• Journal of Biosystems Engineering
• /
• v.17 no.1
• /
• pp.65-78
• /
• 1992

When using a computer vision system for a measurement, the geometrically distorted input image usually restricts the site and size of the measuring window. A geometrically distorted image caused by the image sensing and processing hardware degrades the accuracy of the visual measurement and prohibits the arbitrary selection of the measuring scope. Therefore, an image calibration is inevitable to improve the measuring accuracy. A calibration process is usually done via four steps such as measurement, modeling, parameter estimation, and compensation. In this paper, the efficient error calibration technique of a geometrically distorted input image was developed using a neural network. After calibrating a unit pixel, the distorted image was compensated by training CMLAN(Cerebellar Model Linear Associator Network) without modeling the behavior of any system element. The input/output training pairs for the network was obtained by processing the image of the devised sampled pattern. The generalization property of the network successfully compensates the distortion errors of the untrained arbitrary pixel points on the image space. The error convergence of the trained network with respect to the network control parameters were also presented. The compensated image through the network was then post processed using a simple DDA(Digital Differential Analyzer) to avoid the pixel disconnectivity. The compensation effect was verified using known sized geometric primitives. A way to extract directly a real scaled geometric quantity of the object from the 8-directional chain coding was also devised and coded. Since the developed calibration algorithm does not require any knowledge of modeling system elements and estimating parameters, it can be applied simply to any image processing system. Furthermore, it efficiently enhances the measurement accuracy and allows the arbitrary sizing and locating of the measuring window. The applied and developed algorithms were coded as a menu driven way using MS-C language Ver. 6.0, PC VISION PLUS library functions, and VGA graphic functions.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.6
• /
• pp.87-94
• /
• 2008

Iris diagnosis is an alternative medicine technique whose proponents believe that patterns, colors, and other characteristics of the iris can be examined to determine information about a patient's systemic health. However, because most of previous studies only find a sign pattern in a gray iris image, they are not enough to be used for a iris diagnosis system. In this paper, we developed an iris diagnosis system based on a color image processing and iris medical information stored in database. The system includes four modules : input module with an iris camera, iris signs extraction module, medical database, output module with printing. Based on a color image processing approach, this paper presents the extraction algorithms of 7 major iris signs and correction manually for improving the accuracy of analysis. We can use the iridology and patient's health DB in the stage of signs analysis. Compared with the existing system, the developed system can be applied to an iris diagnosis system since it provides various additional functions.

• Korean Journal of Optics and Photonics
• /
• v.4 no.4
• /
• pp.420-427
• /
• 1993

Dielectric thin film mirrors are embedded in multimode and single-mode fibers by a fusion splicing technique. The fibers with $45{\circ}$ angled embedded mirrors serve as ultra-compact directional couplers with low excess optical loss of 0.2 dB for multimode and 0.5 dB for single mode at 1.3 ${\mu}m$ and excellent mechanical properties. The reflectance is wavelength dependent and strongly polarization depencient. Far-field scans of the reflected output power measured with a white-light source show a pattern which is almost circularly symmetric with aspect ratio of 1.09 at 5% of the peak power. The splitting ratio in a multimode coupler measured with a diode laser source is much less dependent on input coupling conditions than in conventional fused biconical-taper couplers, indicating that these couplers are less susceptible to modal noise occuring in optical fiber communication systems. Spectral properties of multilayer internal mirrors normal to the fiber axis have been investigated experimentally, and a matrix analysis has been used to explain the results.

• Journal of Korea Water Resources Association
• /
• v.37 no.9
• /
• pp.737-744
• /
• 2004

In this study, to evaluate the effect of forest vegetation on the long-term water balance in a watershed, semi-distributed and physically based parameter model, SWAT was applied to the Bocheong watershed, and the variation of hydrological components such as evapotranspiration, surface flow, lateral flow, base flow, and total runoff was investigated with coniferous and deciduous forests, respectively. First, SWAT model was modified to simulate the actual plant growth pattern of coniferous trees which have the uniform value of leaf area index all the seasons of the year. The modified model was applied to the watershed that is assumed to have only one land cover in the whole watershed, and the variation of the water balance components was investigated for each land cover. It was found that coniferous forest affected the increase in evapotranspiration and decrease in runoff more than deciduous forest. However, the age and the density of stand, the location, and soil characteristics and meteorological conditions including the tree species should be also considered to examine the effect more quantitatively and to reduce the uncertainties in simulated output from the hydrological model.

