• 한국수자원학회논문집
• /
• 제41권10호
• /
• pp.1059-1065
• /
• 2008

강우자료는 수문 해석에 있어 가장 기본이 되는 입력 자료이며, 다양한 원인에 의해 결측이 발생된다. 본 연구에서는 복잡한 자연현상 문제 해결에 그 응용성이 입증된 신경망 기법을 이용하여 결측 처리된 강우를 추정하기 위해서 소양강댐 유역 12개 강우량 관측소를 대상으로 신경망 모형을 구축하였으며, 모형의 성능 평가를 위해 실무에서 가장 많이 사용되고 있는 우량 보정 방법인 역거리법(RDS)과 산술평균법(AMM)으로 추정한 값과 비교하여 신경망을 이용한 추정 방법의 우수성을 보였다. 그리고 온라인상에서 보다 신뢰성 있는 수문자료를 재난관련 유관기관으로 전송하기 위해서 신경망 모형을 이용한 상시 실시간 보정이 가능하도록 신경망 학습기로 구성된 자동 보정시스템을 제안하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제5권9호
• /
• pp.1492-1512
• /
• 2011

Due to multiple hops, mobility and time-varying channel, supporting delay sensitive real-time traffic in wireless local area network-based (WLAN) mesh networks is a challenging task. In particular for real-time traffic subject to medium access control (MAC) layer control overhead, such as preamble, carrier sense waiting time and the random backoff period, the performance of real-time flows will be degraded greatly. In order to support real-time traffic, an efficient adaptive packet scheduling (APS) scheme is proposed, which aims to improve the system performance by guaranteeing inter-class, intra-class service differentiation and adaptively adjusting the packet length. APS classifies incoming packets by the IEEE 802.11e access class and then queued into a suitable buffer queue. APS employs strict priority service discipline for resource allocation among different service classes to achieve inter-class fairness. By estimating the received signal to interference plus noise ratio (SINR) per bit and current link condition, APS is able to calculate the optimized packet length with bi-dimensional markov MAC model to improve system performance. To achieve the fairness of intra-class, APS also takes maximum tolerable packet delay, transmission requests, and average allocation transmission into consideration to allocate transmission opportunity to the corresponding traffic. Detailed simulation results and comparison with IEEE 802.11e enhanced distributed channel access (EDCA) scheme show that the proposed APS scheme is able to effectively provide inter-class and intra-class differentiate services and improve QoS for real-time traffic in terms of throughput, end-to-end delay, packet loss rate and fairness.

• 한국시뮬레이션학회논문지
• /
• 제24권3호
• /
• pp.9-16
• /
• 2015

본 연구에서는 북한의 잠수함 발사 탄도미사일의 비행궤적을 시뮬레이션하고 발사방법에 따른 특성을 분석하였다. 최근 북한은 잠수함 발사 탄도미사일의 비행시험을 실시하였으며, 이는 국제적인 안보에 상당한 위협이 되고 있다. 북한은 러시아의 퇴역 잠수함을 해체하는 과정에서 잠수함 발사 탄도미사일 관련 기술을 확보하였고, 이와 관련된 실험을 지속적으로 하는 것으로 알려졌다. 북한의 잠수함 발사 탄도미사일 개발이 완료되고 실전 배치된다면, 이는 우리나라에 비대칭적인 위협 요소로 작용하게 될 것이다. 따라서 이러한 위협에 능동적으로 대응하기 위해서는 잠수함 발사 탄도미사일의 위협에 대한 과학적이고 논리적인 분석이 이루어져야 한다. 이러한 관점에서 본 연구에서는 북한의 잠수함 발사 탄도미사일의 운동 모델을 작성하고 이를 시뮬레이션 하였다. 또한 잠수함 발사 탄도미사일의 자세각을 조절하여 사거리를 조정하였으며 이에 대한 특성변화에 대해 기술하였다. 도출된 SLBM 비행궤적을 고려할 때 중간 단계부터 종말 단계까지의 효과적인 대응을 위해서는 해상기반 탄도미사일 방어체계가 필수적으로 요구되어 진다.

