• Progress in Medical Physics
• /
• v.32 no.4
• /
• pp.92-98
• /
• 2021

Purpose: This study automatically discriminates homogeneous and structure edge regions on computed tomography (CT) images, and it evaluates the noise level and edge preservation ratio (EPR) according to the different types of iterative reconstruction (IR). Methods: The dataset consisted of CT scans of 10 patients reconstructed with filtered back projection (FBP), statistical IR (iDose⁴), and iterative model-based reconstruction (IMR). Using the 10th and 85th percentiles of the structure coherence feature, homogeneous and structure edge regions were localized. The noise level was estimated using the averages of the standard deviations for five regions of interests (ROIs), and the EPR was calculated as the ratio of standard deviations between homogeneous and structural edge regions on subtraction CT between the FBP and IR. Results: The noise levels were 20.86±1.77 Hounsfield unit (HU), 13.50±1.14 HU, and 7.70±0.46 HU for FBP, iDose⁴, and IMR, respectively, which indicates that iDose⁴ and IMR could achieve noise reductions of approximately 35.17% and 62.97%, respectively. The EPR had values of 1.14±0.48 and 1.22±0.51 for iDose⁴ and IMR, respectively. Conclusions: The iDose⁴ and IMR algorithms can effectively reduce noise levels while maintaining the anatomical structure. This study suggested automated evaluation measurements of noise levels and EPRs, which are important aspects in CT image quality with patients' cases of FBP, iDose⁴, and IMR. We expect that the inclusion of other important image quality indices with a greater number of patients' cases will enable the establishment of integrated platforms for monitoring both CT image quality and radiation dose.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.4
• /
• pp.73-79
• /
• 2022

The Python language widely used in artificial intelligence (AI) projects is an interpreter language, and errors occur at runtime. In order to prevent project failure due to errors, it is necessary to handle exceptions in code that can cause exceptional situations in advance. In particular, in AI projects that require a lot of resources, exceptions that occur after long execution lead to a large waste of resources. However, since exception handling depends on the developer's experience, developers have difficulty determining the appropriate exception to catch. To solve this need, we propose an approach that recommends exceptions to catch to developers during development by learning the existing exception handling statements. The proposed method receives the source code of the try block as input and recommends exceptions to be handled in the except block. We evaluate our approach for a large project consisting of two frameworks. According to our evaluation results, the average AUPRC is 0.92 or higher when performing exception recommendation. The study results show that the proposed method can support the developer's exception handling with exception recommendation performance that outperforms the comparative models.

• International Journal of Computer Science & Network Security
• /
• v.22 no.6
• /
• pp.346-356
• /
• 2022

The jurisprudential legal rules govern the way Muslims react and interact to daily life. This creates a huge stream of questions, that require highly qualified and well-educated individuals, called Muftis. With Muslims representing almost 25% of the planet population, and the scarcity of qualified Muftis, this creates a demand supply problem calling for Automation solutions. This motivates the application of Artificial Intelligence (AI) to solve this problem, which requires a well-designed Question-Answering (QA) system to solve it. In this work, we propose a QA system, based on retrieval augmented generative transformer model for jurisprudential legal question. The main idea in the proposed architecture is the leverage of both state-of-the art transformer models, and the existing knowledge base of legal sources and question-answers. With the sensitivity of the domain in mind, due to its importance in Muslims daily lives, our design balances between exploitation of knowledge bases, and exploration provided by the generative transformer models. We collect a custom data set of 850,000 entries, that includes the question, answer, and category of the question. Our evaluation methodology is based on both quantitative and qualitative methods. We use metrics like BERTScore and METEOR to evaluate the precision and recall of the system. We also provide many qualitative results that show the quality of the generated answers, and how relevant they are to the asked questions.

• ETRI Journal
• /
• v.44 no.4
• /
• pp.573-587
• /
• 2022

The agricultural sector is completely different from other sectors since it completely relies on various natural and climatic factors. Climate changes have many effects, including lack of annual rainfall and pests, heat waves, changes in sea level, and global ozone/atmospheric CO₂ fluctuation, on land and agriculture in similar ways. Climate change also affects the environment. Based on these factors, farmers chose their crops to increase productivity in their fields. Many existing agricultural ontologies are either domain-specific or have been created with minimal vocabulary and no proper evaluation framework has been implemented. A new agricultural ontology focused on subdomains is designed to assist farmers using Jaccard relative extractor (JRE) and Naïve Bayes algorithm. The JRE is used to find the similarity between two sentences and words in the agricultural documents and the relationship between two terms is identified via the Naïve Bayes algorithm. In the proposed method, the preprocessing of data is carried out through natural language processing techniques and the tags whose dimensions are reduced are subjected to rule-based formal concept analysis and mapping. The subdomain ontologies of weather, pest, and soil are built separately, and the overall agricultural ontology are built around them. The gold standard for the lexical layer is used to evaluate the proposed technique, and its performance is analyzed by comparing it with different state-of-the-art systems. Precision, recall, F-measure, Matthews correlation coefficient, receiver operating characteristic curve area, and precision-recall curve area are the performance metrics used to analyze the performance. The proposed methodology gives a precision score of 94.40% when compared with the decision tree(83.94%) and K-nearest neighbor algorithm(86.89%) for agricultural ontology construction.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.192-192
• /
• 2023