• Environmental Analysis Health and Toxicology
• /
• v.11 no.1_2
• /
• pp.31-39
• /
• 1996

Leachate from municipal solid waste (MSW) landfill, effluent from leachate treatment plant, and ground water sample from a monitoring well near landfill site were tested for an acute toxicity. Microtox toxicity test was used for testing the acute toxicity of leachate and other samples. EC$_{50}$ values which a concentration of pollutant for reducing 50% light output from luminescent bacteria, Photobacterium phosphoreum were determined to assess the toxicity of pollutants as well as the relative toxicity. In addition, characteristics of leachate were studied and compared to those of phenol and pentachlorophenol (PCP) which are typical aquatic toxic pollutants. For leachate, EC$_{50}$ for 30 min incubation was 10.8%, while for phenol and PCP, 46 ppm and 1.2 ppm, respectively. the relative toxicity of treated leachate by in situ aeration with activated sludge was reduced to more than 75% of toxicity of the untreated leachate. Microtox toxicity test was failed to figure out EC$_{50}$ values for groundwater from a monitoring well since the relative toxicity of the unconcentrated sample was too low to estimate EC$_{50}$. Addition of activated carbon to leachate was reduced the relative toxicity. The reduction Pattern of the relative toxicity of leachate by mechanical aeration was similar to that of PCP, but different from that of phenol. These findings suggest that the toxicity of leachate may come from PCP-like toxic compounds rather than phenol-like one. In conclusion, the process of aeration with activated sludge might be very important to reduce the environmental toxicity of leachate. And Microtox test could be a reasonable bioassay for screening and monitoring the environmental toxicity of leachate from municipal solid waste landfill as well as for determining the reduction efficiency of the leachate toxicity by various treatment processes in leachate treatment plant.

• Journal of Digital Convergence
• /
• v.16 no.10
• /
• pp.235-241
• /
• 2018

The printout management system should analyze the pattern of existence of personal information (resident number, card number) in the output log and users should be provided with functions such as warning message pop-up, forced printing termination, mailing to administrator, independently logs management. Authentication management can also be performed only by registered users by installing an agent on a user PC, and it should have a restriction function to permit or deny work according to user information. In addition, when printing/copying/scanning using this equipment, it is possible to use document printing and multifunction copier after ID card authentication and ID/PW should be input to device when ID card is not used. In this study, we developed these interfaces with WOWSOFT co., Ltd, a security company that has better technology than the existing printout security methods, to construct the printout management system. Also we designed the interface of basic functions necessary for printout management and contributed to the establishment of printout management system.

• Proceedings of the Korea Association of Information Systems Conference
• /
• 2000.11a
• /
• pp.1.2-24
• /
• 2000

The field of neural networks has been a recent surge in activity as a result of progress in developments of efficient training algorithms. For this reason, and coupled with the widespread availability of powerful personal computer hardware for running simulations of networks, there is increasing focus on the potential benefits this field can offer. The neural network may be viewed as an advanced pattern recognition technique and can be applied in many areas such as financial time series forecasting, medical diagnostic expert system and etc.. The intention of this study is to build and implement one simple artificial neural networks hereinafter called ANN. For this purpose, some literature survey was undertaken to understand the structures and algorithms of ANN theoretically. Based on the review of theories about ANN, the system adopted 3-layer back propagation algorithms as its learning algorithm to simulate one case of medical diagnostic model. The adopted ANN algorithm was performed in PC by using turbo PASCAL and many input parameters such as the numbers of layers, the numbers of nodes, the number of cycles for learning, learning rate and momentum term. The system output more or less successful results which nearly agree with goals we assumed. However, the system has some limitations such as the simplicity of the programming structure and the range of parameters it can dealing with. But, this study is useful for understanding general algorithms and applications of ANN system and can be expanded for further refinement for more complex ANN algorithms.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.3
• /
• pp.22-28
• /
• 2010

