• Journal of the Korea Convergence Society
• /
• v.9 no.5
• /
• pp.1-6
• /
• 2018

In smart grid an accurate load forecasting is crucial in planning resources, which aids in improving its operation efficiency and reducing the dynamic uncertainties of energy systems. Research in this area has included the use of shallow neural networks and other machine learning techniques to solve this problem. Recent researches in the field of computer vision and speech recognition, have shown great promise for Deep Neural Networks (DNN). To improve the performance of daily electric peak load forecasting the paper presents a new deep neural network model which has the architecture of two multi-layer neural networks being serially connected. The proposed network model is progressively pre-learned layer by layer ahead of learning the whole network. For both one day and two day ahead peak load forecasting the proposed models are trained and tested using four years of hourly load data obtained from the Korea Power Exchange (KPX).

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.6
• /
• pp.1055-1065
• /
• 2023

Recently, various studies using deep reinforcement learning (deep RL) technology have been conducted to solve complex problems using big data collected at industrial internet of things. Deep RL uses reinforcement learning"s trial-and-error algorithms and cumulative compensation functions to generate and learn its own data and quickly explore neural network structures and parameter decisions. However, studies so far have shown that the larger the size of the learning data is, the higher are the memory usage and search time, and the lower is the accuracy. In this study, model-agnostic learning for efficient federated deep RL was utilized to solve privacy invasion by increasing robustness as 55.9% and achieve 97.8% accuracy, an improvement of 5.5% compared with the comparative optimization-based meta learning models, and to reduce the delay time by 28.9% on average.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.75-76
• /
• 2022

현재 산업용 로봇 팔의 경로 계획을 생성할 때, 로봇 팔 경로 계획은 로봇 엔지니어가 수동으로 로봇을 제어하며 최적 경로 계획을 탐색한다. 미래에 고객의 다양한 요구에 따라 공정을 유연하게 변경하는 대량 맞춤 시대에는 기존의 경로 계획 수립 방식은 부적합하다. 심층강화학습 프레임워크는 가상 환경에서 로봇 팔 경로 계획 수립을 학습해 새로운 공정으로 변경될 때, 최적 경로 계획을 자동으로 수립해 로봇 팔에 전달하여 빠르고 유연한 공정 변경을 지원한다. 본 논문에서는 심층강화학습 에이전트를 위한 학습 환경 구축과 인공지능 모델과 학습 환경의 연동을 중심으로, 로봇 팔 경로 계획 수립을 위한 심층강화학습 프레임워크 구조를 설계한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.10a
• /
• pp.617-620
• /
• 2016

본 논문에서는 이미지 캡션 생성과 모델 전이에 효과적인 심층 신경망 모델을 제시한다. 본 모델은 멀티 모달 순환 신경망 모델의 하나로서, 이미지로부터 시각 정보를 추출하는 컨볼루션 신경망 층, 각 단어를 저차원의 특징으로 변환하는 임베딩 층, 캡션 문장 구조를 학습하는 순환 신경망 층, 시각 정보와 언어 정보를 결합하는 멀티 모달 층 등 총 5 개의 계층들로 구성된다. 특히 본 모델에서는 시퀀스 패턴 학습과 모델 전이에 우수한 LSTM 유닛을 이용하여 순환 신경망 층을 구성하고, 컨볼루션 신경망 층의 출력을 임베딩 층뿐만 아니라 멀티 모달 층에도 연결함으로써, 캡션 문장 생성을 위한 매 단계마다 이미지의 시각 정보를 이용할 수 있는 연결 구조를 가진다. Flickr8k, Flickr30k, MSCOCO 등의 공개 데이터 집합들을 이용한 다양한 비교 실험을 통해, 캡션의 정확도와 모델 전이의 효과 면에서 본 논문에서 제시한 멀티 모달 순환 신경망 모델의 우수성을 입증하였다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.854-857
• /
• 2022

본 논문에서는 기존 이미지를 통해 위상 홀로그램을 생성하는 네트워크를 학습 및 최적화하여, 기존에 사용하는 알고리즘 방식인 GS 알고리즘(Gerchberg-Saxton algorithm)을 대체하는 것을 목표로 한다. GS는 반복 최적화 기법으로 한 장의 이미지에서 위상 홀로그램을 생성하는데 많은 시간이 걸리지만, 심층 학습 기반으로 학습된 모델을 통해 위상 홀로그램을 생성할 경우, 반복 최적화 과정 없이 짧은 시간 안에 위상 홀로그램을 생성할 수 있다. GS와 심층 학습 기반으로 각각 생성한 위상 홀로그램을 ASM(Angular Spectrum Method)을 통해 수치적으로 재복원하여 PSNR로 원본 이미지와 비교한 결과, 심층 학습 기반으로 생성한 위상 홀로그램에서 더 좋은 화질의 이미지를 짧은 시간 안에 얻을 수 있었다.

