• 디지털콘텐츠학회 논문지
• /
• 제19권4호
• /
• pp.749-756
• /
• 2018

본 연구는 머신러닝 기법을 이용한 온실 제어를 위한 예측모델을 개발하는 것이 목적이다. 시설원예연구소의 실험온실에서 측정된 데이터(2016년)를 사용하여 예측모델을 개발하였다. 모델의 예측성능 향상과 데이터의 신뢰성 확보를 위해 상관관계분석을 통해 데이터의 축소를 수행하였다. 데이터는 계절별 특성을 고려하여 봄, 여름, 가을 및 겨울로 나누어 구축하였다. 머신러닝 기반의 예측모델로 인공신경망, 순환신경망 및 다중회귀모델을 구축하고 비교분석을 통해 타당성을 평가하였다. 분석 결과에서, Selected dataset에서는 인공신경망 모델이 Full dataset에서는 다중회귀모델이 좋은 예측성능을 보였다.

• 한국컴퓨터정보학회논문지
• /
• 제23권11호
• /
• pp.43-49
• /
• 2018

In this paper, we propose a displacement measurement method based on deep learning using image data obtained from tensile tests of a material specimen. We focus on the fact that the sequential images during the tension are generated and the displacement of the specimen is represented in the image data. So, we designed sample generation model which makes sequential images of specimen. The behavior of generated images are similar to the real specimen images under tensile force. Using generated images, we trained and validated our model. In the deep neural network, sequential images are assigned to a multi-channel input to train the network. The multi-channel images are composed of sequential images obtained along the time domain. As a result, the neural network learns the temporal information as the images express the correlation with each other along the time domain. In order to verify the proposed method, we conducted experiments by comparing the deformation measuring performance of the neural network changing the displacement range of images.

• 산업경영시스템학회지
• /
• 제35권3호
• /
• pp.62-69
• /
• 2012

This thesis proposes a new social network simulator, which can be used for the social network analysis (SNA). It is composed of three modules; initialization, network evolution, and output generation. For the network evolution module, we suggest a modified JGN (MJGN) based on JGN, the network evolution model developed by Jin, Girvan, and Newman. Arena, one of the most popular simulation tools, was used to model the agent based social network simulator. Lastly, some test results were presented to show the value of the proposed simulator when one performs SNA at the longitudinal point of view.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권2호
• /
• pp.473-493
• /
• 2019

5G vehicular communication is one of key enablers in next generation intelligent transportation system (ITS), that require ultra-reliable and low latency communication (URLLC). To meet this requirement, a new hybrid vehicular network structure which supports both centralized network structure and distributed structure is proposed in this paper. Based on the proposed network structure, a new vehicular network utility model considering the latency and reliability in vehicular networks is developed based on Euclidean norm theory. Building on the Pareto improvement theory in economics, a vehicular network uplink optimization algorithm is proposed to optimize the uplink utility of vehicles on the roads. Simulation results show that the proposed scheme can significantly improve the uplink vehicular network utility in vehicular networks to meet the URLLC requirements.

• 스마트미디어저널
• /
• 제10권1호
• /
• pp.79-87
• /
• 2021

In recent years research on automatic font generation with machine learning mainly focus on using transformation-based methods, in comparison, generative model-based methods of font generation have received less attention. Transformation-based methods learn a mapping of the transformations from an existing input to a target. This makes them ambiguous because in some cases a single input reference may correspond to multiple possible outputs. In this work, we focus on font generation using the generative model-based methods which learn the buildup of the characters from noise-to-image. We propose a novel way to train a conditional generative deep neural model so that we can achieve font style control on the generated font images. Our research demonstrates how to generate new font images conditioned on both character class labels and character style labels when using the generative model-based methods. We achieve this by introducing a modified generator network which is given inputs noise, character class, and style, which help us to calculate losses separately for the character class labels and character style labels. We show that adding the character style vector on top of the character class vector separately gives the model rich information about the font and enables us to explicitly specify not only the character class but also the character style that we want the model to generate.

• International Journal of Computer Science & Network Security
• /
• 제22권5호
• /
• pp.1-4
• /
• 2022

The growth in global population and industrialization has led to an increasing demand for electricity. Accordingly, the electricity providers need to increase the electricity generation. Due to the economical and environmental concerns associated with the generation of electricity from fossil fuels. Alternative power recourses that can potentially mitigate the economical and environmental are of interest. Renewable energy resources are promising recourses that can participate in producing power. Among renewable power resources, solar energy is an abundant resource and is currently a field of research interest. Photovoltaic solar power is a promising renewable energy resource. The power output of PV systems is mainly affected by the solar irradiation and ambient temperature. this paper investigates the utilization of machine learning unsupervised neural network techniques that potentially improves the reliability of PV solar power systems during integration into the electrical grid.

