콘크리트 포장 내부 온도는 열응력 발생, 균열 거동, 구조 성능 및 유지관리 의사결정에 직접적인 영향을 미 치는 핵심 변수이다. 그러나 기존의 물리식 기반 예측 모델은 특정 지역과 제한된 기상 조건에서 보정된 계수 에 의존하는 경우가 많아, 지역 및 기후 조건이 달라질 경우 적용성과 확장성에 한계가 있다. 이에 본 연구는 한국 기상대 자료와 인천국제공항 유도로 콘크리트 포장의 실측 온도 데이터를 활용하여, 깊이별 내부 온도를 예측하는 CNN 기반 모형을 구축하고 공항 포장 유지관리 및 구조 평가에 활용 가능한 데이터 기반 예측 체계 를 제시하고자 하였다. 연구 데이터는 2017년 1월 1일부터 2018년 12월 31일까지의 1시간 단위 시계열로 구 성하였으며, 입력 변수로는 기온, 풍속, 강수량, 습도, 일조량, 일사량, 적설량, 적운량, 지면온도 등 기상 인자 를 사용하고, 출력 변수로는 포장 내부 0.05 m, 0.15 m, 0.25 m, 0.35 m, 0.45 m 깊이의 온도를 설정하였 다. 또한 한국도로연구프로그램(KPRP)의 열평형 방정식 기반 지식을 보조적으로 활용하여 데이터 기반 예측 결 과의 물리적 타당성을 검토하고 모형 고도화 방향을 함께 모색하였다. 제안된 CNN 모형은 다변량 시계열 입력 으로부터 시간대별 변동 패턴, 계절성 및 기상 인자 간 국부적 상관관계를 추출하도록 설계하였으며, 합성곱 연산을 통해 급격한 기온 변화, 강수·적설 이벤트, 주야간 반복 패턴 등 온도 변화 특성을 안정적으로 학습할 수 있도록 하였다. 특히 깊이별 온도를 동시에 예측하는 다중출력 구조를 적용하여 표면과 내부층 간 연계 거 동을 반영하고자 하였다. 아울러 ANN 기반 접근과 비교 가능한 평가 체계를 마련하여 예측 정확도뿐 아니라 일반화 성능 및 계절별·시간대별 재현성을 검토함으로써, 콘크리트 포장 깊이별 온도 예측에서 CNN의 적용 타 당성과 실무 활용 가능성을 평가하고 향후 공항 포장 관리 시스템과 연계 가능한 예측 기반 기술로 확장하기 위한 기초자료를 제공하고자 한다.

Rapid post-earthquake retrofit decisions require reliable estimates of interstory drift ratio. Conventional field practices either depend on instrumented measurements constrained by sparse sensor coverage or rely on qualitative expert judgment. This study aims to develop a CNN-based interstory drift ratio prediction method for reinforced concrete columns using strain-derived damage images. Reinforced concrete columns are modeled and analyzed in OpenSees to obtain strains and displacements. Strain fields are converted into strain-derived damage images through threshold-based staging that encodes discrete damage states. Structural parameters are concatenated to the damage image by adding fixed-value columns so the network can read structural context in a single two-dimensional input. We design systematic comparisons to isolate the benefit of structural information and section coverage. First, models without structural parameters are trained. Second, single-parameter variants are trained where only one attribute is provided. Third, full-parameter models include all attributes. For each setting, both single-section and multi-section inputs are evaluated. Samples are split by case and then divided 80/20 into training and validation sets. Model performance is reported using RMSE, MAE, and R-squared. The proposed approach achieves accurate inter-story drift ratio prediction overall, with improved performance when all structural parameters and multi-section inputs are used.

Passive acoustic monitoring (PAM) has emerged as an effective tool for studying underwater soundscapes and monitoring marine organisms. In this study, the biological sounds of three fish species that mainly inhabit or occur in the Korean coastal oceans, brown croaker (Miichthys miiuy), Pacific cod (Gadus macrocephalus), and small yellow croaker (Larimichthys polyactis) were recorded using the PAM method. The possibility of automatic classification was evaluated using a deep learning-based convolutional neural network (CNN) model based on the measured data. The biological fish sounds were recorded using hydrophones in the sea cage environments. The three fish species data were converted into spectrogram images and used as input for training and evaluating the CNN model. Gaussian noise was added to the test data to simulate low signal-to-noise ratio (SNR) environments. The model achieved high classification performance, with F1-score of about 96% on raw data and about 77% accuracy under signal-to-noise ratio conditions. These results suggest that CNN-based models be adequate for fish sound classification, even in acoustically complex underwater environments. Applying CNN models to classify and detect fish sounds can improve the automation and efficiency of PAM-based acoustic analysis, thereby improving the monitoring of fish populations, resource assessment, and ecological management in the future.

