• 한국정보통신학회논문지
• /
• 제21권8호
• /
• pp.1560-1566
• /
• 2017

최근 사물 인터넷 센서가 설치된 스마트 돈사의 보급을 통해 돈사 관련 빅데이터 축적이 가능해졌고, 다양한 기계 학습방안들이 수집된 데이터에 적용되어 축산농가의 생산성을 향상시키고 있다. 본 연구에서는 다양한 기계학습 방안을 이용하여 돈사관리에서 가장 중요한 요소 중 하나인 급수량을 예측하였다. 구체적으로 실제 돈사에서 수집된 데이터에 회귀 방안인 선형회귀, 회귀트리 및 아다부스트 회귀 방안과 분류 방안인 로지스틱 분류, 결정트리 및 서포트 벡터 머신 (SVM) 분류방안을 적용하여 돈사의 온도와 습도를 기반으로 급수량을 예측하였다. 성능 분석을 통해서 제안한 방안이 높은 정확도로 급수량을 예측하는 것을 확인할 수 있었다. 제안한 방안은 돈사의 급수시설 이상을 조기에 파악하는데 활용되어 가축을 폐사를 막고 돈사 생산성을 높이는데 활용될 수 있다.

• 한국컴퓨터정보학회논문지
• /
• 제27권3호
• /
• pp.1-12
• /
• 2022

해양조난사고 발생 시 해상 익수자의 안전과 생명 보장을 위해 구조자산을 활용한 신속한 탐색 및 구조작전은 매우 중요하다. 본 연구는 해양관측부이에서 수집되는 기상정보에 다중선형회귀분석, 의사결정나무, 서포트벡터머신, 벡터자기회귀, 순환신경망의 LSTM을 활용하여 울릉도 북서해역의 표층해류를 분석하고 유향과 유속에 대한 각각의 예측모형을 구축하여 예측된 유향과 유속정보를 통해 해상 익수자의 이동경로를 예측하는 모형들을 제안한다. 본 연구에서 적용한 다양한 기계학습 모형을 MAE와 RMSE의 성능 평가척도로 비교해 볼 때 LSTM이 가장 우수한 성능을 보였다. 또한, 익수자 이동지점과 예측모형의 예측지점 간 거리 차이에 있어서도 LSTM이 다른 모형들에 비해 탁월한 성능을 나타내었다.

• Smart Structures and Systems
• /
• 제31권5호
• /
• pp.485-500
• /
• 2023

Machine learning-based structural health monitoring (ML-based SHM) methods are researched extensively in the recent decade due to the availability of advanced information and sensing technology. ML methods are well-known for their pattern recognition capability for complex problems. However, the main obstacle of ML-based SHM is that it often requires pre-collected historical data for model training. In most actual scenarios, damage presence can be detected using the unsupervised learning method through anomaly detection, but to further identify the damage types would require prior knowledge or historical events as references. This creates the cold-start problem, especially for new and unobserved structures. Modal-based methods identify damages based on the changes in the structural global properties but often require dense measurements for accurate results. Therefore, a two-stage hybrid modal-machine learning damage detection scheme is proposed. The first stage detects damage presence using Principal Component Analysis-Frequency Response Function (PCA-FRF) in an unsupervised manner, whereas the second stage further identifies the damage. To solve the cold-start problem, mode shape assessment using the first mode is initiated when no trained model is available yet in the second stage. The damage identified by the modal-based method would be stored for future training. This work highlights the performance of the scheme in alleviating the cold-start issue as it transitions through different phases, starting from zero damage sample available. Results showed that single and multiple damages can be identified at an acceptable accuracy level even when training samples are limited.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1999년도 제14차 학술회의논문집
• /
• pp.292-297
• /
• 1999

Evolving in artificial agent is an extremely difficult problem, but on the other hand, a challenging task. At present the studies mainly centered on single agent learning problem. In our case, we use simulated soccer to investigate multi-agent cooperative learning. Consider the fundamental differences in learning mechanism, existing reinforcement learning algorithms can be roughly classified into two types-that based on evaluation functions and that of searching policy space directly. Genetic Programming developed from Genetic Algorithms is one of the most well known approaches belonging to the latter. In this paper, we give detailed algorithm description as well as data construction that are necessary for learning single agent strategies at first. In following step moreover, we will extend developed methods into multiple robot domains. game. We investigate and contrast two different methods-simple team learning and sub-group loaming and conclude the paper with some experimental results.

• 정보처리학회논문지:컴퓨터 및 통신 시스템
• /
• 제5권10호
• /
• pp.353-360
• /
• 2016

여러 개의 태양전지들이 붙어 있는 태양광 패널을 이용하여 전력을 생산하는 태양광 발전은 최근 신재생 에너지 기술로 빠르게 성장하고 있는 분야이다. 하지만 태양광발전의 단점 중 하나인 불규칙한 전력 생산문제로 인해, 장비 및 패널 결함에 빠르게 대응하지 못하는 문제가 발생한다. 이 연구에서는 다양한 기후데이터와 패널 정보를 이용하여 태양광발전량 예측 방법들을 비교하여 최적의 예측 알고리즘을 평가하고 이를 기반으로 태양광발전소 결함 검출 시스템을 개발하여 국내 태양광 발전소에 적용한 사례를 기술한다.

