• Smart Structures and Systems
• /
• v.29 no.1
• /
• 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
• /
• v.24 no.2
• /
• 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
• /
• v.29 no.1
• /
• 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.

• Economic and Environmental Geology
• /
• v.30 no.4
• /
• 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
• /
• v.43 no.1
• /
• 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
• /
• v.45 no.7
• /
• pp.891-895
• /
• 2002

Purpose : The prevalence of renal anomalies in Turner syndrome(TS) has been reported to vary from 33% to 60%. The purpose of this study was to clarify the true incidence of renal malformations in Korean TS. Methods : We evaluated 33 patients with Turner syndrome diagnosed by karyotype in Inje University Busan Paik hospital and Youngnam University from January 1995. Intravenous pyelography(IVP) was performed on all patients; abdominal ultrasonography and 99mTc-DMSA renal scan were performed on some. Cytogenetic analysis was performed on all patients with peripheral blood lymphocytes. Results : Of the total 33 patients, the karyotype showed 45, X in 18(54.5%) patients, mosaicism in 11(33.3%) patients and structural aberration in 4(12.2%) patients. The overall incidence of renal anomalies was 36.4%. The renal anomalies included four cases of horeshoe kidney, six cases of abnormal renal collecting system one case of single kidney and one case of malrotation. The incidence of renal anomalies in 45, X karotype(44.4%) showed a higher rate than that of mosaicism and structural aberration(26.7%), but there is no statistical significance. Conclusion : The incidence of renal anomalies in Korean TS reveals 36.4%. This rate is similar to other foreign TS studies. We recommend that renal ultrasonography or IVP for investigation of renal anomalies should be done as a screening procedure for the better quality of life in patients with TS.

• Structural Engineering and Mechanics
• /
• v.88 no.6
• /
• 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.

• Journal of KIISE
• /
• v.41 no.10
• /
• pp.847-858
• /
• 2014

Until now, a lot of image quality assessment techniques or tools for optimal human visual system(HVS)-awareness have been researched and SSIM(Structural SIMilarity) and its improved techniques are representative examples. However, they often cannot cope with various images and different distortion types robustly, and thus this can cause a large gap between their index values and HVS-awareness. In this paper, we conduct image quality assessment on SSIM and its variants intensively and analyze the causes of each component function's observed anomalies. Then, we propose a novel image quality assessment technique to compensate and improve such anomalies. Additionally, through extensive image assessment simulations, we show that the proposed technique can indicate HVS-awareness more robustly and consistently than SSIM and its variants for various images and different distortion types.

• Smart Structures and Systems
• /
• v.29 no.4
• /
• 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
• /
• v.49 no.9
• /
• pp.1000-1004
• /
• 2006

Atretic cephalocele is a degenerative form of encephalocele, which is detected as a cystic mass in the head, primarily in infants. Its presentation and prognosis vary and depend on various factors, including the nature of the tissues within the cyst, other concomitant anomalies, the site of development, and the presence or absence of an embryonic straight sinus. We here report 2 cases of atretic encephalocele, that were transferred to our hospital because round tumors, misdiagnosed as dermoid cysts, were detected in their parietal lobes immediately after birth. On diagnostic and differential MRI, an embryonic straight sinus was detected while histochemical results indicated that the lesions contained cerebral tissues. Despite these structural anomalies, the two patients developed normally neurologically and no other anomalies were detected. We here discuss these two cases and present a review of the relevant literature.