• 한국지능시스템학회논문지
• /
• 제27권1호
• /
• pp.22-28
• /
• 2017

Convolutional Neural Network(CNN)는 특징 추출과 분류의 두 단계로 나눌 수 있다. 그 중 특징 추출 단계의 커널의 크기, 채널의 수, stride 등의 hyperparameter는 CNN의 구조를 결정할 뿐만 아니라 특징을 추출하는 데에도 영향을 주기 때문에 CNN의 전체적인 성능에도 영향을 준다. 본 논문에서는 Parameter-Setting-Free Harmony Search(PSF-HS) 알고리즘을 이용하여 CNN의 특징 추출 단계에서의 hyperparameter를 최적화 하는 방법을 제안하였다. CNN의 전체 구조를 설정한 뒤 hyperparameter를 변수로 설정하였고 PSF-HS 알고리즘을 적용하여 hyperparameter를 최적화 하였다. 시뮬레이션은 MATLAB을 이용하여 진행하였고 CNN은 mnist 데이터를 이용하여 학습과 테스트를 했다. 총 500번 동안 변수를 업데이트했고 제안하는 방법을 이용하여 구한 CNN 구조 중 가장 높은 정확도를 가지는 구조는 99.28%의 정확도로 mnist 데이터를 분류하는 것을 확인할 수 있었다.

• 방송공학회논문지
• /
• 제23권3호
• /
• pp.369-382
• /
• 2018

본 논문은 딥 컨볼루션 뉴럴 네트워크(CNN)를 이용하여 행 별로 서로 다른 노출로 촬영된 단일 영상을 HDR 영상으로 변환하는 기법을 제안한다. 제안하는 알고리즘은 먼저 입력 영상에서 저조도 또는 포화로 인해 발생하는 정보 손실 영역을 CNN을 이용하여 복원하여 휘도맵을 생성한다. 또한, CNN 학습 과정에서 인간의 시각 인지 특성을 고려할 수 있는 손실 함수를 제안한다. 마지막으로 복원된 휘도맵에 디모자이킹 필터를 적용하여 최종 HDR 영상을 획득한다. 컴퓨터 모의실험을 통해 제안하는 알고리즘이 기존의 기법에 비해서 높은 품질의 HDR 영상을 취득하는 것을 확인한다.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2020년도 학술발표회
• /
• pp.120-120
• /
• 2020

Spatial precipitation data is one of the essential components in modeling hydrological problems. The estimation of these data has achieved significant achievements own to the recent advances in remote sensing technology. However, there are still gaps between the satellite-derived rainfall data and observed data due to the significant dependence of rainfall on spatial and temporal characteristics. An effective approach based on the Convolutional Neural Network (CNN) model to correct the satellite-derived rainfall data is proposed in this study. The Mekong River basin, one of the largest river system in the world, was selected as a case study. The two gridded precipitation data sets with a spatial resolution of 0.25 degrees used in the CNN model are APHRODITE (Asian Precipitation - Highly-Resolved Observational Data Integration Towards Evaluation) and PERSIANN-CDR (Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks). In particular, PERSIANN-CDR data is exploited as satellite-based precipitation data and APHRODITE data is considered as observed rainfall data. In addition to developing a CNN model to correct the satellite-based rain data, another statistical method based on standard deviations for precipitation bias correction was also mentioned in this study. Estimated results indicate that the CNN model illustrates better performance both in spatial and temporal correlation when compared to the standard deviation method. The finding of this study indicated that the CNN model could produce reliable estimates for the gridded precipitation bias correction problem.

• 한국산학기술학회논문지
• /
• 제21권5호
• /
• pp.14-21
• /
• 2020

두 통신자간 정보를 전송함에 있어 기밀성 서비스를 제공하기 위해서는 하나의 대칭 비밀키를 이용하는 블록데이터 암호화를 수행한다. 데이터 암호 시스템에 대한 전력 분석 공격은 데이터 암호를 위한 디바이스가 구동할 때 발생하는 소비 전력을 측정하여 해당 디바이스에 내장된 비밀키를 찾아내는 부채널 공격 방법 중 하나이다. 본 논문에서는 딥 러닝 기법인 CNN (Convolutional Neural Network) 알고리즘에 기반한 전력 분석 공격을 시도하여 비밀 정보를 복구하는 방법을 제안하였다. 특히, CNN 알고리즘이 이미지 분석에 적합한 기법인 점을 고려하여 1차원의 전력 분석파형을 2차원 데이터로 이미지화하여 처리하는 RP(Recurrence Plots) 신호 처리 기법을 적용하였다. 제안한 CNN 공격 모델을 XMEGA128 실험 보드에 블록 암호인 AES-128 암호 알고리즘을 구현하여 공격을 수행한 결과, 측정한 전력소비 파형을 전처리 과정없이 그대로 학습시킨 결과는 약 22.23%의 정확도로 비밀키를 복구해 냈지만, 전력 파형에 RP기법을 적용했을 경우에는 약 97.93%의 정확도로 키를 찾아낼 수 있었음을 확인하였다.

