• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.131-131
• /
• 2022

기후변화의 영향으로 극치강우의 변동성이 커지고 있으며 계획빈도를 초과하는 폭우로 피해가 증가하고 있다. 기존의 물리기반의 홍수예측모델은 개념적 및 구조적 제약과 함께 다양한 유역조건 및 수문기상 조건에 기인한 강우-유출 관계의 불확실성을 고려하는 데 한계가 있다. 특히 한정된 홍수 사상을 통해 구축된 관측 자료로 인해 새로운 홍수 사상 예측 능력이 저조할 수밖에 없다. 따라서 기존 물리모형 기반의 홍수예측과 함께, 딥러닝(deep learning) 모형을 고려한 홍수예측 모델 개발과 개선이 필요하다. 본 연구에서는 다양한 분야에서 활용되는 인공지능(artificial intelligence, AI) 기술을 종합적으로 검토하고, 홍수 예측 측면에서의 활용 가능성 및 신뢰성을 고려하여 AI 기법을 채택하였다. 한강수계에 존재하는 댐 중 일부를 선정하여 대상 댐의 수문·기상학적 자료를 전처리한 후, 인공지능 기반의 홍수예측모형을 구축 및 최적화하였다. 다양한 예측인자와 모델 구성으로 홍수예측력에 대한 평가를 다각적으로 수행함으로써 홍수예측모델의 신뢰성을 제고하였다. 전반적으로 우수한 결과를 도출하였고, 유역면적이 작을수록 결과가 좋았다. 이는 넓은 유역일수록 복잡한 강우-유출 과정이 내재되어 있기 때문으로 판단되며, 넓은 유역에는 본 연구에서 활용한 자료에 추가적인 자료를 도입하여 모형 개선이 이루어져야 할 것으로 판단하였다. 수문 예측 연구에 통계모형이나 기계학습모형의 적용은 많이 있었지만, 딥러닝 기법 활용은 새로운 시도라는 점에서 의미가 있다.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.2
• /
• pp.41-50
• /
• 2023

Gait analysis is an important tool in the clinical management of cerebral palsy, allowing for the assessment of condition severity, identification of potential gait abnormalities, planning and evaluation of interventions, and providing a baseline for future comparisons. However, traditional methods of gait analysis are costly and time-consuming, leading to a need for a more convenient and continuous method. This paper proposes a method for analyzing the posture of cerebral palsy patients using only smartphone videos and deep learning models, including a ResNet-based image tilt correction, AlphaPose for human pose estimation, and SmoothNet for temporal smoothing. The indicators employed in medical practice, such as the imbalance angles of shoulder and pelvis and the joint angles of spine-thighs, knees and ankles, were precisely examined. The proposed system surpassed pose estimation alone, reducing the mean absolute error for imbalance angles in frontal videos from 4.196° to 2.971° and for joint angles in sagittal videos from 5.889° to 5.442°.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.2
• /
• pp.93-100
• /
• 2022

Keyword-oriented search methods are mainly used as data search methods, but this is not suitable as a search method in the legal field where professional terms are widely used. In response, this paper proposes an effective data search method in the legal field. We describe embedding methods optimized for determining similarities between sentences in the field of natural language processing of legal domains. After embedding legal sentences based on keywords using TF-IDF or semantic embedding using Universal Sentence Encoder, we propose an optimal way to search for data by combining BERT models to check similarities between sentences in the legal field.

• Annual Conference of KIPS
• /
• 2022.11a
• /
• pp.55-56
• /
• 2022

Hypertension is a severe health problem and increases the risk of other health issues, such as heart disease, heart attack, and stroke. In this research, we propose a machine learning-based prediction method for the risk of chronic hypertension. The proposed method consists of four main modules. In the first module, the linear interpolation method fills missing values of the integration of gas and meteorological datasets. In the second module, the OrdinalEncoder-based normalization is followed by the Decision tree algorithm to select important features. The prediction analysis module builds three models based on k-Nearest Neighbors, Decision Tree, and Random Forest to predict hypertension levels. Finally, the features used in the prediction model are explained by the DeepSHAP approach. The proposed method is evaluated by integrating the Korean meteorological agency dataset, natural gas leakage dataset, and Korean National Health and Nutrition Examination Survey dataset. The experimental results showed important global features for the hypertension of the entire population and local components for particular patients. Based on the local explanation results for a randomly selected 65-year-old male, the effect of hypertension increased from 0.694 to 1.249 when age increased by 0.37 and gas loss increased by 0.17. Therefore, it is concluded that gas loss is the cause of high blood pressure.

• Journal of IKEEE
• /
• v.27 no.4
• /
• pp.456-463
• /
• 2023

In this paper, we introduce the SSResUNet network model, which integrates the SPADE structure with the U-Net network model for accurate land cover classification using high-resolution satellite imagery without requiring user intervention. The proposed network possesses the advantage of preserving the spatial characteristics inherent in satellite imagery, rendering it a robust classification model even in intricate environments. Experimental results, obtained through training on KOMPSAT-3A satellite images, exhibit superior performance compared to conventional U-Net and U-Net++ models, showcasing an average Intersection over Union (IoU) of 76.10 and a Dice coefficient of 86.22.

