• 대한조선학회논문집
• /
• 제48권2호
• /
• pp.147-157
• /
• 2011

A RANS(Reynolds averaged Navier-Stokes) based numerical method is developed for the evaluation of ship resistance and self-propulsion performances. In the usability aspect of CFD for the hull form design, the field grid around practical hull forms is generated by solving a grid Poisson equation based on the hull surface grid generated from station offsets and centerline profile. A body force technique is introduced to model the effects of the propeller in which the propeller loads are obtained from potential flow analysis using an unsteady lifting surface method. The free surface is captured by using a two-phase level-set method and the realizable $k-{\varepsilon}$ model is used for turbulence closure. The hull attitude in vertical plane, i.e., trim and sinkage, is calculated by using a quasi-steady method and then considered in the computation by translating and rotating the grid system according to the values. For the validation of the proposed method, the numerical results of resistance tests for KCS, KLNG, and KVLCC1 and of self-propulsion test for KCS are compared with experimental data.

• 대한치과교정학회지
• /
• 제52권2호
• /
• pp.112-122
• /
• 2022

Objective: This study aimed to present and evaluate a new deep learning model for determining cervical vertebral maturation (CVM) degree and growth spurts by analyzing lateral cephalometric radiographs. Methods: The study sample included 890 cephalograms. The images were classified into six cervical stages independently by two orthodontists. The images were also categorized into three degrees on the basis of the growth spurt: pre-pubertal, growth spurt, and post-pubertal. Subsequently, the samples were fed to a transfer learning model implemented using the Python programming language and PyTorch library. In the last step, the test set of cephalograms was randomly coded and provided to two new orthodontists in order to compare their diagnosis to the artificial intelligence (AI) model's performance using weighted kappa and Cohen's kappa statistical analyses. Results: The model's validation and test accuracy for the six-class CVM diagnosis were 62.63% and 61.62%, respectively. Moreover, the model's validation and test accuracy for the three-class classification were 75.76% and 82.83%, respectively. Furthermore, substantial agreements were observed between the two orthodontists as well as one of them and the AI model. Conclusions: The newly developed AI model had reasonable accuracy in detecting the CVM stage and high reliability in detecting the pubertal stage. However, its accuracy was still less than that of human observers. With further improvements in data quality, this model should be able to provide practical assistance to practicing dentists in the future.

• 디지털융복합연구
• /
• 제19권9호
• /
• pp.257-269
• /
• 2021

논문은 심탄도(BCG, Ballistocardiogram) 센서를 이용하여 생체신호 데이터를 비침습, 무구속적인 방식으로 수집하고, ICT 기술과 고성능 컴퓨팅 환경에서 인공지능 기계학습 알고리즘을 활용하여 데이터 기반 혈당 예측 알고리즘 모델 개발 및 검증하는 방법을 제시하고 연구하는 것이다. 혈당수치 예측모델은 MLP 아키텍처에 입력노드는 심박수, 호흡수, 심박출량, 심박변이도, SDNN, RMSSD, PNN50, 나이, 성별이며, 은닉층 7개를 사용하였다. 실험 결과는 5회 실험한 학습데이터의 평균 MSE, MAE 및 RMSE 값은 각각 0.5226, 0.6328 및 0.7692이며 검증데이터 평균 값은 각각 0.5408, 0.6776, 0.7968이었으며, 결정계수(R2) 수치는 0.9997의 결과를 보였다. 데이터를 기반으로 한 혈당수치를 예측하는 모델을 표준화하고 데이터셋 수집과 예측 정확성을 검증하는 연구가 계속적으로 진행된다면 비침습 방식의 혈당 수준 관리에 활용될 수 있을 것으로 사료된다.

