• Smart Structures and Systems
• /
• 제29권3호
• /
• pp.513-522
• /
• 2022

Due to the importance of accurate analysis of bearing capacity in civil engineering projects, this paper studies the efficiency of two novel metaheuristic-based models for this objective. To this end, black hole algorithm (BHA) and multi-verse optimizer (MVO) are synthesized with an artificial neural network (ANN) to build the proposed hybrid models. Based on the settlement of a two-layered soil (and a shallow footing) system, the stability values (SV) of 0 and 1 (indicating the stability and failure, respectively) are set as the targets. Each model predicted the SV for 901 stages. The results indicated that the BHA and MVO can increase the accuracy (i.e., the area under the receiving operating characteristic curve) of the ANN from 94.0% to 96.3 and 97.2% in analyzing the SV pattern. Moreover, the prediction accuracy rose from 93.1% to 94.4 and 95.0%. Also, a comparison between the ANN's error decreased by the BHA and MVO (7.92% vs. 18.08% in the training phase and 6.28% vs. 13.62% in the testing phase) showed that the MVO is a more efficient optimizer. Hence, the suggested MVO-ANN can be used as a reliable approach for the practical estimation of bearing capacity.

• 한국멀티미디어학회논문지
• /
• 제21권12호
• /
• pp.1439-1447
• /
• 2018

Palm image acquisition without contact has advantages in user convenience and hygienic issues, but such images generally display more image variations than those acquired employing a contact plate or pegs. Therefore, it is necessary to develop a palmprint identification method which is robust to affine variations. This study proposes a deep learning approach which can effectively identify contactless palmprints. In general, it is very difficult to collect enough volume of palmprint images for training a deep convolutional neural network(DCNN). So we adopted an approach to use a pretrained DCNN. We designed two new DCNNs based on the VGGNet. One combines the VGGNet with SVM. The other add a shallow network on the middle-level of the VGGNet. The experimental results with two public palmprint databases show that the proposed method performs well not only contact-based palmprints but also contactless palmprints.

• 한국융합학회논문지
• /
• 제9권5호
• /
• pp.1-6
• /
• 2018

스마트그리드에서 정확한 단기 부하 예측을 통한 자원의 이용 계획은 에너지 시스템 운영의 불확실성을 줄이고 운영 효율을 높이는데 있어서 매우 중요하다. 단기 부하 예측에 얕은 신경회로망을 포함한 다수의 머신 러닝 기법이 적용되어왔지만 예측 정확도의 개선이 요구되고 있다. 최근에는 컴퓨터 비전이나 음성인식 분야에서 심층 신경회로망의 뛰어난 연구 결과로 인해 심층 신경회로망을 단기 전력수요 예측에 적용해 예측 정확도를 개선하려는 시도가 주목 받고 있다. 본 논문에서는 일별 전력 부하 첨두치를 예측하기 위한 다층신경회로망 구조의 심층 신경회로망 모델을 제안한다. 제안된 심층 신경회로망은 층별 학습이 선행된 후 전체 모델의 학습이 이루어진다. 한국전력거래소에서 얻은 4년 동안의 일별 전력 수요 데이터를 사용, 하루 및 이틀 앞선 전력수요 첨두치를 예측하는 심층 신경회로망 모델을 구축하고 예측 정확도를 비교, 평가한다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2019년도 춘계학술발표대회
• /
• pp.398-400
• /
• 2019

Faced with the increasing demand for image recognition on mobile devices, how to run convolutional neural network (CNN) models on mobile devices with limited computing power and limited storage resources encourages people to study efficient model design. In recent years, many effective architectures have been proposed, such as mobilenet_v1, mobilenet_v2 and PeleeNet. However, in the process of feature selection, all these models neglect some information of shallow features, which reduces the capture of shallow feature location and semantics. In this study, we propose an effective framework based on Feature Pyramid Networks to improve the recognition accuracy of deep and shallow images while guaranteeing the recognition speed of PeleeNet structured images. Compared with PeleeNet, the accuracy of structure recognition on CIFA-10 data set increased by 4.0%.

• 한국정보통신학회논문지
• /
• 제23권3호
• /
• pp.237-246
• /
• 2019

추천 시스템의 등급 예측 정확도를 높이기 위해서는, 사용자 항목 등급 데이터뿐만 아니라 주석, 태그 또는 설명과 같은 항목의 보조 정보도 고려해야만 한다. 기존 접근법에서는 단어 단위에서 bag-of-words 모델을 사용하여 보조 정보를 모델링한다. 그러나 이러한 모델은 보조 정보를 효과적으로 활용할 수 없으므로 보조 정보를 제한적으로 이해하게 된다. 한편, 컨볼루션 신경망(CNN)에서는 보조 정보로부터 특징 벡터를 효과적으로 포착하고 추출할 수 있다. 따라서 본 논문에서는 새로운 추천 모델을 위해 딥 CNN을 행렬 분해에 통합시킨 문자 수준의 딥 컨볼루션 신경망 기반 행렬 분해 (Char-DCNN-MF) 방법을 제안한다. Char-DCNN-MF에서는 보조 정보를 더 심층적으로 이해하고 추천 성능을 더욱 향상시킬 수 있다. 실험은 세 가지 다른 실제 데이터 세트에서 수행되었으며 그 결과는 Char-DCNN-MF가 다른 비교 모델보다 유의적으로 뛰어난 성능을 보여주었다.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2019년도 하계학술대회
• /
• pp.102-105
• /
• 2019

