• 인터넷정보학회논문지
• /
• 제20권6호
• /
• pp.29-36
• /
• 2019

When dealing with outdoor images in a variety of computer vision applications, the presence of shadow degrades performance. In order to understand the information occluded by shadow, it is essential to remove the shadow. To solve this problem, in many studies, involves a two-step process of shadow detection and removal. However, the field of shadow detection based on CNN has greatly improved, but the field of shadow removal has been difficult because it needs to be restored after removing the shadow. In this paper, it is assumed that shadow is detected, and shadow-less image is generated by using original image and shadow mask. In previous methods, based on CGAN, the image created by the generator was learned from only the aspect of the image patch in the adversarial learning through the discriminator. In the contrast, we propose a novel method using a discriminator that judges both the whole image and the local patch at the same time. We not only use the residual generator to produce high quality images, but we also use joint loss, which combines reconstruction loss and GAN loss for training stability. To evaluate our approach, we used an ISTD datasets consisting of a single image. The images generated by our approach show sharp and restored detailed information compared to previous methods.

• 대한전기학회논문지:전력기술부문A
• /
• 제52권8호
• /
• pp.471-480
• /
• 2003

The design of a measurement system to perform Harmonic State Estimation (HSE) is a very complex problem. Among the reasons for its complexity are the system size, conflicting requirements of estimator accuracy, reliability in the presence of transducer noise and data communication failures, adaptability to change in the network topology and cost minimization. In particular, the number of harmonic instruments available is always limited. Therefore, a systematic procedure is needed to design the optimal placement of measurement points. This paper presents a new HSE algorithm which is based on an optimal placement of measurement points using Genetic Algorithms (GAs) which is widely used in areas such as: optimization of the objective function, learning of neural networks, tuning of fuzzy membership functions, machine learning, system identification and control. This HSE has been applied to the Simulation Test Power System for the validation of the new HSE algorithm. The study results have indicated an economical and effective method for optimal placement of measurement points using Genetic Algorithms (GAs) in the Harmonic State Estimation (HSE).

• 디지털융복합연구
• /
• 제19권12호
• /
• pp.353-358
• /
• 2021

노년기에 접어들면서 알츠하이머 다음으로 흔한 퇴행성 뇌 질환은 파킨슨병이다. 파킨슨병의 증상은 손 떨림, 행동의 느려짐, 인지기능의 저하 등 일상생활의 삶의 질을 저하시키는 요인이 된다. 파킨슨병은 조기진단을 통하여 병의 진행 속도를 늦출 수 있는 질환이다. 파킨슨병의 조기진단을 위해 오디오 음성 파일 입력으로 wav2vec을 이용하여 특징을 추출하고 딥러닝(ANN)으로 파킨슨병의 유무를 진단하는 알고리즘을 구현하였다. 오디오 음성 파일을 이용하여 파킨슨병을 진단하는 실험 결과 정확도는 97.47%로 나타났다. 기존의 뉴럴네트워크를 이용하여 파킨슨병을 진단하는 결과보다 좋은 결과를 나타냈다. 오디오 음성 파일을 wav2vec 이용으로 간단하게 실험을 과정을 줄일 수 있었으며, 실험 결과 향상된 결과를 얻을 수 있었다.

• Nuclear Engineering and Technology
• /
• 제53권4호
• /
• pp.1181-1188
• /
• 2021

When abnormal events occur in a nuclear power plant, operators must conduct appropriate abnormal operating procedures. It is burdensome though for operators to choose the appropriate procedure considering the numerous main plant parameters and hundreds of alarms that should be judged in a short time. Recently, various research has applied deep-learning algorithms to support this problem by classifying each abnormal condition with high accuracy. Most of these models are trained with simulator data because of a lack of plant data for abnormal states, and as such, developed models may not have tolerance for plant data in actual situations. In this study, two approaches are investigated for a deep-learning model trained with simulator data to overcome the performance degradation caused by noise in actual plant data. First, a preprocessing method using several filters was employed to smooth the test data noise, and second, a data augmentation method was applied to increase the acceptability of the untrained data. Results of this study confirm that the combination of these two approaches can enable high model performance even in the presence of noisy data as in real plants.

• 대한건축학회논문집:구조계
• /
• 제35권11호
• /
• pp.163-170
• /
• 2019

Most of the current crack investigation work consists of visual inspection using simple measuring equipment such as crack scale. These methods involve the subjection of the inspector, which may lead to differences in the inspection results prepared by the inspector, and may lead to a large number of measurement errors. So, this study proposes an image-based crack detection method to enhance objectivity and efficiency of concrete crack investigation. In this study, YOLOv2 was used to determine the presence of cracks in the image information to ensure the speed and accuracy of detection for real-time analysis. In addition, we extracted shapes of cracks and calculated quantitatively, such as width and length using various image processing techniques. The results of this study will be used as a basis for the development of image-based facility defect diagnosis automation system.

