• International Journal of Computer Science & Network Security
• /
• v.21 no.6
• /
• pp.77-88
• /
• 2021

Heart Failure represents a critical pathological case that is challenging to predict and discover at an early age, with a notable increase in morbidity and mortality. Machine Learning and Neural Network techniques play a crucial role in predicting heart attacks, diseases and more. These techniques give valuable perspectives for clinicians who may then adjust their diagnosis for each individual patient. This paper evaluated neural network models for heart attacks predictions. Several online learning methods were investigated to automatically and accurately predict heart attacks. The UCI dataset was used in this work to train and evaluate First Order and Second Order Online Learning methods; namely Backpropagation, Delta bar Delta, Levenberg Marquardt and QuickProp learning methods. An optimizer technique was also used to minimize the random noise in the database. A regularization concept was employed to further improve the generalization of the model. Results show that a three layers' NN model with a Backpropagation algorithm and Nadam optimizer achieved a promising accuracy for the heart attach prediction tasks.

• Economic and Environmental Geology
• /
• v.30 no.6
• /
• pp.543-551
• /
• 1997

Poongjeon talc deposits is emplaced in dolomite and dolomitic limestone of the Cambro-Ordovician Samtaesan Formation. Ore in Poongjeon is low grade talc and the deposit has been known as the contact metasomatic or hydrothermal replacement type related to the intrusion of late Cretaceous granite in this area. X-ray diffraction, electron microprobe analysis, fluid inclusion and stable isotope analysis were utilized to examine the mineralogy of the ore and the origin of the ore fluid. The ore from Poongjeon mine mainly consists of talc and tremolite with minor amount of illite, vermiculite, smectite, and chlorite-vermiculite mixed layer. Occurrence of ore body indicates that the talc-tremolite ore was formed through the replacement by the $SiO_2$-rich hydrothermal fluid along the bedding and dike boundaries, or contact of amphibolite and basic dike with carbonate rocks. The temperature and pressure of the ore forming fluids at the time of the talc mineralization were estimated as $350^{\circ}C$ and 400 bar, respectively, based on the heating and freezing data of the fluid inclusions in quartz from talc-tremolite veins. During the talc-tremolite formation, fluids were divided into $CO_2$-enriched fluid and $CO_2$-poor fluid from $CO_2$ immiscibility (or effervescence). Oxygen isotope values (${\delta}^{18}O$) of the talc-tremolite fall within a range between 12.2 and 12.9‰. Hydrogen isotope values(${\delta}D$) of the ore range from -60 to -85‰ and $H_2O$ contents range from 2.0 to 3.4 wt.%. ${\delta}^{18}O$ and ${\delta}D$ values of talc ore indicate that the hydrothermal fluid involved in talc-tremolite formation was of igneous origin. Oxygen and hydrogen isotopic exchange between talc ore and the surface water was negligible after talc-tremolite ore formation.

• Computers and Concrete
• /
• v.3 no.5
• /
• pp.301-312
• /
• 2006

Experimental research revealed that the spatial dispersion of aggregate grains exerts pronounced influences on the mechanical and durability properties of concrete. Therefore, insight into this phenomenon is of paramount importance. Experimental approaches do not provide direct access to three-dimensional spacing information in concrete, however. Contrarily, simulation approaches are mostly deficient in generating packing systems of aggregate grains with sufficient density. This paper therefore employs a dynamic simulation system (with the acronym SPACE), allowing the generation of dense random packing of grains, representative for concrete aggregates. This paper studies by means of SPACE packing structures of aggregates with a Fuller type of size distribution, generally accepted as a suitable approximation for actual aggregate systems. Mean free spacing $\bar{\lambda}$, mean nearest neighbour distance (NND) between grain centres $\bar{\Delta}_3$, and the probability density function of ${\Delta}_3$ are used to characterize the spatial dispersion of aggregate grains in model concretes. Influences on these spacing parameters are studied of volume fraction and the size range of aggregate grains. The values of these descriptors are estimated by means of stereological tools, whereupon the calculation results are compared with measurements. The simulation results indicate that the size range of aggregate grains has a more pronounced influence on the spacing parameters than exerted by the volume fraction of aggregate. At relatively high volume density of aggregates, as met in the present cases, theoretical and experimental values are found quite similar. The mean free spacing is known to be independent of the actual dispersion characteristics (Underwood 1968); it is a structural parameter governed by material composition. Moreover, scatter of the mean free spacing among the serial sections of the model concrete in the simulation study is relatively small, demonstrating the sample size to be representative for composition homogeneity of aggregate grains. The distribution of ${\Delta}_3$ observed in this study is markedly skew, indicating a concentration of relatively small values of ${\Delta}_3$. The estimate of the size of the representative volume element (RVE) for configuration homogeneity based on NND exceeds by one order of magnitude the estimate for structure-insensitive properties. This is in accordance with predictions of Brown (1965) for composition and configuration homogeneity (corresponding to structure-insensitive and structure-sensitive properties) of conglomerates.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2005.11a
• /
• pp.500-506
• /
• 2005

