• 한국멀티미디어학회논문지
• /
• 제23권7호
• /
• pp.803-811
• /
• 2020

This paper proposes an image classification algorithm that transforms the number of convolution layers in the residual block of ResNet, CNN's representative method. The proposed method modified the structure of 34/50 layer of ResNet structure. First, we analyzed the performance of small and many convolution layers for the structure consisting of only shortcut and 3 × 3 convolution layers for 34 and 50 layers. And then the performance was analyzed in the case of small and many cases of convolutional layers for the bottleneck structure of 50 layers. By applying the results, the best classification method in the residual block was applied to construct a 34-layer simple structure and a 50-layer bottleneck image classification model. To evaluate the performance of the proposed image classification model, the results were analyzed by applying to the cifar10 dataset. The proposed 34-layer simple structure and 50-layer bottleneck showed improved performance over the ResNet-110 and Densnet-40 models.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권5호
• /
• pp.1431-1445
• /
• 2022

We construct a deep neural network model named ECGResNet. This model can diagnosis diseases based on 12-lead ECG data of eight common cardiovascular diseases with a high accuracy. We chose the 16 Blocks of ResNet50 as the main body of the model and added the Squeeze-and-Excitation module to learn the data information between channels adaptively. We modified the first convolutional layer of ResNet50 which has a convolutional kernel of 7 to a superposition of convolutional kernels of 8 and 16 as our feature extraction method. This way allows the model to focus on the overall trend of the ECG signal while also noticing subtle changes. The model further improves the accuracy of cardiovascular and cerebrovascular disease classification by using a fully connected layer that integrates factors such as gender and age. The ECGResNet model adds Dropout layers to both the residual block and SE module of ResNet50, further avoiding the phenomenon of model overfitting. The model was eventually trained using a five-fold cross-validation and Flooding training method, with an accuracy of 95% on the test set and an F1-score of 0.841.We design a new deep neural network, innovate a multi-scale feature extraction method, and apply the SE module to extract features of ECG data.

• 한국조경학회지
• /
• 제52권2호
• /
• pp.96-109
• /
• 2024

본 연구는 딥러닝 모델 중 VGG-16 및 ResNet50 모델을 활용하여 전시 정원의 유사성 평가 방법을 제시하는 것에 목적이 있다. VGG-16과 ResNet50 모델을 기반으로 전시 정원 유사성 판단을 위한 모형을 개발하였고, 이를 DRG(deep recognition of similarity in show garden design)모형이라 한다. 평가를 위한 방법으로 GAP와 피어슨 상관계수를 활용한 알고리즘을 사용하여 모형을 구축하고 1순위(Top1), 3순위(Top3), 5순위(Top5)에서 원본 이미지와 유사한 이미지를 도출하는 총 개수 비교로 유사성의 정확도를 분석하였다. DRG 모형에 활용된 이미지 데이터는 국외 쇼몽가든페스티벌 전시 정원 총 278개 작품과 국내 정원박람회인 서울정원박람회 27개 작품 및 코리아가든쇼 전시정원 이미지 17개 작품이다. DRG모형을 활용하여 동일 집단과 타 집단간의 이미지 분석을 진행하였고, 이를 기반으로 전시 정원 유사성의 가이드라인을 제시하였다. 첫째, 전체 이미지 유사성 분석은 ResNet50 모델을 기반으로 하여 데이터 증강 기법을 적용하는 것이 유사성 도출에 적합하였다. 둘째, 내부 구조와 외곽형태에 중점을 둔 이미지 분석에서는 형태에 집중하기 위한 일정한 크기의 필터(16cm × 16cm)를 적용하여 이미지를 생성하고 VGG-16 모델을 적용하여 유사성을 비교하는 방법이 효과적임을 알 수 있었다. 이때, 이미지 크기는 448 × 448 픽셀이 효과적이며, 유채색의 원본 이미지를 기본으로 설정함을 제안하였다. 이러한 연구 결과를 토대로 전시 정원 유사성 판단에 대한 정량적 방법을 제안하고, 향후 다양한 분야와의 융합 연구를 통해 정원 문화의 지속적인 발전에 기여할 것으로 기대한다.

• 대한건축학회논문집:구조계
• /
• 제36권3호
• /
• pp.113-120
• /
• 2020

The purpose of this study is to compare the models of Deep Learning-based Convolution Neural Network(CNN) for concrete crack detection. The comparison models are AlexNet, GoogLeNet, VGG16, VGG19, ResNet-18, ResNet-50, ResNet-101, and SqueezeNet which won ImageNet Large Scale Visual Recognition Challenge(ILSVRC). To train, validate and test these models, we constructed 3000 training data and 12000 validation data with 256×256 pixel resolution consisting of cracked and non-cracked images, and constructed 5 test data with 4160×3120 pixel resolution consisting of concrete images with crack. In order to increase the efficiency of the training, transfer learning was performed by taking the weight from the pre-trained network supported by MATLAB. From the trained network, the validation data is classified into crack image and non-crack image, yielding True Positive (TP), True Negative (TN), False Positive (FP), False Negative (FN), and 6 performance indicators, False Negative Rate (FNR), False Positive Rate (FPR), Error Rate, Recall, Precision, Accuracy were calculated. The test image was scanned twice with a sliding window of 256×256 pixel resolution to classify the cracks, resulting in a crack map. From the comparison of the performance indicators and the crack map, it was concluded that VGG16 and VGG19 were the most suitable for detecting concrete cracks.