• Journal of the Korea Convergence Society
• /
• v.9 no.6
• /
• pp.39-44
• /
• 2018

The application of deep neural networks to finance has received a great deal of attention from researchers because no assumption about a suitable mathematical model has to be made prior to forecasting and they are capable of extracting useful information from large sets of data, which is required to describe nonlinear input-output relations of financial time series. The paper presents a new deep neural network model where single layered autoencoder and 4 layered neural network are serially coupled for stock price forecasting. The autoencoder extracts deep features, which are fed into multi-layer neural networks to predict the next day's stock closing prices. The proposed deep neural network is progressively learned layer by layer ahead of the final learning of the total network. The proposed model to predict daily close prices of KOrea composite Stock Price Index (KOSPI) is built, and its performance is demonstrated.

• Journal of the Korea Computer Graphics Society
• /
• v.27 no.5
• /
• pp.45-54
• /
• 2021

Recently, deep learning-based denoising approaches have been actively studied. In particular, with the advances of blind denoising techniques, it become possible to train a deep learning-based denoising model only with noisy images in an image domain where it is impossible to obtain a clean image. We no longer require pairs of a clean image and a noisy image to obtain a restored clean image from the observation. However, it is difficult to recover the target using a deep learning-based denoising model trained by only noisy images if the distribution of the noisy image is far from the distribution of the clean image. To address this limitation, unpaired image denoising approaches have recently been studied that can learn the denoising model from unpaired data of the noisy image and the clean image. ISCL showed comparable performance close to that of supervised learning-based models based on pairs of clean and noisy images. In this study, we propose suitable normalization techniques for each purpose of architectures (e.g., generator, discriminator, and extractor) of ISCL. We demonstrate that the proposed method outperforms state-of-the-art unpaired image denoising approaches including ISCL.

• The Journal of the Korea Contents Association
• /
• v.19 no.11
• /
• pp.278-287
• /
• 2019

Spatial information extraction is to retrieve static and dynamic aspects in natural language text by explicitly marking spatial elements and their relational words. This paper proposes a deep learning approach for spatial information extraction for Korean language using a two-step bidirectional LSTM-CRF ensemble model. The integrated model of spatial element extraction and spatial relation attribute extraction is proposed too. An experiment with the Korean SpaceBank demonstrates the better efficiency of the proposed deep learning model than that of the previous CRF model, also showing that the proposed ensemble model performed better than the single model.

• 재활복지
• /
• v.21 no.3
• /
• pp.129-146
• /
• 2017

In an event of an emergency, such as fire in a building, visually impaired and blind people are prone to exposed to a level of danger that is greater than that of normal people, for they cannot be aware of it quickly. Current fire detection methods such as smoke detector is very slow and unreliable because it usually uses chemical sensor based technology to detect fire particles. But by using vision sensor instead, fire can be proven to be detected much faster as we show in our experiments. Previous studies have applied various image processing and machine learning techniques to detect fire, but they usually don't work very well because these techniques require hand-crafted features that do not generalize well to various scenarios. But with the help of recent advancement in the field of deep learning, this research can be conducted to help solve this problem by using deep learning-based object detector that can detect fire using images from security camera. Deep learning based approach can learn features automatically so they can usually generalize well to various scenes. In order to ensure maximum capacity, we applied the latest technologies in the field of computer vision such as YOLO detector in order to solve this task. Considering the trade-off between recall vs. complexity, we introduced two convolutional neural networks with slightly different model's complexity to detect fire at different recall rate. Both models can detect fire at 99% average precision, but one model has 76% recall at 30 FPS while another has 61% recall at 50 FPS. We also compare our model memory consumption with each other and show our models robustness by testing on various real-world scenarios.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.129-131
• /
• 2021

본 논문에서는 심층 특징 앙상블을 사용하여 목조 문화재의 변위 현상 중 하나인 배부름 현상을 감지할 수 있는 모델을 제안한다. 우선 총 4개의 서로 다른 사전 학습된 합성 곱 신경망을 사용하여 입력 영상에 대한 심층 특징들을 추출한다. 그 이후 4개의 서로 다른 심층 특징들을 결합하여 하나의 특징 벡터를 생성한다. 그 이후 합쳐진 특징 벡터는 완전 연결 계층의 입력 값으로 들어와서 최종적으로 변위가 존재하는지 아닌지에 대한 예측을 수행하게 된다. 데이터 셋으로는 충주시 근처의 문화재에 방문해서 수집한 목조 문화재 이미지를 가지고 정상 및 비정상으로 구분한 데이터 셋을 사용하였다. 실험 결과 심층 특징 앙상블 기법을 사용한 모델이 앙상블 기법을 사용하지 않은 모델보다 더 좋은 성능을 나타냄을 확인하였다. 이러한 결과로 부터 우리가 제안한 방법이 목재 문화재의 배부름 현상에 대한 변위 검출에 있어서 매우 적합함을 보여준다.