• International Journal of Advanced Culture Technology
• /
• 제10권1호
• /
• pp.274-283
• /
• 2022

Korea is facing a number difficulties arising from rising housing prices. As 'housing' takes the lion's share in personal assets, many difficulties are expected to arise from fluctuating housing prices. The purpose of this study is creating housing price prediction model to prevent such risks and induce reasonable real estate purchases. This study made many attempts for understanding real estate instability and creating appropriate housing price prediction model. This study predicted and validated housing prices by using the LSTM technique - a type of Artificial Intelligence deep learning technology. LSTM is a network in which cell state and hidden state are recursively calculated in a structure which added cell state, which is conveyor belt role, to the existing RNN's hidden state. The real sale prices of apartments in autonomous districts ranging from January 2006 to December 2019 were collected through the Ministry of Land, Infrastructure, and Transport's real sale price open system and basic apartment and commercial district information were collected through the Public Data Portal and the Seoul Metropolitan City Data. The collected real sale price data were scaled based on monthly average sale price and a total of 168 data were organized by preprocessing respective data based on address. In order to predict prices, the LSTM implementation process was conducted by setting training period as 29 months (April 2015 to August 2017), validation period as 13 months (September 2017 to September 2018), and test period as 13 months (December 2018 to December 2019) according to time series data set. As a result of this study for predicting 'prices', there have been the following results. Firstly, this study obtained 76 percent of prediction similarity. We tried to design a prediction model of real estate transaction price with the LSTM Model based on AI and Bigdata. The final prediction model was created by collecting time series data, which identified the fact that 76 percent model can be made. This validated that predicting rate of return through the LSTM method can gain reliability.

• 한국방사선학회논문지
• /
• 제14권1호
• /
• pp.39-44
• /
• 2020

본 연구에서는 CNN과 빅데이터 기술을 이용한 Deep Learning을 통해 흉부 X-ray 영상 분류 및 정확성 연구에 대하여 알아보고자 한다. 총 5,873장의 흉부 X-ray 영상에서 Normal 1,583장, Pneumonia 4,289장을 사용하였다. 데이터 분류는 train(88.8%), validation(0.2%), test(11%)로 분류하였다. Convolution Layer, Max pooling layer pool size 2×2, Flatten layer, Image Data Generator로 구성하였다. Convolution layer가 3일 때와 4일 때 각각 filter 수, filter size, drop out, epoch, batch size, 손실함수 값을 설정하였다. test 데이터로 Convolution layer가 4일 때, filter 수 64-128-128-128, filter size 3×3, drop out 0.25, epoch 5, batch size 15, 손실함수 RMSprop으로 설정 시 정확도가 94.67%였다. 본 연구를 통해 높은 정확성으로 분류가 가능하였으며, 흉부 X-ray 영상뿐만 아니라 다른 의료영상에서도 많은 도움이 될 것으로 사료된다.

• 한국BIM학회 논문집
• /
• 제6권2호
• /
• pp.29-38
• /
• 2016

Road bridges are deteriorating gradually, and it is forecasted that the number of road bridges aging over 30 years will increase by more than 3 times of the current number. To maintain road bridges in a safe condition, current safety conditions of the bridges must be estimated for repair or reinforcement. However, budget and professional manpower required to perform in-depth inspections of road bridges are limited. This study proposes an estimation model for safety rating of road bridges by analyzing the data from Facility Management System (FMS) and Yearbook of Road Bridges and Tunnel. These data include basic specifications, year of completion, traffic, safety rating, and others. The distribution of safety rating was imbalanced, indicating 91% of road bridges have safety ratings of A or B. To improve classification performance, five safety ratings were integrated into two classes of G (good, A and B) and P (poor ratings under C). This rearrangement was set because facilities with ratings under C are required to be repaired or reinforced to recover their original functionality. 70% of the original data were used as training data, while the other 30% were used for validation. Data of class P in the training data were oversampled by 3 times, and Repeated Incremental Pruning to Produce Error Reduction (RIPPER) algorithm was used to develop the estimation model. The results of estimation model showed overall accuracy of 84.8%, true positive rate of 67.3%, and 29 classification rule. Year of completion was identified as the most critical factor on affecting lower safety ratings of bridges.

