Deep learning-based computer vision anomaly detection algorithms are widely utilized in various fields. Especially in the manufacturing industry, the difficulty in collecting abnormal data compared to normal data, and the challenge of defining all potential abnormalities in advance, have led to an increasing demand for unsupervised learning methods that rely on normal data. In this study, we conducted a comparative analysis of deep learning-based unsupervised learning algorithms that define and detect abnormalities that can occur when transparent contact lenses are immersed in liquid solution. We validated and applied the unsupervised learning algorithms used in this study to the existing anomaly detection benchmark dataset, MvTecAD. The existing anomaly detection benchmark dataset primarily consists of solid objects, whereas in our study, we compared unsupervised learning-based algorithms in experiments judging the shape and presence of lenses submerged in liquid. Among the algorithms analyzed, EfficientAD showed an AUROC and F1-score of 0.97 in image-level tests. However, the F1-score decreased to 0.18 in pixel-level tests, making it challenging to determine the locations where abnormalities occurred. Despite this, EfficientAD demonstrated excellent performance in image-level tests classifying normal and abnormal instances, suggesting that with the collection and training of large-scale data in real industrial settings, it is expected to exhibit even better performance.

In this study, we estimated the distribution density of giant jellyfish in coastal waters of Korea in 2023 and compared the occurrence of giant jellyfish over four years. In May, the giant jellyfish were mainly distributed in the waters of the Yangtze River outflow, and in July, they were highly distributed in the west of Jeju Island and near the south coast of Korea. In addition, when comparing the distribution densities of giant jellyfish in Korea over four years, both acoustic and sighting surveys showed that the highest density of jellyfish occurred in 2021.

Recently, there has been an increasing attempt to replace defect detection inspections in the manufacturing industry using deep learning techniques. However, obtaining substantial high-quality labeled data to enhance the performance of deep learning models entails economic and temporal constraints. As a solution for this problem, semi-supervised learning, using a limited amount of labeled data, has been gaining traction. This study assesses the effectiveness of semi-supervised learning in the defect detection process of manufacturing using the MixMatch algorithm. The MixMatch algorithm incorporates three dominant paradigms in the semi-supervised field: Consistency regularization, Entropy minimization, and Generic regularization. The performance of semi-supervised learning based on the MixMatch algorithm was compared with that of supervised learning using defect image data from the metal casting process. For the experiments, the ratio of labeled data was adjusted to 5%, 10%, 25%, and 50% of the total data. At a labeled data ratio of 5%, semi-supervised learning achieved a classification accuracy of 90.19%, outperforming supervised learning by approximately 22%p. At a 10% ratio, it surpassed supervised learning by around 8%p, achieving a 92.89% accuracy. These results demonstrate that semi-supervised learning can achieve significant outcomes even with a very limited amount of labeled data, suggesting its invaluable application in real-world research and industrial settings where labeled data is limited.

Smart factory companies are installing various sensors in production facilities and collecting field data. However, there are relatively few companies that actively utilize collected data, academic research using field data is actively underway. This study seeks to develop a model that detects anomalies in the process by analyzing spindle power data from a company that processes shafts used in automobile throttle valves. Since the data collected during machining processing is time series data, the model was developed through unsupervised learning by applying the Holt Winters technique and various deep learning algorithms such as RNN, LSTM, GRU, BiRNN, BiLSTM, and BiGRU. To evaluate each model, the difference between predicted and actual values was compared using MSE and RMSE. The BiLSTM model showed the optimal results based on RMSE. In order to diagnose abnormalities in the developed model, the critical point was set using statistical techniques in consultation with experts in the field and verified. By collecting and preprocessing real-world data and developing a model, this study serves as a case study of utilizing time-series data in small and medium-sized enterprises.

본 연구는 네트워크 이상 감지 및 예측을 위해 벡터 자기회귀(VAR) 모델의 사용을 비교 분석한다. VAR 모 델에 대한 간략한 개요를 제공하고 네트워크 이상 체크로 사용 가능한 두 가지 버전을 검토하며 두 종류의 VAR 모델을 통한 경험적인 평가를 제시한다. VAR-Filtered moving-common-AR 모델이 단일 노드 이상 감지 성능에서 우수하며, VAR-Adaptive Learning 버전은 몇 개의 노드 간 이상을 효과적으로 식별하는 데 특히 효 과적이며 두 가지 주요VAR 모델의 전반적인 성능 차이에 대한 근본적인 이유도 분석한다. 각 기술의 장단점 을 개요로 제공하고 성능 향상을 위한 제안도 제시하고자 한다.

