• The Bulletin of The Korean Astronomical Society
• /
• v.46 no.1
• /
• pp.42.1-42.1
• /
• 2021

In this study, we present a visual explanation of a deep learning solar flare forecast model and its relationship to physical parameters of solar active regions (ARs). For this, we use full-disk magnetograms at 00:00 UT from the Solar and Heliospheric Observatory/Michelson Doppler Imager and the Solar Dynamics Observatory/Helioseismic and Magnetic Imager, physical parameters from the Space-weather HMI Active Region Patch (SHARP), and Geostationary Operational Environmental Satellite X-ray flare data. Our deep learning flare forecast model based on the Convolutional Neural Network (CNN) predicts "Yes" or "No" for the daily occurrence of C-, M-, and X-class flares. We interpret the model using two CNN attribution methods (guided backpropagation and Gradient-weighted Class Activation Mapping [Grad-CAM]) that provide quantitative information on explaining the model. We find that our deep learning flare forecasting model is intimately related to AR physical properties that have also been distinguished in previous studies as holding significant predictive ability. Major results of this study are as follows. First, we successfully apply our deep learning models to the forecast of daily solar flare occurrence with TSS = 0.65, without any preprocessing to extract features from data. Second, using the attribution methods, we find that the polarity inversion line is an important feature for the deep learning flare forecasting model. Third, the ARs with high Grad-CAM values produce more flares than those with low Grad-CAM values. Fourth, nine SHARP parameters such as total unsigned vertical current, total unsigned current helicity, total unsigned flux, and total photospheric magnetic free energy density are well correlated with Grad-CAM values.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.16 no.4
• /
• pp.145-151
• /
• 2021

In this paper, we propose a novel visualization technique to explain the predictions of deep neural networks. We use knowledge distillation (KD) to identify the interior of a black-box model for which we know only inputs and outputs. The information of the black box model will be transferred to a white box model that we aim to create through the KD. The white box model will learn the representation of the black-box model. Second, the white-box model generates attention maps for each of its layers using Grad-CAM. Then we combine the attention maps of different layers using the pixel-wise summation to generate a final saliency map that contains information from all layers of the model. The experiments show that the proposed technique found important layers and explained which part of the input is important. Saliency maps generated by the proposed technique performed better than those of Grad-CAM in deletion game.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.510-512
• /
• 2023

In order to enhance a model's capability for detecting facial expressions, this research suggests a pipeline that makes use of the GradCAM component. The patching module and the pseudo-labeling module make up the pipeline. The patching component takes the original face image and divides it into four equal parts. These parts are then each input into a 2Dconvolutional layer to produce a feature vector. Each picture segment is assigned a weight token using GradCAM in the pseudo-labeling module, and this token is then merged with the feature vector using principal component analysis. A convolutional neural network based on transfer learning technique is then utilized to extract the deep features. This technique applied on a public dataset MMI and achieved a validation accuracy of 96.06% which is showing the effectiveness of our method.

• 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 Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.315-316
• /
• 2022

본 논문은 스마트 인솔의 압력 데이터를 이용하는 컨볼루션 신경망 모델에 해석가능한 인공지능 방법인 Grad-CAM을 적용하는 방법을 제안한다. 학습된 각 모델에 Grad-CAM을 적용하여 모델에서 중요한 역할을 하는 압력센서와 중요하지 않은 압력센서를 알아내는 방법을 제안하고 데이터마다 학습을 진행하고 학습된 모델을 통해 실제로 중요한 압력센서와 그렇지 않은 압력센서에 대해서 알아본다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.586-589
• /
• 2024

본 실험 연구에서는 주의 메커니즘과 컨볼루션 신경망을 결합하여 모델을 개선하는 방법을 탐색하는 딥 러닝 기술을 소개한다. 이 기술은 지도 학습 방식을 위해 공개 데이터 세트의 쓰레기 분류 데이터를 사용하고, Grad-CAM 기술과 채널 주의 메커니즘 SE 를 적용하여 모델의 분류 의사 결정 과정을 더 잘 이해하기 위해 히트 맵을 생성한다. Grad-CAM 기술을 사용하여 히트 맵을 생성하면 분류 중에 모델이 집중하는 영역을 시각화할 수 있다. 이는 모델의 분류 결정을 설명하는 방법을 제공하여 다양한 이미지 카테고리에 대한 모델 결정의 기초를 더 잘 이해할 수 있다. 실험 결과는 전통적인 합성곱 신경망과 비교하여 제안한 방법이 쓰레기 분류 작업에서 더나은 성능을 달성한다는 것을 보여준다. 주의 메커니즘과 히트맵 해석을 결합함으로써 우리 모델은분류 정확도를 향상시킬 수 있다. 이는 실제 응용 분야의 이미지 분류 작업에 큰 의미가 있으며 해석 가능성에 대한 딥 러닝 연구 진행을 촉진하는 데 도움이 된다.