• 한국정보과학회논문지:시스템및이론
• /
• 제34권7호
• /
• pp.276-281
• /
• 2007

본 논문에서는 한국인의 대표질환 중 하나인 만성 간염에 대한 질환 감수성을 예측하기 위해서 Single Nucleotide Polymorphism 데이타와 대표적인 기계학습 기술인 Support Vector Machine을 이용하였다. 실험을 위한 데이타로 만성간염 환자 173명과 정상인 155명의 SNP 데이타를 사용하였으며, 평가를 위한 방법으로는 Leave-One-Out Cross Valication을 사용하였다. 실험결과 SNP 데이터만으로는 67.1%의 예측 결과를 얻었으며 기본적인 건강요소인 나이와 성별을 특징요소로 사용함으로서 74.9%의 예측 결과를 보였다. 향후 보다 많은 SNP 데이타와 건강관련정보 그리고 생활패턴에 대한 요소들을 특징요소로 감수성 예측에 함께 사용한다면, SVM은 만성 간염 예측을 위한 보다 효과적인 도구가 될 것이다.

• 터널과지하공간
• /
• 제16권2호
• /
• pp.135-145
• /
• 2006

본 연구에서는 조건부 모사 기법 중 순차 가우시안 시뮬레이션(SGS)과 순차 지시 시뮬레이션(SIS)을 이용하여 터널설계 시 미시추구간의 암반등급(RMR)을 예측하여 보았다. 총 30개의 시추공자료 가운데 25개의 시추공자료를 이용하여 순차 가우시안 시뮬레이션과 순차 지시 시뮬레이션을 수행하였으며, 나머지 5개의 시추공에서의 실제 암반등급과 예측 암반등급을 비교하여 보았다. 그 결과 조건부 모사 기법은 암반등급의 공간적 분포특성을 비교적 잘 예측할 수 있고, 예측의 불확실성을 정량적으로 평가할 수 있는 효과적인 방법임을 확인할 수 있었다. 따라서 조건부 모사 기법의 결과는 미시추구간의 암반등급을 예측하는데 있어서 유용한 정보를 제공 해 줄 수 있을 것으로 판단된다.

• International Journal of Automotive Technology
• /
• 제5권1호
• /
• pp.33-46
• /
• 2004

A finite element model development of a 50th percentile male cervical spine is presented in this paper. The model consists of rigid, geometrically accurate vertebrae held together with deformable intervertibral disks, facet joints, and ligaments modeled as a series of nonlinear springs. These deformable structures were rigorously tuned, through failure, to mimic existing experimental data; first as functional unit characterizations at three cervical levels and then as a fully assembled c-spine using the experimental data from Duke University and other data in the NHTSA database. After obtaining satisfactory validation of the performance of the assembled ligamentous cervical spine against available experimental data, 22 cervical muscle pairs, representing the majority of the neck's musculature, were added to the model. Hill's muscle model was utilized to generate muscle forces within the assembled cervical model. The muscle activation level was assumed to be the same for all modeled muscles and the degree of activation was set to correctly predict available human volunteer experimental data from NBDL. The validated model is intended for use as a post processor of dummy measurement within the simulated injury monitor (SIMon) concept being developed by NHTSA where measured kinematics and kinetic data obtained from a dummy during a crash test will serve as the boundary conditions to "drive" the finite element model of the neck. The post-processor will then interrogate the model to determine whether any ligament have exceeded its known failure limit. The model will allow a direct assessment of potential injury, its degree and location thus eliminating the need for global correlates such as Nij.

• 한국지구과학회지
• /
• 제44권2호
• /
• pp.105-118
• /
• 2023

본 연구에서는 2016년부터 2020년까지 내륙 관측소 중 안개 최다발 지역인 안동을 대상으로 XGBoost-DART 머신러닝 알고리즘을 이용하여 1 시간 후 안개 유무를 예측하였다. 기상자료, 농업관측자료, 추가 파생자료와 각 자료를 오버 샘플링한 확장자료, 총 6개의 데이터 세트를 사용하였다. 목측으로 획득한 기상현상번호와 시정계 관측으로 측정된 시정거리 자료를 각각 안개 유[1]무[0]로 이진 범주화하였다. 총 12개의 머신러닝 모델링 실험을 설계하였고, 안개가 사회와 지역사회에 미치는 유해성을 고려하여 모델의 성능은 재현율과 AUC-ROC를 중심으로 평가하였다. 전체적으로, 오버샘플링한 기상자료와 기상현상번호 기반의 예측 목표를 조합한 실험이 최고 성능을 보였다. 이 연구 결과는 머신러닝 알고리즘을 활용한 안개 예측에 있어서, 목측으로 획득한 기상현상번호의 중요성을 암시한다.