• Smart Structures and Systems
• /
• 제19권1호
• /
• pp.105-113
• /
• 2017

A microstructure-dependent dynamic model for silicon nanobeams with axial motion is developed by considering the effects of nonlocal elasticity and surface energy. The nanobeam is considered to subject to both transverse and longitudinal loads arising from nanostructural surface effect and all positive directions of physical quantities are defined clearly prior to modeling so as to clarify the confusions of sign in governing equations of previous work. The nonlocal and surface effects are taken into consideration in the dynamic behaviors of silicon nanobeams with axial motion including circular natural frequency, vibration mode, transverse displacement and critical speed. Various supporting conditions are presented to investigate the circular frequencies by a numerical method and the effects of many variables such as nonlocal nanoscale, axial velocity and external loads on non-dimensional circular frequencies are addressed. It is found that both nonlocal and surface effects play remarkable roles on the dynamics of nanobeams with axial motion and cause the frequencies and critical speed to decrease compared with the classical continuum results. The comparisons of the non-dimensional calculation values by present and previous studies validate the correctness of the present work. Additionally, numerical examples for silicon nanobeams with axial motion are addressed to show the nonlocal and surface effects on circular frequencies intuitively. Results obtained in this paper are helpful for the design and optimization of nanobeam-like microstructures based sensors and oscillators at nanoscale with desired dynamic mechanical properties.

• 한국인터넷방송통신학회논문지
• /
• 제21권5호
• /
• pp.47-52
• /
• 2021

최근 제조 산업에서 생산공정 관리에 대한 인공지능 솔루션 수요가 증가하고 있다. 그러나, 제조산업의 AI 솔루션 적용을 통하여 POP, MES와 같은 레거시 스마트공장 솔루션의 한계가 존재한다. 따라서, 본 논문에서는 이를 극복하기 위하여 이미지 인식 시스템에 인공지능 개념인 지도학습을 적용하여, 생산관리 효율을 향상시키고자 하였다. 시스템 흐름에서는 As_is To be를 구분하여 실제 업무 흐름을 적용하였으며, 전체 생산성 효율을 위하여 프로세스 개선을 하였다. AI 지도학습을 위한 사전 전처리 계획을 수립하고 관련 AI 모델 설계, 개발, 시뮬레이션을 수행하여, 그 결과로는 97%의 인식률을 확인하였다.

• Nuclear Engineering and Technology
• /
• 제51권3호
• /
• pp.807-817
• /
• 2019

Airborne Gamma Ray Spectrometry (AGRS) with its important applications such as gathering radiation information of ground surface, geochemistry measuring of the abundance of Potassium, Thorium and Uranium in outer earth layer, environmental and nuclear site surveillance has a key role in the field of nuclear science and human life. The Broyden-Fletcher-Goldfarb-Shanno (BFGS), with its advanced numerical unconstrained nonlinear optimization in collaboration with Artificial Neural Networks (ANNs) provides a noteworthy opportunity for modern AGRS. In this study a new AGRS system empowered by ANN-BFGS has been proposed and evaluated on available empirical AGRS data. To that effect different architectures of adaptive ANN-BFGS were implemented for a sort of published experimental AGRS outputs. The selected approach among of various training methods, with its low iteration cost and nondiagonal scaling allocation is a new powerful algorithm for AGRS data due to its inherent stochastic properties. Experiments were performed by different architectures and trainings, the selected scheme achieved the smallest number of epochs, the minimum Mean Square Error (MSE) and the maximum performance in compare with different types of optimization strategies and algorithms. The proposed method is capable to be implemented on a cost effective and minimum electronic equipment to present its real-time process, which will let it to be used on board a light Unmanned Aerial Vehicle (UAV). The advanced adaptation properties and models of neural network, the training of stochastic process and its implementation on DSP outstands an affordable, reliable and low cost AGRS design. The main outcome of the study shows this method increases the quality of curvature information of AGRS data while cost of the algorithm is reduced in each iteration so the proposed ANN-BFGS is a trustworthy appropriate model for Gamma-ray data reconstruction and analysis based on advanced novel artificial intelligence systems.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제10권11호
• /
• pp.521-528
• /
• 2021

군사 분야에서 사용 중인 기존 영상 판독 시스템은 판독관들이 직접 영상을 분석 및 식별하여 관련 내용을 보고서에 작성하고 전파하는 방식으로 진행되는데 이 과정에서 반복 작업이 빈번하여 업무 과부하가 발생한다. 본 논문에서는 이러한 문제를 해결하고자, 기존의 문장 단위로 동작하는 Seq2Seq 모델을 단어 단위로 동작할 수 있는 알고리즘을 제안하고, Attention 기법을 적용해 정확도를 향상시키고자 한다. 또한 Beam 탐색 기법을 응용하여 특정 지역의 과거 식별내용을 바탕으로 현재 식별 문장을 다양하게 추천하고자 한다. 실험을 통해 Beam 탐색 기법이 기존 Greedy 탐색 기법보다 효과적으로 문장을 추천하는 것을 확인하였고, Beam의 크기가 클 때 추천의 정확도가 높아지는 것을 확인하였다.

