• 한국환경복원기술학회지
• /
• 제26권6호
• /
• pp.67-84
• /
• 2023

In some areas of the Republic of Korea, the designation and management of conservation areas do not adequately reflect regional characteristics and often impose behavioral regulations without considering the local context. One prominent example is the Busan EDC area. As a result, conflicts may arise, including large-scale civil complaints, regarding the conservation and utilization of these areas. Therefore, for the efficient designation and management of protected areas, it is necessary to consider various ecosystem factors, changes in land use, and regional characteristics. In this study, we specifically focused on the Busan EDC area and applied machine learning techniques to analyze the habitat of regional species. Additionally, we employed Explainable Artificial Intelligence techniques to interpret the results of our analysis. To analyze the regional characteristics of the waterfront area in the Busan EDC district and the habitat of migratory birds, we used bird observations as dependent variables, distinguishing between presence and absence. The independent variables were constructed using land cover, elevation, slope, bridges, and river depth data. We utilized the XGBoost (eXtreme Gradient Boosting) model, known for its excellent performance in various fields, to predict the habitat probabilities of 11 bird species. Furthermore, we employed the SHapley Additive exPlanations technique, one of the representative methodologies of XAI, to analyze the relative importance and impact of the variables used in the model. The analysis results showed that in the EDC business district, as one moves closer to the river from the waterfront, the likelihood of bird habitat increases based on the overlapping habitat probabilities of the analyzed bird species. By synthesizing the major variables influencing the habitat of each species, key variables such as rivers, rice fields, fields, pastures, inland wetlands, tidal flats, orchards, cultivated lands, cliffs & rocks, elevation, lakes, and deciduous forests were identified as areas that can serve as habitats, shelters, resting places, and feeding grounds for birds. On the other hand, artificial structures such as bridges, railways, and other public facilities were found to have a negative impact on bird habitat. The development of a management plan for conservation areas based on the objective analysis presented in this study is expected to be extensively utilized in the future. It will provide diverse evidential materials for establishing effective conservation area management strategies.

• 한국멀티미디어학회논문지
• /
• 제24권10호
• /
• pp.1414-1424
• /
• 2021

In this paper, the importance of input factors of a DNN (Deep Neural Network) PM_2.5 forecasting model using LRP(Layer-wise Relevance Propagation) is analyzed, and forecasting performance is improved. Input factor importance analysis is performed by dividing the learning data into time and PM_2.5 concentration. As a result, in the low concentration patterns, the importance of weather factors such as temperature, atmospheric pressure, and solar radiation is high, and in the high concentration patterns, the importance of air quality factors such as PM_2.5, CO, and NO₂ is high. As a result of analysis by time, the importance of the measurement factors is high in the case of the forecast for the day, and the importance of the forecast factors increases in the forecast for tomorrow and the day after tomorrow. In addition, date, temperature, humidity, and atmospheric pressure all show high importance regardless of time and concentration. Based on the importance of these factors, the LRP_DNN prediction model is developed. As a result, the ACC(accuracy) and POD(probability of detection) are improved by up to 5%, and the FAR(false alarm rate) is improved by up to 9% compared to the previous DNN model.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권3호
• /
• pp.974-992
• /
• 2021

Recently, the healthcare field has undergone rapid changes owing to the accumulation of health big data and the development of machine learning. Data mining research in the field of healthcare has different characteristics from those of other data analyses, such as the structural complexity of the medical data, requirement for medical expertise, and security of personal medical information. Various methods have been implemented to address these issues, including the machine learning model and cloud platform. However, the machine learning model presents the problem of opaque result interpretation, and the cloud platform requires more in-depth research on security and efficiency. To address these issues, this paper presents a recent technology for Internet-of-Things-based (IoT-based) health big data processing. We present a cloud-based IoT health platform and health big data processing technology that reduces the medical data management costs and enhances safety. We also present a data mining technology for health-risk prediction, which is the core of healthcare. Finally, we propose a study using explainable artificial intelligence that enhances the reliability and transparency of the decision-making system, which is called the black box model owing to its lack of transparency.

• 산업경영시스템학회지
• /
• 제46권2호
• /
• pp.1-12
• /
• 2023

To make semiconductor chips, a number of complex semiconductor manufacturing processes are required. Semiconductor chips that have undergone complex processes are subjected to EDS(Electrical Die Sorting) tests to check product quality, and a wafer bin map reflecting the information about the normal and defective chips is created. Defective chips found in the wafer bin map form various patterns, which are called defective patterns, and the defective patterns are a very important clue in determining the cause of defects in the process and design of semiconductors. Therefore, it is desired to automatically and quickly detect defective patterns in the field, and various methods have been proposed to detect defective patterns. Existing methods have considered simple, complex, and new defect patterns, but they had the disadvantage of being unable to provide field engineers the evidence of classification results through deep learning. It is necessary to supplement this and provide detailed information on the size, location, and patterns of the defects. In this paper, we propose an anomaly detection framework that can be explained through FCDD(Fully Convolutional Data Description) trained only with normal data to provide field engineers with details such as detection results of abnormal defect patterns, defect size, and location of defect patterns on wafer bin map. The results are analyzed using open dataset, providing prominent results of the proposed anomaly detection framework.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2021년도 추계학술발표대회
• /
• pp.797-800
• /
• 2021

인공지능을 활용한 주가 예측 모형을 실제 금융 서비스에 도입한 사례가 많아지고 있다. 주식 데이터는 일반적인 시계열 데이터와 다르게 예측을 어렵게 하는 복합적인 요소가 존재하며 주식은 리스크가 큰 자산 상품 중 하나이다. 주가 예측 모형의 활용 가능성을 높이기 위해선 성능을 향상시키는 것과 함께 모델을 해석 가능한 형태로 제시해 신뢰성을 향상시킬 필요성이 있다. 본 논문은 주가 전망 결정 방법에 따른 예측 결과를 비교하고, 설명 가능성을 부여해 모형 개선했다는 것에 의의가 있다. 연구 결과, 주가 전망을 장기적으로 결정할수록 정확도가 증가하고, XAI 기법을 통해 모형의 개선 근거를 제시할 수 있음을 알 수 있었다. 본 연구를 통해 인공지능 모형의 신뢰성을 확보하고, 합리적인 투자 결정에 도움을 줄 수 있을 것으로 기대한다.

