• Journal of Information Processing Systems
• /
• v.13 no.6
• /
• pp.1467-1486
• /
• 2017

Fuzzy co-clustering is sensitive to noise data. To overcome this noise sensitivity defect, possibilistic clustering relaxes the constraints in FCM-type fuzzy (co-)clustering. In this paper, we introduce a new possibilistic fuzzy co-clustering algorithm based on information bottleneck (ibPFCC). This algorithm combines fuzzy co-clustering and possibilistic clustering, and formulates an objective function which includes a distance function that employs information bottleneck theory to measure the distance between feature data point and feature cluster centroid. Many experiments were conducted on three datasets and one artificial dataset. Experimental results show that ibPFCC is better than such prominent fuzzy (co-)clustering algorithms as FCM, FCCM, RFCC and FCCI, in terms of accuracy and robustness.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.7
• /
• pp.1098-1101
• /
• 2022

With the development of computer music notation programs, when drawing sheet music, it is often drawn using a computer. However, there are still many use of hand-written notations for educational purposes or to quickly draw sheet music such as listening and dictating. In previous studies, OMR focused on recognizing the printed music sheet made by music notation program. the result of handwritten OMR with camera is poor because different people have different writing methods, and lens distortion. In this study, as a pre-processing process for recognizing handwritten music sheet, we propose a method for recognizing a staff using linear regression and a method for recognizing a bar using CNN. F₁ scores of staff recognition and barline detection are 99.09% and 95.48%, respectively. This methodologies are expected to contribute to improving the accuracy of handwriting.

• Journal of Korea Multimedia Society
• /
• v.21 no.5
• /
• pp.609-616
• /
• 2018

In this paper, we designed a multimodal bio-signal measurement system to observe changes in the brain nervous system and vascular system during sleep. Changes in the nervous system and the cerebral blood flow system in the brain during sleep induce a unique correlation between the changes in the nervous system and the blood flow system. Therefore, it is necessary to simultaneously observe changes in the brain nervous system and changes in the blood flow system to observe the sleep state. To measure the change of the nervous system, EEG, EOG and EMG signal used for the sleep stage analysis were designed. We designed a system for measuring cerebral blood flow changes using functional near-infrared spectroscopy. Among the various imaging methods to measure blood flow and metabolism, it is easy to measure simultaneously with EEG signal and it can be easily designed for miniaturization of equipment. The sleep stage was analyzed by the measured data, and the change of the cerebral blood flow was confirmed by the change of the sleep stage.

• Structural Engineering and Mechanics
• /
• v.55 no.6
• /
• pp.1177-1202
• /
• 2015

In this paper, a new intensity measure of earthquakes for probabilistic seismic analysis is presented for skewed highway bridges. Three different cases of skewed bridges with different skew angles ($0^{\circ}$, $30^{\circ}$ and $45^{\circ}$) are considered. Well-known intensity measures (e.g., PGA, $S_a$) are evaluated and critically discussed based on sensitivity analysis: efficiency, practically, proficiency and sufficiency of intensity measures are considered in detail. The analyses demonstrated that the intensity measures have to take into account structural acceleration on a wide range of periods so that a new seismic intensity measure is proposed showing that it has less dispersion compared to others. Since the proposed intensity represents the average value of the $S_a$ (between a lower and upper structural period) it has been called Averaged Spectral Acceleration (ASA). Based on performed incremental dynamic analysis (IDA), the seismic analytical fragility curves of typical skewed highway bridges have been evaluated for different states of damage controlling the low dispersion of the ASA index as well as its proficiency and sufficiency.

• Korean Journal of Mathematics
• /
• v.32 no.1
• /
• pp.137-162
• /
• 2024

This paper consists of two significant aims. The first aim of this paper is to establish the criteria for the existence of solutions to nonlinear Volterra-Fredholm (V-F) fractional integral equations on [0, L], where 0 < L < ∞. The fractional integral is described here in the sense of the Katugampola fractional integral of order λ > 0 and with the parameter β > 0. The concepts of the fixed point theorem and the measure of noncompactness are used as the main tools to prove the existence of solutions. The second aim of this paper is to introduce a computational method to obtain approximate numerical solutions to the considered problem. This method is based on the Fibonacci wavelets with collocation technique. Besides, the results of the error analysis and discussions of the accuracy of the solutions are also presented. To the best knowledge of the authors, this is the first computational method for this generalized problem to obtain approximate solutions. Finally, two examples are discussed with the computational tables and convergence graphs to interpret the efficiency and applicability of the presented method.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.3
• /
• pp.33-42
• /
• 2020

