• 대한임베디드공학회논문지
• /
• 제16권6호
• /
• pp.323-330
• /
• 2021

Visual object tracking is a challenging area of study in the field of computer vision due to many difficult problems, including a fast variation of target shape, occlusion, and arbitrary ground truth object designation. In this paper, we focus on the reinforced feature of the dynamic search area to get better performance than conventional discriminative model prediction trackers on the condition when the accuracy deteriorates since low feature discrimination. We propose a reinforced input feature method shown like the spotlight effect on the dynamic search area of the target tracking. This method can be used to improve performances for deep learning based discriminative model prediction tracker, also various types of trackers which are used to infer the center of the target based on the visual object tracking. The proposed method shows the improved tracking performance than the baseline trackers, achieving a relative gain of 38% quantitative improvement from 0.433 to 0.601 F-score at the visual object tracking evaluation.

• Structural Engineering and Mechanics
• /
• 제63권2호
• /
• pp.237-249
• /
• 2017

The Self-Organization Feature Map as an unsupervised network is very widely used these days in engineering science. The applied network in this paper is the Self Organization Feature Map with constant weights which includes Kohonen Network. In this research, Reinforced Concrete Shear Wall buildings with different stories and heights are analyzed and a database consisting of measured fundamental periods and characteristics of 78 RC SW buildings is created. The input parameters of these buildings include number of stories, height, length, width, whereas the output parameter is the fundamental period. In addition, using Genetic Algorithm, the structure of the Self-Organization Feature Map algorithm is optimized with respect to the numbers of layers, numbers of nodes in hidden layers, type of transfer function and learning. Evaluation of the SOFM model was performed by comparing the obtained values to the measured values and values calculated by expressions given in building codes. Results show that the Self-Organization Feature Map, which is optimized by using Genetic Algorithm, has a higher capacity, flexibility and accuracy in predicting the fundamental period.

• Earthquakes and Structures
• /
• 제27권3호
• /
• pp.177-189
• /
• 2024

Accurately predicting the failure modes of reinforced concrete (RC) columns is essential for structural design and assessment. In this study, the challenges of imbalanced datasets and complex feature selection in machine learning (ML) methods were addressed through an optimized ML approach. By combining feature selection and oversampling techniques, the prediction of seismic failure modes in rectangular RC columns was improved. Two feature selection methods were used to identify six input parameters. To tackle class imbalance, the Borderline-SMOTE1 algorithm was employed, enhancing the learning capabilities of the models for minority classes. Eight ML algorithms were trained and fine-tuned using k-fold shuffle split cross-validation and grid search. The results showed that the artificial neural network model achieved 96.77% accuracy, while k-nearest neighbor, support vector machine, and random forest models each achieved 95.16% accuracy. The balanced dataset led to significant improvements, particularly in predicting the flexure-shear failure mode, with accuracy increasing by 6%, recall by 8%, and F1 scores by 7%. The use of the Borderline-SMOTE1 algorithm significantly improved the recognition of samples at failure mode boundaries, enhancing the classification performance of models like k-nearest neighbor and decision tree, which are highly sensitive to data distribution and decision boundaries. This method effectively addressed class imbalance and selected relevant features without requiring complex simulations like traditional methods, proving applicable for discerning failure modes in various concrete members under seismic action.

• Smart Structures and Systems
• /
• 제32권4호
• /
• pp.207-218
• /
• 2023

Real-time monitoring of the behavior of reinforced soil retaining wall (RSW) is required for safety checks. In this study, a targetless displacement measurement technology (TDMT) consisting of an image registration module and a displacement calculation module was proposed to monitor the behavior of RSW, in which facing displacement and settlement typically occur. Laboratory and field experiments were conducted to compare the measuring performance of natural target (NT) with the performance of artificial target (AT). Feature count- and location-based performance metrics and displacement calculation performance were analyzed to determine their correlations. The results of laboratory and field experiments showed that the feature location-based performance metric was more relevant to the displacement calculation performance than the feature count-based performance metric. The mean relative errors of the TDMT were less than 1.69 % and 5.50 % for the laboratory and field experiments, respectively. The proposed TDMT can accurately monitor the behavior of RSW for real-time safety checks.

• 한국콘크리트학회:학술대회논문집
• /
• 한국콘크리트학회 1998년도 봄 학술발표회 논문집(I)
• /
• pp.321-326
• /
• 1998

Shear failure of reinforced concrete beams is serious problem due to sudden brittle failure and many experimental results proved that size effect in shear behavior is an important feature of reinforced concrete members. For this reason, the structural safety of the reinforced concrete beams for shear has been checked by applying empirical design formula, which includes the size-effect, derived from experimental data. However, as the sizes of reinforced concrete members become extremely large, experiments sometimes become very difficult so that the formula or the experimental data could not be obtained and size-effect analyses of shear behavior become significant. In this study, size-effect analysis of shear behavior in reinforced concrete beams is performed by modeling tension stiffening/shear stiffening on reinforced concrete and the tension softening/shear softening on plain concrete. Then, the influences of models in the size-effect analyses of shear behavior in reinforced concrete beams are analyzed.

