• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2022년도 춘계학술발표대회
• /
• pp.161-164
• /
• 2022

Homomorphic Encryption (HE) schemes have been recently growing as a reliable solution to preserve users' information owe to maintaining and operating the user data in the encrypted state. In addition to that, several Neural Networks models merged with HE schemes have been developed as a prospective tool for privacy-preserving machine learning. Those mentioned works demonstrated that it is possible to match the accuracy of non-encrypted models but there is always a trade-off in the computation time. In this work, we evaluate the implementation of CKKS HE scheme operations over the layers of a LeNet5 convolutional inference model, however, owing to the limitations of the evaluation environment, the scope of this work is not to develop a complete LeNet5 encrypted model. The evaluation was performed using the MNIST dataset with Microsoft SEAL (MSEAL) open-source homomorphic encryption library ported version on Python (PyFhel). The behavior of the encrypted model, the limitations faced and a small description of related and future work is also provided.

• Geomechanics and Engineering
• /
• 제36권5호
• /
• pp.441-453
• /
• 2024

Sinkhole subsidence and collapse is a common geohazard often formed in karst areas such as the state of Florida, United States of America. To predict the sinkhole occurrence, we need to understand the formation mechanism of sinkhole and its karst hydrogeology. For this purpose, investigating the factors affecting sinkholes is an essential and important step. The main objectives of the presenting study are (1) the development of a machine learning (ML)-based model, namely C5.0 decision tree (C5.0 DT), for the prediction of sinkhole susceptibility, which accounts for sinkhole/subsidence inventory and sinkhole contributing factors (e.g., geological/hydrogeological) and (2) the construction of a regional-scale sinkhole susceptibility map. The study area is east central Florida (ECF) where a cover-collapse type is commonly reported. The C5.0 DT algorithm was used to account for twelve (12) identified hydrogeological factors. In this study, a total of 1,113 sinkholes in ECF were identified and the dataset was then randomly divided into 70% and 30% subsets for training and testing, respectively. The performance of the sinkhole susceptibility model was evaluated using a receiver operating characteristic (ROC) curve, particularly the area under the curve (AUC). The C5.0 model showed a high prediction accuracy of 83.52%. It is concluded that a decision tree is a promising tool and classifier for spatial prediction of karst sinkholes and subsidence in the ECF area.

• 사상체질의학회지
• /
• 제36권2호
• /
• pp.39-48
• /
• 2024

Objectives The aim was to develop a method for detecting Sasang constitution based on the ratio of facial landmarks and provide an objective and reliable tool for Sasang constitution classification. Methods Facial images, KS-15 scores, and certainty scores were collected from subjects identified by Korean Medicine Data Center. Facial ratio landmarks were detected, yielding 2279 facial ratio features. Tree-based models were trained to classify Sasang constitution, and Shapley Additive Explanations (SHAP) analysis was employed to identify important facial features. Additionally, Body Mass Index (BMI) and personality questionnaire were incorporated as supplementary information to enhance model performance. Results Using the Tree-based models, the accuracy for classifying Taeeum, Soeum, and Soyang constitutions was 81.90%, 90.49%, and 81.90% respectively. SHAP analysis revealed important facial features, while the inclusion of BMI and personality questionnaire improved model performance. This demonstrates that facial ratio-based Sasang constitution analysis yields effective and accurate classification results. Conclusions Facial ratio-based Sasang constitution analysis provides rapid and objective results compared to traditional methods. This approach holds promise for enhancing personalized medicine in Korean traditional medicine.

• 문화기술의 융합
• /
• 제10권1호
• /
• pp.121-128
• /
• 2024

최근 AI기반 온라인 번역 도구의 활용도가 높아짐에 따라 이에 대한 교육적 활용 방안 및 효과에 대한 관심이 높아지고 있다. 본 연구에서는 초등 예비교사를 30명을 대상으로 AI기반 온라인 번역도구를 활용한 영작문 과업을 수행하고 영어 글쓰기 능력에 미치는 영향과 실제적 경험을 기반으로 AI번역도구에 대한 활용 가능성, 교육적 활용도 및 장단점 등에 대한 인식을 살펴보았다. 작문시험, 설문조사와 인터뷰를 통해 수집된 자료를 바탕으로 분석한 결과, 영어 글쓰기의 완성도 및 충실도에 있어서 유의미한 증가를 보였으며, 학습자들의 인식에서도 번역도구의 사용은 학습에 대한 즉각적인 지원과 편의성을 제공, 효과적인 도구활용을 위한 교육적 전략의 필요성에 대한 긍정적 인식도 나타났으나, 번역의 완성도나 정확성을 높이기 위한 방법, 도구 활용에 대한 과용과 의존성에 대한 우려도 제기되었다. 번역도구의 효과적 활용을 위해서 교육적 전략이나 교사의 역할의 중요한 것으로 나타났다.