우량계는 강우 자료를 수집하는 전통적인 방법 중 하나로, 연속적이고 직접적인 설치가 가능하다. 하지만 지형적 특성에 영향을 받아 강우량을 과소 측정하는 문제점이 있다. 이러한 문제를 해결하기 위해 국지적인 호우, 강우 이동 및 강우 상황 등을 파악할 수 있는 레이더를 이용한 강우 측정이 활용된다. 하지만 레이더 기반 측정 또한 우량계와 마찬가지로 과소 측정하는 문제점이 있다. 측정 한계를 극복하기 위해 최근에는 위성 기반 강우 자료를 사용하고 있다. 위성 기반의 강우 자료는 측정이 어려운 장소에서도 강우량의 수집이 가능하며, 지표 변화를 관측하여 강우 측정의 정확도를 높일 수 있다. 고화질 위성 자료인 CHIRPS (Climate Hazards Group InfraRed Precipitation with Stations) 자료는 미국 국제개발처, 항공우주국, 해양 대기청의 지원으로 1980년부터 현재까지 전 지구적 (50°S-50°N, 180°E-180°W) 0.05° × 0.05°의 해상도를 가진 강우량 데이터를 개발하였다. 본 연구에서는 전국 54개 ASOS (Automated Synpotic Observing System)에서 관측한 월 단위 및 일 단위 강우 자료를 기준으로 CHIRPS 강우 자료를 비교하였다. 또한, 다른 위성 강우 자료들 (APHRODITE (Asian Precipitation Highly Resolved Observation Data Integration Towards Evaluation), CMORPH (Climate Prediction Cneter morphing method))과도 비교하여 국내 적용성을 확인하였다. 강우 자료의 정확도를 비교하기 위해서 Box-plot, RMSE (Root Mean Squared Error) 등을 산정하였으며, 강우 발생 일을 비교하고자 오차 행렬을 활용하였다. 비교 결과를 통해서 CHIRPS 강우 자료가 다른 위성 강우 자료들에 비해서 국내 적용성이 높은 것을 확인할 수 있었으며, 추후 국내 수문학 연구에서 기초자료로서 활용될 수 있을 것으로 판단된다.

• Korean Journal of Remote Sensing
• /
• v.39 no.4
• /
• pp.371-393
• /
• 2023

Crack detection in structures plays a vital role in ensuring their safety, durability, and reliability. Traditional crack detection methods sometimes need significant manual inspections, which are laborious, expensive, and prone to error by humans. Deep learning algorithms, which can learn intricate features from large-scale datasets, have emerged as a viable option for automated crack detection recently. This study presents an in-depth review of crack detection methods used till now, like image processing, traditional machine learning, and deep learning methods. Specifically, it will provide a comparative analysis of crack detection methods using deep learning, aiming to provide insights into the advancements, challenges, and future directions in this field. To facilitate comparative analysis, this study surveys publicly available crack detection datasets and benchmarks commonly used in deep learning research. Evaluation metrics employed to check the performance of different models are discussed, with emphasis on accuracy, precision, recall, and F1-score. Moreover, this study provides an in-depth analysis of recent studies and highlights key findings, including state-of-the-art techniques, novel architectures, and innovative approaches to address the shortcomings of the existing methods. Finally, this study provides a summary of the key insights gained from the comparative analysis, highlighting the potential of deep learning in revolutionizing methodologies for crack detection. The findings of this research will serve as a valuable resource for researchers in the field, aiding them in selecting appropriate methods for crack detection and inspiring further advancements in this domain.

• Journal of the Korean Society of Radiology
• /
• v.17 no.4
• /
• pp.625-631
• /
• 2023

The important requirement of industrial dynamic X-ray detector operating under high tube voltage up to 450 kVp for 24 hours and 7 days is to obtain significantly high radiation resistance. This study presents the radiation resistance characteristics of various thin film transistors (TFTs) with a-Si, poly-Si and IGZO semiconducting layers. IGZO TFT offering dozens of times higher field effect mobility than a-Si TFT was processed with highly hydrogenated plasma in between IGZO semiconducting layer and inter-layered dielectric. The hydrogenated IGZO TFT showed most sustainable radiation resistance up to 10,000Gy accumulated, thus, concluded that it is a sole switching device in X-ray imaging sensor offering dynamic X-ray imaging at high frame rate under extremely severe radiation environment such as automated X-ray inspection.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.7
• /
• pp.1773-1793
• /
• 2023