• Structural Engineering and Mechanics
• /
• 제77권4호
• /
• pp.495-508
• /
• 2021

This study devises a novel approach, namely quadruple 1D convolutional neural network, for detecting connection stiffness reduction in steel truss bridge structure using experimental and numerical modal data. The method is developed based on expertise in two domains: firstly, in Structural Health Monitoring, the mode shapes and its high-order derivatives, including second, third, and fourth derivatives, are accurate indicators in assessing damages. Secondly, in the Machine Learning literature, the deep convolutional neural networks are able to extract relevant features from input data, then perform classification tasks with high accuracy and reduced time complexity. The efficacy and effectiveness of the present method are supported through an extensive case study with the railway Nam O bridge. It delivers highly accurate results in assessing damage localization and damage severity for single as well as multiple damage scenarios. In addition, the robustness of this method is tested with the presence of white noise reflecting unavoidable uncertainties in signal processing and modeling in reality. The proposed approach is able to provide stable results with data corrupted by noise up to 10%.

• 한국멀티미디어학회논문지
• /
• 제25권3호
• /
• pp.502-509
• /
• 2022

With the development of media technology, virtual reality (VR) technology is widely used in education, medical care, aerospace, entertainment and other fields. Among them, application in teaching courseware is a relatively new topic. Compared with traditional coursewares, virtual games visualized and extruded abstract teaching contents. Thus it strengthened teaching effects and expanded dimensions of learning. We hypothesized that virtual coursewares could increase users'sense of presence and enhance their focus. In this study, virtual courseswares were compared with traditional coursewares. At the same time, its feasibility and advantages of application were analyzed through literature researching, practical researching and statistical analysis from questionnaires. Furthermore, we designed a teaching system for VR coursewares and explored its performance in multidimensional and contextual teaching situations. It was found that Virtual coursewares have changed the boring traditional teaching methods. The teaching content was displayed in the form of three-dimensional images, videos and sounds through VR equipment, which effectively improved teaching efficiency. In addition, the feasibility of virtual courseware was demonstrated through factor analysis in questionnaires. Compared with traditional teaching courseware, VR coursewares can attract students' attention and improve learning efficiency. It provides a good example and is valuable for the research of virtual realities in education.

• International journal of advanced smart convergence
• /
• 제12권3호
• /
• pp.104-108
• /
• 2023

This paper deals with research on innovative systems using Python-based artificial intelligence technology in the field of plant growth monitoring. The importance of monitoring and analyzing the health status and growth environment of plants in real time contributes to improving the efficiency and quality of crop production. This paper proposes a method of processing and analyzing plant image data using computer vision and deep learning technologies. The system was implemented using Python language and the main deep learning framework, TensorFlow, PyTorch. A camera system that monitors plants in real time acquires image data and provides it as input to a deep neural network model. This model was used to determine the growth state of plants, the presence of pests, and nutritional status. The proposed system provides users with information on plant state changes in real time by providing monitoring results in the form of visual or notification. In addition, it is also used to predict future growth conditions or anomalies by building data analysis and prediction models based on the collected data. This paper is about the design and implementation of Python-based plant growth monitoring systems, data processing and analysis methods, and is expected to contribute to important research areas for improving plant production efficiency and reducing resource consumption.

• Journal of Medicine and Life Science
• /
• 제20권1호
• /
• pp.8-14
• /
• 2023

Interest in the metaverse is increasing as learners participate in learning with presence, improving learning motivation, and interaction. Currently, the use of metaverse in medical education remains in a test-phase of introduction within some companies, while some medical school professors are beginning to utilize it. Therefore, it is difficult to ascertain whether the metaverse has educational potential when used in medical education. This exploratory study investigates the possibility of the educational use of the metaverse. Both the educational usefulness and the examples of its educational usage in domestic and foreign medical schools are explored. As the metaverse is expected to be introduced and utilized more actively in the future, some of its advantages and limitations in medical education have been identified. In light of the vast potential of the metaverse in medical education, the method of educating and preparing medical students should be developed by preparing a new educational foundation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권6호
• /
• pp.1674-1688
• /
• 2023

The remarkable advancement of quantum steganography offers enhanced security for quantum communications. However, there is a significant concern regarding the potential misuse of this technology. Moreover, the current research on identifying malicious quantum steganography is insufficient. To address this gap in steganalysis research, this paper proposes a specialized quantum steganalysis algorithm. This algorithm utilizes quantum machine learning techniques to detect steganography in general quantum secure communication schemes that are based on pure states. The algorithm presented in this paper consists of two main steps: data preprocessing and automatic discrimination. The data preprocessing step involves extracting and amplifying abnormal signals, followed by the automatic detection of suspicious quantum carriers through training on steganographic and non-steganographic data. The numerical results demonstrate that a larger disparity between the probability distributions of steganographic and non-steganographic data leads to a higher steganographic detection indicator, making the presence of steganography easier to detect. By selecting an appropriate threshold value, the steganography detection rate can exceed 90%.