• 한국지반공학회논문집
• /
• 제39권4호
• /
• pp.5-17
• /
• 2023

도심지 지하굴착 공사가 대형화되면서 공사 중 안전사고에 대한 위험요인이 더욱 증가하고 있다. 이에 따라 공사현장의 위험요소를 모니터링하고 사전에 예측할 수 있는 기술이 필요하다. 굴착으로 인한 흙막이 벽체의 변형을 예측하는 방법에는 크게 경험식과 수치해석 두 가지 방법으로 분류할 수 있으며, 최근에는 인공지능 기술의 발달과 함께 머신러닝 기법을 활용한 예측 모델이 한 가지 방법으로 자리 잡고 있다. 본 연구에서는 예측력과 효율성이 우수한 부스팅 계열 알고리즘 및 앙상블 모델을 이용하여 시공 중 흙막이 벽체 변형을 예측하는 모델을 구축하였다. 지하흙막이 공사의 설계-시공-유지관리 과정에서 도출되는 자료들을 복합적으로 활용하여 데이터베이스를 구축하고, 이 자료를 토대로 학습모델을 만들고 성능을 평가하였다. 모델 성능 평가 결과, 높은 정확도로 흙막이 벽체 변형을 예측할 수 있었으며, 지반계측 자료를 학습에 활용함으로써 실제 시공과정의 특성이 반영된 예측결과를 제시할 수 있었다. 본 연구에서 구축한 예측 모델을 활용하여 시공 중 흙막이 벽체의 안정성 평가 및 모니터링에 활용할 수 있을 것으로 기대된다.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 2000년도 추계학술대회 및 정기총회
• /
• pp.33-36
• /
• 2000

관찰학습(OLA: Observational Learning Algorithm)은 앙상블 네트워크의 각 구성 모델들이 다른 모델들을 관찰함으로써 얻어진 가상 데이터와 초기에 bo otstrap된 실제 데이터를 학습에 함께 이용하는 방법이다. 본 논문에서는, 초기 학습 데이터 셋을 분할하고 분할된 각 데이터 셋에 대하여 앙상블의 구성 모델들을 전문화(specialize)시키는 방법을 적용하여 기존의 관찰학습 알고리즘을 개선시켰다. 제안된 알고리즘은 bagging 및 boosting과의 비교실험에 의하여, 보다 적은 수의 구성 모델로 동일 내지 보다 나은 성능을 나타냄이 실험적으로 검증되었다.

• 한국멀티미디어학회논문지
• /
• 제17권12호
• /
• pp.1383-1392
• /
• 2014

In this paper, we proposed a method to automatically determine the optimal radius through multi-scale LBP operation generalizing the size of radius variation and boosting learning in facial emotion recognition. When we looked at the distribution of features vectors, the most common was $LBP_{8.1}$ of 31% and sum of $LBP_{8.1}$ and $LBP_{8.2}$ was 57.5%, $LBP_{8.3}$, $LBP_{8.4}$, and $LBP_{8.5}$ were respectively 18.5%, 12.0%, and 12.0%. It was found that the patterns of relatively greater radius express characteristics of face well. In case of normal and anger, $LBP_{8.1}$ and $LBP_{8.2}$ were mainly distributed. The distribution of $LBP_{8.3}$ is greater than or equal to the that of $LBP_{8.1}$ in laugh and surprise. It was found that the radius greater than 1 or 2 was useful for a specific emotion recognition. The facial expression recognition rate of proposed multi-scale LBP method was 97.5%. This showed the superiority of proposed method and it was confirmed through various experiments.

• 전기학회논문지
• /
• 제65권3호
• /
• pp.504-510
• /
• 2016

In general, a fault locator is installed in Sub-Station of AT(Auto-transformer) feeding system to estimate the fault location and to protect the Korean AT feeding system. Since the line impedance characteristic is different to normal 3-phase transmission line, we need particular modification factors, which can be calculated using fault location recording data, to estimate the accurate fault location. Up to recently, forcible ground test has been used to calculate the modification factors of the fault locator. However, large amount of current is occurred when the forcible ground test is performed, and this current affects to adjacent equipments. Therefore, we proposed a novel calculation method of modification factors, arbitrary trip test, using boosting current of the operating electric train. Through several field test, we confirmed that modification factors for fault locator can be easily calculated by using proposed method. Moreover, we verified the accuracy and stability of the proposed calculation method.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2009년도 춘계학술대회
• /
• pp.403-406
• /
• 2009

본 논문은 ATM(Automated Teller Machine)에서 사용자의 얼굴을 검출하여 ATM의 사용 허가 여부를 판별하는 방법을 제안한다. 입력 영상에서 피부색 영역을 추출하여 얼굴 후보 영상을 만들고 AdaBoost(Adaptive Boosting) 알고리즘을 이용하여 얼굴을 검출한다. 검출된 얼굴에서 선글라스, 마스크 등의 액세서리 착용여부를 판단하기 위하여 template matching을 수행하며 그 결과를 이용하여 ATM의 사용 허가를 판별한다. 제안된 방법을 이용하여 실내 ATM 환경에서 액세서리 착용여부를 검출했을 때 만족할 만한 성능을 나타내는 것을 실험을 통하여 확인하였다.

