• Journal of Bio-Environment Control
• /
• v.31 no.3
• /
• pp.255-260
• /
• 2022

This study aimed to develop a service model that uses a deep learning algorithm for detecting diseases and pests in strawberries through image data. In addition, the pest detection performance of deep learning models was further improved by proposing segmented image data sets specialized in disease and pest symptoms. The CNN-based YOLO deep learning model was selected to enhance the existing R-CNN-based model's slow learning speed and inference speed. A general image data set and a proposed segmented image dataset was prepared to train the pest and disease detection model. When the deep learning model was trained with the general training data set, the pest detection rate was 81.35%, and the pest detection reliability was 73.35%. On the other hand, when the deep learning model was trained with the segmented image dataset, the pest detection rate increased to 91.93%, and detection reliability was increased to 83.41%. This study concludes with the possibility of improving the performance of the deep learning model by using a segmented image dataset instead of a general image dataset.

• Land and Housing Review
• /
• v.14 no.2
• /
• pp.125-135
• /
• 2023

Drones are used in various fields, including land survey, transportation, forestry/agriculture, marine, environment, disaster prevention, water resources, cultural assets, and construction, as their industrial importance and market size have increased. In this study, image data for deep learning was collected using a mavic3 drone capturing images at a shooting altitude was 20 m with ×7 magnification. Swin Transformer and UperNet were employed as the backbone and architecture of the deep learning model. About 800 sheets of labeled data were augmented to increase the amount of data. The learning process encompassed three rounds. The Cross-Entropy loss function was used in the first and second learning; the Tversky loss function was used in the third learning. In the future, when the crack detection model is advanced through convergence with the Internet of Things (IoT) through additional research, it will be possible to detect patching or potholes. In addition, it is expected that real-time detection tasks of drones can quickly secure the detection of pavement maintenance sections.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.2
• /
• pp.204-211
• /
• 2020

In this paper, we propose an optimal deep learning network architecture for main object location detection through weak supervised learning. The proposed network adds convolution blocks for improving the localization accuracy of the main object through weakly-supervised learning. The additional deep learning network consists of five additional blocks that add a composite product layer based on VGG-16. And the proposed network was trained by the method of weakly-supervised learning that does not require real location information for objects. In addition, Grad-CAM to compensate for the weakness of GAP in CAM, which is one of weak supervised learning methods, was used. The proposed network was tested through the CUB-200-2011 data set, we could obtain 50.13% in top-1 localization error. Also, the proposed network shows higher accuracy in detecting the main object than the existing method.

• Journal of Digital Convergence
• /
• v.20 no.4
• /
• pp.389-396
• /
• 2022

Deep Learning is based on a perceptron, and is currently being used in various fields such as image recognition, voice recognition, object detection, and drug development. Accordingly, a variety of learning algorithms have been proposed, and the number of neurons constituting a neural network varies greatly among researchers. This study analyzed the learning characteristics according to the number of neurons of the currently used SGD, momentum methods, AdaGrad, RMSProp, and Adam methods. To this end, a neural network was constructed with one input layer, three hidden layers, and one output layer. ReLU was applied to the activation function, cross entropy error (CEE) was applied to the loss function, and MNIST was used for the experimental dataset. As a result, it was concluded that the number of neurons 100-300, the algorithm Adam, and the number of learning (iteraction) 200 would be the most efficient in deep learning learning. This study will provide implications for the algorithm to be developed and the reference value of the number of neurons given new learning data in the future.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.73-74
• /
• 2021

코로나로 인해 X-ray, CT, MRI와 같은 의료영상 분야에서 딥러닝을 많이 접목시키고 있다. 간단히 접할 수 있는 X-ray 영상으로 코로나 진단을 위해 CNN, R-CNN 등과 같은 영상 딥러닝 분야에서 많은 연구가 진행되고 있다. 의료영상 기반 딥러닝 학습은 바이오마커를 정확히 찾아내고, 최소한의 손실률과 높은 정확도를 필요로한다, 따라서 본 논문에서는 높은 정확도를 위한 학습 모델을 선정하고 실험을 진행하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.535-536
• /
• 2021

빅데이터를 활용한 기계학습 모델을 개발하기 위해서는 빅데이터 처리를 위한 플랫폼과 딥러닝 프레임 워크 등 고급 분석을 수행할 수 있는 도구의 활용이 동시에 요구된다. 그러나 빅데이터 플랫폼과 딥러닝 프레임워크를 자유롭게 활용하기 위해서는 상당한 수준의 기술적 지식과 경험이 필요하다. 또한 빅데이터를 이용한 딥러닝 모델을 개발할 경우 분산처리와 병렬처리에 대한 지식과 추가적인 작업이 요구된다. 본 연구에서는 빅데이터를 활용한 기계학습 모형을 자유롭게 개발 및 공유하고 분산 딥러닝을 위한 시스템적 지원을 통해 분야별로 딥러닝 모형을 개발하는 응용 연구자들이 활용할 수 있는 플랫폼을 제시하였다. 본 연구를 통해 다양한 분야의 연구자들이 자신의 데이터를 이용하여 모형을 개발할 경우 분산처리와 병렬처리를 위한 기술적 제약을 극복하고 보다 빠르고 효율적인 방법으로 모형을 개발하고 현업에 활용할 수 있을 것으로 기대한다.