• 디지털콘텐츠학회 논문지
• /
• 제5권1호
• /
• pp.7-11
• /
• 2004

차세대 고속 통신망을 구축하기 위해서는 해결해야 할 많은 문제들이 있는데, 이 중에서 기본적으로 고려해야 할 사항은 바로 망에 흐르는 트래픽의 특성 분석이다. 현재 제공되는 많은 인터넷 서비스들의 동작 특성은 자기 유사성(Self-similar)이라는 기존에 고려되던 트래픽 특성과는 완전히 다른 장기간 의존성의 성질들을 가진다는 것이 증명되었다 이러한 장기간 의존성 성질을 표현하기 위한 모델로는 자기유사 모델이 있는데, 이것은 단기간 의존성을 표현하는 기존의 모델인 포아송 모델과는 상반되는 개념이다. 따라서 차세대 통신망의 설계 및 디멘져닝을 위해서는 무엇보다도 데이터 트래픽의 주요 특성인 버스트성(Burstiness)과 자기유사성이 반영된 트래픽 모델이 요구된다. 여기서 자기유사성은 허스트 파라미터(Hurst Parameter)로 특성화 될 수 있다. 본 논문에서는 데이터 트래픽의 자기유사성 및 큐잉지연을 고려한 유효대역폭 산출식을 유도하여 시뮬레이션 결과와 비교 분석하였다.

• 조명전기설비학회논문지
• /
• 제23권12호
• /
• pp.210-216
• /
• 2009

마이크로그리드는 전력시스템의 계획 및 실시간 운영에 있어서 매우 큰 영향을 미치며 중요한 역할을 할 것으로 판단된다. 따라서 본 연구에서는 빌딩의 마이크로그이드의 중요한 마이크로소오스인 마이크로터빈 발전시스템의 Matlab/Simulink 모델과 전압-주파수제어기를 개발하였다. 또한 부하에 독립적으로 전원을 공급하기 위한 전력시스템을 구성, 모의를 통하여 MTG시스템의 특성을 분석하였다.

• JSTS:Journal of Semiconductor Technology and Science
• /
• 제16권6호
• /
• pp.832-841
• /
• 2016

The voltage-frequency island (VFI) design paradigm has strong potential for achieving high energy efficiency in communication centric manycore system-on-chip (SoC) design called network-on-chip (NoC). However, because of the diminished scaling of wire-dimension and supply voltage as well as threshold voltage in modern CMOS technology, the vulnerability to link failure in VFI NoC is becoming a crucial challenge. In this paper, we propose an energy-optimized topology generation technique for VFI NoC to cope with permanent link failures. Based on the energy consumption model, we exploit the on-chip communication traffic patterns and characteristics of link failures in the early design stage to accommodate diverse applications and architectures. Experimental results using a number of multimedia application benchmarks show the effectiveness of the proposed three-step custom topology generation method in terms of energy consumption and latency without any degradation in the fault coverage metric.

• 한국시뮬레이션학회:학술대회논문집
• /
• 한국시뮬레이션학회 1998년도 The Korea Society for Simulation 98 춘계학술대회 논문집
• /
• pp.101-105
• /
• 1998

A large system predictor, which can perform prediction of sales trend in a huge number of distribution centers, is presented using neural predictive model. There are 20,000 number of distribution centers, and each distribution center need to forecast future demand in order to establish a reasonable inventory policy. Therefore, the number of forecasting models corresponds to the number of distribution centers, which is not possible to estimate that kind of huge number of accurate models in ERP (Enterprise Resource Planning)module. Multilayer neural net as universal approximation is employed for fitting the prediction model. In order to improve prediction accuracy, a sequential simulation procedure is performed to get appropriate network structure and also to improve forecasting accuracy. The proposed simulation procedure includes neural structure identification and virtual predictive model generation. The predictive model generation consists of generating virtual signals and estimating predictive model. The virtual predictive model plays a key role in tuning the real model by absorbing the real model errors. The complement approach, based on real and virtual model, could forecast the future demands of various distribution centers.