• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.39-39
• /
• 2019

인구의 도시 집중화로 인하여 다량의 생활용수의 사용에 따라 하천의 자정능력을 초과하여 오염을 유발시키고 있다. 이에 도시하천들의 오염은 점점 심해져 경제적으로 많은 문제를 유발하고 있다. 이러한 하천오염 문제를 과학적으로 대응하기 위해서는 오염물질의 농도 측정 및 데이터 축척을 통한 오염예측이 필수적이라 할 수 있으며, 부산광역시 보건환경정보 공개시스템에서는 하천수질 자동측정망을 설치하여 시간 단위로 오염물질을 측정하고 있다. 그러나 온천천의 하천수질 데이터는 계속 쌓여가고 있는데 이 데이터를 활용해서 하천수질 인자 예측이 거의 이뤄지지 않고 있다. 본 연구에서는 순환신경망 알고리즘을 활용하여 일 단위의 하천수질 인자 예측을 시도하였다. 순환신경망은 인공신경망의 발전된 형태인 시계열 학습에 강한 RNN, LSTM 알고리즘을 활용한 일단위 하천수질 인자 예측을 하고자 하였다. 연구에 앞서 시간 단위로 쌓여있는 데이터를 평균 내어 일 단위로 변경하였고 이 데이터를 가지고 일 단위 하천수질 인자 예측을 진행하였다. 연구에는 Google에서 개발한 딥러닝 오픈소스 라이브러리인 텐서플로우를 활용하여 DO, 탁도 등 항목을 예측하였다. 하천오염의 학습과 예측을 위해 대상지로는 부산지역 온천천의 부곡교, 세병교, 이섭교 관측소를 선택하였다. 연구를 위해 DO, 탁도 등 자료 수집은 부산광역시 보건환경정보 공개시스템의 자료를 활용하였다. 모형의 학습을 위해 입력자료로는 하천수질 인자 자료를 이용하였고, 자료의 학습에는 2014년~2017년 4년간의 자료를 학습자료로 사용하였고, 2018년 1년간의 자료는 모형의 검증을 위해 사용하였다. RNN, LSTM 알고리즘을 활용하여 분석 시 은닉층의 개수, 반복시행횟수, sequence length 등의 값을 조절하여 하천수질 인자 예측을 하였다. 모형의 검증을 위해 $R^2$(r square)와 RMSE(root mean square error)을 이용하여 통계분석을 실시하였다.

• Journal of the Korean Society of Propulsion Engineers
• /
• v.22 no.4
• /
• pp.99-107
• /
• 2018

In this study, the injector transfer function (ITF) of a gas-gas coaxial jet-swirl injector is measured by perturbing jet or swirl flow using a speaker as jet flow increases. As a result of measuring the ITF varying feed system length, a peak occurs at a resonance frequency of space where the perturbed flow passes. With jet excitation, the ITF magnitude decreases, but increases thereafter as increasing the jet flow. Therefore the larger the velocity difference between jet and swirl flow, the larger the ITF. With swirl excitation, ITF decreases as increasing the jet flow because of the energy decrease with respect to the constant downstream flow.

• Journal of the Korea Convergence Society
• /
• v.12 no.9
• /
• pp.21-30
• /
• 2021

Unlike behaviors that are generally known, information regarding unspecific behaviors is insufficient. For an education or guidance regarding the unspecific behaviors, collection and management of data regarding the unspecific behaviors of special-needs students are needed. In this paper, a consultation management model based on behavior classification of special-needs students using machine learning is proposed. It collects data by photographing the behavior of special students in real time, analyzes the behavior pattern, composes a data set, and trains it in the suggestion system. It is possible to improve the accuracy by comparing the behavior of special students photographed later into the suggestion system and analyzing the results by comparing it with the existing data again. The test has been performed by arbitrarily applying unspecific behaviors that are not stored in the database, and the forecast model has accurately classified and grouped the input data. Also, it has been verified that it is possible to accurately distinguish and classify the behaviors through the feature data of the behaviors even if there are some errors in the input process.

• Journal of the Korean Recycled Construction Resources Institute
• /
• v.9 no.3
• /
• pp.389-396
• /
• 2021

In this paper, it was evaluated that the effect of self-healing microcapsules on the quality and healing properties of cement composites. In the mixing of microcapsules, the plastic viscosity and yield stress of the cement composites decreased due to the particle properties of the microcapsules, and decreased in proportion to the mixing ratio. The table flow showed a tendency to decrease as the core material acted as a stimulant due to the loss of microcapsules, and the compressive strength could be supplemented through unit quantity correction. As a result of evaluating the effect of microcapsule mixing on the healing properties of cement composites, it was found that the unit water flow rate decreased by the healing reaction immediately after crack initiation. When more than 3% of microcapsules were mixed, it was found that there was a healing rate of more than 95% at 7 days of healing age.

