• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.57-73
• /
• 2021

Maintenance and prevention of failure through anomaly detection of ICT infrastructure is becoming important. System monitoring data is multidimensional time series data. When we deal with multidimensional time series data, we have difficulty in considering both characteristics of multidimensional data and characteristics of time series data. When dealing with multidimensional data, correlation between variables should be considered. Existing methods such as probability and linear base, distance base, etc. are degraded due to limitations called the curse of dimensions. In addition, time series data is preprocessed by applying sliding window technique and time series decomposition for self-correlation analysis. These techniques are the cause of increasing the dimension of data, so it is necessary to supplement them. The anomaly detection field is an old research field, and statistical methods and regression analysis were used in the early days. Currently, there are active studies to apply machine learning and artificial neural network technology to this field. Statistically based methods are difficult to apply when data is non-homogeneous, and do not detect local outliers well. The regression analysis method compares the predictive value and the actual value after learning the regression formula based on the parametric statistics and it detects abnormality. Anomaly detection using regression analysis has the disadvantage that the performance is lowered when the model is not solid and the noise or outliers of the data are included. There is a restriction that learning data with noise or outliers should be used. The autoencoder using artificial neural networks is learned to output as similar as possible to input data. It has many advantages compared to existing probability and linear model, cluster analysis, and map learning. It can be applied to data that does not satisfy probability distribution or linear assumption. In addition, it is possible to learn non-mapping without label data for teaching. However, there is a limitation of local outlier identification of multidimensional data in anomaly detection, and there is a problem that the dimension of data is greatly increased due to the characteristics of time series data. In this study, we propose a CMAE (Conditional Multimodal Autoencoder) that enhances the performance of anomaly detection by considering local outliers and time series characteristics. First, we applied Multimodal Autoencoder (MAE) to improve the limitations of local outlier identification of multidimensional data. Multimodals are commonly used to learn different types of inputs, such as voice and image. The different modal shares the bottleneck effect of Autoencoder and it learns correlation. In addition, CAE (Conditional Autoencoder) was used to learn the characteristics of time series data effectively without increasing the dimension of data. In general, conditional input mainly uses category variables, but in this study, time was used as a condition to learn periodicity. The CMAE model proposed in this paper was verified by comparing with the Unimodal Autoencoder (UAE) and Multi-modal Autoencoder (MAE). The restoration performance of Autoencoder for 41 variables was confirmed in the proposed model and the comparison model. The restoration performance is different by variables, and the restoration is normally well operated because the loss value is small for Memory, Disk, and Network modals in all three Autoencoder models. The process modal did not show a significant difference in all three models, and the CPU modal showed excellent performance in CMAE. ROC curve was prepared for the evaluation of anomaly detection performance in the proposed model and the comparison model, and AUC, accuracy, precision, recall, and F1-score were compared. In all indicators, the performance was shown in the order of CMAE, MAE, and AE. Especially, the reproduction rate was 0.9828 for CMAE, which can be confirmed to detect almost most of the abnormalities. The accuracy of the model was also improved and 87.12%, and the F1-score was 0.8883, which is considered to be suitable for anomaly detection. In practical aspect, the proposed model has an additional advantage in addition to performance improvement. The use of techniques such as time series decomposition and sliding windows has the disadvantage of managing unnecessary procedures; and their dimensional increase can cause a decrease in the computational speed in inference.The proposed model has characteristics that are easy to apply to practical tasks such as inference speed and model management.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.20 no.1
• /
• pp.13-19
• /
• 2016

