• 전기학회논문지
• /
• 제67권1호
• /
• pp.114-123
• /
• 2018

This paper concerns a design and learning method of softmax function neural networks based on K-means clustering. The partial discharge data Information is preliminarily processed through simulation using an Epoxy Mica Coupling sensor and an internal Phase Resolved Partial Discharge Analysis algorithm. The obtained information is processed according to the characteristics of the pattern using a Motor Insulation Monitoring System program. At this time, the processed data are total 4 types that void discharge, corona discharge, surface discharge and slot discharge. The partial discharge data with high dimensional input variables are secondarily processed by principal component analysis method and reduced with keeping the characteristics of pattern as low dimensional input variables. And therefore, the pattern classifier processing speed exhibits improved effects. In addition, in the process of extracting the partial discharge data through the MIMS program, the magnitude of amplitude is divided into the maximum value and the average value, and two pattern characteristics are set and compared and analyzed. In the first half of the proposed partial discharge pattern classifier, the input and hidden layers are classified by using the K-means clustering method and the output of the hidden layer is obtained. In the latter part, the cross entropy error function is used for parameter learning between the hidden layer and the output layer. The final output layer is output as a normalized probability value between 0 and 1 using the softmax function. The advantage of using the softmax function is that it allows access and application of multiple class problems and stochastic interpretation. First of all, there is an advantage that one output value affects the remaining output value and its accompanying learning is accelerated. Also, to solve the overfitting problem, L2-normalization is applied. To prove the superiority of the proposed pattern classifier, we compare and analyze the classification rate with conventional radial basis function neural networks.

• 한국정보기술학회논문지
• /
• 제16권11호
• /
• pp.105-113
• /
• 2018

본 논문에서는 사람 얼굴의 눈, 코, 입을 효과적으로 분류하는 방법을 제안한다. 최근 대부분의 이미지 분류는 CNN(Convolutional Neural Network)을 이용한다. 그러나 CNN으로 추출한 특징은 충분하지 않아 분류 효과가 낮은 경우가 있다. 분류 효과를 더 높이기 위해 새로운 알고리즘을 제안한다. 제안하는 방법은 크게 세 부분으로 나눌 수 있다. 첫 번째는 Haar 특징추출 알고리즘을 사용하여 얼굴의 눈, 코, 입 데이터?을 구성한다. 두번째는 CNN 구조 중 하나인 AlexNet을 사용하여 이미지의 CNN 특징을 추출한다. 마지막으로 Haar 특징 추출 뒤에 합성(Convolution) 연산을 수행하여 Haar-CNN 특징을 추출한다. 그 후 CNN 특징과 Haar-CNN을 혼합하여 Softmax를 이용해 분류한다. 혼합한 특징을 사용한 인식률은 기존의 CNN 특징 보다 약 4% 향상되었다. 실험을 통해 제안하는 방법의 성능을 증명하였다.

• 한국멀티미디어학회논문지
• /
• 제23권8호
• /
• pp.965-976
• /
• 2020

We present in this work a segmentation method of E. coli bacterial images generated via phase contrast microscopy using a deep learning based hybrid feature generation. Unlike conventional machine learning methods that use the hand-crafted features, we adopt the denoising autoencoder in order to generate a precise and accurate representation of the pixels. We first construct a hybrid vector that combines original image, difference of Gaussians and image gradients. The created hybrid features are then given to a deep autoencoder that learns the pixels' internal dependencies and the cells' shape and boundary information. The latent representations learned by the autoencoder are used as the inputs of a softmax classification layer and the direct outputs from the classifier represent the coarse segmentation mask. Finally, the classifier's outputs are used as prior information for a graph partitioning based fine segmentation. We demonstrate that the proposed hybrid vector representation manages to preserve the global shape and boundary information of the cells, allowing to retrieve the majority of the cellular patterns without the need of any post-processing.

