• Composites Research
• /
• v.37 no.1
• /
• pp.40-45
• /
• 2024

In this research, we introduce a novel approach that employs a 3D convolutional neural network (CNN) model to predict the permeability of Gas Diffusion Layers (GDLs). For training the model, we create an artificial dataset of GDL representative volume elements (RVEs) by extracting morphological characteristics from actual GDL images obtained through X-ray tomography. These morphological attributes involve statistical distributions of porosity, fiber orientation, and diameter. Subsequently, a permeability analysis using the Lattice Boltzmann Method (LBM) is conducted on a collection of 10,800 RVEs. The 3D CNN model, trained on this artificial dataset, well predicts the permeability of actual GDLs.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.2
• /
• pp.242-246
• /
• 2010

In this paper, we propose a quality assessment method of biometrics for estimating an authentication result in an user authentication system. The proposed quality assessment method is designed to compute a quality score called CIMR (Confidence Interval Matching Ratio) as a result by small-sample analysis like T-test. We use the C/MR-based quality assessment method for testing how to well draw a distinction between various biometrics in a multimodal biometric system. We also test a predictability for authentication results of obtained biometrics using the mean $\bar{X}$ and the variance $s^2$ in T-test-based CIMR. As a result, we achieved the maximum 88% accuracy for estimation of user authentication results.

• Journal of Bio-Environment Control
• /
• v.32 no.4
• /
• pp.434-441
• /
• 2023

Determining the size or area of a plant's leaves is an important factor in predicting plant growth and improving the productivity of indoor farms. In this study, we developed a convolutional neural network (CNN)-based model to accurately predict the length and width of lettuce leaves using photographs of the leaves. A callback function was applied to overcome data limitations and overfitting problems, and K-fold cross-validation was used to improve the generalization ability of the model. In addition, ImageDataGenerator function was used to increase the diversity of training data through data augmentation. To compare model performance, we evaluated pre-trained models such as VGG16, Resnet152, and NASNetMobile. As a result, NASNetMobile showed the highest performance, especially in width prediction, with an R_squared value of 0.9436, and RMSE of 0.5659. In length prediction, the R_squared value was 0.9537, and RMSE of 0.8713. The optimized model adopted the NASNetMobile architecture, the RMSprop optimization tool, the MSE loss functions, and the ELU activation functions. The training time of the model averaged 73 minutes per Epoch, and it took the model an average of 0.29 seconds to process a single lettuce leaf photo. In this study, we developed a CNN-based model to predict the leaf length and leaf width of plants in indoor farms, which is expected to enable rapid and accurate assessment of plant growth status by simply taking images. It is also expected to contribute to increasing the productivity and resource efficiency of farms by taking appropriate agricultural measures such as adjusting nutrient solution in real time.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.399-401
• /
• 2022

A definitive diagnosis to classify the breast malignancy status may be achieved by microscopic analysis using surgical open biopsy. However, this procedure requires experts in the specializing of histopathological image analysis directing to time-consuming and high cost. To overcome these issues, deep learning is considered practically efficient to categorize breast cancer into benign and malignant from histopathological images in order to assist pathologists. This study presents a pre-trained convolutional neural network model architecture with a 100% fine-tuning scheme and Adagrad optimizer to classify the breast cancer histopathological images into benign and malignant using a 40× magnification BreaKHis dataset. The pre-trained architecture was constructed using the InceptionResNetV2 model to generate a modified InceptionResNetV2 by substituting the last layer with dense and dropout layers. The results by demonstrating training loss of 0.25%, training accuracy of 99.96%, validation loss of 3.10%, validation accuracy of 99.41%, test loss of 8.46%, and test accuracy of 98.75% indicated that the modified InceptionResNetV2 model is reliable to predict the breast malignancy type from histopathological images. Future works are necessary to focus on k-fold cross-validation, optimizer, model, hyperparameter optimization, and classification on 100×, 200×, and 400× magnification.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.3
• /
• pp.33-43
• /
• 2022

In this paper, we propose an ensemble model facilitated by multi-channel palm images with attention U-Net models and pretrained convolutional neural networks (CNNs) for establishing a contactless palm-based user identification system using conventional inexpensive camera sensors. Attention U-Net models are used to extract the areas of interest including hands (i.e., with fingers), palms (i.e., without fingers) and palm lines, which are combined to generate three channels being ped into the ensemble classifier. Then, the proposed palm information-based user identification system predicts the class using the classifier ensemble with three outperforming pre-trained CNN models. The proposed model demonstrates that the proposed model could achieve the classification accuracy, precision, recall, F1-score of 98.60%, 98.61%, 98.61%, 98.61% respectively, which indicate that the proposed model is effective even though we are using very cheap and inexpensive image sensors. We believe that in this COVID-19 pandemic circumstances, the proposed palm-based contactless user identification system can be an alternative, with high safety and reliability, compared with currently overwhelming contact-based systems.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.7
• /
• pp.33-40
• /
• 2024

