• International Journal of Internet, Broadcasting and Communication
• /
• v.14 no.2
• /
• pp.136-146
• /
• 2022

Some surface defects make the weak quality of steel materials. To limit these defects, we advocate a one-stage detector model RetinaNet among diverse detection algorithms in deep learning. There are several backbones in the RetinaNet model. We acknowledged two backbones, which are ResNet50 and VGG19. To validate our model, we compared and analyzed several traditional models, one-stage models like YOLO and SSD models and two-stage models like Faster-RCNN, EDDN, and Xception models, with simulations based on steel individual classes. We also performed the correlation of the time factor between one-stage and two-stage models. Comparative analysis shows that the proposed model achieves excellent results on the dataset of the Northeastern University surface defect detection dataset. We would like to work on different backbones to check the efficiency of the model for real world, increasing the datasets through augmentation and focus on improving our limitation.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.659-660
• /
• 2021

본 논문에서는 데카르트 좌표계 기반으로 노드를 압축함으로써 SR(Super-resolution) 기반 연기 합성을 효율적으로 처리할 수 있는 방법을 제안한다. 제안하는 방법은 다운 스케일링과 이진화를 통하여 연기 시뮬레이션의 계산 공간을 효율적으로 줄이고, 데카르트 좌표계 축을 기준으로 쿼드트리의 말단 노드를 압축함으로써 네트워크의 입력으로 전달하는 데이터 개수를 줄인다. 학습에 사용된 데이터는 COCO 2017 데이터셋이며, 인공신경망은 VGG19 기반 네트워크를 사용한다. 컨볼루션 계층을 거칠 때 데이터의 손실을 막기 위해 잔차(Residual)방식과 유사하게 이전 계층의 출력 값을 더해주며 학습한다. 결과적으로 제안하는 방법은 이전 결과에 비해 네트워크로 전달해야 하는 데이터가 압축되어 개수가 줄어드는 결과를 얻었으며, 그로 인해 네트워크 단계에서 필요한 I/O 과정을 효율적으로 처리할 수 있게 되었다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.01a
• /
• pp.261-264
• /
• 2021

본 논문에서는 SR(Super-Resolution)을 계산하는데 필요한 데이터를 효율적으로 분류하고 분할하여 빠르게 SR연산을 가능하게 하는 쿼드트리 기반 최적화 기법을 제안한다. 제안하는 방법은 입력 데이터로 사용하는 연기 데이터를 다운스케일링(Downscaling)하여 쿼드트리 연산 소요 시간을 감소시키며, 이때 연기의 밀도를 이진화함으로써, 다운스케일링 과정에서 밀도가 손실되는 문제를 피한다. 학습에 사용된 데이터는 COCO 2017 Dataset이며, 인공신경망은 VGG19 기반 네트워크를 사용한다. 컨볼루션 계층을 거칠 때 데이터의 손실을 막기 위해 잔차(Residual)방식과 유사하게 이전 계층의 출력 값을 더해주며 학습한다. 결과적으로 제안하는 방법은 이전 결과 기법에 비해 약15~18배 정도의 속도향상을 얻었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.61-64
• /
• 2024

최근 고성능 컴퓨팅 장치의 수요 증가와 함께, 메모리 내에 연산을 가능하게 하는 하드웨어 구조가 새로이 발표되고 있다. 본 논문은 기존 DRAM 에 계산 유닛을 통합하는 새로운 메모리 내 연산 구조를 제안한다. 특히, 데이터 집약적인 합성곱 신경망 작업을 위해 최적화된 이 구조는 기존 메모리 구조를 사용하면서도 기존 구조에 분기를 추가함으로서 CNN 연산의 속도와 에너지 효율을 향상시킨다. VGG19, AlexNet, ResNet-50 과 같은 다양한 CNN 모델을 활용한 실험 결과, PINN 아키텍처는 기존 연구에 비해 최대 2.95 배까지의 성능 향상을 달성할 수 있음을 확인하였다. 이러한 결과는 PINN 기술이 저장 및 연산 성능의 한계를 극복하고, 머신 러닝과 같은 고급 어플리케이션의 요구를 충족시킬 수 있는 방안임을 시사한다.

• International Journal of Computer Science & Network Security
• /
• v.22 no.5
• /
• pp.175-181
• /
• 2022

COVID-19 is an acute respiratory syndrome that affects the host's breathing and respiratory system. The novel disease's first case was reported in 2019 and has created a state of emergency in the whole world and declared a global pandemic within months after the first case. The disease created elements of socioeconomic crisis globally. The emergency has made it imperative for professionals to take the necessary measures to make early diagnoses of the disease. The conventional diagnosis for COVID-19 is through Polymerase Chain Reaction (PCR) testing. However, in a lot of rural societies, these tests are not available or take a lot of time to provide results. Hence, we propose a COVID-19 classification system by means of machine learning and transfer learning models. The proposed approach identifies individuals with COVID-19 and distinguishes them from those who are healthy with the help of Deep Visual Embeddings (DVE). Five state-of-the-art models: VGG-19, ResNet50, Inceptionv3, MobileNetv3, and EfficientNetB7, were used in this study along with five different pooling schemes to perform deep feature extraction. In addition, the features are normalized using standard scaling, and 4-fold cross-validation is used to validate the performance over multiple versions of the validation data. The best results of 88.86% UAR, 88.27% Specificity, 89.44% Sensitivity, 88.62% Accuracy, 89.06% Precision, and 87.52% F1-score were obtained using ResNet-50 with Average Pooling and Logistic regression with class weight as the classifier.