• Journal of Advanced Navigation Technology
• /
• v.26 no.2
• /
• pp.113-118
• /
• 2022

Motivated by people highlighting important phrases while reading or taking notes we propose a neural network training method by highlighting defective pixel areas to classify effectively defect types of images with complex background textures. To verify our proposed method we apply it to the problem of classifying the defect types of tire band fabric images that are too difficult to classify. In addition we propose a backlight highlighting technique which is tailored to the tire band fabric images. Backlight highlighting images can be generated by using both the GradCAM and simple image processing. In our experiment we demonstrated that the proposed highlighting method outperforms the traditional method in the view points of both classification accuracy and training speed. It achieved up to 13.4% accuracy improvement compared to the conventional method. We also showed that the backlight highlighting technique tailored for highlighting tire band fabric images is superior to a contour highlighting technique in terms of accuracy.

• Smart Media Journal
• /
• v.11 no.11
• /
• pp.92-98
• /
• 2022

Identifying defects in textiles is a key procedure for quality control. This study attempted to create a model that detects defects by analyzing the images of the fabrics. The models used in the study were deep learning-based VGGNet and ResNet, and the defect detection performance of the two models was compared and evaluated. The accuracy of the VGGNet and the ResNet model was 0.859 and 0.893, respectively, which showed the higher accuracy of the ResNet. In addition, the region of attention of the model was derived by using the Grad-CAM algorithm, an eXplainable Artificial Intelligence (XAI) technique, to find out the location of the region that the deep learning model recognized as a defect in the fabric image. As a result, it was confirmed that the region recognized by the deep learning model as a defect in the fabric was actually defective even with the naked eyes. The results of this study are expected to reduce the time and cost incurred in the fabric production process by utilizing deep learning-based artificial intelligence in the defect detection of the textile industry.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.01a
• /
• pp.3-5
• /
• 2022

본 연구는 VGGNet을 사용하여 광섬유 복합가공 지선 설비의 양/불량 판별을 수행한다. 광섬유 복합가공 지선이란, 전력선의 보호 및 전력 시설 간 통신을 담당하는 중요 설비로 고장 발생 전, 결함의 조기 발견 및 유지 관리가 중요하다. 현재 한국전력공사에서는 드론에서 촬영된 영상을 점검원이 이상 여부를 점검하는 방식이 주로 사용되고 있으나 이는 점검원의 숙련도, 경험에 따른 정확성 및 비용과 시간 측면에서 한계를 지니고 있다. 본 연구는 드론에서 촬영된 영상으로 VGGNet 기반의 양/불량 판정을 수행했다. 그 결과, 정확도 약 95.15%, 정밀도 약 96%, 재현율 약 95%, f1 score 약 95%의 성능을 확인하였다. 결과 확인 방법으로는 설명 가능한 인공지능(XAI) 알고리즘 중 하나인 Grad-CAM을 적용하였다. 이러한 광섬유 복합가공 지선 설비의 양/불량 판별은 점검원의 단순 작업에 대한 비용 및 점검 시간을 줄이며, 부가가치가 높은 업무에 집중할 수 있게 해준다. 또한, 고장 결함 발견에 있어서 객관적인 점검을 수행하기 때문에 일정한 점검 품질을 유지한다는 점에서 적용 가치가 있다.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.3
• /
• pp.121-138
• /
• 2024

Artificial intelligence is crucial to manufacturing productivity. Understanding the difficulties in producing disruptions, especially in linear feed robot systems, is essential for efficient operations. These mechanical tools, essential for linear movements within systems, are prone to damage and degradation, especially in the LM guide, due to repetitive motions. We examine how explainable artificial intelligence (XAI) may diagnose wafer linear robot linear rail clearance and ball screw clearance anomalies. XAI helps diagnose problems and explain anomalies, enriching management and operational strategies. By interpreting the reasons for anomaly detection through visualizations such as Class Activation Maps (CAMs) using technologies like Grad-CAM, FG-CAM, and FFT-CAM, and comparing 1D-CNN with 2D-CNN, we illustrates the potential of XAI in enhancing diagnostic accuracy. The use of datasets from accelerometer and torque sensors in our experiments validates the high accuracy of the proposed method in binary and ternary classifications. This study exemplifies how XAI can elucidate deep learning models trained on industrial signals, offering a practical approach to understanding and applying AI in maintaining the integrity of critical components such as LM guides in linear feed robots.