The live weight of livestock is important information for managing their health and housing conditions, and it can be used to determine the optimal amount of feed and the timing of shipment. In general, it takes a lot of human resources and time to weigh livestock using a scale, and it is not easy to measure each stage of growth, which prevents effective breeding methods such as feeding amount control from being applied. In this paper, we aims to improve the accuracy of weight measurement of piglets, weaned pigs, nursery pigs, and fattening pigs by collecting, analyzing, learning, and predicting video and image data in animal husbandry and pig farming. For this purpose, we trained using Pytorch, YOLO(you only look once) 5 model, and Scikit Learn library and found that the actual and prediction graphs showed a similar flow with a of RMSE(root mean square error) 0.4%. and MAPE(mean absolute percentage error) 0.2%. It can be utilized in the mammalian pig, weaning pig, nursery pig, and fattening pig sections. The accuracy is expected to be continuously improved based on variously trained image and video data and actual measured weight data. It is expected that efficient breeding management will be possible by predicting the production of pigs by part through video reading in the future.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.67-76
• /
• 2023

Although deep learning models are making innovative achievements in the field of computer vision, the problem of vulnerability to adversarial examples continues to be raised. Adversarial examples are attack methods that inject fine noise into images to induce misclassification, which can pose a serious threat to the application of deep learning models in the real world. In this paper, we propose a model that detects adversarial examples using differences in predictive values between edge-learned classification models and underlying classification models. The simple process of extracting the edges of the objects and reflecting them in learning can increase the robustness of the classification model, and economical and efficient detection is possible by detecting adversarial examples through differences in predictions between models. In our experiments, the general model showed accuracy of {49.9%, 29.84%, 18.46%, 4.95%, 3.36%} for adversarial examples (eps={0.02, 0.05, 0.1, 0.2, 0.3}), whereas the Canny edge model showed accuracy of {82.58%, 65.96%, 46.71%, 24.94%, 13.41%} and other edge models showed a similar level of accuracy also, indicating that the edge model was more robust against adversarial examples. In addition, adversarial example detection using differences in predictions between models revealed detection rates of {85.47%, 84.64%, 91.44%, 95.47%, and 87.61%} for each epsilon-specific adversarial example. It is expected that this study will contribute to improving the reliability of deep learning models in related research and application industries such as medical, autonomous driving, security, and national defense.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.557-558
• /
• 2022

본 논문에서는 인공신경망을 통해 화면에 투영된 거품입자를 효율적으로 생성할 수 있는 기법에 대해 소개한다. 유체 시뮬레이션 기반으로 바다거품을 계산하기 위해서는 유체역학과 수치해석학에 대한 이해가 필요하며, 유속의 유기물, 풍속 등 다양한 물리적 요소를 고려해야하기 때문에 복잡하고 계산양이 커진다. 오일러리안(Eulerian)접근법에서는 격자의 해상도가 커지게 되고, 라그랑지안(Lagrangian)접근법에서는 입자의 개수가 많아지기 때문에 이 문제를 다루기 쉽지 않은 문제이다. 이러한 문제를 완화하기 위해 본 논문에서는 인공신경망을 이용한 분류 모델 학습을 통해 3차원 유체 시뮬레이션으로부터 투영된 2차원 스크린 이미지로부터 거품이 생성될 위치를 예측한다. 결과적으로 물의 스크린에 투영된 물 입자의 깊이와 가속도로부터 거품의 생성 위치를 예측함으로서 복잡한 수치해석학 없이 학습을 통해 효율적으로 거품을 표현하는 결과를 보여준다.

• The KIPS Transactions:PartB
• /
• v.15B no.5
• /
• pp.477-486
• /
• 2008

Facial expression, which changes face geometry, usually has an adverse effect on the performance of a face recognition system. To improve the face recognition rate, we propose a normalization method of facial expression to diminish the difference of facial expression between probe and gallery faces. Two approaches are used to facial expression modeling and normalization from single still images using a generic facial muscle model without the need of large image databases. The first approach estimates the geometry parameters of linear muscle models to obtain a biologically inspired model of the facial expression which may be changed intuitively afterwards. The second approach uses RBF(Radial Basis Function) based interpolation and warping to normalize the facial muscle model as unexpressed face according to the given expression. As a preprocessing stage for face recognition, these approach could achieve significantly higher recognition rates than in the un-normalized case based on the eigenface approach, local binary patterns and a grey-scale correlation measure.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.4
• /
• pp.577-586
• /
• 2022

Detection and classification of steel surface defects are critical for product quality control in the steel industry. However, due to its low accuracy and slow speed, the traditional approach cannot be effectively used in a production line. The current, widely used algorithm (based on deep learning) has an accuracy problem, and there are still rooms for development. This paper proposes a method of steel surface defect detection combining EfficientNetV2 for image classification and YOLOv5 as an object detector. Shorter training time and high accuracy are advantages of this model. Firstly, the image input into EfficientNetV2 model classifies defect classes and predicts probability of having defects. If the probability of having a defect is less than 0.25, the algorithm directly recognizes that the sample has no defects. Otherwise, the samples are further input into YOLOv5 to accomplish the defect detection process on the metal surface. Experiments show that proposed model has good performance on the NEU dataset with an accuracy of 98.3%. Simultaneously, the average training speed is shorter than other models.