본 논문에서는 자가 생성 지도 학습 알고리즘을 이용한 운송 컨테이너 식별자 인식 시스템을 제안한다. 일반적으로 운송 컨테이너의 식별자들은 글자의 색이 검정색 또는 흰색으로 이루어져 있는 특정이 있다. 이러한 특성을 고려하여 원 컨테이너 영상에 대해 검은색과 흰색을 제외하고는 모든 부분을 잡음으로 처리하기 위해 퍼지 추론 방법을 이용하여 식별자 영역과 바탕영역을 구별한다. 식별자 영역으로 구분 된 영역은 그대로 두고, 바탕 영역으로 구분된 영역 은 전체 영상의 평균 픽셀 값으로 대체시킨다. 그리고 Sobel 마스크를 이용하여 에지를 검출하고, 추출된 에지를 이용하여 수직 블록과 수평 블록을 검출 하여 컨테이너의 식별자 영역을 추출하고 이진화한다. 이진화 된 식별자 영역에 대해 검정색의 빈도수를 이용하여 흰바탕과 민바탕을 구분하고 4 방향 윤곽선 추적 알고리즘을 적용하여 개별 식별자를 추출 한다. 개별 식별자 인식을 위해 자가 생성 지도 학습 알고리즘을 제안하여 개별 식별자 인식에 적용한다. 제안된 자가 생성 지도 학습 알고리즘은 입력층과 은닉층 사이의 구조를 ART-l을 개선하여 적용하고 은닉층과 출력층 사이에는 일반화된 델타 학습 방법과 Delta-bar-Delta 알고리즘을 적용하여 학습 및 인식 성능을 개선한다. 실제 80 개의 컨테이너 영상을 대상으로 실험한 결과, 제안된 식별자 추출 방법이 이전의 개별 추출 방법보다 추출률이 개선되었고 FCM 기반 자가 생성 지도 학습 알고리즘보다 제안된 자가 생성 지도 학습 알고리즘이 컨테이너 식별자의 학습 및 인식에 있어서 개선된 것을 확인하였다.색 문제를 해결하고자 하는 것이 연구의 목적이다. 정보추출은 사용자의 관심사에 적합한 문서들로부터 어떤 구체적인 사실이나 관계를 정확히 추출하는 작업을 가리킨다.앞으로 e-메일, 매신저, 전자결재, 지식관리시스템, 인터넷 방송 시스템의 기반 구조 역할을 할 수 있다. 현재 오픈웨어에 적용하기 위한 P2P 기반의 지능형 BPM(Business Process Management)에 관한 연구와 X인터넷 기술을 이용한 RIA (Rich Internet Application) 기반 웹인터페이스 연구를 진행하고 있다.태도와 유아의 창의성간에는 상관이 없는 것으로 나타났고, 일반 유아의 아버지 양육태도와 유아의 창의성간의 상관에서는 아버지 양육태도의 성취-비성취 요인에서와 창의성제목의 추상성요인에서 상관이 있는 것으로 나타났다. 따라서 창의성이 높은 아동의 아버지의 양육태도는 일반 유아의 아버지와 보다 더 애정적이며 자율성이 높지만 창의성이 높은 아동의 집단내에서 창의성에 특별한 영향을 더 미치는 아버지의 양육방식은 발견되지 않았다. 반면 일반 유아의 경우 아버지의 성취지향성이 낮을 때 자녀의 창의성을 향상시킬 수 있는 것으로 나타났다. 이상에서 자녀의 창의성을 향상시키는 중요한 양육차원은 애정성이나 비성취지향성으로 나타나고 있어 정서적인 측면의 지원인 것으로 밝혀졌다.징에서 나타나는 AD-SR맥락의 반성적 탐구가 자주 나타났다. 반성적 탐구 척도 두 그룹을 비교 했을 때 CON 상호작용의 특징이 낮게 나타나는 N그룹이 양적으로 그리고 내용적으로 더 의미 있는 반성적 탐구를 했다용을 지원하는 홈페이지를 만들어 자료

