• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.63-75
• /
• 2022

The raw data collected by structural health monitoring (SHM) systems may suffer multiple patterns of anomalies, which pose a significant barrier for an automatic and accurate structural condition assessment. Therefore, the detection and classification of these anomalies is an essential pre-processing step for SHM systems. However, the heterogeneous data patterns, scarce anomalous samples and severe class imbalance make data anomaly detection difficult. In this regard, this study proposes a convolutional neural network-based data anomaly detection method. The time and frequency domains data are transferred as images and used as the input of the neural network for training. ResNet18 is adopted as the feature extractor to avoid training with massive labelled data. In addition, the focal loss function is adopted to soften the class imbalance-induced classification bias. The effectiveness of the proposed method is validated using acceleration data collected in a long-span cable-stayed bridge. The proposed approach detects and classifies data anomalies with high accuracy.

• Pediatric Gastroenterology, Hepatology & Nutrition
• /
• 제24권2호
• /
• pp.238-243
• /
• 2021

Caudal regression syndrome (CRS) is a rare neural tube defect that affects the terminal spinal segment, manifesting as neurological deficits and structural anomalies in the lower body. We report a case of a 31-month-old boy presenting with constipation who had long been considered to have functional constipation but was finally confirmed to have CRS. Small, flat buttocks with bilateral buttock dimples and a short intergluteal cleft were identified on close examination. Plain radiographs of the abdomen, retrospectively reviewed, revealed the absence of the distal sacrum and the coccyx. During the 5-year follow-up period, we could find his long-term clinical course showing bowel and bladder dysfunction without progressive neurologic deficits. We present this case to highlight the fact that a precise physical examination, along with a close evaluation of plain radiographs encompassing the sacrum, is necessary with a strong suspicion of spinal dysraphism when confronting a child with chronic constipation despite the absence of neurologic deficits or gross structural anomalies.

• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.117-127
• /
• 2022

Data anomalies seriously threaten the reliability of the bridge structural health monitoring system and may trigger system misjudgment. To overcome the above problem, an efficient and accurate data anomaly detection method is desiderated. Traditional anomaly detection methods extract various abnormal features as the key indicators to identify data anomalies. Then set thresholds artificially for various features to identify specific anomalies, which is the artificial experience method. However, limited by the poor generalization ability among sensors, this method often leads to high labor costs. Another approach to anomaly detection is a data-driven approach based on machine learning methods. Among these, the bidirectional long-short memory neural network (BiLSTM), as an effective classification method, excels at finding complex relationships in multivariate time series data. However, training unprocessed original signals often leads to low computation efficiency and poor convergence, for lacking appropriate feature selection. Therefore, this article combines the advantages of the two methods by proposing a deep learning method with manual experience statistical features fed into it. Experimental comparative studies illustrate that the BiLSTM model with appropriate feature input has an accuracy rate of over 87-94%. Meanwhile, this paper provides basic principles of data cleaning and discusses the typical features of various anomalies. Furthermore, the optimization strategies of the feature space selection based on artificial experience are also highlighted.

• 자원환경지질
• /
• 제30권4호
• /
• pp.363-369
• /
• 1997

As a part of the study to know the deep geological structure of the Ogcheon Zone. gravity survey is performed along the survey line of which direction is roughly perpendicular to major faults of the Zone. Recent studies for petrology. geochemistry. and structural geology in south-western Ogcheon Zone are outlined. Raw gravity data are corrected to obtain Bouguer anomalies and the anomalies are interpreted to obtain subsurface structures along the survey line. The subterranean density discontinuities determined from the power spectrum method are appeared at depths of 15.4 km and 2.8 km. It is considered that the depth of 15.4 km indicates the boundary between upper and lower crust. Probably the depth of 2.8 km represents the boundary between upper volcanic formations and granites. Alternatively. the observed Bouguer anomalies are interpreted in terms of lateral density variation model. Finally. the subterranean geological structure to satisfy the Bouguer anomalies is presented through the iterative forward method in which results obtained from surface geological informations and from the inverse method are adopted as an initial model.

