• Molecules and Cells
• /
• 제44권2호
• /
• pp.88-100
• /
• 2021

Anoctamin 6/TMEM16F (ANO6) is a dual-function protein with Ca2+-activated ion channel and Ca2+-activated phospholipid scramblase activities, requiring a high intracellular Ca2+ concentration (e.g., half-maximal effective Ca2+ concentration [EC50] of [Ca2+]i > 10 μM), and strong and sustained depolarization above 0 mV. Structural comparison with Anoctamin 1/TMEM16A (ANO1), a canonical Ca2+-activated chloride channel exhibiting higher Ca2+ sensitivity (EC50 of 1 μM) than ANO6, suggested that a homologous Ca2+-transferring site in the N-terminal domain (Nt) might be responsible for the differential Ca2+ sensitivity and kinetics of activation between ANO6 and ANO1. To elucidate the role of the putative Ca2+-transferring reservoir in the Nt (Nt-CaRes), we constructed an ANO6-1-6 chimera in which Nt-CaRes was replaced with the corresponding domain of ANO1. ANO6-1-6 showed higher sensitivity to Ca2+ than ANO6. However, neither the speed of activation nor the voltage-dependence differed between ANO6 and ANO6-1-6. Molecular dynamics simulation revealed a reduced Ca2+ interaction with Nt-CaRes in ANO6 than ANO6-1-6. Moreover, mutations on potentially Ca2+-interacting acidic amino acids in ANO6 Nt-CaRes resulted in reduced Ca2+ sensitivity, implying direct interactions of Ca2+ with these residues. Based on these results, we cautiously suggest that the net charge of Nt-CaRes is responsible for the difference in Ca2+ sensitivity between ANO1 and ANO6.

• Journal of Information Processing Systems
• /
• 제18권2호
• /
• pp.197-207
• /
• 2022

The applications and user interfaces (UIs) of smart mobile devices are constantly diversifying. For example, deep learning can be an innovative solution to classify widgets in screen images for increasing convenience. To this end, the present research leverages captured images and the ReDraw dataset to write deep learning datasets for image classification purposes. First, as the validation for datasets using ResNet50 and EfficientNet, the experiments show that the dataset composed in this study is helpful for classification according to a widget's functionality. An implementation for widget detection and classification on RetinaNet and EfficientNet is then executed. Finally, the research suggests the Widg-C and Widg-D datasets-a deep learning dataset for identifying the widgets of smart devices-and implementing them for use with representative convolutional neural network models.

• International Journal of Computer Science & Network Security
• /
• 제22권5호
• /
• 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.

• 한국전자거래학회지
• /
• 제26권2호
• /
• pp.19-43
• /
• 2021

공연예술 기관에서의 공연에 대한 흥행 예측은 공연예술 산업 및 기관에서 매우 흥미롭고도 중요한 문제이다. 이를 위해 출연진, 공연장소, 가격 등 정형화된 데이터를 활용한 전통적인 예측방법론, 데이터마이닝 방법론이 제시되어 왔다. 그런데 관객들은 공연안내 포스터에 의하여 관람 의도가 소구되는 경향이 있음에도 불구하고, 포스터 이미지 분석을 통한 흥행 예측은 거의 시도되지 않았다. 그러나 최근 이미지를 통해 판별하는 CNN 계열의 딥러닝 방법이 개발되면서 포스터 분석의 가능성이 열렸다. 이에 본 연구의 목적은 공연 관련 포스터 이미지를 통해 흥행을 예측할 수 있는 딥러닝 방법을 제안하는 것이다. 이를 위해 KOPIS 공연예술 통합전산망에 공개된 포스터 이미지를 학습데이터로 하여 Pure CNN, VGG-16, Inception-v3, ResNet50 등 딥러닝 알고리즘을 통해 예측을 수행하였다. 또한 공연 관련 정형데이터를 활용한 전통적 회귀분석 방법론과의 앙상블을 시도하였다. 그 결과 흥행 예측 정확도 85%를 상회하는 높은 판별 성과를 보였다. 본 연구는 공연예술 분야에서 이미지 정보를 활용하여 흥행을 예측하는 첫 시도이며 본 연구에서 제안한 방법은 연극 외에 영화, 기관 홍보, 기업 제품 광고 등 포스터 기반의 광고를 하는 영역으로도 적용이 가능할 것이다.

• International Journal of Computer Science & Network Security
• /
• 제22권4호
• /
• pp.101-110
• /
• 2022

Histopathological analysis of biopsy specimens is still used for diagnosis and classifying the brain tumors today. The available procedures are intrusive, time consuming, and inclined to human error. To overcome these disadvantages, need of implementing a fully automated deep learning-based model to classify brain tumor into multiple classes. The proposed CNN model with an accuracy of 92.98 % for categorizing tumors into five classes such as normal tumor, glioma tumor, meningioma tumor, pituitary tumor, and metastatic tumor. Using the grid search optimization approach, all of the critical hyper parameters of suggested CNN framework were instantly assigned. Alex Net, Inception v3, Res Net -50, VGG -16, and Google - Net are all examples of cutting-edge CNN models that are compared to the suggested CNN model. Using huge, publicly available clinical datasets, satisfactory classification results were produced. Physicians and radiologists can use the suggested CNN model to confirm their first screening for brain tumor Multi-classification.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2024년도 춘계학술발표대회
• /
• pp.592-595
• /
• 2024