Anomaly detection technique for the Unmanned Aerial Vehicles (UAVs) is one of the important techniques for ensuring airframe stability. There have been many researches on anomaly detection techniques using deep learning. However, most of research on the anomaly detection techniques are not consider the limited computational processing power and available energy of UAVs. Deep learning model convert to the model compression has significant advantages in terms of computational and energy efficiency for machine learning and deep learning. Therefore, this paper suggests a real-time anomaly detection model for the UAVs, achieved through model compression. The suggested anomaly detection model has three main layers which are a convolutional neural network (CNN) layer, a long short-term memory model (LSTM) layer, and an autoencoder (AE) layer. The suggested anomaly detection model undergoes model compression to increase computational efficiency. The model compression has same level of accuracy to that of the original model while reducing computational processing time of the UAVs. The proposed model can increase the stability of UAVs from a software perspective and is expected to contribute to improving UAVs efficiency through increased available computational capacity from a hardware perspective.

The casting manufacturing process of aluminum automotive wheels often involves processing various wheel models during stages such as flow forming, machining, packaging, and delivery. Traditionally, separate equipment or production lines were required for each model, which led to higher facility investment costs and increased labor costs for classification. However, the implementation of machine learning-based model classification technology has made it possible to automatically and accurately distinguish between different wheel models, resulting in significant cost savings and enhanced production efficiency. Additionally, this approach helps prevent product mix-ups during the final inspection process and allows for the quick and precise identification of wheel models during packaging and delivery, reducing shipping errors and improving customer satisfaction. Despite these benefits, the high cost of machine learning equipment presents a challenge for small and medium-sized enterprises(SMEs) to adopt such technologies. Therefore, this paper analyzes the characteristics of existing machine learning architectures applicable to the automotive wheel manufacturing process and proposes a custom CNN(Convolutional Neural Network) that can be used efficiently and cost-effectively.

This study aimed to investigate the difference that convolutional neural network(CNN) shows in the determining osteoporosis on panoramic radiograph by performing a paired test by inputting the original image and the limited image including the cortical bone of the posterior border of the mandible used by radiologists. On panoramic radiographs of a total of 661 subjects (mean age 66.3 years ± 11.42), the area including the cortical bone of the posterior part of the mandible was divided into the left and right sides, and the ROI was set, and the remaining area was masked in black to form the limited image. For training of VGG-16, panoramic radiographs of 243 osteoporosis subjects (mean age 72.67 years ± 7.97) and 222 normal subjects (mean age 53.21 years ± 2.46) were used, and testing 1 and testing 2 were performed on the original and limited images, respectively, using panoramic radiographs of 51 osteoporosis subjects (mean age 72.78 years ± 8.3) and 47 normal subjects (mean age 53.32 years ± 2.81). The accuracy of VGG-16 for determining osteoporosis was 97%, in the testing 1 and 100% in the testing 2. When determining osteoporosis on the original image, CNN showed sensitivity in a wide range of areas including not only the inferior cortical bone of the mandible but also the maxillary and mandibular cancellous bone, cervical spine, and zygomatic bone. When the same ROI including the lower inferior cortical border of the mandible of the osteoporosis group was applied and the sensitive region was compared between the original image and the limited image, the original image showed wider sensitive region in cancellous bone and cortical bone than on the limited image (p<.05). Since osteoporosis is a disease that affects throughout the skeletal system, this finding seems very valid.