• 한국안전학회지
• /
• 제16권1호
• /
• pp.88-93
• /
• 2001

본 연구에서는 복합소재인 GFRP(Glass Fiber Reinforced Polyester)의 2차원 절삭공정에서 절삭 메커니즘과 소재의 신뢰도 및 안전성과 밀접한 관련이 있는 표면정도를 중심으로 한 공정의 특성화를 시도하고, 주파수 분석에 관하여도 논의한다. 구체적으로는, 공정중 발생하는 절삭력 신호를 AR(Autoregressive) 모델링하여 해석에 사용한다. 특히, 특징추출과정을 통해 AR계수로 이루어진 패턴벡터 중 다양한 절삭 메카니즘에 민감한 계수만 선택할 수 있다. 이들 계수와 절삭 메커니즘과의 실험적 관계를 설정함으로써 섬유경사각(Fiber orientation angle), 절삭 변수 그리고 공구형상이 절삭 메커니즘에 미치는 영향을 평가하였다.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2001년도 가을 학술발표회 논문집
• /
• pp.323-328
• /
• 2001

In the ordinary reinforced earth wall, which was constructed by incremental construction method, the horizontal deformation of the facing due to the compaction induced horizontal earth pressure was unavoidable. Thus the KOESWall system which are adopted the isolated construction method was developed by I&S Eng. Co., Ltd. in 1999. Due to its systematical feature, KOESWall system is able to minimizes the horizontal deformation of reinforced wall effectively and it can be used as temporary structures more economically without the lacing block. In this report, it is shown that the concept and case histories of KOESWall system as a retaining structures.

• 대한토목학회논문집
• /
• 제43권4호
• /
• pp.511-523
• /
• 2023

철근콘크리트 손상 감지를 위한 무인항공기와 딥러닝 연계에 대한 연구가 활발히 진행 중이다. 컨볼루션 신경망은 객체 분류, 검출, 분할 모델의 백본으로 모델 성능에 높은 영향을 준다. 사전학습 컨볼루션 신경망인 모바일넷은 적은 연산량으로 충분한 정확도가 확보 될 수 있어 무인항공기 기반 실시간 손상 감지 백본으로 효율적이다. 바닐라 컨볼루션 신경망과 모바일넷을 분석 한 결과 모바일넷이 바닐라 컨볼루션 신경망의 15.9~22.9% 수준의 낮은 연산량으로도 6.0~9.0% 높은 검증 정확도를 가지는 것으로 평가되었다. 모바일넷V2, 모바일넷V3Large, 모바일넷 V3Small은 거의 동일한 최대 검증 정확도를 가지는 것으로 나타났으며 모바일넷의 철근콘트리트 손상 이미지 특성 추출 최적 조건은 옵티마이저 RMSprop, 드롭아웃 미적용, 평균풀링인 것으로 분석되었다. 본 연구에서 도출된 모바일넷V2 기반 7가지 손상 감지 최대 검증 정확도 75.49%는 이미지 축적과 지속적 학습으로 향상 될 수 있다.

• Steel and Composite Structures
• /
• 제17권6호
• /
• pp.777-790
• /
• 2014

The purpose of this study is to investigate the seismic performance of reinforced concrete (RC) frames strengthened by profiled steel sheet bracing which takes the influence of infill walls into consideration. One-bay, two-story, 1/3 scale two specimens shared same feature of dimensions, one specimen consists only beams and columns; the other one is reinforced by profiled steel sheet bracing with infill walls. Hysteretic curves, envelope curves, stiffness degradation curves and energy dissipation capacities are presented based on test data. Test results indicate that the ultimate load of strengthened specimen has been improved by 225%. The stiffness of reinforced by profiled steel sheet bracing has been increased by 108%. This demonstrates that infill walls and profiled steel sheet bracing enhanced the strength and stiffness distinctly. Energy dissipation has an obvious increase after 12 cycles. This shows that the reinforced specimen is able to bear the lateral load effectively and absorb lots of seismic energy.

• Coupled systems mechanics
• /
• 제3권1호
• /
• pp.111-145
• /
• 2014

In this paper we present a new model for computing the nonlinear response of reinforced concrete frame systems subjected to extreme thermomechanical loads. The first main feature of the model is its ability to account for both bending and shear failure of the reinforced concrete composites within frame-like model. The second prominent feature concerns the model capability to represent the total degradation of the material properties due to high temperature and the thermal deformations. Several numerical simulations are given to confirm these capabilities and illustrate a very satisfying model performance.