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.1 no.1
• /
• pp.82-86
• /
• 1989

A study has been conducted experimentally on heat transfer characteristics of the heat exchangers with louvered fins in air. The experimental results are as follows; 1. Mean heat transfer coefficient is decreased with increasing temperature difference and model III is the best at constant temperature difference. 2. Pressure drop is increased with increasing air velocity, but it is decreased as the heat transfer area increases. 3. $\bar{h}/^{\Delta}p$ is increased and then decreased as air velocity increases.

• Honam Mathematical Journal
• /
• v.40 no.3
• /
• pp.433-446
• /
• 2018

In this present investigation, we introduce a new class of harmonic univalent functions of the form $f=h+{\bar{g}}$ in the open unit disk ${\Delta}$. We get basic properties, like, necessary and sufficient convolution conditions, distortion bounds, compactness and extreme points for these classes of functions.

• Proceedings of the KWS Conference
• /
• 2002.10a
• /
• pp.570-576
• /
• 2002

Application of the aged Inconel 718 in hydrogen environment is seriously restraint by its high hydrogen embrittlement (HE) sensitivity. m previous researches, we have suggested the possibility and applicability of the laser surface annealing (LSA) process in improving the HE resistance of this alloy. Sequentially, a study on the effects of the precipitates in the Inconel 718 on its HE sensitivity was conducted in this research. Firstly, flat bar specimens were heat-treated to obtain various kinds of precipitation microstructures concerning the ${\gamma}$" phase and the 6 phase. Hydrogen was charged into the specimen by a cathodic charging process. The loss in reduction of area (RA) caused by hydrogen charging was used to assess the HE sensitivity. The HE sensitivity of the alloy was lowered with decreasing the volume fraction of ${\gamma}$". Moreover, it was possible to increase the HE resistance of the aged alloy by dissolving the $\delta$ phase, keeping the strength at the same level as that of the common aged alloy. Thus, we concluded that both the $\delta$ phase and the ${\gamma}$" phase affected the HE sensitivity of Inconel 718. Next, two kinds of notch tensile specimens were fabricated, one kind having $\delta$ phase and the other having no $\delta$ phase. All these specimens were aged via the same aging heat treatment process. The LSA process annealed a thin layer of the notch bottom of each specimen. One specimen of each kind was charged with hydrogen by the cathodic hydrogen charging process. Loss in the notch tensile strength (NTS) caused by hydrogen was used to evaluate the HE sensitivity. It was found that while the HE sensitivity of conventionally aged Inconel 718 was decreased by the LSA process, the HE sensitivity of the $\delta$-free aged Inconel 718 could further be decreased. Therefore, for applications in hydrogen environments, it is possible to fabricate alloys with both good HE resistance and high strength by controlling the precipitation conditions, and to improve HE resistance further via applying the LSA process.