Purpose In order to calculate the left ventricular ejection fraction (LVEF) accurately, it is important to acquire the best septal view of left ventricle in the multi-gated cardiac blood pool scan (GBP). This study aims to acquire the best septal view by measuring angle of ventricular septal wall (${\theta}$) using enhanced CT scan and compare with conventional method using left anterior oblique (LAO) 45 view. Materials and Methods From March to July in 2015, we analyzed the 253 patients who underwent both enhanced chest CT and GBP scan in the department of nuclear medicine at National Cancer Center. Angle (${\theta}$) between ventricular septum and imaginary midline was measured in transverse image of enhanced chest CT scan, and the patients whose difference between the angle of ${\theta}$ and 45 degree was more than 10 degrees were included. GBP scan was acquired using both LAO 45 and LAO ${\theta}$ views, and LVEFs measured by automated and manual region of interest (Auto-ROI and Manual-ROI) modes respectively were analyzed. Results $Mean{\pm}SD$ of ${\theta}$ on total 253 patients was $37.0{\pm}8.5^{\circ}$. Among them, the patients whose difference between 45 and ${\theta}$ degrees were more than ${\pm}10$ degrees were 88 patients ($29.3{\pm}6.1^{\circ}$). In Auto-ROI mode, there was statistically significant difference between LAO 45 and LAO ${\theta}$ (LVEF $45=62.0{\pm}6.6%$ vs. LVEF ${\theta}=64.0{\pm}5.6%$; P = 0.001). In Manual-ROI mode, there was also statistically significant difference between LAO 45 and LAO ${\theta}$ (LVEF $45=66.7{\pm}7.2%$ vs. LVEF ${\theta}=69.0{\pm}6.4%$; P < 0.001). Intraclass correlation coefficients of both methods were more than 95%. In case of comparison between Auto-ROI and Manual ROI of each LAO 45 and LAO ${\theta}$, there was no significant difference statistically. Conclusion We could measure the angle of ventricular septal wall accurately by using transverse image of enhanced chest CT and applied to LAO acquisition in the GBP scan. It might be the alternative method to acquire the best septal view of LAO effectively. We could notify significant difference between conventional LAO 45 and LAO ${\theta}$ view.

• The Korean Journal of Nuclear Medicine
• /
• v.37 no.2
• /
• pp.83-93
• /
• 2003

Background: Lung-to-heart uptake ratio (LHR) in $^{201}Tl-chloride$ myocardial perfusion scan is believed to be a reliable marker for left ventricular (LV) dysfunction, but the clinical value of LHR is controversial for $^{99m}Tc-MIBI$ imaging. Furthermore, most of results suggesting lung uptake of $^{99m}Tc-MIBI$ as a potential marker for LV dysfunction used immediate post-stress images, instead of routine images acquired 1 hour after tracer injection. The goal of our study was to investigate whether LHR evaluated with routine gated $^{99m}Tc-MIBI$ imaging can reflect the degree of perfusion defect or left ventricular performance. Subjects and Methods: 241 patients underwent exercise $^{99m}Tc-MIBI$ myocardial SPECT were classified into normal myocardial perfusion (NP, n=135) and abnormal myocardial perfusion (AP, n=106) group according to the presence of perfusion defect. LHR was calculated from anterior projection image taken at 1-hour after injection. Two legions of interest (ROIs) were placed on left lung above LV and on myocardium showing the highest radioactivity. Subjects were classified by left ventricular ejection fraction (LVEF), as Gr-I: >50%, Gr-II: 36-50%, Gr-III: <36% and by summed stress score (SSS), as Gr-A: <4, Gr-B: 4-8, Gr-C: 9-13, Gr-D: >13, LHR was compared among these groups. Results: In NP group(n=135), LHR, were higher in men than women ($men:\;0.311{\pm}0.03,\;women:\;0.296{\pm}0.03,\;p<0.05$). Significant difference, in LHR were found between NP and AP groups both for men and women ($men:\;0.311{\pm}0.03\;vs\;.\;0.331{\pm}0.06,\;women:\;0.296{\pm}0.03\;vs.\;0.321{\pm}0.07.\;p<0.05$). There were weak negative correlation between LHR and LVEF (r=-0.342, p<0.05) and weak positive correlation between LHR and SSS (r=0.478, p<0.05) in men, but not in women (LVEF: r=-0.279, p=0.100, SSS: r=0.276, p=0.103). Increased LHR was defined when for more than mean + 2SD value ($men{\geq}0.38,\;women{\geq}0.37$) of the LHR of the subject with normal perfusion. Increased LHR were observed more frequently in subjects with lower LVEF (Gr-I: 11.1%, Gr-II: 27.0%, Gr-III: 35.4%, p<0.05) and higher SSS(Gr-A: 14.0%, Gr-B: 5.7%, Gr-C: 18.2%, Gr-D: 40.7%, p<0.05). Conclusions: LHRs obtained from routine $^{99m}Tc-MIBI$ gated SPECT images were weakly correlated with LVEF and perfusion defect. Although significant overlaps were observed between normal and abnormal perfusion group, LHRs could be used as an indirect marker of severe perfusion defect or reduced left ventricular function.