• Proceedings of the Korean Society of Disaster Information Conference
• /
• 2022.10a
• /
• pp.347-348
• /
• 2022

본 연구에서는 무인이동체를 활용한 철도교량의 외관조사 점검을 보다 효율적이고 객관성 있게 수행하기 위하여 무인이동체를 통해 촬영된 이미지를 딥러닝 기반 분석기술을 활용하여 손상 자동으로 분석 하기위한 기술을 연구하였다. 철도교량의 외관 손상 중 균열, 콘크리트 박리·박락, 누수, 철근노출에 대한 손상 이미지를 추출하여 딥러닝 분석 모델을 생성하고 학습한 분석 모델을 적용한 시스템을 실제 현장에 적용 테스트를 수행하였으며 학습 구현된 분석모델의 검측 재현율을 검토한 결과 평균 95%이상의 감지성능을 검토할 수 있었다. 개발 제안된 자동손상분석 기술은 기존 육안점검 결과 대비 보다 객관적이고 정밀한 손상 검측이 가능하며 철도 유지관리 분야에서 무인이동체를 활용한 외관조사 업무를 수행함에 있어 기존 대비 객관적인 결과도출과 소요시간, 비용저감이 가능할 것으로 기대된다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.97-97
• /
• 2023

최근 재해분야에서 인공신경망(ANN), 기계학습(ML), 딥러닝(DL) 등 AI 기술이 활용성이 점차 증가하고 있으며, 센싱정보와 연계한 시설물 안전관리, 원격탐사와 연계한 재해감시(녹조, 산사태, 산불 등), 수문시계열(수위, 유량 등) 예측, 레이더·위성강수 자료의 보정과 예측, 상하수도 관망누수예측 등 다양한 분야에서 AI 기술이 적용되고 그 활용성이 검증된 바 있다. 본 연구에서는 ML, DL, 물리기반신경망(Pysics-informed Neural Networks, PINNs)을 이용한 다양한 재해분석 사례를 소개하고, 그 활용성과 한계에 대해서 논의하고자 한다. 주요사례로는 (1) SAR영상과 기계학습을 이용한 재해피해지역(울진 산불) 감지, (2) 국가 디지털 정보를 이용한 산사태 위험지역 판별(인제 산사태) (3) 기계학습 및 딥러닝 기법을 이용한 위성강수 자료의 보정·예측 및 유출해석, (4) 수리해석을 위한 수치해석분야에서의 PINNs의 적용성(1차원 Saint-Venant 식 해석) 평가 연구결과를 공유한다. 특히, 자료의 입·출력 자료만으로 학습된 인공신경망 모형 대신 지배방정식(물리방정식)을 만족하도록 강제한 PINNs의 경우, 인공신경망 모형보다 우수한 모의능력을 보여주었으며, 향후 복잡한 수리모델링 등 수치해석분야에서 그 활용가능성이 매우 높을 것으로 판단된다.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.3
• /
• pp.845-850
• /
• 2023

In this paper, we propose a method for diagnosing ball bearing vibration using transfer learning. STFT, which can analyze vibration signals in time-frequency, was used as input to CNN to diagnose failures. In order to rapidly learn CNN-based deep artificial neural networks and improve diagnostic performance, we proposed a transfer learning-based deep learning learning technique. For transfer learning, the feature extractor and classifier were selectively learned using a VGG-based image classification model, the data set for learning was publicly available ball bearing vibration data provided by Case Western Reserve University, and performance was evaluated by comparing the proposed method with the existing CNN model. Experimental results not only prove that transfer learning is useful for condition diagnosis in ball bearing vibration data, but also allow other industries to use transfer learning to improve condition diagnosis.

• The Journal of Society for e-Business Studies
• /
• v.26 no.1
• /
• pp.107-126
• /
• 2021

In e-commerce, rapid and accurate automatic product classification according to product information is important. Recent developments in deep learning technology have been actively applied to automatic product classification. In order to develop a deep learning model with good performance, the quality of training data and data preprocessing suitable for the model are crucial. In this study, when categories are inferred based on text product data using a deep learning model, both effects of the data preprocessing and of the selection of training data are extensively compared and analyzed. We employ our CNN model as an example of deep learning model. In the experimental analysis, we use a real e-commerce data to ensure the verification of the study results. The empirical analysis and results shown in this study may be meaningful as a reference study for improving performance when developing a deep learning product classification model.