• Archives of Plastic Surgery
• /
• 제43권1호
• /
• pp.19-25
• /
• 2016

Background The vermilion plays an important role in both the aesthetic and functional aspects of facial anatomy. Due to its structural features, the complete excision of vascular anomalies on the vermilion is challenging, making it difficult to determine the appropriate treatment strategy. Thus, the authors analyzed the results of surgical treatment of vascular anomalies on the vermilion. Methods The medical records of 38 patients with vascular anomalies on the vermilion who underwent surgery from 1995 to 2013 were analyzed. Nine of the cases had an involuted hemangioma, and 29 cases had a vascular malformation; of the vascular malformations, 13, 11, one, and four cases involved were capillary malformations (CMs), venous malformations (VMs), lymphatic malformations (LMs), and arteriovenous malformations (AVMs), respectively. We investigated the surgical methods used to treat these patients, the quantity of surgical procedures, complications and instances of recurrence, and self-assessed satisfaction scores. Results A total of 50 operations were carried out: 28 horizontal partial excisions, eight vertical partial excisions, and 14 operations using other surgical methods. All cases of AVM underwent complete excision. Six cases experienced minor complications and one case of recurrence was observed. The overall average satisfaction score was 4.1 out of 5, while the satisfaction scores associated with each lesion type were 4.2 for hemangiomas, 3.9 for CMs, 4.2 for VMs, 5.0 for LMs, and 4.0 for AVMs. Conclusions It is difficult to completely excise vascular anomalies that involve the vermilion. This study suggests that partial excision focused on correcting the overall contour of the lips is effective and leads to satisfactory results.

• Clinical and Experimental Pediatrics
• /
• 제45권7호
• /
• pp.891-895
• /
• 2002

목 적 : 터너 증후군에서 신기형은 보고자에 따라 차이가 있으나 대개 33-60%의 발생빈도를 나타낸다. 국내에서는 노 등이 9.2%의 동반율을 보고하면서, 한국 소아 터너 증후군 환자에서 신기형의 동반율이 다른 외국에 비해 낮을 가능성을 제시하였다. 이에 저자 들은 본 연구를 통하여 터너 증후군 환자에서 신기형의 발생빈도를 조사하고, 핵형에 따라 신기형의 발생 빈도에 차이가 있는지를 분석하였다. 방 법: 1995년 1월부터 인제의대 부산백병원과 영남대학교병원에서 염색체 검사를 시행하여 터너 증후군으로 진단된 33명의 환자를 대상으로 하였다. 환자 전원을 대상으로 경정맥 신우 조영술을 실시하였으며, 일부 환자에서는 복부 초음파 검사 및 99mTc-DMSA 신주사(renal scan)를 함께 시행하였다. 환자들은 핵형에 따라 전형적인 45, X형, 모자이시즘(mosaicism)인 경우 그리고 X 염색체의 구조상의 이상(structural aberration)이 있는 경우로 분류하였다. 결 과 : 염색체 핵형의 비율은 전형적인 45, X형이 18명으로 54.5%를 차지하였고, 모자이시즘이 11명으로 33.3% 그리고 X 염색체의 구조상의 이상이 있는 경우가 4명으로 12.2%를 차지하였다. 33명의 터너 증후군 환자 중 12명에서 신기형이 동반되어 전체적으로 36.4%의 빈도를 나타내었다. 동반된 신기형의 종류를 살펴보면 마제신이 4명에서 관찰되었으며, 단일신이 1명, 회전이상이 1명, renal collecting system의 이상이 6명에서 관찰되었다. 핵형에 따른 신기형의 빈도를 살펴보면 전형적인 45, X형의 경우 44.4%로 모자이시즘과 X 염색체 구조적 이상의 26.7%보다 발생 빈도가 높았으나 통계적으로 유의하지는 않았다(P>0.05). 결 론: 본 연구에서 터너 증후군 환자에서의 신장 기형의 동반율은 36.4%였다. 이는 외국의 다른 연구 결과와 비슷한 발생빈도를 보여 준다. 핵형에 따른 신 기형의 빈도는 전형적인 45, X형의 경우 44.4%였으며, 모자이시즘과 X 염색체 구조상의 이상인 경우 26.7%로 나타났다. 그러므로 터너 증후군 환자에서 신장 초음파 검사나 경정맥 신우 조영술 검사를 시행하여 신장 기형의 동반 여부를 조사하는 것이 환자의 질적인 관리에 매우 중요하다고 생각한다.

