본 연구는 선박용 공기압축기의 상태기반보전 시스템에 필요한 이상치 탐지 알고리즘 적용에 대한 실험적 연구로서 고장모사 실험을 통해 시계열 전류 센서 데이터를 이용한 이상탐지 적용 가능성을 확인하였다. 고장 유형 10개에 대해 실험실 규모의 고장 모사 실험을 수행하여 정상 운전데이터와 고장 데이터를 구축하였다. 실험 결과 구축된 이상탐지 모델은 시계열 데이터의 주기에 변화를 유발하는 이상은 잘 탐지하는 반면 미세한 부하 변동에 대한 탐지 성능은 떨어졌다. 또한 오토인코더를 이용한 시계열 이상탐지 모델은 입력 시 퀀스의 길이와 초모수 조정에 따라 이상 탐지 성능이 상이한 것으로 나타났다.

This study explores the application aspect of The detailed rules of Census (1896) through the change of Kan numbers in Gyeonpyeong-bang. Although Gyeonpyeong-bang was a high-priority area because of its location, it was difficult to trace the operation of the urban situation due to lack of data. This study is focusing on restoring space and society in the Gyeonpyeong-bang using the information on the type of houses and the number of Kan listed in the family register of Hanseong-bu. The detailed rules of Census sets out provisions for the family registry and the rules of making Tong. Especially when it comes to the rules of making Tong, this rule deals with the code of making ten Hos into one Tong. This study was conducted by dividing the status of the Tong into three types: uncompleted Tong, exceeded Tong without vacant Ho number, and exceeded Tong with the vacant Ho number. Since these three types of Tong are in the process of change towards the complete Tong with 10 Hos, they were thought to be able to demonstrate the specific application of the rules. This study will be meaningful as a case study that expands the point of existing research on the Tong making rules, which was not focused relatively on restoring urban conditions at that time, by looking at the changes in exceptions that deviated from the Sipgajaktong rule.

Facial feature extraction and tracking are essential steps in human-robot-interaction (HRI) field such as face recognition, gaze estimation, and emotion recognition. Active shape model (ASM) is one of the successful generative models that extract the facial features. However, applying only ASM is not adequate for modeling a face in actual applications, because positions of facial features are unstably extracted due to limitation of the number of iterations in the ASM fitting algorithm. The unaccurate positions of facial features decrease the performance of the emotion recognition. In this paper, we propose real-time facial feature extraction and tracking framework using ASM and LK optical flow for emotion recognition. LK optical flow is desirable to estimate time-varying geometric parameters in sequential face images. In addition, we introduce a straightforward method to avoid tracking failure caused by partial occlusions that can be a serious problem for tracking based algorithm. Emotion recognition experiments with k-NN and SVM classifier shows over 95% classification accuracy for three emotions: "joy", "anger", and "disgust".