본 연구는 추가적인 장비 없이 UAV만을 사용한 균열폭 측정 및 균열의 3차원 재구성 방법을 제안한다. UAV 사진측량법 및 CNN을이용한 균열의 3차원 재구성 및 균열폭 측정 검증을 위해 5곳의 균열이 존재하는 벽면을 대상으로 균열의 3차원 재구성을 하였 으며 UAV와 균열 사이의 거리 4가지에 대해 균열폭을 측정하고 균열 현미경 측정값과 비교하여 정확성을 검증하였다. 대부분의 균열 에서 균열폭을 정확히 측정하였으나 균열폭이 0.5mm보다 작은 경우와 벽면이 심하게 그늘져 어두운 곳에서는 측정 유효성이 떨어지 는 결과를 보였다.

미세구조 특성의 불확실성은 재료 특성에 많은 영향을 준다. 시멘트 기반 재료의 공극 분포 특성은 재료의 역학적 특성에 큰 영향을 미치며, 재료에 랜덤하게 분포되어 있는 많은 공극은 재료의 물성 예측을 어렵게 한다. 공극의 특성 분석과 재료 응답 간의 상관관계 규명에 대한 기존 연구는 통계적 관계 분석에 국한되어 있으며, 그 상관관계가 아직 명확히 규명되어 있지 않다. 본 연구에서는 합성곱 신경망(CNN, convolutional neural network)을 활용한 이미지 기반 데이터 접근법을 통해 시멘트 기반 재료의 역학적 응답을 예측하 고, 공극분포와 재료 응답의 상관관계를 분석하였다. 머신러닝을 위한 데이터는 고해상도 마이크로-CT 이미지와 시멘트 기반 재료의 물성(인장강도)로 구성하였다. 재료의 메시 구조 특성을 분석하였으며, 재료의 응답은 상장균열모델(phase-field fracture model)에 기 반을 둔 2D 직접 인장(direct tension) 유한요소해석 시뮬레이션을 활용하여 평가하였다. 입력 이미지 영역의 기여도를 분석하여 시편 에서 재료 응답 예측에 가장 큰 영향을 미치는 영역을 CNN을 통하여 식별하였다. CNN 과정 중 활성 영역과 공극분포를 비교 분석하 여 공극분포특성과 재료 응답의 상관관계를 분석하여 제시하였다.

Determining the size or area of a plant's leaves is an important factor in predicting plant growth and improving the productivity of indoor farms. In this study, we developed a convolutional neural network (CNN)-based model to accurately predict the length and width of lettuce leaves using photographs of the leaves. A callback function was applied to overcome data limitations and overfitting problems, and K-fold cross-validation was used to improve the generalization ability of the model. In addition, ImageDataGenerator function was used to increase the diversity of training data through data augmentation. To compare model performance, we evaluated pre-trained models such as VGG16, Resnet152, and NASNetMobile. As a result, NASNetMobile showed the highest performance, especially in width prediction, with an R_squared value of 0.9436, and RMSE of 0.5659. In length prediction, the R_squared value was 0.9537, and RMSE of 0.8713. The optimized model adopted the NASNetMobile architecture, the RMSprop optimization tool, the MSE loss functions, and the ELU activation functions. The training time of the model averaged 73 minutes per Epoch, and it took the model an average of 0.29 seconds to process a single lettuce leaf photo. In this study, we developed a CNN-based model to predict the leaf length and leaf width of plants in indoor farms, which is expected to enable rapid and accurate assessment of plant growth status by simply taking images. It is also expected to contribute to increasing the productivity and resource efficiency of farms by taking appropriate agricultural measures such as adjusting nutrient solution in real time.

Synthetic Aperture Radar (SAR) images are affected by noise called speckle, which is very severe and may hinder image exploitation. Despeckling is an important task that aims to remove such noise so as to improve the accuracy of all downstream image processing tasks. Many different schemes have been proposed for the restoration of SAR images. Among the different possible approaches, methods based on convolutional neural networks(CNNs) have recently shown to reach state-of-the-art performance for SAR image restoration. DnCNN(DeNoising Convolutional Neural Network) is one of the most widely used neural network architecture embedded in baseline SAR image despeckling methods. In military applications of SAR satellite image, fast processing is the most critical factor except the precision rate of the recognition. In this paper, we propose an improved DnCNN architecture for faster SAR image despeckling. The experimental results on real-world SAR images show that our proposed method takes faster processing time than the original DnCNN architecture without despeckling performance downgrade. Subjective visual inspection demonstrates that the proposed method has great potential in preserving the image signal details and suppressing speckle noise.