• Journal of Information Processing Systems
• /
• 제17권2호
• /
• pp.385-398
• /
• 2021

The complexity of deep learning models affects the real-time performance of gesture recognition, thereby limiting the application of gesture recognition algorithms in actual scenarios. Hence, a residual learning neural network based on a deep convolutional neural network is proposed. First, small convolution kernels are used to extract the local details of gesture images. Subsequently, a shallow residual structure is built to share weights, thereby avoiding gradient disappearance or gradient explosion as the network layer deepens; consequently, the difficulty of model optimisation is simplified. Additional convolutional neural networks are used to accelerate the refinement of deep abstract features based on the spatial importance of the gesture feature distribution. Finally, a fully connected cascade softmax classifier is used to complete the gesture recognition. Compared with the dense connection multiplexing feature information network, the proposed algorithm is optimised in feature multiplexing to avoid performance fluctuations caused by feature redundancy. Experimental results from the ISOGD gesture dataset and Gesture dataset prove that the proposed algorithm affords a fast convergence speed and high accuracy.

• Journal of information and communication convergence engineering
• /
• 제22권2호
• /
• pp.165-171
• /
• 2024

In this study, we present a novel approach for enhancing chest X-ray image classification (normal, Covid-19, edema, mass nodules, and pneumothorax) by combining contrastive learning and machine learning algorithms. A vast amount of unlabeled data was leveraged to learn representations so that data efficiency is improved as a means of addressing the limited availability of labeled data in X-ray images. Our approach involves training classification algorithms using the extracted features from a linear fine-tuned Momentum Contrast (MoCo) model. The MoCo architecture with a Resnet34, Resnet50, or Resnet101 backbone is trained to learn features from unlabeled data. Instead of only fine-tuning the linear classifier layer on the MoCopretrained model, we propose training nonlinear classifiers as substitutes for softmax in deep networks. The empirical results show that while the linear fine-tuned ImageNet-pretrained models achieved the highest accuracy of only 82.9% and the linear fine-tuned MoCo-pretrained models an increased highest accuracy of 84.8%, our proposed method offered a significant improvement and achieved the highest accuracy of 87.9%.

• 농업과학연구
• /
• 제50권3호
• /
• pp.357-364
• /
• 2023

In this study, we propose a ripe tomato bunch localization method based on convolutional neural networks, to be applied in robotic harvesting systems. Tomato images were obtained from a smart greenhouse at the Rural Development Administration (RDA). The sample images for training were extracted based on tomato maturity and resized to 128 × 128 pixels for use in the classification model. The model was constructed based on four-layer convolutional neural networks, and the classes were determined based on stage of maturity, using a Softmax classifier. The localization of the ripe tomato bunch region was indicated on a class activation map. The class activation map could show the approximate location of the tomato bunch but tends to present a local part or a large part of the ripe tomato bunch region, which could lead to poor performance. Therefore, we suggest a recursive method to improve the performance of the model. The classification results indicated that the accuracy, precision, recall, and F1-score were 0.98, 0.87, 0.98, and 0.92, respectively. The localization performance was 0.52, estimated by the Intersection over Union (IoU), and through input recursion, the IoU was improved by 13%. Based on the results, the proposed localization of the ripe tomato bunch area can be incorporated in robotic harvesting systems to establish the optimal harvesting paths.

• 한국음향학회지
• /
• 제39권6호
• /
• pp.592-599
• /
• 2020

본 논문은 다양한 지진 이벤트 분류를 위해 지진 데이터의 정적인 특성과 동적인 특성을 동시에 반영할 수 있는 합성곱 순환 신경망(Convolutional Recurrent Neural Net, CRNN) 구조를 제안한다. 중규모 지진뿐만 아니라 미소 지진, 인공 지진을 포함한 지진 이벤트 분류 문제를 해결하려면 효과적인 특징 추출 및 분류 방법이 필요하다. 본 논문에서는 먼저 주의 기반 합성곱 레이어를 통해 지진 데이터의 정적 특성을 추출 하게 된다. 추출된 특징은 다중 입력 단일 출력 장단기메모리(Long Short-Term Memory, LSTM) 네트워크 구조에 순차적으로 입력되어 다양한 지진 이벤트 분류를 위한 동적 특성을 추출하게 되며 완전 연결 레이어와 소프트맥스 함수를 통해 지진 이벤트 분류를 수행한다. 국내외 지진을 이용한 모의 실험 결과 제안된 모델은 다양한 지진 이벤트 분류에 효과적인 모습을 보여 주었다.