• Nuclear Medicine and Molecular Imaging
• /
• v.40 no.4
• /
• pp.218-227
• /
• 2006

Purpose: The HSV1-tk reporter gene system is the most widely used system because of its advantage that direct monitoring is possible without the introduction of a separate reporter gene in case of HSV1-tk suicide gene therapy. In this study, we investigate the usefulness of the reporter probe (substrate), $9-(4-[^{18}F]Fluoro-3-hydroxymethylbutyl)$guanine ($[^{18}F]FHBG$) for non-invasive reporter gene imaging using PET in HSV1-tk expressing hepatoma model. Materials and Methods: Radiolabeled FHBG was prepared in 8 steps from a commercially available triester. The labeling reaction was carried out by NCA nucleophilic substitution with $K[^{18}F]/K2.2.2.$ in acetonitrile using N2-monomethoxytrityl-9-14-(tosyl)-3-monomethoxytritylmethylbutyl]guanine as a precursor, followed by deprotection with 1 N HCl. Preliminary biological properties of the probe were evaluated with MCA cells and MCA-tk cells transduced with HSV1-tk reporter gene. In vitro uptake and release-out studies of $[^{18}F]FHBG$ were performed, and was analyzed correlation between $[^{18}F]FHBG$ uptake ratio according to increasing numeric count of MCA-tk cells and degree of gene expression. MicroPET scan image was obtained with MCA and MCA-tk tumor bearing Balb/c-nude mouse model. Results: $[^{18}F]FHBG$ was purified by reverse phase semi-HPLC system and collected at around 16-18 min. Radiothemical yield was about 20-25%) (corrected for decay), radiochemical purity was >95% and specific activity was around >55.5 $GBq/{\mu}\;mol$. Specific accumulation of $[^{18}F]FHBG$ was observed in HSV1-tk gene transduced MCA-tk cells but not in MCA cells, and consecutive 1 hour release-out results showed more than 86% of uptaked $[^{18}F]FHBG$ was retained inside of cells. The uptake of $[^{18}F]FHBG$ was showed a highly significant linear correlation ($R^2=0.995$) with increasing percentage of MCA-tk numeric cell count. In microPET scan images, remarkable difference of accumulation was observed for the two type of tumors. Conclusion: $[^{18}F]FHBG$ appears to be a useful as non-invasive PET imaging substrate in HSV1-tk expressing hepatoma model.

• Journal of Korean Medicine Rehabilitation
• /
• v.19 no.1
• /
• pp.135-143
• /
• 2009