Adaboost is well known for a representative learner as one of the kernel methods. Adaboost which is based on the statistical learning theory shows good generalization performance and has been applied to various pattern recognition problems. However, Adaboost is basically to deal with a two-class classification problem, so we cannot solve directly a multi-class problem with Adaboost. One-Vs-All and Pair-Wise have been applied to solve the multi-class classification problem, which is one of the multi-class problems. The two methods above are ones of the output coding methods, a general approach for solving multi-class problem with multiple binary classifiers, which decomposes a complex multi-class problem into a set of binary problems and then reconstructs the outputs of binary classifiers for each binary problem. However, two methods cannot show good performance. In this paper, we propose the method to solve a multi-target classification problem by using radial basis function of Adaboost weak classifier.

• Sleep Medicine and Psychophysiology
• /
• v.6 no.1
• /
• pp.19-25
• /
• 1999

Sleep alters both breathing pattern and the ventilatory responses to external stimuli. These changes during sleep permit the development or aggravation of sleep-related hypoxemia in patients with respiratory disease and contribute to the pathogenesis of apneas in patients with the sleep apnea syndrome. Fundamental effects of sleep on the ventilatory control system are 1) removal of wakefulness input to the upper airway leading to the increase in upper airway resistance, 2) loss of wakefulness drive to the respiratory pump, 3) compromise of protective respiratory reflexes, and 4) additional sleep-induced compromise of ventilatory control initiated by reduced functional residual capacity on supine position assumed in sleep, decreased $CO_2$ production during sleep, and increased cerebral blood flow in especially rapid eye movement(REM) sleep. These effects resulted in periodic breathing during unsteady non-rapid eye movement(NREM) sleep even in normal subjects, regular but low ventilation during steady NREM sleep, and irregular breathing during REM sleep. Sleep-induced breathing instabilities are divided due primarily to transient increase in upper airway resistance and those that involve overshoots and undershoots in neural feedback mechanisms regulating the timing and/or amplitude of respiratory output. Following ventilatory overshoots, breathing stability will be maintained if excitatory short-term potentiation is the prevailing influence. On the other hand, apnea and hypopnea will occur if inhibitory mechanisms dominate following the ventilatory overshoot. These inhibitory mechanisms include 1) hypocapnia, 2) inhibitory effect from lung stretch, 3) baroreceptor stimulation, 4) upper airway mechanoreceptor reflexes, 5) central depression by hypoxia, and 6) central system inertia. While the respiratory control system functions well during wakefulness, the control of breathing is commonly disrupted during sleep. These changes in respiratory control resulting in breathing instability during sleep are related with the pathophysiologic mechanisms of obstructive and/or central apnea, and have the therapeutic implications for nocturnal hypoventilation in patients with chronic obstructive pulmonary disease or alveolar hypoventilation syndrome.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.6
• /
• pp.586-591
• /
• 2014

In this study, we introduce Radial Basis Function Neural Networks(RBFNNs) classifier using Artificial Bee Colony(ABC) algorithm in order to classify between precipitation event and non-precipitation event from given radar data. Input information data is rebuilt up through feature analysis of meteorological radar data used in Korea Meteorological Administration. In the condition phase of the proposed classifier, the values of fitness are obtained by using Fuzzy C-Mean clustering method, and the coefficients of polynomial function used in the conclusion phase are estimated by least square method. In the aggregation phase, the final output is obtained by using fuzzy inference method. The performance results of the proposed classifier are compared and analyzed by considering both QC(Quality control) data and CZ(corrected reflectivity) data being used in Korea Meteorological Administration.