• Nuclear Engineering and Technology
• /
• v.55 no.1
• /
• pp.339-352
• /
• 2023

Prediction of the time-related traits of pebble flow inside pebble-bed HTGRs is of great significance for reactor operation and design. In this work, an image-driven approach with the aid of a convolutional neural network (CNN) is proposed to predict the remaining time of initially loaded pebbles and the time interval of paired flow images of the pebble bed. Two types of strategies are put forward: one is adding FC layers to the classic classification CNN models and using regression training, and the other is CNN-based deep expectation (DEX) by regarding the time prediction as a deep classification task followed by softmax expected value refinements. The current dataset is obtained from the discrete element method (DEM) simulations. Results show that the CNN-aided models generally make satisfactory predictions on the remaining time with the determination coefficient larger than 0.99. Among these models, the VGG19+DEX performs the best and its CumScore (proportion of test set with prediction error within 0.5s) can reach 0.939. Besides, the remaining time of additional test sets and new cases can also be well predicted, indicating good generalization ability of the model. In the task of predicting the time interval of image pairs, the VGG19+DEX model has also generated satisfactory results. Particularly, the trained model, with promising generalization ability, has demonstrated great potential in accurately and instantaneously predicting the traits of interest, without the need for additional computational intensive DEM simulations. Nevertheless, the issues of data diversity and model optimization need to be improved to achieve the full potential of the CNN-aided prediction tool.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.1
• /
• pp.317-326
• /
• 2024

Biometric recognition is a technology that determines whether a person is identified by extracting information on a person's biometric and behavioral characteristics with a specific device. Cyber threats such as forgery, duplication, and hacking of biometric characteristics are increasing in the field of biometrics. In response, the security system is strengthened and complex, and it is becoming difficult for individuals to use. To this end, multiple biometric models are being studied. Existing studies have suggested feature fusion methods, but comparisons between feature fusion methods are insufficient. Therefore, in this paper, we compared and evaluated the fusion method of multiple biometric models using fingerprint, face, and iris images. VGG-16, ResNet-50, EfficientNet-B1, EfficientNet-B4, EfficientNet-B7, and Inception-v3 were used for feature extraction, and the fusion methods of 'Sensor-Level', 'Feature-Level', 'Score-Level', and 'Rank-Level' were compared and evaluated for feature fusion. As a result of the comparative evaluation, the EfficientNet-B7 model showed 98.51% accuracy and high stability in the 'Feature-Level' fusion method. However, because the EfficietnNet-B7 model is large in size, model lightweight studies are needed for biocharacteristic fusion.

• Journal of Multimedia Information System
• /
• v.9 no.3
• /
• pp.177-182
• /
• 2022

A deep neural network (DNN) includes variables whose values keep on changing with the training process until it reaches the final point of convergence. These variables are the co-efficient of a polynomial expression to relate to the feature extraction process. In general, DNNs work in multiple 'dimensions' depending upon the number of channels and batches accounted for training. However, after the execution of feature extraction and before entering the SoftMax or other classifier, there is a conversion of features from multiple N-dimensions to a single vector form, where 'N' represents the number of activation channels. This usually happens in a Fully connected layer (FCL) or a dense layer. This reduced 2D feature is the subject of study for our analysis. For this, we have used the FCL, so the trained weights of this FCL will be used for the weight-class correlation analysis. The popular DNN models selected for our study are ResNet-101, VGG-19, and GoogleNet. These models' weights are directly used for fine-tuning (with all trained weights initially transferred) and scratch trained (with no weights transferred). Then the comparison is done by plotting the graph of feature distribution and the final FCL weights.

• International Journal of Computer Science & Network Security
• /
• v.21 no.7
• /
• pp.182-190
• /
• 2021

Deep learning is an advanced technology for large-scale data analysis, with numerous promising cases like image processing, object detection and significantly more. It becomes customarily to use transfer learning and fine-tune a pre-trained CNN model for most image recognition tasks. Having people taking photos and tag themselves provides a valuable resource of in-data. However, these tags and labels might be noisy as people who annotate these images might not be experts. This paper aims to explore the impact of noisy labels on fine-tuning pre-trained CNN models. Such effect is measured on a food recognition task using Food101 as a benchmark. Four pre-trained CNN models are included in this study: InceptionV3, VGG19, MobileNetV2 and DenseNet121. Symmetric label noise will be added with different ratios. In all cases, models based on DenseNet121 outperformed the other models. When noisy labels were introduced to the data, the performance of all models degraded almost linearly with the amount of added noise.

• International Journal of Computer Science & Network Security
• /
• v.23 no.5
• /
• pp.73-88
• /
• 2023

Brain tumors can also be an abnormal collection or accumulation of cells in the brain that can be life-threatening due to their ability to invade and metastasize to nearby tissues. Accurate diagnosis is critical to the success of treatment planning, and resonant imaging is the primary diagnostic imaging method used to diagnose brain tumors and their extent. Deep learning methods for computer vision applications have shown significant improvements in recent years, primarily due to the undeniable fact that there is a large amount of data on the market to teach models. Therefore, improvements within the model architecture perform better approximations in the monitored configuration. Tumor classification using these deep learning techniques has made great strides by providing reliable, annotated open data sets. Reduce computational effort and learn specific spatial and temporal relationships. This white paper describes transfer models such as the MobileNet model, VGG19 model, InceptionResNetV2 model, Inception model, and DenseNet201 model. The model uses three different optimizers, Adam, SGD, and RMSprop. Finally, the pre-trained MobileNet with RMSprop optimizer is the best model in this paper, with 0.995 accuracies, 0.99 sensitivity, and 1.00 specificity, while at the same time having the lowest computational cost.