There has been difficulties in identifying objects by relying on the naked eye in various surveillance systems. There is a growing need for automated surveillance systems to replace soldiers in the field of military surveillance operations. Even though the object detection technology is developing rapidly in the civilian domain, but the research applied to the military is insufficient due to a lack of data and interest. Thus, in this paper, we applied one of deep learning algorithms, Convolutional Neural Network-based binary classification to develop an autonomous identification model of both friend and foe helicopters (AH-64, Mi-17) among the military weapon systems, and evaluated the model performance by considering accuracy, precision, recall and F-measure. As the result, the identification model demonstrates 97.8%, 97.3%, 98.5%, and 97.8 for accuracy, precision, recall and F-measure, respectively. In addition, we analyzed the feature map on convolution layers of the identification model in order to check which area of imagery is highly weighted. In general, rotary shaft of rotating wing, wheels, and air-intake on both of ally and foe helicopters played a major role in the performance of the identification model. This is the first study to attempt to classify images of helicopters among military weapons systems using CNN, and the model proposed in this study shows higher accuracy than the existing classification model for other weapons systems.

• Progress in Superconductivity
• /
• v.7 no.1
• /
• pp.28-35
• /
• 2005

We propose a method to measure atrial arrhythmias (AA) such as atrial fibrillation (Afb) and atrial flutter (Afl) with a SQUID magnetocardiograph (MCG) system. To detect AA is one of challenging topics in MCG. As the AA generally have irregular rhythm and atrio-ventricular conduction, the MCG signal cannot be improved by QRS averaging; therefore a SQUID MCG system having a high SNR is required to measure informative atrial excitation with a single scan. In the case of Afb, diminished f waves are much smaller than normal P waves because the sources are usually located on the posterior wall of the heart. In this study, we utilize an MCG system measuring tangential field components, which is known to be more sensitive to a deeper current source. The average noise spectral density of the whole system in a magnetic shielded room was $10\;fT/{\surd}Hz(a)\;1\;Hz\;and\;5\;fT/{\surd}Hz\;(a)\;100\;Hz$. We measured the MCG signals of patients with chronic Afb and Afl. Before the AA measurement, the comparison between the measurements in supine and prone positions for P waves has been conducted and the experiment gave a result that the supine position is more suitable to measure the atrial excitation. Therefore, the AA was measured in subject's supine position. Clinical potential of AA measurement in MCG is to find an aspect of a reentry circuit and to localize the abnormal stimulation noninvasively. To give useful information about the abnormal excitation, we have developed a method, separative synthetic aperture magnetometry (sSAM). The basic idea of sSAM is to visualize current source distribution corresponding to the atrial excitation, which are separated from the ventricular excitation and the Gaussian sensor noises. By using sSAM, we localized the source of an Afl successfully.

• Journal of Korean Academy of Fundamentals of Nursing
• /
• v.7 no.2
• /
• pp.164-176
• /
• 2000

Purpose : This study was done to identify the factors of decisional balance for smoking cessation among middle aged men in Korea. This was composed of a set of variables at the level of decision making when middle aged men decide to stop smoking. It was used to classify and identify the characteristics of the stages of change for smoking cessation to which the middle aged men belong, and was used to identify the variables of decisional balance which influenced the stages of change for smoking cessation in middle aged men. Methods : A convenience sample of 169 men who had smoked and were smoking, were between age 30 and 60 and lived in Seoul(mean age=44), were selected from the community. The data was collected from December 10, 1999 to February 28, 2000. The research instrument was the Decisional Balance Measure for Smoking Cessation (Velicer et al., 1985). and Stage of Change Measure(DiClemente et al., 1991). The data were analyzed using the SAS Program. Results : 1. According to stage of change measure, the 169 subjects were distributed in each stage of change for smoking cessation: in the pre-contemplation stage 63 subjects(32.7%), contemplation stage 60 subjects (35.5%), preparation stage 17 subjects(10.1%), and maintenance stage 29 subjects(17.2%). 2. Factor analysis identified 4 factors of decisional balance as appropriate factors for smoking cessation of middle aged men. There were named by the researchers; 1)'Perceived Burden to Self', 2)'Perceived Benefit to Others' 3)'Perceived Approval to Others', and 4)'Perceived Disapproval to Self'. 3. Analysis of variance showed that the three components, 1)'Perceived Burden to Self(F=8.50, P=.0001)', 2)'Perceived Benefit to Others(F=3.19, P=.025)' and 3)'Perceived DisApproval to Self(F=2.87, P=.038)were significantly associated with stage of change. 4. Through discriminant analysis, it was found that 'Perceived Burden to self' was the most influential variable in discriminating the four stages of change(pre-contemplation, contemplation, preparation, and maintenance). Conclusion : The results are consistent with the application of the Transtheoretical model, which has been used to understand how people change health behavior. Even though this study is a cross-sectional, not a longitudinal study, the findings of this study give useful information for smoking cessation intervention for the middle aged men.

