• 반도체디스플레이기술학회지
• /
• 제21권3호
• /
• pp.63-68
• /
• 2022

In this study, we produced defect detection models using parallel convolution neural networks. If convolution neural networks are constructed parallel type, the model's detection accuracy will increase and detection time will decrease. We produced parallel-type defect detection models using 4 types of convolutional algorithms. The performance of models was evaluated using evaluation indicators. The model's performance is detection accuracy and detection time. We compared the performance of each parallel model. The detection accuracy of the model using AlexNet is 97 % and the detection time is 0.3 seconds. We confirmed that when AlexNet algorithm is constructed parallel type, the model has the highest performance.

• 한국멀티미디어학회논문지
• /
• 제25권8호
• /
• pp.1203-1211
• /
• 2022

Melanoma is a skin cancer that starts in pigment-producing cells (melanocytes). The death rates of skin cancer like melanoma can be reduced by early detection and diagnosis of diseases. It is common for doctors to spend a lot of time trying to distinguish between skin lesions and healthy cells because of their striking similarities. The detection of melanoma lesions can be made easier for doctors with the help of an automated classification system that uses deep learning. This study presents a new approach for melanoma classification based on an ensemble of deep convolution neural networks and a Log-Gabor filter. First, we create the Log-Gabor representation of the original image. Then, we input the Log-Gabor representation into a new ensemble of deep convolution neural networks. We evaluated the proposed method on the melanoma dataset collected at Yonsei University and Dongsan Clinic. Based on our numerical results, the proposed framework achieves more accuracy than other approaches.

• Journal of Information Processing Systems
• /
• 제17권3호
• /
• pp.556-570
• /
• 2021

The existing video expression recognition methods mainly focus on the spatial feature extraction of video expression images, but tend to ignore the dynamic features of video sequences. To solve this problem, a multi-mode convolution neural network method is proposed to effectively improve the performance of facial expression recognition in video. Firstly, OpenFace 2.0 is used to detect face images in video, and two deep convolution neural networks are used to extract spatiotemporal expression features. Furthermore, spatial convolution neural network is used to extract the spatial information features of each static expression image, and the dynamic information feature is extracted from the optical flow information of multiple expression images based on temporal convolution neural network. Then, the spatiotemporal features learned by the two deep convolution neural networks are fused by multiplication. Finally, the fused features are input into support vector machine to realize the facial expression classification. Experimental results show that the recognition accuracy of the proposed method can reach 64.57% and 60.89%, respectively on RML and Baum-ls datasets. It is better than that of other contrast methods.

• 한국멀티미디어학회논문지
• /
• 제24권11호
• /
• pp.1552-1559
• /
• 2021

Convolution neural networks (CNNs) show notable performance in image processing and are used as representative core models. CNNs extract and learn features from large amounts of train dataset. In general, it has a structure in which a convolution layer and a fully connected layer are stacked. The core of CNN is the convolution layer. The size of the kernel used for feature extraction and the number that affect the depth of the feature map determine the amount of weight parameters of the CNN that can be learned. These parameters are the main causes of increasing the computational complexity and memory usage of the entire neural network. The most computationally expensive components in CNNs are fully connected and spatial convolution computations. In this paper, we propose a Fourier Convolution Neural Network that performs the operation of the convolution layer in the Fourier domain. We work on modifying and improving the amount of computation by applying the fast fourier transform method. Using the MNIST dataset, the performance was similar to that of the general CNN in terms of accuracy. In terms of operation speed, 7.2% faster operation speed was achieved. An average of 19% faster speed was achieved in experiments using 1024x1024 images and various sizes of kernels.

• 한국음향학회지
• /
• 제15권5호
• /
• pp.13-20
• /
• 1996

현재 신경회로망의 구현에 관한 여러 가지 연구가 진행되고 있으며, 이들 중 신경회로망의 VLSI 구현에 대한 연구가 매우 활발하다. 디지털 신경회로망은 느린 처리속도와 넓은 면적을 차지하는 점이 주요 단점으로 지적되는데 본 논문에서는 neural cell을 곱셈과 덧셈을 Binary Convolution 기법과 Counter를 사용하여 설계함으로써 속도를 높이고 단위 뉴런의 소요 Tr수를 줄여 그 소요 면적을 줄이도록 하였다. 본 cell의 구조를 이용하여 layer당 16개씩의 cell을 가지는 3-layer neural network을 구성하였을 경우 0.8${\mu}$ standard cell 설계시 50MHz까지 동작하였으며 26MCPS의 동작을 확보하였다.