• Economic and Environmental Geology
• /
• v.27 no.4
• /
• pp.345-361
• /
• 1994

Lens shaped titanomagnetite ore bodies in the Soyeonpyeong iron mine are embedded in amphibolites, which were intruded into Precambrian metasediments such as garnet-mica schist, marble, mica schist, and quartz schist. Mineral chemistry, K-Ar dating and hydrogen and oxygen stable isotopic analysis for the amphibolites and titanomagnetite ores were conducted to interpret petrogenesis of amphibolite and ore genesis of titanomagnetite iron ore deposits. Amphibolites of igneous origin have unusually high content of $TiO_2$, ranging from 0.94 to 6.39 wt.% with an average value of 4.05 wt.%. REE patterns of the different lithology of the amphibolite show the similar trend with an enrichment of LREE. Amphiboles of amphibolites are consist mainly of calcic amphiboles such as ferro-hornblende, tschermakite, ferroan pargasite, and ferroan pargasitic hornblende. K-Ar ages of hornblende from amphibolite and gneissic amphibolite were determined as $440.04{\pm}6.39Ma$ and $351.03{\pm}5.21Ma$, respectively. This indicates two metamorphic events of Paleozoic age in the Korean peninsula which are correlated with Altin orogeny in China. The titanomagnetite mineralization seems to have occurred before Cambrian age based on occurrence of orebodies and ages of host amphibolites. The Soyeonpyeong iron ores are composed mainly of titanomagnetite, ilmenite, and secondary minerals such as ilmenite and hercynite exsolved in titanomagnetite. The temperature and the oxygen fugacity estimated by the titanomagnetite-ilmenite geothermometer are $500{\sim}600^{\circ}C$ (ave. $550^{\circ}C$) and about $2{\pm}10^{-23}bar$, respectively. Hornblendes from ores and amphibolites which responsible for magnetite ore mineralization, have a relatively homogeneous isotopic composition ranging from +0.8 to +3.9 ‰ in ${\delta}^{18}O$ and from -87.8 to -113.3 ‰ in ${\delta}D$. The calculated oxygen and hydrogen isotopic compositions of the fluids which were in equilibrium with hornblende at $550^{\circ}C$, range from 2.8 to 5.9‰ in ${\delta}^{18}O_{H2O}$ and from -60.41 to -81.31 ‰ in ${\delta}D_{H2O}$. The ${\delta}^{18}O_{H2O}$ value of magnetite ore fluids are in between +6.4 to + 7.9 ‰. All of these values fall in the range of primary magmatic water. A slight oxygen shift means that $^{18}O$-depleted meteoric water be acted with basic fluids during immiscible processes between silicate and titaniferous oxide melt. Mineral chemistry, isotopic compositions, and occurences of amphibolites and orebodies, suggest that the titanomagnetite melt be separated immisciblely from the titaniferous basic magma.

• Journal of the Korean Chemical Society
• /
• v.36 no.1
• /
• pp.28-32
• /
• 1992

The critical micelle concentration(CMC) values of Dodecylpyridinium bromide(DoPB) were determined by an electric conductivity method at 1${\sim}$2000 bars and $25^{\circ}C$. The CMC of DoPB increases with the addition of urea in the whole pressure region studied, and the CMC increases with an increase of the pressure in the low-pressure region, while in the high-pressure region the CMC decreases. The partial molar volume change $({\Delta}V^m_o)$ on micellization was also investigated in some urea aqueous solutions. The change $({\Delta}V^m_o)$ was reduced by the addition of urea. The results suggest that the "iceberg" structure of water around the hydrocarbon chain of the monomeric surfactant is effectively broken down by urea.

• Journal of Sensor Science and Technology
• /
• v.8 no.1
• /
• pp.45-52
• /
• 1999

In this raper, an enhanced learning method is proposed for improving the learning speed of the error back propagation learning algorithm. In order to cope with the premature saturation phenomenon at the initial learning stage, a variation scheme of active functions is introduced by using higher order functions, which does not need much increase of computation load. It naturally changes the learning rate of inter-connection weights to a large value as the derivative of sigmoid function abnormally decrease to a small value during the learning epoch. Also, we suggest the hybrid learning method incorporated the proposed method with the momentum training algorithm. Computer simulation results show that the proposed learning algorithm outperforms the conventional methods such as momentum and delta-bar-delta algorithms.