In the classical single-image super-resolution (SISR) reconstruction method using convolutional neural networks, the extracted features are not fully utilized, and the training time is too long. Aiming at the above problems, we proposed an improved SISR method based on a residual network. Our proposed method uses a feature fusion technology based on improved residual blocks. The advantage of this method is the ability to fully and effectively utilize the features extracted from the shallow layers. In addition, we can see that the feature fusion can adaptively preserve the information from current and previous residual blocks and stabilize the training for deeper network. And we use the global residual learning to make network training easier. The experimental results show that the proposed method gets better performance than classic reconstruction methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권12호
• /
• pp.3991-4007
• /
• 2022

In the public healthcare, a computational system that can automatically and efficiently detect and classify falls from a video sequence has significant potential. With the advancement of deep learning, which can extract temporal and spatial information, has become more widespread. However, traditional 3D CNNs that usually adopt shallow networks cannot obtain higher recognition accuracy than deeper networks. Additionally, some experiences of neural network show that the problem of gradient explosions occurs with increasing the network layers. As a result, an enhanced three-dimensional ResNet-based method for fall detection (3D-ERes-FD) is proposed to directly extract spatio-temporal features to address these issues. In our method, a 50-layer 3D residual network is used to deepen the network for improving fall recognition accuracy. Furthermore, enhanced residual units with four convolutional layers are developed to efficiently reduce the number of parameters and increase the depth of the network. According to the experimental results, the proposed method outperformed several state-of-the-art methods.

• Wind and Structures
• /
• 제9권1호
• /
• pp.37-58
• /
• 2006

The paper describes a study about effects of upstream hills on design wind loads using two mathematical approaches: Computational Fluid Dynamics (CFD) and Artificial Neural Network (NN for short). For this purpose CFD and NN tools have been developed using an object-oriented approach and C++ programming language. The CFD tool consists of solving the Reynolds time-averaged Navier-Stokes equations and $k-{\varepsilon}$ turbulence model using body-fitted nearly-orthogonal coordinate system. Subsequently, design wind load parameters such as speed-up ratio values have been generated for a wide spectrum of two-dimensional hill geometries that includes isolated and multiple steep and shallow hills. Ground roughness effect has also been considered. Such CFD solutions, however, normally require among other things ample computational time, background knowledge and high-capacity hardware. To assist the enduser, an easier, faster and more inexpensive NN model trained with the CFD-generated data is proposed in this paper. Prior to using the CFD data for training purposes, extensive validation work has been carried out by comparing with boundary layer wind tunnel (BLWT) data. The CFD trained NN (CFD-NN) has produced speed-up ratio values for cases such as multiple hills that are not covered by wind design standards such as the Commentaries of the National Building Code of Canada (1995). The CFD-NN results compare well with BLWT data available in literature and the proposed approach requires fewer resources compared to running BLWT experiments.

• Geomechanics and Engineering
• /
• 제37권6호
• /
• pp.629-641
• /
• 2024

The presence of excavations or cavities beneath the foundations of a building can have a significant impact on their stability and cause extensive damage. Traditional methods for calculating the bearing capacity and subsidence of foundations over cavities can be complex and time-consuming, particularly when dealing with conditions that vary. In such situations, machine learning (ML) and deep learning (DL) techniques provide effective alternatives. This study concentrates on constructing a prediction model based on the performance of ML and DL algorithms that can be applied in real-world settings. The efficacy of eight algorithms, including Regression Analysis, k-Nearest Neighbor, Decision Tree, Random Forest, Multivariate Regression Spline, Artificial Neural Network, and Deep Neural Network, was evaluated. Using a Python-assisted automation technique integrated with the PLAXIS 2D platform, a dataset containing 272 cases with eight input parameters and one target variable was generated. In general, the DL model performed better than the ML models, and all models, except the regression models, attained outstanding results with an R² greater than 0.90. These models can also be used as surrogate models in reliability analysis to evaluate failure risks and probabilities.

• 한국지반신소재학회논문집
• /
• 제22권2호
• /
• pp.1-12
• /
• 2023

국내외적으로 다양한 산사태 발생원인 분석과 취약지역의 예측이 이루어지고 있다. 본 연구에서는 산사태에서 발생하는 재해의 분석 및 예측에 사용되는 많은 특성 중 필수적인 요소인 유효토심을 지형정보를 이용해 예측했다. 지형정보 데이터를 각 기관별로 획득한 후 100m × 100m의 격자에 속성정보로 할당하고 데이터 등급화를 통해 차원을 축소 시켜주었다. 분류기준으로 3개 깊이(얕음, 보통, 깊음)와 5개 깊이(매우 얕음, 얕음, 보통, 깊음, 아주 깊음)의 두 가지 경우에 대해 유효토심을 예측했다. K-최근접 이웃, 랜덤 포레스트, 심층인공신경망 모델을 통해 예측하고 정확도, 정밀도, 재현율, F1-점수를 계산해 그 성능을 비교했다. 예측결과 모델에 따라 50% 후반에서 70% 초반의 성능을 보였다. 3개 분류기준의 정확도가 5개 분류기준의 정확도보다 5% 정도 높았다. 본 연구에서 제시한 등급화 기준과 분류모델의 성능은 아직 미흡하지만 유효토심의 예측에 있어서 분류모델의 적용이 가능하다고 판단된다. 큰 지역을 획일적으로 가정하여 사용하는 현재의 유효토심보다 신뢰성 있는 값의 예측이 가능하다고 사료된다.