• 한국컴퓨터정보학회논문지
• /
• 제21권1호
• /
• pp.1-8
• /
• 2016

Convolutional neural network (CNN) consists of a few pairs of both convolution layer and subsampling layer. Thus it has more hidden layers than multi-layer perceptron. With the increased layers, the size of convolution mask ultimately determines the total number of weights in CNN because the mask is shared among input images. It also is an important learning factor which makes or breaks CNN's learning. Therefore, this paper proposes the best method to choose the convolution size and the number of layers for learning CNN successfully. Through our face recognition with vast learning examples, we found that the best size of convolution mask is 5 by 5 and 7 by 7, regardless of the number of layers. In addition, the CNN with two pairs of both convolution and subsampling layer is found to make the best performance as if the multi-layer perceptron having two hidden layers does.

• 한국음향학회지
• /
• 제37권2호
• /
• pp.118-128
• /
• 2018

본 논문은 사이드 스캔 소나 영상을 컨볼루션 신경망으로 학습하여 수중물체를 탐색하는 방법을 다루었다. 사이드 스캔 소나 영상을 사람이 직접 분석하던 방법에서 컨볼루션 신경망 알고리즘이 보강되면 분석의 효율성을 높일 수 있다. 연구에 사용한 사이드 스캔 소나의 영상 데이터는 미 해군 수상전센터에서 공개한 자료이고 4종류의 합성수중물체로 구성되었다. 컨볼루션 신경망 알고리즘은 관심영역 기반으로 학습하는 Faster R-CNN(Region based Convolutional Neural Networks)을 기본으로 하며 신경망의 세부사항을 보유한 데이터에 적합하도록 구성하였다. 연구의 결과를 정밀도-재현율 곡선으로 비교하였고 소나 영상 데이터에 지정한 관심영역의 변경이 탐지성능에 미치는 영향을 검토함으로써 컨볼루션 신경망의 수중물체 탐지 적용성에 대해 살펴보았다.

• International Journal of Computer Science & Network Security
• /
• 제22권11호
• /
• pp.265-271
• /
• 2022

Social media is a form of communication based on the internet to share information through content and images. Their choice of profile images and type of image they post can be closely connected to their personality. The user posted images are designated as personality traits. The objective of this study is to predict five factor model personality dimensions from profile images by using deep learning and neural networks. Developed a deep learning framework-based neural network for personality prediction. The personality types of the Big Five Factor model can be quantified from user profile images. To measure the effectiveness, proposed two models using convolution Neural Networks to classify each personality of the user. Done performance analysis among two different models for efficiently predict personality traits from profile image. It was found that VGG-69 CNN models are best performing models for producing the classification accuracy of 91% to predict user personality traits.

• 한국음향학회지
• /
• 제39권6호
• /
• pp.615-621
• /
• 2020

본 논문은 다중 관측소에서 측정된 지진 신호를 이용한 그래프 합성곱 신경망 기반 지진 이벤트 분류 방법을 제안한다. 기존의 딥러닝 기반 지진 이벤트 분류 방법은 대부분 단일 관측소에서 측정된 신호로부터 지진 이벤트를 분류한다. 지진 관측망에는 수많은 지진 관측소가 존재하며 하나의 관측소만 사용하는 방법보다 여러 관측소의 정보를 동시에 활용하는 방법이 지진 이벤트 분류 성능 향상을 이끌 수 있다. 본 논문에서는 단일 관측소에서 측정된 지진 신호들에 합성곱 신경망을 적용해 임베딩 특징을 추출한 후 그래프 합성곱 신경망을 이용해 단일 관측소들 사이의 정보를 융합하는 다중 관측소 기반 지진 이벤트 분류 구조를 제안한다. 관측소의 개수 변화 등 다양한 실험을 통해 제안한 모델의 성능 검증을 수행하였으며 실험 결과 제안하는 모델이 단일 관측소 기반 분류 모델보다 약 10 % 이상의 정확도와 이벤트 재현율 성능 향상을 보여주었다.

• ETRI Journal
• /
• 제39권6호
• /
• pp.841-850
• /
• 2017

We investigate neural network image reconstruction for magnetic particle imaging. The network performance strongly depends on the convolution effects of the spectrum input data. The larger convolution effect appearing at a relatively smaller nanoparticle size obstructs the network training. The trained single-layer network reveals the weighting matrix consisting of a basis vector in the form of Chebyshev polynomials of the second kind. The weighting matrix corresponds to an inverse system matrix, where an incoherency of basis vectors due to low convolution effects, as well as a nonlinear activation function, plays a key role in retrieving the matrix elements. Test images are well reconstructed through trained networks having an inverse kernel matrix. We also confirm that a multi-layer network with one hidden layer improves the performance. Based on the results, a neural network architecture overcoming the low incoherence of the inverse kernel through the classification property is expected to become a better tool for image reconstruction.