones. 2. Personality traits of socially-handicapped children are less desirable than those of normal ones. 3. Socially handicapped children tend to be less adaptable to school life than normal ones. 4. Peer-relationship of socially-handicapped children is less desirable than of normal ones . II. Contents of study The thesis consists of the following five main parts; 1. Introduction 2. Related Studies 3. Procedure 4. Results 5. Summary and Conclusions III. Instruments The following instruments were used for this study; 1. Family background record prepared by the school. 2. Questionnaire prepared by the writer. 3. General personality test (written by Kim Ki-Suk and published by Korean Testing Center). 4. School activity record. 5. Sociocratic test. IV. The following conclusions were derived from the study 1, As compared with normal children, socially-handicapped ones have, in many cases, larger number of siblings, their families belong to lower economic bracket: their parents were indifferent to their children, and their mothers were less educated. 2. As compared with normal children, socially-handicapped ones are emotionally unstable, although they are the same as normal children in their sense of dominancy, responsibility, sociality, and confidence. 3. As compared with normal children, socially-handicapped ones are tardy in their learning, although they are almost the same as normal ones in their intelligence development. 4. As compared with normal children, socially-handicapped ones make friends more easily with pupils of other classes and schools rather than those of their own class or school.

• Journal of the Korean Mathematical Society
• /
• v.55 no.3
• /
• pp.671-694
• /
• 2018

In this paper, we investigate the weighted vector-valued bounds for a class of multilinear singular integral operators, and its commutators, from $L^{p_1}(l^{q_1};\;{\mathbb{R}}^n,\;w_1){\times}{\cdots}{\times}L^{p_m}(l^{q_m};\;{\mathbb{R}}^n,\;w_m)$ to $L^p(l^q;\;{\mathbb{R}}^n,\;{\nu}_{\vec{w}})$, with $p_1,{\cdots},p_m$, $q_1,{\cdots},q_m{\in}(1,\;{\infty})$, $1/p=1/p_1+{\cdots}+1/p_m$, $1/q=1/q_1+{\cdots}+1/q_m$ and ${\vec{w}}=(w_1,{\cdots},w_m)$ a multiple $A_{\vec{P}}$ weights. Our argument also leads to the weighted weak type endpoint estimates for the commutators. As applications, we obtain some new weighted estimates for the $Calder{\acute{o}}n$ commutator.