• 한국분말재료학회지
• /
• 제30권3호
• /
• pp.210-216
• /
• 2023

In this study, machine learning models are proposed to predict the Vickers hardness of AlSi10Mg alloys fabricated by laser powder bed fusion (LPBF). A total of 113 utilizable datasets were collected from the literature. The hyperparameters of the machine-learning models were adjusted to select an accurate predictive model. The random forest regression (RFR) model showed the best performance compared to support vector regression, artificial neural networks, and k-nearest neighbors. The variable importance and prediction mechanisms of the RFR were discussed by Shapley additive explanation (SHAP). Aging time had the greatest influence on the Vickers hardness, followed by solution time, solution temperature, layer thickness, scan speed, power, aging temperature, average particle size, and hatching distance. Detailed prediction mechanisms for RFR are analyzed using SHAP dependence plots.

• 산업경영시스템학회지
• /
• 제46권1호
• /
• pp.76-83
• /
• 2023

Recently, the development of computer vision with deep learning has made object detection using images applicable to diverse fields, such as medical care, manufacturing, and transportation. The manufacturing industry is saving time and money by applying computer vision technology to detect defects or issues that may occur during the manufacturing and inspection process. Annotations of collected images and their location information are required for computer vision technology. However, manually labeling large amounts of images is time-consuming, expensive, and can vary among workers, which may affect annotation quality and cause inaccurate performance. This paper proposes a process that can automatically collect annotations and location information for images using eXplainable AI, without manual annotation. If applied to the manufacturing industry, this process is thought to save the time and cost required for image annotation collection and collect relatively high-quality annotation information.

• 한국재난정보학회 논문집
• /
• 제19권4호
• /
• pp.924-935
• /
• 2023

Purpose: The central aim of this study is to leverage machine learning techniques for the classification of Intrusion Detection System (IDS) data, with a specific focus on identifying the variables responsible for enhancing overall performance. Method: First, we classified 'R2L(Remote to Local)' and 'U2R (User to Root)' attacks in the NSL-KDD dataset, which are difficult to detect due to class imbalance, using seven machine learning models, including Logistic Regression (LR) and K-Nearest Neighbor (KNN). Next, we use the SHapley Additive exPlanation (SHAP) for two classification models that showed high performance, Random Forest (RF) and Light Gradient-Boosting Machine (LGBM), to check the importance of variables that affect classification for each model. Result: In the case of RF, the 'service' variable and in the case of LGBM, the 'dst_host_srv_count' variable were confirmed to be the most important variables. These pivotal variables serve as key factors capable of enhancing performance in the context of classification for each respective model. Conclusion: In conclusion, this paper successfully identifies the optimal models, RF and LGBM, for classifying 'R2L' and 'U2R' attacks, while elucidating the crucial variables associated with each selected model.

• 한국빅데이터학회지
• /
• 제5권2호
• /
• pp.215-229
• /
• 2020

산업 분야를 막론하고 머신러닝의 관심이 매우 높아지고 있으나, 머신러닝이 지닌 설명 불가능성은 여전히 문제로 남아있어 적극적인 업무 적용에 어려움이 있다. 본고에서는 증권사 금융 고객을 대상으로 이탈예측 모델 개발 사례를 소개하고 SHAP Value 기법을 사용하여 설명 가능한 머신러닝 모델 개발 시도와 해석 가능성 도출에 대한 연구 결과를 소개한다. 총 6가지 고객이탈 모델을 비교 분석하였으며, SHAP Value와 고객의 자산 변화에 따른 유형 분류 및 데이터 분석을 통해 고객 이탈 원인을 추론한다. 본 연구 결과를 토대로, 향후 마케팅 담당자의 실제 고객 마케팅 수행에 있어 원인 추론이 가능한 이탈 예측 결괏값을 사용하고 고객별 마케팅 여부를 점검하는 등의 종합적 판단 지표로 활용할 수 있을 것으로 판단된다.

• 한국ITS학회 논문지
• /
• 제21권5호
• /
• pp.233-252
• /
• 2022

자율주행자동차 상용화를 위해 자율주행자동차 안전성 제고를 위한 다양한 연구가 수행되고 있으며, 그 중 시나리오 연구가 안전성 평가에 직접적으로 연관되어 필수적으로 고려되고 있다. 그러나 기존 시나리오 제시의 경우 데이터 부재 및 전문가 개입으로 인해 객관성 및 설명력이 보완될 필요가 있다는 의견이 제시되고 있다. 이에 본 연구에서는 실제 사고 데이터 및 설명력 있는 인공지능 방법론인 ViT 모델을 활용하여 확장된 자율주행자동차 안전성 평가 시나리오를 제시한다. 활용 데이터에 최적화시킨 ViT 모델 학습 결과, 94% 정확도가 확인되었으며 Attention Map을 추가적으로 활용하여 설명력 있는 시나리오를 제시하였다. 본 연구를 통해 기존 시나리오 접근법의 한계를 보완하고 인공지능을 활용하여 새로운 안전성 평가 시나리오 수립 프레임워크를 제시할 수 있을 것으로 기대된다.