• Journal of the Korean Recycled Construction Resources Institute
• /
• v.9 no.3
• /
• pp.397-404
• /
• 2021

In this study, it was reviewed that the effect of solid capsules on the quality of surface repair materials and the healing properties of long-term aging, as part of a study to utilize self-healing surface repair materials using solid capsules as repair materials. As a result of evaluation of the rheological properties of self-healing surface repair materials according to the mixing of solid capsules, plastic viscosity, yield stress, and table flow tended to decrease. In the case of compressive strength, 1MPa per 1% of the solid capsule decreased proportionally. As a result of evaluating the long-term healing properties, when 10% of solid capsules were mixed, a healing rate of 90% was shown at 28 days of healing, because the solid capsule was preserved even after 91 days of age had elapsed. after 91 days of healing, even in the case of 5% of solid capsules, a healing rate of 90% was shown.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.25 no.6
• /
• pp.27-32
• /
• 2021

This study was conducted to improve the workability of cementitious composites using nano-bubble water. The used nano-bubble water contains 7% of nano-sized bubbles with an averaged bubble size of 750 nm. Various different types of cementitious composites including ultar-high performance concrete, lightweight cementitious composites, and high-strength mortar have been tested to identify the changes of material properties. From the use of nano-bubble water, it was confirmed that workability has been improved by 3-22%. On the other hand, other material characteristics such as compressive strength did not have noticeable changes. Therefore, it was proposed that the use of nano-bubble water can enhance workability of cementitious composites without having significant impact on other material properties.

• International Area Studies Review
• /
• v.15 no.2
• /
• pp.51-76
• /
• 2011

Since Japanese government took reformative measures of public investment in the period of 2000s, this paper investigates how the economic effects of public investments has improved in the period of 2000s. The empirical findings do not show that the output elasticity with respect to public capital has been higher in the 2000s than that of 1990s. Rather, some output elasticity estimates for 2000s has lowered after the advent of year 2000. In addition, the impact of public capital on the productivity of private capital has not improved in the 2000s compared with that of 1990s in Japan. Another major finding shows that the crowding-out effect of public investment has been stronger in the 2000s than before. Those findings imply that the reforms done by Japanese government in the 2000s regarding public investment do not spread out into the private aggregate production and investment.

• Journal of the Korea Institute of Building Construction
• /
• v.18 no.6
• /
• pp.551-558
• /
• 2018

This study evaluate the fluidity and hardening properties of mortar by replacement ratio of ferronickel slag powder to estimate the applicability of ferronickel slag powder for cement replacement materials. Ferronickel slag powder was replaced by 0, 5, 10, 15 and 20% of the cement weight. In addition, blast furnace slag powder and fly ash were also used for comparing with the mixtures using ferronickel slag powder. As the test results, the micro-hydration heat of the mixture containing the ferronickel slag powder was lower than that of the mixtures containing the same amount of blast furnace slag powder and fly ash. The flow of the sample with ferronickel slag powder was relatively higher than the other mixtures. In all ages, the compressive strength of the mixture with ferronickel slag powder and fly ash was similar to that of the mix containing only fly ash. In case of drying shrinkage, the mixture containing ferronickel slag powder exhibited lower drying shrinkage than the mixture using blast furnace slag powder, and similar to the mixture containing fly ash.

• Journal of Convergence for Information Technology
• /
• v.8 no.6
• /
• pp.149-157
• /
• 2018

In this paper, we propose an attack detection technology using SDN Controller to study security threats in IoT environment. The research methodology has been developed by applying IoT security threat management technology to the IoT layer and analyzing the research trend of applied security technology. The study results show that the effectiveness of the detection method using the sampling method is studied by adding OpenFlow based SDN Controller to the network switch equipment of the existing IoT network. This method can detect the monitoring and attack of the whole network by interworking with IDS and IPS without affecting the performance of existing IoT devices. By applying such improved security threat countermeasure technology, we expect to be able to relieve anxiety of IoT security threat and increase service reliability.

• Journal of the Korea Society for Simulation
• /
• v.28 no.2
• /
• pp.97-105
• /
• 2019

The tactical mobile ad-hoc network(MANET) consists of distributed autonomous networks between individual ground nodes, which is effective in terms of network survivability and flexibility. However, due to constraints such as limited power, terrain, and mobility, frequent link disconnection and shadow area may occur in communication. On the other hand, the satellite network has the advantage of providing a wide-area wireless link overcoming terrain and mobility, but has limited bandwidth and high-latency characteristic. In the future battlefield, an integrated network architecture for interworking multi-layer networks through a heterogeneous network gateway (HNG) is required to overcome the limitations of the existing individual networks and increase reliability and efficiency of communication. In this paper, we propose a new HNG architecture and detailed algorithm that integrates satellite network and the tactical MANET and enables reliable data transfer based on flow characteristics of traffic. The simulations validated the proposed architecture using Riverbed Modeler, a network-level simulator.