• 한국통신학회논문지
• /
• 제41권8호
• /
• pp.958-964
• /
• 2016

본 논문에서는 여러 개의 이원 support vector machine (binary SVM)을 사용하여 세 개 이상의 클래스를 분류하는 multi-class SVM과 유사하게 다중의 판별 deep neural network (DNN) 모델을 사용하는 i-벡터 기반의 언어 인식 시스템을 제안한다. 제안하는 시스템은 NIST 2015 i-vector Machine Learning Challenge 데이터베이스에 포함된 i-벡터들을 이용하여 학습 및 테스트 되었으며, 오픈 세트에서 기존의 cosine distance, multi-class SVM 및 단일 neural network (NN) 기반의 언어 인식 시스템에 비하여 높은 성능을 보임이 확인되었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권8호
• /
• pp.3567-3582
• /
• 2020

Human activities are often affected by weather conditions. Automatic weather recognition is meaningful to traffic alerting, driving assistance, and intelligent traffic. With the boost of deep learning and AI, deep convolutional neural networks (CNN) are utilized to identify weather situations. In this paper, a three-channel convolutional neural network (3C-CNN) model is proposed on the basis of ResNet50.The model extracts global weather features from the whole image through the ResNet50 branch, and extracts the sky and ground features from the top and bottom regions by two CNN5 branches. Then the global features and the local features are merged by the Concat function. Finally, the weather image is classified by Softmax classifier and the identification result is output. In addition, a medium-scale dataset containing 6,185 outdoor weather images named WeatherDataset-6 is established. 3C-CNN is used to train and test both on the Two-class Weather Images and WeatherDataset-6. The experimental results show that 3C-CNN achieves best on both datasets, with the average recognition accuracy up to 94.35% and 95.81% respectively, which is superior to other classic convolutional neural networks such as AlexNet, VGG16, and ResNet50. It is prospected that our method can also work well for images taken at night with further improvement.

• 정보관리학회지
• /
• 제40권4호
• /
• pp.307-327
• /
• 2023

이 연구는 짧은 텍스트인 서명에 단어 임베딩이 미치는 영향을 분석하기 위해 Word2vec, GloVe, fastText 모형을 이용하여 단행본 서명을 임베딩 벡터로 생성하고, 이를 분류자질로 활용하여 자동분류에 적용하였다. 분류기는 k-최근접 이웃(kNN) 알고리즘을 사용하였고 자동분류의 범주는 도서관에서 도서에 부여한 DDC 300대 강목을 기준으로 하였다. 서명에 대한 단어 임베딩을 적용한 자동분류 실험 결과, Word2vec와 fastText의 Skip-gram 모형이 TF-IDF 자질보다 kNN 분류기의 자동분류 성능에서 더 우수한 결과를 보였다. 세 모형의 다양한 하이퍼파라미터 최적화 실험에서는 fastText의 Skip-gram 모형이 전반적으로 우수한 성능을 나타냈다. 특히, 이 모형의 하이퍼파라미터로는 계층적 소프트맥스와 더 큰 임베딩 차원을 사용할수록 성능이 향상되었다. 성능 측면에서 fastText는 n-gram 방식을 사용하여 하부문자열 또는 하위단어에 대한 임베딩을 생성할 수 있어 재현율을 높이는 것으로 나타났다. 반면에 Word2vec의 Skip-gram 모형은 주로 낮은 차원(크기 300)과 작은 네거티브 샘플링 크기(3이나 5)에서 우수한 성능을 보였다.