엄청난 성능에도 불구하고, 심층 신경망은 예측결과에 대한 설명이 없는 블랙 박스로 작동한다는 비판을 받고 있다. 이러한 불투명한 표현은 신뢰성을 제한하고 모델의 대한 과학적 이해를 방해한다. 본 연구는 여러 개의 교사 신경망으로부터 설명 중심의 학생 신경망으로 지식 증류를 통해 해석 가능성을 향상시키는 것을 제안한다. 구체적으로, 인간이 정의한 개념 활성화 벡터 (CAV)를 통해 교사 모델의 개념 민감도를 방향성 도함수를 사용하여 계량화한다. 목표 개념에 대한 민감도 점수에 비례하여 교사 지식 융합을 가중치를 부여함으로써 증류된 학생 모델은 양호한 성능을 달성하면서 네트워크 논리를 해석으로 집중시킨다. 실험 결과, ResNet50, DenseNet201 및 EfficientNetV2-S 앙상블을 7 배 작은 아키텍처로 압축하여 정확도가 6% 향상되었다. 이 방법은 모델 용량, 예측 능력 및 해석 가능성 사이의 트레이드오프를 조화하고자 한다. 이는 모바일 플랫폼부터 안정성이 중요한 도메인에 걸쳐 믿을 수 있는 AI 의 미래를 여는 데 도움이 될 것이다.

• 대한방사선기술학회지:방사선기술과학
• /
• 제46권6호
• /
• pp.535-542
• /
• 2023

This study aimed to implement a deep learning model that can perform quantitative quality control through ACTS software used for quantitative evaluation of ACR phantom in CT quality control and evaluate its usefulness. By changing the scanning conditions, images of three modules of the ACR phantom's slice thickness (ST), low contrast resolution (LC), and high contrast resolution (HC) were obtained and classified as ACTS software. The deep learning model used ResNet18, implementing three models in which ST, HC, and LC were learned with epoch 50 and an integrated model in which three modules were learned with Epoch 10, 30, and 50 at once. The performance of each model was evaluated through Accuracy and Loss. When comparing and evaluating the accuracy and loss function values of the deep learning models by ST, LC, and HC modules, the Accuracy and Loss of the HC model were the best with 100% and 0.0081, and in the integrated model according to the Epoch value, Accuracy and Loss with epoch 50 were the best with 96.29% and 0.1856. This paper showed that quantitative quality control is possible through a deep learning model, and it can be used as a basis and evidence for applying deep learning to the CT quality control.

• 태양에너지
• /
• 제20권3호
• /
• pp.39-50
• /
• 2000

Radiant barrier systems(RES) constructed with low emissivity materials bounded by an open air space can be used to reduce the net radiation transfer between two surfaces. To analyze the heat transfer characteristics of the radiant barrier systems which consist of a single-glass and radiation barriers, a simple theoretical model based on energy balances was suggested. And the model was validated by means of the experimental results. Using a guarded hot box, the temperatures of layers in selected RES and energy use for each cases were measured. The results show that the model well explained the heat transfer characteristics of those RES. Also, the heat transfer coefficient correlations considering natural and forced convection heat transfer ware suggested. It is found that the heat transfer efficiency of a RBS with aluminium surface improved up to 66.6% over that of a single glazing system.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2021년도 추계학술발표대회
• /
• pp.930-932
• /
• 2021

영상처리에서 데이터 증강(Data augmentation)은 단순히 사진을 편집하여 사진의 개수를 증강하는 것이다. 단순 데이터 증강은 동물의 반점이나 다양한 색깔을 반영하지 못하는 한계가 있다. 본 논문에서는 GAN을 통한 데이터 증강 기법을 제안한다. 제안하는 방법은 CycleGAN을 사용하여 GAN 이미지를 생성한 뒤, 데이터 증강을 거쳐 동물의 종 분류 정확도를 측정한다. 정확도 비교를 위해 일반 사진으로만 구성한 집단과 GAN 사진을 추가한 두 집단으로 나누었다. ResNet50을 사용하여 종 분류 정확도를 측정한다.

• International Journal of Internet, Broadcasting and Communication
• /
• 제14권1호
• /
• pp.136-141
• /
• 2022

A very complex task in deep learning such as image classification must be solved with the help of neural networks and activation functions. The backpropagation algorithm advances backward from the output layer towards the input layer, the gradients often get smaller and smaller and approach zero which eventually leaves the weights of the initial or lower layers nearly unchanged, as a result, the gradient descent never converges to the optimum. We propose a two-factor non-saturating activation functions known as Bea-Mish for machine learning applications in deep neural networks. Our method uses two factors, beta (𝛽) and alpha (𝛼), to normalize the area below the boundary in the Mish activation function and we regard these elements as Bea. Bea-Mish provide a clear understanding of the behaviors and conditions governing this regularization term can lead to a more principled approach for constructing better performing activation functions. We evaluate Bea-Mish results against Mish and Swish activation functions in various models and data sets. Empirical results show that our approach (Bea-Mish) outperforms native Mish using SqueezeNet backbone with an average precision (AP50val) of 2.51% in CIFAR-10 and top-1accuracy in ResNet-50 on ImageNet-1k. shows an improvement of 1.20%.