• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.21 no.5
• /
• pp.46-52
• /
• 2022

Although pipe performs various functions in industrial sites and residential spaces, if it is damaged due to corrosion caused by the external environment, it may cause equipment failure or a major accident. For this reason, various studies for safety management are being conducted, but studies on detecting corrosion or cracks on the pipe surface using a laser displacement sensor have hardly been conducted. Therefore, in this study, the corrosion degree of the pipe surface was compared and classified into 4 corrosion conditions, and inspection equipment using a laser scanner was manufactured. The corrosion height was calculated from the four surface data obtained from the measuring equipment and applied to various CNN algorithms, and 91% accuracy was obtained during training using the Modified VGGNet16 code with reduced number of parameters.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.5
• /
• pp.817-826
• /
• 2022

AI technology is being successfully introduced in many fields, and models deployed as a service are deployed with black box environment that does not expose the model's information to protect intellectual property rights and data. In a black box environment, attackers try to steal data or parameters used during training by using model output. This paper proposes a method of inferring the type of model to directly find out the composition of layer of the target model, based on the fact that there is no attack to infer the information about the type of model from the deep learning model. With ResNet, VGGNet, AlexNet, and simple convolutional neural network models trained with MNIST datasets, we show that the types of models can be inferred using the output values in the gray box and black box environments of the each model. In addition, we inferred the type of model with approximately 83% accuracy in the black box environment if we train the big and small relationship feature that proposed in this paper together, the results show that the model type can be infrerred even in situations where only partial information is given to attackers, not raw probability vectors.

• Journal of radiological science and technology
• /
• v.46 no.4
• /
• pp.277-285
• /
• 2023

In this study, pneumonia identification networks with the small number of layers were constructed by using chest X-ray images. The networks had similar trainable-parameters, and the performance of the trained models was quantitatively evaluated with the modification of the network architectures. A total of 6 networks were constructed: convolutional neural network (CNN), VGGNet, GoogleNet, residual network with identity blocks, ResNet with bottleneck blocks and ResNet with identity and bottleneck blocks. Trainable parameters for the 6 networks were set in a range of 273,921-294,817 by adjusting the output channels of convolution layers. The network training was implemented with binary cross entropy (BCE) loss function, sigmoid activation function, adaptive moment estimation (Adam) optimizer and 100 epochs. The performance of the trained models was evaluated in terms of training time, accuracy, precision, recall, specificity and F1-score. The results showed that the trained models with the small number of layers precisely detect pneumonia from chest X-ray images. In particular, the overall quantitative performance of the trained models based on the ResNets was above 0.9, and the performance levels were similar or superior to those based on the CNN, VGGNet and GoogleNet. Also, the residual blocks affected the performance of the trained models based on the ResNets. Therefore, in this study, we demonstrated that the object detection networks with the small number of layers are suitable for detecting pneumonia using chest X-ray images. And, the trained models based on the ResNets can be optimized by applying appropriate residual-blocks.

• Convergence Security Journal
• /
• v.23 no.1
• /
• pp.27-33
• /
• 2023

Digitalization due to COVID-19 has rapidly developed artificial intelligence-based voice recognition technology. However, this technology causes unfair social problems, such as race and gender discrimination if datasets are biased against some groups, and degrades the reliability and security of artificial intelligence services. In this work, we compare and analyze accuracy-based unfairness in biased data environments using VGGNet (Visual Geometry Group Network), ResNet (Residual Neural Network), and MobileNet, which are representative CNN (Convolutional Neural Network) models of artificial intelligence. Experimental results show that ResNet34 showed the highest accuracy for women and men at 91% and 89.9%in Top1-accuracy, while ResNet18 showed the slightest accuracy difference between genders at 1.8%. The difference in accuracy between genders by model causes differences in service quality and unfair results between men and women when using the service.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.460-463
• /
• 2022

세계에서 가장 중요한 온대 과일 작물 중 하나인 사과의 생산성과 품질은 병해충 여부에 큰 영향을 받는다. 이를 진단하기 위해서는 효율적이고 많은 전문 지식과 상당한 시간이 필요하다. 그러므로 이를 해결하기 위해 효율적이고 정확하게 다양한 병해충을 진단하는 시스템이 필요하다. 본 논문에서는 이미지 분석에 큰 효율을 보인 딥러닝 기반 CNN 들을 비교 분석하여 사과의 병해충 여부를 판별하고 최적의 모델을 제시한다. 딥러닝 기반 CNN 구조를 가진 AlexNet, VGGNet, Inception-ResNet-v2, DenseNet 을 채택해 사과 병해충 분류 성능 평가를 진행했다. 그 결과 DenseNet 이 가장 우수한 성능을 보여주었다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.17-20
• /
• 2021

