• 시스템엔지니어링학술지
• /
• 제19권2호
• /
• pp.18-31
• /
• 2023

Exploring artificial intelligence and machine learning for nuclear safety has witnessed increased interest in recent years. To contribute to this area of research, a machine learning model capable of accurately predicting nuclear power plant response with minimal computational cost is proposed. To develop a robust machine learning model, the Best Estimate Plus Uncertainty (BEPU) approach was used to generate a database to train three models and select the best of the three. The BEPU analysis was performed by coupling Dakota platform with the best estimate thermal hydraulics code RELAP/SCDAPSIM/MOD 3.4. The Code Scaling Applicability and Uncertainty approach was adopted, along with Wilks' theorem to obtain a statistically representative sample that satisfies the USNRC 95/95 rule with 95% probability and 95% confidence level. The generated database was used to train three models based on Recurrent Neural Networks; specifically, Long Short-Term Memory, Gated Recurrent Unit, and a hybrid model with Long Short-Term Memory coupled to Convolutional Neural Network. In this paper, the System Engineering approach was utilized to identify requirements, stakeholders, and functional and physical architecture to develop this project and ensure success in verification and validation activities necessary to ensure the efficient development of ML meta-models capable of predicting of the nuclear power plant response.

• 한국멀티미디어학회논문지
• /
• 제23권2호
• /
• pp.343-350
• /
• 2020

In the era of the Fourth Industrial Revolution in the digital revolution is taking place, various attempts have been made to provide various contents in a digital environment. In this paper, agent-recruitment service system based on collaborative deep learning is proposed for the intelligent head hunting service. The service system is improved from previous research [7] using collaborative deep learning for more reliable recommendation results. The Collaborative deep learning is a hybrid recommendation algorithm using "Recurrent Neural Network(RNN)" specialized for exponential calculation, "collaborative filtering" which is traditional recommendation filtering methods, and "KNN-Clustering" for similar user analysis. The proposed service system can expect more reliable recommendation results than previous research and showed high satisfaction in user survey for verification.

• 전기학회논문지
• /
• 제60권3호
• /
• pp.566-571
• /
• 2011

As Plug-in Hybrid Vehicle and Electric Vehicle (PHEV/EV) take a greater share in the personal automobile market, their high penetration levels may bring potential challenges to electric utility especially at the distribution level. Thus, there is a need for the flexible charging management strategy to compromise the benefits of both PHEV/EV owners and power grid side. There are many different management methods that depend on the objective function and the constraints caused by the system. In this paper, the schema and dispatching schedule of centralized PHEV/EV charging spot network are analyzed. Also, we proposed and compared three power allocation strategies for centralized charging spot. The first strategy aims to maximize state of vehicles at plug-out time, the rest methods are equalized allocation and prioritized allocation based on vehicles SoC. The simulation results show that each run of the optimized algorithms can produce the satisfactory solutions to response properly the requirement from PHEV/EV customers.

• 한국군사과학기술학회지
• /
• 제20권6호
• /
• pp.758-766
• /
• 2017

In this paper, we propose a robust duality of CNN(Du-CNN) method which can classify the target and clutter in coastal environment for IR Imaging Sensor. In coastal environment, there are various clutter that have many similarities with real target due to diverse change of air temperature, water temperature, weather and season. Also, real target have various feature due to the same reason. Thus, the proposed Du-CNN method adopts human's multiple personality utilization and CNN technique to learn and classify target and clutter. This method has an advantage of the real time operation. Experimental results on sampled dataset of real infrared target and clutter demonstrate that the proposed method have better success rate to classify the target and clutter than general CNN method.

• International Journal of Computer Science & Network Security
• /
• 제22권3호
• /
• pp.163-172
• /
• 2022

The interconnection of an enormous number of devices into the Internet at a massive scale is a consequence of the Internet of Things (IoT). As a result, tasks offloading from these IoT devices to remote cloud data centers become expensive and inefficient as their number and amount of its emitted data increase exponentially. It is also a challenge to optimize IoT device energy consumption while meeting its application time deadline and data delivery constraints. Consequently, Fog Computing was proposed to support efficient IoT tasks processing as it has a feature of lower service delay, being adjacent to IoT nodes. However, cloud task offloading is still performed frequently as Fog computing has less resources compared to remote cloud. Thus, optimized schemes are required to correctly characterize and distribute IoT devices tasks offloading in a hybrid IoT, Fog, and cloud paradigm. In this paper, we present a detailed survey and classification of of recently published research articles that address the energy efficiency of task offloading schemes in IoT-Fog-Cloud paradigm. Moreover, we also developed a taxonomy for the classification of these schemes and provided a comparative study of different schemes: by identifying achieved advantage and disadvantage of each scheme, as well its related drawbacks and limitations. Moreover, we also state open research issues in the development of energy efficient, scalable, optimized task offloading schemes for Fog computing.