• The KIPS Transactions:PartB
• /
• v.14B no.5
• /
• pp.383-390
• /
• 2007

Interactions between proteins and genes are often considered essential in the description of biomolecular phenomena and networks of interactions are considered as an entre for a Systems Biology approach. Recently, many works try to extract information by analyzing biomolecular text using natural language processing technology. Previous researches insist that linguistic information is useful to improve the performance in detecting gene interactions. However, previous systems do not show reasonable performance because of low recall. To improve recall without sacrificing precision, this paper proposes a new method for detection of gene interactions based on syntactic relations. Without biomolecular knowledge, our method shows reasonable performance using only small size of training data. Using the format of LLL05(ICML05 Workshop on Learning Language in Logic) data we detect the agent gene and its target gene that interact with each other. In the 1st phase, we detect encapsulation types for each agent and target candidate. In the 2nd phase, we construct verb lists that indicate the interaction information between two genes. In the last phase, to detect which of two genes is an agent or a target, we learn direction information. In the experimental results using LLL05 data, our proposed method showed F-measure of 88% for training data, and 70.4% for test data. This performance significantly outperformed previous methods. We also describe the contribution rate of each phase to the performance, and demonstrate that the first phase contributes to the improvement of recall and the second and last phases contribute to the improvement of precision.

• Korean Journal of Acupuncture
• /
• v.23 no.1
• /
• pp.15-36
• /
• 2006

Objectives . The aim of this study was to examine the effect of electroacupuncture(EA) at the ST36 on normal humans by using power spectral analysis. Methods : EEG(Electroencephalogram) power spectral exhibits site-specific and state-related differences in specific frequency bands. In this study, power spectrum was used as a measure of complexity. 32 channel EEG study was carried out in 12 subjects (10 males; age=26.7 years old, 2females; age=28 years old). Results ; In ${\alpha}$ (alpha) band, the power values at Fp2, F7, F3, Fz, FTC1, FTC2, T3, C3, Cz, C4, TT1, TCP1, CP1, CP2,T5, P3, Pz, P4, Po1, Po2, O1, Oz,O2 channels(p<0.05) during the ST36-acupoint treatment were significantly increased. In ${\beta}$ (beta) band, the power values at Fp2, F7, F3, Fz, F4, F8, FTC1, FTC2, T3, C3, Cz, C4, TT1, TCP1, CP1, CP2, T5, P3, Pz, P4, Po1, Po2, O1, Oz, O2 channels(p<0.05) during the ST36-acupoint treatment were significantly decreased. In ${\delta}$ (delta) band, the power values at F7, Fz, T3, C3, TT1, TCP1, CP1, CP2, T5, P3, Pz,T6, Po1, PO2,O1, Oz, O2 channels(p<0.05) during the ST36-acupoint treatment were significantly decreased. In ${\theta}$(theta) band, the power values at F7, Fz, FTC1, T3, TCP1, CP2, TCP2, Po1, Po2 channels(p<0.05) during the ST36-acupoint treatment were significantly decreased. ${\alpha}$/${\beta}$ values at Cz, T5, O1, Oz, O2 channels during the ST36-acupoint treatment were increased. ${\beta}$/${\theta}$ values at Fpl, F7, F3, Fz, F4, F8, FTC1, FTC2, T3, C3, C4, T4, TT1, TCP1, TCP2, TT2, P3, P4, T6, Pol channels during the ST36-acupoint treatment were increased. Conclusions : This results suggest that Electroacupuncture at the ST36 mostly affects the charge on alpha(23 channels), beta(25 channels) bands.