• Journal of Information Science Theory and Practice
• /
• 제9권1호
• /
• pp.1-23
• /
• 2021

This study introduces novel research using Practice Context Models supported by Knowledge Networks and Percolation Theory with the aim to contribute to knowledge management in Proof-of-Concept (PoC) activities. The authors envision this proposal as a potential instrument to identify network structures based on a percolation (propagation) threshold and to analyze the importance of nodes (e.g., practitioners, practices, competencies, movements, and scenarios) during the percolation of knowledge in PoC activities. After thirty months immersed in the natural PoC habitat, acting as observers and practitioners, and supported by an ethnographic exercise and a designer-research mindset, the authors identified the production of meaning in PoC activities occurring in a hermeneutic circle characterized by the presence of several knowledge networks; thus, discovering the 'natural knowledge' in PoC as a spectrum of cognitive development spread throughout its network, as each node could produce and disseminate certain knowledge that flows and influences other nodes. Therefore, this research presents the use of Practice Context Models 'connected' to Knowledge Networks and Percolation Theory as a potential and feasible proposal to be built using the attribution of values (weights) to the nodes (e.g., practitioners, practices, competencies, movements, scenarios, and also knowledge) in the context of PoC with the aim to allow the players (e.g., PoC practitioners) to have more flexibility in building alliances with other players (new nodes); that is, focusing on those nodes with higher value (focus on quality) in collaboration networks, i.e., alliances (connections) with the aim to contribute to knowledge management in the context of PoC.

• International Journal of Computer Science & Network Security
• /
• 제23권5호
• /
• pp.148-162
• /
• 2023

Classification systems can significantly assist the medical sector by allowing for the precise and quick diagnosis of diseases. As a result, both doctors and patients will save time. A possible way for identifying risk variables is to use machine learning algorithms. Non-surgical technologies, such as machine learning, are trustworthy and effective in categorizing healthy and heart-disease patients, and they save time and effort. The goal of this study is to create a medical intelligent decision support system based on machine learning for the diagnosis of heart disease. We have used a mixed feature creation (MFC) technique to generate new features from the UCI Cleveland Cardiology dataset. We select the most suitable features by using Least Absolute Shrinkage and Selection Operator (LASSO), Recursive Feature Elimination with Random Forest feature selection (RFE-RF) and the best features of both LASSO RFE-RF (BLR) techniques. Cross-validated and grid-search methods are used to optimize the parameters of the estimator used in applying these algorithms. and classifier performance assessment metrics including classification accuracy, specificity, sensitivity, precision, and F1-Score, of each classification model, along with execution time and RMSE the results are presented independently for comparison. Our proposed work finds the best potential outcome across all available prediction models and improves the system's performance, allowing physicians to diagnose heart patients more accurately.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2021년도 학술발표회
• /
• pp.60-60
• /
• 2021

Investigating Backward-Facing Step(BFS) flow is important in that it is a representative case for separation flows in various engineering flow systems. There have been a wide range of experimental, theoretical, and numerical studies to investigate the flow characteristics over BFS, such as flow separation, reattachment length and recirculation zone. However, most of such previous studies were concentrated only on the perpendicular step angle. In this study, several numerical investigations on the flow pattern over BFS with various step angles (10° ~ 90°) and expansion ratios (1.48, 2 and 3.27) under different Reynolds numbers (5000 ~ 64000) were carried out, mainly focused on the reattachment length. The numerical simulations were performed using an open source 3D CFD software, OpenFOAM, in which the velocity profiles and turbulence intensities are calculated by RANS (Reynolds Averaged Navier-Stokes equation) and 3D LES (Large Eddy Simulation) turbulence models. Overall, it shows a good agreement between simulations and the experimental data by Ruck and Makiola (1993). In comparison with the results obtained from RANS and 3D LES, it was shown that 3D LES model can capture much better and more details on the velocity profiles, turbulence intensities, and reattachment length behind the step for relatively low Reynolds number(Re < 11000) cases. However, the simulation results by both of RANS and 3D LES showed very good agreement with the experimental data for the high Reynolds number cases(Re > 11000). For Re > 11000, the reattachment length is no longer dependent on the Reynolds number, and it tends to be nearly constant for the step angles larger than 30°.) Based on the calibrated and validated numerical simulations, several additional numerical simulations were also conducted with higher Reynolds number and another expansion ratio which were not considered in the experiments by Ruck and Makiola (1993).