• Annual Conference of KIPS
• /
• 2023.11a
• /
• pp.311-313
• /
• 2023

딥러닝에 대한 관심이 증가함에 따라 다양한 분야의 연구자 사이에 딥러닝 모델의 적용 및 재현이 중요한 작업으로 자리잡았다. 하지만 모델을 재현하고 활용하는데 있어 다양한 환경과 자원의 한계가 발생하여 문제가 되고 있다. 이러한 문제를 해결하기 위해 본 논문에서는 국가연구데이터커먼즈체계인 KRDC 프레임워크를 활용하여 딥러닝 학습 모델의 재현 방안을 제안하였다. 이를 통해 딥러닝 연구에 익숙하지 않은 사용자도 학습 모델의 적용 및 활용을 용이하게 할 수 있음을 확인하였다. KRDC 프레임워크는 사용자가 원하는 데이터와 태스크를 정의하고, 워크플로우로 구성, 학습 모델의 재현 및 활용을 지원한다.

• Electronics and Telecommunications Trends
• /
• v.39 no.4
• /
• pp.54-62
• /
• 2024

The emergence and resurgence of novel respiratory infectious diseases since the turn of the millennium, including SARS, H1N1 flu, MERS, and COVID-19, have posed a significant global health threat. Efforts to combat these threats have involved various approaches, however, continued research and development are crucial to prepare for the possibility of emerging viruses and viral variants. Direct detection methods for viral pathogens include molecular diagnostic techniques and immunodiagnostic methods, while indirect diagnostic methods involve detecting changes in the condition of infected patients through imaging diagnostics, gas analysis, and biosignal measurement. Molecular diagnostic techniques, utilizing advanced technologies such as gene editing, are being developed to enable faster detection than traditional PCR methods, and research is underway to improve the efficiency of diagnostic devices. Diagnostic technologies for infectious diseases continue to evolve, and several key trends are expected to emerge in the future. Automation will facilitate widespread adoption of rapid and accurate diagnostics, portable diagnostic devices will enable immediate on-site diagnosis by healthcare professionals, and advancements in AI-based deep learning diagnostic models will enhance diagnostic accuracy.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.10
• /
• pp.513-519
• /
• 2024

Advancements in artificial intelligence(AI) have significantly improved deep learning-based audio deepfake technology, which has been exploited for criminal activities. To detect audio deepfake, we propose CoNSIST, an advanced audio deepfake detection model. CoNSIST builds on AASIST, which a graph-based end-to-end model, by integrating three key components: Squeeze and Excitation, Positional Encoding, and Reformulated HS-GAL. These additions aim to enhance feature extraction, eliminate unnecessary operations, and incorporate diverse information. Our experimental results demonstrate that CoNSIST significantly outperforms existing models in detecting audio deepfakes, offering a more robust solution to combat the misuse of this technology.

• International conference on construction engineering and project management
• /
• 2024.07a
• /
• pp.1073-1080
• /
• 2024

The imperative for real-time automatic construction progress monitoring (ACPM) to avert project delays is widely acknowledged in construction project management. Current ACPM methodologies, however, face a challenge as they rely on collecting data from construction sites and processing it offline for progress analysis. This delayed approach poses a risk of late identification of critical construction issues, potentially leading to rework and subsequent project delays. This research introduces a real-time construction progress monitoring framework that integrates cutting-edge semantic Simultaneous Localization and Mapping (SLAM) techniques. The innovation lies in the framework's ability to promptly identify structural components during site inspections conducted through a robotic system. Incorporating deep learning models, specifically those employing semantic segmentation, enables the system to swiftly acquire and process real-time data, identifying specific structural components and their respective locations. Furthermore, by seamlessly integrating with Building Information Modeling (BIM), the system can effectively evaluate and compare the progress status of each structural component. This holistic approach offers an efficient and practical real-time progress monitoring solution for construction projects, ensuring timely issue identification and mitigating the risk of project delays.

• Korean Journal of Radiology
• /
• v.22 no.3
• /
• pp.476-488
• /
• 2021

Objective: We aimed to develop a deep neural network for segmenting lung parenchyma with extensive pathological conditions on non-contrast chest computed tomography (CT) images. Materials and Methods: Thin-section non-contrast chest CT images from 203 patients (115 males, 88 females; age range, 31-89 years) between January 2017 and May 2017 were included in the study, of which 150 cases had extensive lung parenchymal disease involving more than 40% of the parenchymal area. Parenchymal diseases included interstitial lung disease (ILD), emphysema, nontuberculous mycobacterial lung disease, tuberculous destroyed lung, pneumonia, lung cancer, and other diseases. Five experienced radiologists manually drew the margin of the lungs, slice by slice, on CT images. The dataset used to develop the network consisted of 157 cases for training, 20 cases for development, and 26 cases for internal validation. Two-dimensional (2D) U-Net and three-dimensional (3D) U-Net models were used for the task. The network was trained to segment the lung parenchyma as a whole and segment the right and left lung separately. The University Hospitals of Geneva ILD dataset, which contained high-resolution CT images of ILD, was used for external validation. Results: The Dice similarity coefficients for internal validation were 99.6 ± 0.3% (2D U-Net whole lung model), 99.5 ± 0.3% (2D U-Net separate lung model), 99.4 ± 0.5% (3D U-Net whole lung model), and 99.4 ± 0.5% (3D U-Net separate lung model). The Dice similarity coefficients for the external validation dataset were 98.4 ± 1.0% (2D U-Net whole lung model) and 98.4 ± 1.0% (2D U-Net separate lung model). In 31 cases, where the extent of ILD was larger than 75% of the lung parenchymal area, the Dice similarity coefficients were 97.9 ± 1.3% (2D U-Net whole lung model) and 98.0 ± 1.2% (2D U-Net separate lung model). Conclusion: The deep neural network achieved excellent performance in automatically delineating the boundaries of lung parenchyma with extensive pathological conditions on non-contrast chest CT images.