• 지능정보연구
• /
• 제18권3호
• /
• pp.13-34
• /
• 2012

본 논문에서는 국제학술대회 참가자를 위한 개인화 된 정보추천서비스를 제안한다. 국제학술대회에서는 많은 논문들이 동시에 여러 세션으로 구성되어 발표되고 여러 연구관련 활동들이(예를 들어, 튜토리얼, 산업계토론, 공동연구논의 등) 짧은 기간 동안 이루어지므로 발표되는 논문들을 일일이 확인하고 그 발표에 참여하기가 쉽지 않다. 또한 학술대회의 정보 추천은, 기존의 영화, 책, 음악 등의 상품추천과 달리, 이미 정해진 해당 연구관련 커뮤니티가 대회 참가자들 및 발표자들을 중심으로 구성되어 있으므로 보다 명확한 소셜네트워크 기반추천 서비스가 가능하다. 본 논문에서는 각 학술대회에서 발표되는 논문들의 내용은 무엇인지, 참가자들이 어떤 논문에 관심을 가지는지, 그리고 각 참가자들이 다른 참가자들과의 맺은 소셜네트워크 등의 정보를 통해 발표에 참여할 만한 논문들을 추천하였다. 특히, 실제 운용되고 있는 국제학술대회 정보시스템, Conference Navigator를 이용하여, 여러 학술논문 관련 추천서비스를 비교 실험하였다. 기존의 Collaborative filtering 추천 알고리듬뿐만 아니라 학술대회참가자들의 소셜네트워크 기반 추천 서비스를 제공하였으며 연구결과 Cold-start 사용자들에게 특히 소셜네트워크 기반추천이 가장 좋은 결과를 보여주었다.

• ETRI Journal
• /
• 제40권4호
• /
• pp.421-434
• /
• 2018

The application of deep neural networks (DNNs) to connect the world with cyber physical systems (CPSs) has attracted much attention. However, DNNs require a large amount of memory and computational cost, which hinders their use in the relatively low-end smart devices that are widely used in CPSs. In this paper, we aim to determine whether DNNs can be efficiently deployed and operated in low-end smart devices. To do this, we develop a method to reduce the memory requirement of DNNs and increase the inference speed, while maintaining the performance (for example, accuracy) close to the original level. The parameters of DNNs are decomposed using a hybrid of canonical polyadic-singular value decomposition, approximated using a tensor power method, and fine-tuned by performing iterative one-shot hybrid fine-tuning to recover from a decreased accuracy. In this study, we evaluate our method on frequently used networks. We also present results from extensive experiments on the effects of several fine-tuning methods, the importance of iterative fine-tuning, and decomposition techniques. We demonstrate the effectiveness of the proposed method by deploying compressed networks in smartphones.

• 융합보안논문지
• /
• 제1권1호
• /
• pp.57-68
• /
• 2001

컴퓨터망의 확대 및 컴퓨터 이용의 급격한 증가에 따른 부작용으로 컴퓨터 보안 문제가 중요하게 대두되고 있다. 이에 따라 침입자로부터 침입을 줄이기 위한 침입탐지시스템에 관한 연구가 활발하다. 본 논문은 멀티레벨에서 감사자료를 수집하고, 필터링하여 오용행위 탐지기법에 대한 선천성면역, 비정상행위 탐지기법에 대한 후천성 면역을 사용한 하이브리드 침입탐지 시스템이다. 다중호스트 기반에서 감사자료를 하나의 시스템으로 모아서 탐지하므로 하나의 호스트에서 탐지한 침입보다 여러 호스트에서 탐지가 가능하며, 비정상행위 탐지 기법에서 탐지한 침입은 오용행위 탐지 기법에서 신속하게 탐지할 수 있는 면역력을 가진 침입탐지 시스템의 설계 및 구현한다.

• 센서학회지
• /
• 제8권1호
• /
• pp.45-52
• /
• 1999

이 논문에서는 오차 역전파 학습 알고리듬의 학습 속도를 향상시키기 위한 새로운 학습 방법을 제안한다. 제안하고자 하는 방법은 시그모이드 형태를 갖는 신경회로망의 활성화 함수(activation function) 자체에 고차항(higher order)을 적절히 이용하여 초기 학습 단계에서 발생할 수 있는 조기 포화(premature saturation) 현상을 계산량의 큰 증가 없이 효과적으로 대처할 수 있다. 고차항을 이용함으로써 은닉층 활성화 함수의 도합수가 작은 값으로 감소함에 따라 신경망의 연결 강도를 학습시키는 학습율은 적응적으로 큰 값을 갖게 된다. 또한, 은닉층에 고차항을 이용하는 제안한 방법에 모멘텀(momentum) 학습 알고리듬을 결합하는 새로운 hybrid 학습 방법을 제안한다. 컴퓨터 모의 실험을 통해 제안하고자 하는 학습 방법과 기존의 방법들과의 학습 속도 성능을 비교한다.

• 전기학회논문지
• /
• 제65권10호
• /
• pp.1706-1711
• /
• 2016

Electromagnetic wave simulation was performed to predict characteristics of manufactured cutoff probe at low temperature magnetized plasma medium. Microwave cutoff probe is designed for research the properties of magnetized inductively coupled plasma. It was shown that the cutoff probe method can safely be used for weakly magnetized high density plasma sources. Cutoff probe system with two port network analyzer has been prepared and applied to measure electron density distributions in large area, 13.56MHz driven weakly magnetized inductively coupled plasma source. The results shown that, the plasma frequency confirmed cut-off characteristics in low temperature plasma. Especially, cut-off characteristics was found at upper hybrid resonance frequency in the environment of the magnetic field. In case of a induced weak magnetic field in inductively coupled plasma, plasma density estimated from the cutoff frequency in the same way at unmagnetized plasma due to nearly same plasma frequency and upper hybrid resonance frequency. The plasma density is increased and uniformity is improved by applying a induced weak magnetic field in inductively coupled plasma.