• 지능정보연구
• /
• 제7권2호
• /
• pp.51-63
• /
• 2001

데이터로부터 학습하여 룰을 추출하는 귀납적 학습기법은 데이터 마이닝의 주요 도구 중 하나이다. 귀납적 학습 기법은 불필요한 변수나 잡음이 섞인 변수를 포함하여 학습하는 경우 생성된 룰의 예측 성능이 떨어지고 불필요하게 룰이 복잡하게 구성될 수 있다. 따라서 귀납적 학습 기법의 예측력을 높이고 룰의 구성도 간단하게 할 수 있는 주요 변수 부분집합을 선정하는 방안이 필요하다. 귀납적 학습에서 예측력을 높이기 위해 많이 사용되는 부분집합 선정을 위한 포장 기법은 최적의 부분집합을 찾기 위해 전체 부분집합을 탐색한다. 이때 전체 변수의 수가 많아지면 부분집합의 탐색 공간이 너무 커져서 탐색하기 어려운 문제가 된다. 본 연구에서는 포장 기법에 신경망 민감도 분석을 결합한 귀납적 학습 기법의 변수 부분집합 선정 방안을 제시한다. 먼저, 신경망의 민감도 분석 기법을 이용하여 전체 변수를 중요도 순으로 순서화 한다. 다음에 순서화된 정보를 이용하여 귀납적 학습 기법의 예측력을 높일 수 있는 부분집합을 찾아 나간다. 제안된 방법을 세 데이터 셋에 적용한 결과 일정한 반복 회수 이내에 예측력이 향상된 부분집합을 얻을 수 있음을 볼 수 있다.

• 한국정밀공학회지
• /
• 제28권3호
• /
• pp.285-291
• /
• 2011

The error motion of a machine tool spindle directly affects the surface errors of machined parts. The error motions of the spindle are not desired errors in the three linear direction motions and two rotating motions. Those are usually due to the imperfect of bearings, stiffness of spindle, assembly errors, external force or unbalance of rotors. The error motions of the spindle have been needed to be decreased to desired goal of spindle's performance. The level of error motion is needed to be estimated during the design and assembly process of the spindle. In this paper, the estimation method for the five degree of freedom (5 D.O.F) error motions of the spindle is suggested. To estimate the error motions of the spindle, waviness of shaft and bearings, external force model was used as input data. And, the estimation models are considering geometric relationship and force equilibrium of the five degree of the freedom. To calculate error motions of the spindle, not only imperfection of the shaft, bearings, such as rolling element bearing, hydrostatic bearing, and aerostatic bearing, but also driving elements such as worm, pulley, and direct driving motor systems, were considered.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2005년도 춘계학술대회 논문집
• /
• pp.216-227
• /
• 2005

The head penetrations for control rod drive mechanism and instrumentation systems are installed at the reactor pressure vessel head of PWRs. Primary coolant water and the operating conditions of PWR plants can cause cracking of these nickel-based alloy through a process called primary water stress corrosion cracking (PWSCC). Inspection of the head penetrations to ensure the integrity of the head penetrations has been interested since reactor coolant leakages were found at U. S. reactors in 2000 and 2001. The complex geometry of the head penetrations and the very low echo amplitude from the fine, multiple flaws due to the nature of the see made it difficult to detect and size the flaws using conventional pulse-echo UT methods. Time-of-flight-diffraction technique, which utilizes the time difference between the flaw tips while pulse-echo does the flaw response amplitude from the flaw, has been selected for this inspection for it's best performance of the detection and sizing of the head penetration see flaws. This study defines the limits of the detectable and accurately sizable minimum flaw size which can be detected by the General TOFD and the Delta TOFD techniques for circumferentially and axially oriented flaws respectively. These results assures the reliability of the inspection techniques to detect and accurately size for various kind of flaws, and will also be utilized for the future development and qualifications of the TOFD techniques to enhance the detecting sensitivity and sizing accuracy of the flaws of the reactor head penetrations in nuclear power plants.