• Geomechanics and Engineering
• /
• 제32권6호
• /
• pp.583-600
• /
• 2023

The resilient modulus (M_R) of various pavement materials plays a significant role in the pavement design by a mechanistic-empirical method. The M_R determination is done by experimental tests that need time and money, along with special experimental tools. The present paper suggested a novel hybridized extreme gradient boosting (XGB) structure for forecasting the M_R of modified base materials subject to wet-dry cycles. The models were created by various combinations of input variables called deep learning. Input variables consist of the number of W-D cycles (WDC), the ratio of free lime to SAF (CSAFR), the ratio of maximum dry density to the optimum moisture content (DMR), confining pressure (σ₃), and deviatoric stress (σ_d). Two XGB structures were produced for the estimation aims, where determinative variables were optimized by particle swarm optimization (PSO) and black widow optimization algorithm (BWOA). According to the results' description and outputs of Taylor diagram, M1 model with the combination of WDC, CSAFR, DMR, σ₃, and σ_d is recognized as the most suitable model, with R² and RMSE values of BWOA-XGB for model M1 equal to 0.9991 and 55.19 MPa, respectively. Interestingly, the lowest value of RMSE for literature was at 116.94 MPa, while this study could gain the extremely lower RMSE owned by BWOA-XGB model at 55.198 MPa. At last, the explanations indicate the BWO algorithm's capability in determining the optimal value of XGB determinative parameters in M_R prediction procedure.

• Computers and Concrete
• /
• 제33권1호
• /
• pp.77-90
• /
• 2024

Waste foundry sand (WFS) is the waste product that cause environmental hazards. WFS can be used as a partial replacement of cement or fine aggregates in concrete. A database comprising 234 compressive strength tests of concrete fabricated with WFS is used. To construct the machine learning-based prediction models, the water-to-cement ratio, WFS replacement percentage, WFS-to-cement content ratio, and fineness modulus of WFS were considered as the model's inputs, and the compressive strength of concrete is set as the model's output. A base extreme gradient boosting (XGBoost) model together with two hybrid XGBoost models mixed with the tunicate swarm algorithm (TSA) and the salp swarm algorithm (SSA) were applied. The role of TSA and SSA is to identify the optimum values of XGBoost hyperparameters to obtain the higher performance. The results of these hybrid techniques were compared with the results of the base XGBoost model in order to investigate and justify the implementation of optimisation algorithms. The results showed that the hybrid XGBoost models are faster and more accurate compared to the base XGBoost technique. The XGBoost-SSA model shows superior performance compared to previously published works in the literature, offering a reduced system error rate. Although the WFS-to-cement ratio is significant, the WFS replacement percentage has a smaller influence on the compressive strength of concrete. To improve the compressive strength of concrete fabricated with WFS, the simultaneous consideration of the water-to-cement ratio and fineness modulus of WFS is recommended.

• 조명전기설비학회논문지
• /
• 제27권1호
• /
• pp.53-60
• /
• 2013

In this paper, a control algorithm for active power filter (APF), which compensates for the harmonics and power factor, boosting the DC-link voltage is proposed. The proposed scheme employs a pulse-width-modulation (PWM) voltage-source inverter. A simple algorithm to detect the load current harmonics is also proposed. The APF and charging circuit are implemented in one inverter system. Finally, the validity of the proposed scheme is investigated with simulated and experimental results for a prototype APF system rated at 3kVA.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2009년도 정보 및 제어 심포지움 논문집
• /
• pp.31-33
• /
• 2009

Face detection using AdaBoost algorithm is capable of processing images rapidly while having high detection rates. It seemed to be the fastest and the most robust and it is still today. Many improvements or extensions of this method have been proposed. However, previous approaches only deal with upright faces. They suffer from limited discriminant capability for rotated faces as these methods apply the same features for both upright and rotated faces. To solve this problem, it is necessary that we rotate input images or make independently trained detectors. However, this can be slow and can require a lot of training data, since each classifier requires the computation of many different image features. This paper proposes a robust algorithm for finding rotated faces within an image. It reduces the computational and sample complexity, by finding common features that can be shared across the classes. And it will be able to apply with multi-class object detection.

• 한국IT서비스학회지
• /
• 제14권4호
• /
• pp.121-135
• /
• 2015

Ensemble classification is to utilize multiple classifiers instead of using a single classifier. Recently ensemble classifiers have attracted much attention in data mining community. Ensemble learning techniques has been proved to be very useful for improving the prediction accuracy. Bagging, boosting and random subspace are the most popular ensemble methods. In random subspace, each base classifier is trained on a randomly chosen feature subspace of the original feature space. The outputs of different base classifiers are aggregated together usually by a simple majority vote. In this study, we applied the random subspace method to the bankruptcy problem. Moreover, we proposed a method for optimizing the random subspace ensemble. The genetic algorithm was used to optimize classifier subset of random subspace ensemble for bankruptcy prediction. This paper applied the proposed genetic algorithm based random subspace ensemble model to the bankruptcy prediction problem using a real data set and compared it with other models. Experimental results showed the proposed model outperformed the other models.