본 연구는 인원 계수에 딥러닝 알고리즘을 적용한다. 인원 계수는 안전 관리 분야, 상업 분야에 적용될 수 있다. 예를 들어, 건물 내 화재 발생 시, 계수된 인원을 활용하여 인명 피해를 최소화할 수 있다. 다른 예로, 유동인구 데이터를 기반으로 상권을 분석하여 경제적 효율성을 극대화할 수 있다. 이처럼 인원 데이터의 중요성이 증가함에 따라 인원 계수 연구도 활발하다. 그 예로, 객체 탐지(Object Detection) 같은 딥러닝 기반 인원 계수, 센서 기반 인원 계수 등이 있다. 본 연구에선 딥러닝 알고리즘인 VGGNet을 사용하여 인원을 계수했다. 결과로 Mean Absolute Percentage Error(이하 MAPE)는 약 5.9%의 오차율을 보였다. 결과 확인 방법으로는 설명 가능한 인공지능(XAI) 알고리즘 중 하나인 Grad-CAM을 적용했다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.553-555
• /
• 2022

다양한 양념과 조리법을 활용한 식품의 수는 시간이 지날수록 증가하는 추세이다. 따라서 처음 접하는 식품의 알레르기를 판단하는 연구가 필요하다. 우리는 이미지만으로 알레르기 유발 성분을 판단하는 시스템을 제안한다. 알레르기 성분으로 라벨링한 식품 이미지에 VGGNet 알고리즘을 적용하여 실험을 진행하고 제안된 시스템의 유용성을 판단하였다.

• Journal of Internet Computing and Services
• /
• v.20 no.4
• /
• pp.91-102
• /
• 2019

In autonomous driving systems, the ability to classify pedestrians in images captured by cameras is very important for pedestrian safety. In the past, after extracting features of pedestrians with HOG(Histogram of Oriented Gradients) or SIFT(Scale-Invariant Feature Transform), people classified them using SVM(Support Vector Machine). However, extracting pedestrian characteristics in such a handcrafted manner has many limitations. Therefore, this paper proposes a method to classify pedestrians reliably and effectively using CNN's(Convolutional Neural Network) deep features and transfer learning. We have experimented with both the fixed feature extractor and the fine-tuning methods, which are two representative transfer learning techniques. Particularly, in the fine-tuning method, we have added a new scheme, called M-Fine(Modified Fine-tuning), which divideslayers into transferred parts and non-transferred parts in three different sizes, and adjusts weights only for layers belonging to non-transferred parts. Experiments on INRIA Person data set with five CNN models(VGGNet, DenseNet, Inception V3, Xception, and MobileNet) showed that CNN's deep features perform better than handcrafted features such as HOG and SIFT, and that the accuracy of Xception (threshold = 0.5) isthe highest at 99.61%. MobileNet, which achieved similar performance to Xception and learned 80% fewer parameters, was the best in terms of efficiency. Among the three transfer learning schemes tested above, the performance of the fine-tuning method was the best. The performance of the M-Fine method was comparable to or slightly lower than that of the fine-tuningmethod, but higher than that of the fixed feature extractor method.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.27-35
• /
• 2023

In this paper, we propose a process of increasing productivity by applying a deep learning-based defect detection and classification system to the prepreg fiber manufacturing process, which is in high demand in the field of producing composite materials. In order to apply it to toe prepreg manufacturing equipment that requires a solution due to the occurrence of a large amount of defects in various conditions, the optimal environment was first established by selecting cameras and lights necessary for defect detection and classification model production. In addition, data necessary for the production of multiple classification models were collected and labeled according to normal and defective conditions. The multi-classification model is made based on CNN and applies pre-learning models such as VGGNet, MobileNet, ResNet, etc. to compare performance and identify improvement directions with accuracy and loss graphs. Data augmentation and dropout techniques were applied to identify and improve overfitting problems as major problems. In order to evaluate the performance of the model, a performance evaluation was conducted using the confusion matrix as a performance indicator, and the performance of more than 99% was confirmed. In addition, it checks the classification results for images acquired in real time by applying them to the actual process to check whether the discrimination values are accurately derived.

• Journal of the Korean Wood Science and Technology
• /
• v.47 no.4
• /
• pp.385-392
• /
• 2019

In our previous study, we investigated the use of ensemble models based on LeNet and MiniVGGNet to classify the images of transverse and longitudinal surfaces of five Korean softwoods (cedar, cypress, Korean pine, Korean red pine, and larch). It had accomplished an average F1 score of more than 98%; the classification performance of the longitudinal surface image was still less than that of the transverse surface image. In this study, ensemble methods of two different convolutional neural network models (LeNet3 for smartphone camera images and NIRNet for NIR spectra) were applied to lumber species classification. Experimentally, the best classification performance was obtained by the averaging ensemble method of LeNet3 and NIRNet. The average F1 scores of the individual LeNet3 model and the individual NIRNet model were 91.98% and 85.94%, respectively. By the averaging ensemble method of LeNet3 and NIRNet, an average F1 score was increased to 95.31%.