• 한국멀티미디어학회논문지
• /
• 제25권11호
• /
• pp.1643-1652
• /
• 2022

Most of the existing machine reading research has used Recurrent Neural Network (RNN) and Convolutional Neural Network (CNN) algorithms as networks. Among them, RNN was slow in training, and Question Answering Network (QANet) was announced to improve training speed. QANet is a model composed of CNN and self-attention. CNN extracts semantic and syntactic information well from the local corpus, but there is a limit to extracting the corresponding information from the global corpus. Graph Convolutional Networks (GCN) extracts semantic and syntactic information relatively well from the global corpus. In this paper, to take advantage of this strength of GCN, we propose I-QANet, which changed the CNN of QANet to GCN. The proposed model performed 1.2 times faster than the baseline in the Stanford Question Answering Dataset (SQuAD) dataset and showed 0.2% higher performance in Exact Match (EM) and 0.7% higher in F1. Furthermore, in the Korean Question Answering Dataset (KorQuAD) dataset consisting only of Korean, the learning time was 1.1 times faster than the baseline, and the EM and F1 performance were also 0.9% and 0.7% higher, respectively.

• Nuclear Engineering and Technology
• /
• 제54권12호
• /
• pp.4751-4758
• /
• 2022

Two-phase flow may almost exist in every branch of the energy industry. For the corresponding engineering design, it is very essential and crucial to monitor flow patterns and their transitions accurately. With the high-speed development and success of deep learning based on convolutional neural network (CNN), the study of flow pattern identification recently almost focused on this methodology. Additionally, the photographing technique has attractive implementation features as well, since it is normally considerably less expensive than other techniques. The development of such a two-phase flow pattern online monitoring system is the objective of this work, which seldom studied before. The ongoing preliminary engineering design (including hardware and software) of the system are introduced. The flow pattern identification method based on CNNs and transfer learning was discussed in detail. Several potential CNN candidates such as ALexNet, VggNet16 and ResNets were introduced and compared with each other based on a flow pattern dataset. According to the results, ResNet50 is the most promising CNN network for the system owing to its high precision, fast classification and strong robustness. This work can be a reference for the online monitoring system design in the energy system.

• Journal of Information Science Theory and Practice
• /
• 제7권2호
• /
• pp.32-39
• /
• 2019

A convolutional neural network (CNN) has been widely used in facial expression recognition (FER) because it can automatically learn discriminative appearance features from an expression image. To make full use of its discriminating capability, this paper suggests a simple but effective method for CNN based FER. Specifically, instead of an original expression image that contains facial appearance only, the expression image with facial geometry visualization is used as input to CNN. In this way, geometric and appearance features could be simultaneously learned, making CNN more discriminative for FER. A simple CNN extension is also presented in this paper, aiming to utilize geometric expression change derived from an expression image sequence. Experimental results on two public datasets (CK+ and MMI) show that CNN using facial geometry visualization clearly outperforms the conventional CNN using facial appearance only.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 춘계학술대회
• /
• pp.370-373
• /
• 2022

최근 Tensorflow나 Pytorch, Keras 같은 여러가지의 딥러닝 프레임워크 모델들이 나왔다. 또한 이미지 인식에 Tensorflow, Pytorch, Keras 같은 프레임 워크를 이용하여 CNN(Convolutional Neural Network)을 적용시켜 이미지 분류에서의 최적화 모델을 주로 이용한다. 본 논문에서는 딥러닝 이미지 인식분야에서 가장 많이 사용하고 있는 파이토치와 텐서플로우의 프레임 워크를 CNN모델에 학습을 시킨 결과를 토대로 두 프레임 워크를 비교 분석하여 이미지 분석할 때 최적화 된 프레임워크를 도출하였다.

• 대한임베디드공학회논문지
• /
• 제12권2호
• /
• pp.113-120
• /
• 2017

In this paper, we present a night-time vehicle detection method using CNN (Convolutional Neural Network) classification. The camera based night-time vehicle detection plays an important role on various advanced driver assistance systems (ADAS) such as automatic head-lamp control system. The method consists mainly of thresholding, labeling and classification steps. The classification step is implemented by existing CIFAR-10 model CNN. Through the simulations tested on real road video, we show that CNN classification is a good alternative for night-time vehicle detection.

• 말소리와 음성과학
• /
• 제10권1호
• /
• pp.33-38
• /
• 2018

Although deep neural network-based acoustic models have greatly improved the performance of automatic speech recognition (ASR), reverberation still degrades the performance of distant speech recognition in indoor environments. In this paper, we adopt the DenseNet, which has shown great performance results in image classification tasks, to improve the performance of reverberant speech recognition. The DenseNet enables the deep convolutional neural network (CNN) to be effectively trained by concatenating feature maps in each convolutional layer. In addition, we extend the concept of multi-resolution CNN to multi-resolution DenseNet for robust speech recognition in reverberant environments. We evaluate the performance of reverberant speech recognition on the single-channel ASR task in reverberant voice enhancement and recognition benchmark (REVERB) challenge 2014. According to the experimental results, the DenseNet-based acoustic models show better performance than do the conventional CNN-based ones, and the multi-resolution DenseNet provides additional performance improvement.