• Structural Engineering and Mechanics
• /
• 제88권6호
• /
• pp.569-581
• /
• 2023

This paper introduces a system to detect and diagnose anomalies in pumped storage hydropower plants. We collect data from various types of sensors, including those monitoring temperature, vibration, and power. The data are classified according to the operation modes (pump and turbine operation modes) and normalized to remove the influence of the external environment. To detect anomalies and diagnose their types, we adopt a multivariate normal distribution analysis by learning the distribution of the normal data. The feasibility of the proposed system is evaluated using actual monitoring data of a pumped storage hydropower plant. The proposed system can be used to implement condition monitoring systems for other plants through modifications.

• 정보과학회 논문지
• /
• 제41권10호
• /
• pp.847-858
• /
• 2014

지금까지 최적의 인간 시각 만족을 위한 이미지 평가 기법 또는 도구 연구가 많이 이루어져 오고 있는데 SSIM(Structural SIMilarity) 및 이의 개선 기법들이 그 대표적인 예이다. 하지만 이들 기법은 여전히 다양한 이미지 종류 및 이미지 왜곡 종류에 대해 견실하게 대응하지 못하는 한계를 보이며 인간 시각 만족과의 괴리가 크게 존재하고 있다. 이 논문에서는 SSIM 및 개선된 SSIM 기법을 대상으로 집중적인 이미지 평가를 수행하였으며 각각의 함수에서의 관측된 이상 동작 내용에 대해서 원인을 분석하고 이를 보완 및 개선하는 새로운 이미지 평가 기법을 제시한다. 또, 기법에 대한 다양한 이미지 평가 실험을 통해서 제안 기법이 SSIM과 이의 기존 개선 기법보다 여러 이미지 종류와 왜곡 종류에 대해서 인간 시각 만족을 견실하고 일관성 있게 효과적으로 표현하고 있음을 보인다.

• Smart Structures and Systems
• /
• 제29권4호
• /
• pp.561-576
• /
• 2022

Heritage timber structures represent the history and culture of a nation. These structures have been inherited from previous generations; however, they inevitably exhibit deterioration over time, potentially leading to structural deficiencies. Structural Health Monitoring (SHM) offers the potential to assess operational anomalies, deterioration, and damage through processing and analysis of data collected from transducers and sensors mounted on the structure. This paper reports on the design and implementation of a long-term SHM system on the Feiyun Wooden Pavilion in China, a three-story timber building built more than 500 years ago. The principles and features of the design and implementation of SHM systems for heritage timber buildings are systematically discussed. In total, 104 sensors of 6 different types are deployed on the structure to monitor the environmental effects and structural responses, including air temperature and humidity, wind speed and direction, structural temperatures, strain, inclination, and acceleration. In addition, integrated data acquisition and transmission subsystem using a newly developed software platform are implemented. Selected preliminary statistical and correlation analysis using one year of monitoring data are presented to demonstrate the condition assessment capability of the system based on the monitoring data.

• Clinical and Experimental Pediatrics
• /
• 제49권9호
• /
• pp.1000-1004
• /
• 2006

Atretic encephalocele은 1972년 James와 Lassmann에 의해 meningocele manque로 처음 보고 되었고 뇌류의 퇴행성 형태로 정의하였다. 이후로 atretic, occult, abortive, rudimentary cephalocele 등의 다양한 명칭으로 명명되었으며 포함된 조직, 동반 기형, 발생 위치, 배아성 직정맥동의 유무 등에 따른 차이점들에 대해 다양하게 보고 되어왔다. 두정엽의 후부에 낭성 종물을 주소로 입원한 환아의 진단 과정에서 두부 초음파, CT, MRI를 시행하였으며 그 과정에서 MRI가 진단에 가장 효과적인 영상을 제공하였다. 환아 진단 후 수술적 방법으로 종물을 제거하였으며 수술 중 이상 소견 및 추후 관찰 기간 동안 이상 소견관찰되지 않았다. Atretic encephalcele의 희귀함과 진단 방법의 장단점 및 위치상 특성과는 다르게 동반 기형 및 발달 장애가 관찰되지 않은 증례를 치험 하였기에 보고하는 바이다.