장대교량은 낮은 고유진동수와 감쇠비를 가지는 초유연구조물로 진동사용성 문제에 취약하다. 하지만 현재 국내 설계지침에서는 풍속이나 진폭에 대한 임계값을 기반으로 유해진동 발생 여부를 평가하고 있다. 본 연구에서는 장대교량에서 발생하는 유해진동을 보다 정교하게 식별하기 위하여 딥러닝 기반 신호분할 모델을 활용한 데이터 포인트 단위의 와류진동 식별 방법론을 제안한다. 특별 히 포락선을 가지는 사인파를 활용하여 와류진동에 해당하는 데이터를 합성함으로써 모델 구축에 필수적인 와류진동 데이터 획득 및 라벨링 과정을 대체하였다. 이후 푸리에 싱크로스퀴즈드 변환를 적용하여 시간-주파수 특징을 추출하여 신경망의 인풋 데이터로 사 용하였다. 합성데이터만을 이용하여 양방향 장단기 기억신경망(Bidirectional Long-Short-Term-Memory) 모델을 훈련하였고 이를 라 벨 정보를 포함한 실제 사장교의 계측데이터를 이용하여 학습한 모델과 비교하여 모델의 실시간 와류진동 식별 성능을 검증하였다.

빠르게 변화하는 연안지형과 연안침식의 동적변화 현상을 이해하기 위해서는 시·공간의 연속성이 포함된 짧은 주기 그리고 지 속적인 모니터링이 필요하다. 최근 영상 모니터링 분석기술 발전과 함께 원격감지를 활용한 연안 모니터링 연구가 다수 이루어지고 있다. 원격 감지는 일반적으로 항공기나 위성으로부터 거리를 두고 측정된 영상을 활용하여 객체나 지역에 관한 정보를 추출하는 기술로 연안 지형변화를 빠르고 정확하게 분석할 수 있는 장점이 있어 그 활용도가 점차 증가하는 추세이다. 원격 위성영상 기반 해안선 탐지는 위성 영상으로부터 측정가능한 해안선 정의, 해안선 탐지기술 적용을 통한 해안선 추출로 수행된다. 기존 문헌에서 조사된 다양한 자료로부터 위성 영상기반 해안선 정의, 원격 위성영상 현황, 기존 연구동향, 위성영상 기반 해안선 탐지 기술연구 동향을 분석하였으며, 분석 결과로 부터 최신 연구동향, 이상적인 해안선 추출 및 고도화된 디지털 모니터링과의 연계를 위한 실용적 기법을 검토을 위한 연구를 제언한다. 향후 한반도 전역의 변화 경향과 침식정도의 파악을 위해서는 국지적 모니터링에서 벗어나, 광역 위성 영상 등 디지털 모니터링을 활용 한 능동적인 모니터링 체계를 구축할 필요가 있으며 해안선 탐지 분야는 지속적인 연구와 분석 기술의 발전이 가속화 될 것으로 판단된 다.

On pig farms, the highest mortality rate is observed among nursing piglets. To reduce this mortality rate, farmers need to carefully observe the piglets to prevent accidents such as being crushed and to maintain a proper body temperature. However, observing a large number of pigs individually can be challenging for farmers. Therefore, our aim was to detect the behavior of piglets and sows in real-time using deep learning models, such as YOLOv4-CSP and YOLOv7-E6E, that allow for real-time object detection. YOLOv4-CSP reduces computational cost by partitioning feature maps and utilizing Cross-stage Hierarchy to remove redundant gradient calculation. YOLOv7-E6E analyzes and controls gradient paths such that the weights of each layer learn diverse features. We detected standing, sitting, and lying behaviors in sows and lactating and starving behaviors in piglets, which indicate nursing behavior and movement to colder areas away from the group. We optimized the model parameters for the best object detection and improved reliability by acquiring data through experts. We conducted object detection for the five different behaviors. The YOLOv4-CSP model achieved an accuracy of 0.63 and mAP of 0.662, whereas the YOLOv7-E6E model showed an accuracy of 0.65 and mAP of 0.637. Therefore, based on mAP, which includes both class and localization performance, YOLOv4-CSP showed the superior performance. Such research is anticipated to be effectively utilized for the behavioral analysis of fattening pigs and in preventing piglet crushing in the future.

Fishing gear used in coastal fishing should be equipped with fishing buoys, indicating their locations, thus enabling their constant monitoring and detection by other ships to avoid collision. However, common fishing buoys fabricated using Styrofoam, bamboo, or PVC have short detection ranges owing to their weak radar radio wave reflection. Although research on improving the performance of radar equipment is in progress, studies on early detection of fishing gear to reduce collisions with ships sailing nearby are limited. In this study, we conducted experiments to determine methods to prevent collisions between ships and fishing gear by improving both the fishing buoy material and installation method for the reflector to increase the radar detection range of the fishing buoys.