• 정보보호학회논문지
• /
• 제32권5호
• /
• pp.945-954
• /
• 2022

매년 수십억 건의 악성코드가 탐지되고 있지만, 이 중 신종 악성코드는 0.01%에 불과하다. 이러한 상황에 효과적인 악성코드 유형 분류 도구가 필요하지만, 선행 연구들은 복잡하고 방대한 양의 데이터 전처리 과정이 필요하여 많은 양의 악성코드를 신속하게 분석하기에는 한계가 있다. 이 문제를 해결하기 위해 본 논문은 유사성 해시를 기반으로 복잡한 데이터 전처리 과정 없이 악성코드의 유형을 분류하는 기법을 제안한다. 이 기법은 악성코드의 유사성 해시 정보를 바탕으로 XGBoost 모델을 학습하며, 평가를 위해 악성코드 분류 분야에 널리 활용되는 BIG-15 데이터셋을 사용했다. 평가 결과, 98.9%의 정확도로 악성코드를 분류했고, 3,432개의 일반 파일을 100% 정확도로 구분했다. 이 결과는 복잡한 전처리 과정 및 딥러닝 모델을 사용하는 대부분의 최신 연구들보다 우수하다. 따라서 제안한 접근법을 사용하면 보다 효율적인 악성코드 분류가 가능할 것으로 예상된다.

• 한국해양공학회지
• /
• 제36권5호
• /
• pp.313-325
• /
• 2022

Recently around the world, coastal erosion is paying attention as a social issue. Various constructions using low-crested and submerged structures are being performed to deal with the problems. In addition, a prediction study was researched using machine learning techniques to determine the wave attenuation characteristics of low crested structure to develop prediction matrix for wave attenuation coefficient prediction matrix consisting of weights and biases for ease access of engineers. In this study, a deep neural network model was constructed to predict the wave height transmission rate of low crested structures using Tensor flow, an open source platform. The neural network model shows a reliable prediction performance and is expected to be applied to a wide range of practical application in the field of coastal engineering. As a result of predicting the wave height transmission coefficient of the low crested structure depends on various input variable combinations, the combination of 5 condition showed relatively high accuracy with a small number of input variables defined as 0.961. In terms of the time cost of the model, it is considered that the method using the combination 5 conditions can be a good alternative. As a result of predicting the wave transmission rate of the trained deep neural network model, MSE was 1.3×10^-3, I was 0.995, SI was 0.078, and I was 0.979, which have very good prediction accuracy. It is judged that the proposed model can be used as a design tool by engineers and scientists to predict the wave transmission coefficient behind the low crested structure.

• Steel and Composite Structures
• /
• 제48권2호
• /
• pp.179-190
• /
• 2023

Many recent attempts have sought accurate prediction of pile pullout resistance (P_ul) using classical machine learning models. This study offers an improved methodology for this objective. Adaptive neuro-fuzzy inference system (ANFIS), as a popular predictor, is trained by a capable metaheuristic strategy, namely equilibrium optimizer (EO) to predict the P_ul. The used data is collected from laboratory investigations in previous literature. First, two optimal configurations of EO-ANFIS are selected after sensitivity analysis. They are next evaluated and compared with classical ANFIS and two neural-based models using well-accepted accuracy indicators. The results of all five models were in good agreement with laboratory P_uls (all correlations > 0.99). However, it was shown that both EO-ANFISs not only outperform neural benchmarks but also enjoy a higher accuracy compared to the classical version. Therefore, utilizing the EO is recommended for optimizing this predictive tool. Furthermore, a comparison between the selected EO-ANFISs, where one employs a larger population, revealed that the model with the population size of 75 is more efficient than 300. In this relation, root mean square error and the optimization time for the EO-ANFIS (75) were 19.6272 and 1715.8 seconds, respectively, while these values were 23.4038 and 9298.7 seconds for EO-ANFIS (300).