• 한국멀티미디어학회논문지
• /
• 제23권10호
• /
• pp.1250-1257
• /
• 2020

The early detection of diseases is important in agriculture because diseases are major threats of reducing crop yield for farmers. The shape and color of plant leaf are changed differently according to the disease. So we can detect and estimate the disease by inspecting the visual feature in leaf. This study presents a vision-based leaf classification method for detecting the diseases of tomato crop. ResNet-50 model was used to extract the visual feature in leaf and classify the disease of tomato crop, since the model showed the higher accuracy than the other ResNet models with different depths. We propose a new ensemble approach using several DCNN classifiers that have the same structure but have been trained at different ranges in the DCNN layers. Experimental result achieved accuracy of 97.19% for PlantVillage dataset. It validates that the proposed method effectively classify the disease of tomato crop.

• 한국컴퓨터정보학회논문지
• /
• 제28권9호
• /
• pp.9-15
• /
• 2023

컴퓨터 비전 분류 연구에서 합성곱 신경망 (Convolutional Neural Network)은 탁월한 이미지 분류성능을 보여준다. 이에 영감을 받아 예술 관련 이미지 분류 작업에 대한 적용 가능성을 분석해 본다. 본 논문에서는 예술 작품 아티스트 분류의 정확도를 향상시키기 위해 최적화된 합성곱 신경망 구조를 제안한다. 미세 조정 범위 시나리오와 완전연결층 조정 시나리오를 세운 뒤 그에 따른 예술 작품 아티스트 분류의 정확도를 측정했다. 즉, 학습 컨볼루션 레이어(Convolution layer) 수와 완전연결층 수 등 ResNet50 모델의 구조를 변경하며 예술 작품 아티스트 분류의 정확도가 향상되도록 최적화했다. 본 논문에서 제안하는 합성곱 신경망 구조는 기존 예술 작품 아티스트 분류에서 쓰이던 AlexNet 모델을 1-GPU 버전으로 수정한 CaffeNet 모델보다 더 높은 정확도를 실험결과에서 증명한다.

• 한국인터넷방송통신학회논문지
• /
• 제21권3호
• /
• pp.81-89
• /
• 2021

자연 조건에서 Apple 감지에는 가림 문제와 작은 대상 감지 어려움이 있다. 본 논문은 SSD 기반의 개선 된 모델을 제안한다. SSD 백본 네트워크 VGG16은 ResNet50 네트워크 모델로 대체되고 수용 필드 구조 RFB 구조가 도입되었다. RFB 모델은 작은 표적의 특징 정보를 증폭하고 작은 표적의 탐지 정확도를 향상시킨다. 유지해야 하는 정보를 필터링하기 위해 주의 메커니즘 (SE)과 결합하면 감지 대상의 의미 정보가 향상된다. 향상된 SSD 알고리즘은 VOC2007 데이터 세트에 대해 학습된다. SSD에 비해 개선 된 알고리즘은 폐색 및 작은 표적 탐지의 정확도를 3.4 % 및 3.9 % 향상 시켰다. 이 알고리즘은 오 탐지율과 누락된 감지율을 향상 시켰다. 본 논문에서 제안한 개선 된 알고리즘은 더 높은 효율성을 갖는다.

• Journal of information and communication convergence engineering
• /
• 제19권2호
• /
• pp.79-83
• /
• 2021

This paper proposes a novel image classification method based on few-shot learning, which is mainly used to solve model overfitting and non-convergence in image classification tasks of small datasets and improve the accuracy of classification. This method uses model structure optimization to extend the basic convolutional neural network (CNN) model and extracts more image features by adding convolutional layers, thereby improving the classification accuracy. We incorporated certain measures to improve the performance of the model. First, we used general methods such as setting a lower learning rate and shuffling to promote the rapid convergence of the model. Second, we used the data expansion technology to preprocess small datasets to increase the number of training data sets and suppress over-fitting. We applied the model to 10 monkey species and achieved outstanding performances. Experiments indicated that our proposed method achieved an accuracy of 87.92%, which is 26.1% higher than that of the traditional CNN method and 1.1% higher than that of the deep convolutional neural network ResNet50.

• 대한의용생체공학회:의공학회지
• /
• 제39권5호
• /
• pp.213-219
• /
• 2018

Stomach cancer is the most diagnosed cancer in Korea. When gastric cancer is detected early, the 5-year survival rate is as high as 90%. Gastroscopy is a very useful method for early diagnosis. But the false negative rate of gastric cancer in the gastroscopy was 4.6~25.8% due to the subjective judgment of the physician. Recently, the image classification performance of the image recognition field has been advanced by the convolutional neural network. Convolutional neural networks perform well when diverse and sufficient amounts of data are supported. However, medical data is not easy to access and it is difficult to gather enough high-quality data that includes expert annotations. So This paper evaluates the efficacy of transfer learning in gastroscopy classification and diagnosis. We obtained 787 endoscopic images of gastric endoscopy at Gil Medical Center, Gachon University. The number of normal images was 200, and the number of abnormal images was 587. The image size was reconstructed and normalized. In the case of the ResNet50 structure, the classification accuracy before and after applying the transfer learning was improved from 0.9 to 0.947, and the AUC was also improved from 0.94 to 0.98. In the case of the InceptionV3 structure, the classification accuracy before and after applying the transfer learning was improved from 0.862 to 0.924, and the AUC was also improved from 0.89 to 0.97. In the case of the VGG16 structure, the classification accuracy before and after applying the transfer learning was improved from 0.87 to 0.938, and the AUC was also improved from 0.89 to 0.98. The difference in the performance of the CNN model before and after transfer learning was statistically significant when confirmed by T-test (p < 0.05). As a result, transfer learning is judged to be an effective method of medical data that is difficult to collect good quality data.