• Journal of information and communication convergence engineering
• /
• 제14권4호
• /
• pp.258-267
• /
• 2016

Three-dimensional integrated circuits (3D ICs) experience die-to-die variations in addition to the already challenging within-die variations. This adds an additional design complexity and makes variation estimation and full-chip optimization even more challenging. In this paper, we show that the industry standard on-chip variation (AOCV) tables cannot be applied directly to 3D paths that are spanning multiple dies. We develop a new machine learning-based model and methodology for an accurate variation estimation of logic paths in 3D designs. Our model makes use of key parameters extracted from existing GDSII 3D IC design and sign-off simulation database. Thus, it requires no runtime overhead when compared to AOCV analysis while achieving an average accuracy of 90% in variation evaluation. By using our model in a full-chip variation-aware 3D IC physical design flow, we obtain up to 16% improvement in critical path delay under variations, which is verified with detailed Monte Carlo simulations.

• Nuclear Engineering and Technology
• /
• 제53권11호
• /
• pp.3563-3579
• /
• 2021

Measured decay heat data of light water reactor (LWR) spent nuclear fuel (SNF) assemblies are adopted to train machine learning (ML) models. The measured data is available for fuel assemblies irradiated in commercial reactors operated in the United States and Sweden. The data comes from calorimetric measurements of discharged pressurized water reactor (PWR) and boiling water reactor (BWR) fuel assemblies. 91 and 171 measurements of PWR and BWR assembly decay heat data are used, respectively. Due to the small size of the measurement dataset, we propose: (i) to use the method of multiple runs (ii) to generate and use synthetic data, as large dataset which has similar statistical characteristics as the original dataset. Three ML models are developed based on Gaussian process (GP), support vector machines (SVM) and neural networks (NN), with four inputs including the fuel assembly averaged enrichment, assembly averaged burnup, initial heavy metal mass, and cooling time after discharge. The outcomes of this work are (i) development of ML models which predict LWR fuel assembly decay heat from the four inputs (ii) generation and application of synthetic data which improves the performance of the ML models (iii) uncertainty analysis of the ML models and their predictions.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권11호
• /
• pp.5425-5448
• /
• 2018

Wireless sensor network has been widely used in Internet of Things (IoT) applications to support large and dense networks. As sensor nodes are usually tiny and provided with limited hardware resources, the existing multiple access methods, which involve high computational complexity to preserve the protocol performance, is not available under such a scenario. In this paper, we propose an intelligent Medium Access Control (MAC) protocol selection scheme based on machine learning in wireless sensor networks. We jointly consider the impact of inherent behavior and external environments to deal with the application limitation problem of the single type MAC protocol. This scheme can benefit from the combination of the competitive protocols and non-competitive protocols, and help the network nodes to select the MAC protocol that best suits the current network condition. Extensive simulation results validate our work, and it also proven that the accuracy of the proposed MAC protocol selection strategy is higher than the existing work.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권5호
• /
• pp.1671-1686
• /
• 2022

Face manipulation tools represented by Deepfake have threatened the security of people's biological identity information. Particularly, manipulation tools with deep learning technology have brought great challenges to Deepfake detection. There are many solutions for Deepfake detection based on traditional machine learning and advanced deep learning. However, those solutions of detectors almost have problems of poor performance when evaluated on different quality datasets. In this paper, for the sake of making high-quality Deepfake datasets, we provide a preprocessing method based on the image pixel matrix feature to eliminate similar images and the residual channel attention network (RCAN) to resize the scale of images. Significantly, we also describe a Deepfake detector named Cascaded-Hop which is based on the PixelHop++ system and the successive subspace learning (SSL) model. By feeding the preprocessed datasets, Cascaded-Hop achieves a good classification result on different manipulation types and multiple quality datasets. According to the experiment on FaceForensics++ and Celeb-DF, the AUC (area under curve) results of our proposed methods are comparable to the state-of-the-art models.

• 한국ITS학회 논문지
• /
• 제18권2호
• /
• pp.93-103
• /
• 2019

본 연구에서는 대전광역시 내의 보행로 2개소를 대상으로 보행 중 스마트폰 사용이 보행속도에 미치는 영향을 분석하였다. 분석을 위해 스마트폰 사용실태에 대한 영상자료를 취득하고 도로용량편람에서 제시한 보행자 서비스수준의 보행밀도를 기준으로 보행속도를 산정하였다. 보행속도에 미치는 영향을 분석하기 위한 방법으로는 기계학습을 통한 다중회귀분석과 의사결정나무(Decision tree)를 활용하였으며, 설명변수로는 성별, 스마트폰 미사용, 청각을 이용한 스마트폰 사용, 시각을 이용한 스마트폰 사용, 서비스수준A, 서비스수준B, 서비스수준C가 선정되었다. 분석결과 서비스수준C가 보행속도 변화에 가장 높은 영향을 미치는 것으로 나타났으며, 서비스수준C에서 시각을 활용해 스마트폰을 이용한 여성그룹이 가장 낮은 속도로 보행하는 것으로 나타났다. 특히 음악 감상이나 통화와 같은 청각을 이용한 유형보다 시각을 이용하는 경우 대부분의 경우에서 보행속도가 크게 저하되며 통계적으로 유의한 차이가 있음을 확인하였다.