Automated machine learning, often referred to as "AutoML," is the process of automating the time-consuming and iterative procedures that are associated with the building of machine learning models. There have been significant contributions in this area across a number of different stages of accomplishing a data-mining task, including model selection, hyper-parameter optimization, and preprocessing method selection. Among them, preprocessing method selection is a relatively new and fast growing research area. The current work is focused on the recommendation of preprocessing methods, i.e., feature subset selection (FSS) algorithms. One limitation in the existing studies regarding FSS algorithm recommendation is the use of a single learner for meta-modeling, which restricts its capabilities in the metamodeling. Moreover, the meta-modeling in the existing studies is typically based on a single group of data characterization measures (DCMs). Nonetheless, there are a number of complementary DCM groups, and their combination will allow them to leverage their diversity, resulting in improved meta-modeling. This study aims to address these limitations by proposing an architecture for preprocess method selection that uses ensemble learning for meta-modeling, namely AutoFE-Sel. To evaluate the proposed method, we performed an extensive experimental evaluation involving 8 FSS algorithms, 3 groups of DCMs, and 125 datasets. Results show that the proposed method achieves better performance compared to three baseline methods. The proposed architecture can also be easily extended to other preprocessing method selections, e.g., noise-filter selection and imbalance handling method selection.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.4
• /
• pp.113-120
• /
• 2023

Smart farms are steadily increasing in research to minimize labor, energy, and quantity put into crops as IoT technology and artificial intelligence technology are combined. However, research on efficiently managing crop growth information in smart farms has been insufficient to date. In this paper, we propose a management technique that can efficiently monitor crop growth information by applying autonomous sensors to smart farms. The proposed technique focuses on collecting crop growth information through autonomous sensors and then recycling the growth information to crop cultivation. In particular, the proposed technique allocates crop growth information to one slot and then weights each crop to perform load balancing, minimizing interference between crop growth information. In addition, when processing crop growth information in four stages (sensing detection stage, sensing transmission stage, application processing stage, data management stage, etc.), the proposed technique computerizes important crop management points in real time, so an immediate warning system works outside of the management criteria. As a result of the performance evaluation, the accuracy of the autonomous sensor was improved by 22.9% on average compared to the existing technique, and the efficiency was improved by 16.4% on average compared to the existing technique.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.307-307
• /
• 2022

최근 기후변화와 댐 상류 토지이용 변화 등과 같은 다양한 원인에 의해 댐 유입량의 변동성이 증가하면서 댐 관리 및 운영조작 의사 결정에 어려움이 발생하고 있다. 따라서 이러한 댐 유입량의 변동 특성을 반영하여 댐 유입량을 정확하고 효율적으로 예측할 수 있는 방안이 필요한 실정이다. 머신러닝 기술이 발전하면서 Auto-ML(Automated Machine Learning)이 다양한 분야에서 활용되고 있다. Auto-ML은 데이터 전처리, 최적 알고리즘 선택, 하이퍼파라미터 튜닝, 모델 학습 및 평가 등의 모든 과정을 자동화하는 기술이다. 그러나 아직까지 수문 분야에서 댐 유입량을 예측하기 위한 모델을 개발하는데 있어서 Auto-ML을 활용한 사례는 부족하고, 특히 댐 유입량의 예측 정확성을 확보하기 위해 High-inflow and low-inflow 의 변동 특성을 고려한 하이브리드 결합 방식을 통해 Auto-ML 기반 앙상블 모델을 개발하고 평가한 연구는 없다. 본 연구에서는 Auto-ML의 패키지 중 Auto-sklearn을 통해 홍수기, 비홍수기 유입량 변동 특성을 반영한 하이브리드 앙상블 댐 유입량 예측 모델을 개발하였다. 소양강댐을 대상으로 적용한 결과, 하이브리드 Auto-sklearn 앙상블 모델의 댐 유입량 예측 성능은 R² 0.868, RMSE 66.23 m³/s, MAE 16.45 m³/s로 단일 Auto-sklearn을 통해 구축 된 앙상블 모델보다 전반적으로 우수한 것으로 나타났다. 특히 FDC (Flow Duration Curve)의 저수기, 갈수기 구간에서 두 모델의 유입량 예측 경향은 큰 차이를 보였으며, 하이브리드 Auto-sklearn 모델의 예측 값이 관측 값과 더욱 유사한 것으로 나타났다. 이는 홍수기, 비홍수기 구간에 대한 앙상블 모델이 독립적으로 구축되는 과정에서 각 모델에 대한 하이퍼파라미터가 최적화되었기 때문이라 판단된다. 향후 본 연구의 방법론은 보다 정확한 댐 유입량 예측 자료를 생성하기 위한 방안 수립뿐만 아니라 다양한 분야의 불균형한 데이터셋을 이용한 앙상블 모델을 구축하는데도 유용하게 활용될 수 있을 것으로 사료된다.