Objectives : Low back pain(LBP) is a common disabling disease in clinical practice and loss of working hours due to this condition is huge. The aim of this study was to determine if there was an association between fat deposit of paraspinal muscles as observed on MRI scans in patients presenting with unilateral LBP. Methods : 24 patients who visiting our hospital with a clinical presentation of unilateral LBP were recruited to the study. Patients were between 20 and 30 years and had a history of unilateral LBP within 12 months. After MRI scaning, the images were saved in DICOM file format for Picture Archiving and Communication System(PACS). The percentage of fat infiltrated area was measured using a pseudocoloring technique. Data were analyzed comparing the fat deposits of the muscles on the symptomatic and asymptomatic sides. Paired t-test was used to find the difference between the measurements of fat tissue in individual patients. Results : The amount of fat in the symptomatic side was $7.6{\pm}4.51%$, asymptomatic side was $6.7{\pm}4.29%$. There were increases, statistically significant, in the fat changes of the paraspinal muscles at the L4-5 disc level(P <0.05). Also, men were likely than women to have more fat deposit in symptomatic side(men $8.5{\pm}5.1%$, women $6.5{\pm}3.6%$). Conclusions : The amount of fat in the symptomatic side shows significantly increased than asymptomatic side in the paraspinal muscles at the L4-5 disc level. It suggested that fat infiltration in the muscles associated with LBP. Further studies will be needed to confirm the relationship between the muscle fatty changes and LBP in the large sample size. In addition, the correlation of pain severity with fat infiltration needs to be addressed.

• The Korean Journal of Nuclear Medicine
• /
• v.30 no.3
• /
• pp.299-314
• /
• 1996

The purpose of the present study was to validate the use of tissue radioactivity ratios instead of regional metabolic rates for the assessment of regional metabolic changes in Alzheimer's disease(AD) with [$^{18}F$]FDG PET and to examine the correlation of ratio indices with the severity of cognitive impairment in AD. Thirty-seven AD Patients(age $68{\pm}9 yrs$, $mean{\pm}s.d.$; 36 probable and 1 definite AD), 28 patients with dementia of non-Alzheimer type(age $66{\pm}7 yrs$), and 17 healthy controls(age $66{\pm}4 yrs$) underwent [$^{18}F$]FDG PET imaging. Two simplified radioactivity ratio indices were calculated from 37-66 min image: region-to-cerebellar radioactivity ratio(RCR) and a composite radioactivity ratio(a ratio of radioactivity in the most typically affected regions over the least typically affected regions: CRR). Local cerebral metabolic rate for glucose(LCMRglu) was also measured using a three-compartment, five-parameter tracer kinetic model. The ratio indices were significantly lower in AD patients than in controls(RCR in temporoparietal cortex, $0.949{\pm}0.136$ vs. $1.238{\pm}0.129$, p=0.0004; RCR in frontal cortex, $1.027{\pm}0.128$ vs. $1.361{\pm}0.151$, p<0.0001; CRR, $0.886{\pm}0.096$ vs. $1.032{\pm}0.042$. p=0.0024). On the RCR analysis, 86% of AD patients showed a pattern of bilateral temporoparietal hypometabolism with or without frontal involvement; hypometabolism was unilateral in 11% of the patients. When bilateral temporoparietal hypometabolism was considered to be suggestive of AD, the sensitivity and specificity of the RCR analysis for the differential diagnosis of AD were 86% and 73%, respectively. The RCR was correlated significantly with the macroparameter K [$K_1k_3/(k_2+k_3)$] (r=0.775, p<0.0001) and LCMRglu(r=0.633, p=0.0002) measured using the kinetic model. In patients with AD, both average RCR of cortical association areas and CRR were correlated with Mini-Mental Status Examination(r=0.565, p=0.0145; r=0.642, p=0.0031, respectively), Clinical Dementia Rating(r=-0.576, p=0.0124; r=-0.591, p=0.0077), and total score of Mattis Dementia Rating Scale (r=0.574, p=0.0648; r=0.737, p=0.0096). There were also significant correlations between memory and language impairments and corresponding regional RCRs. The results suggest that the [$^{18}F$]FDG PET ratio indices, RCR and CRR, reflect global and regional metabolic rates and correlate with the severity of cognitive impairment in AD. The simplified ratio analysis may be clinically useful for the differential diagnosis and serial monitoring of the disease.

• Investigative Magnetic Resonance Imaging
• /
• v.1 no.1
• /
• pp.94-102
• /
• 1997

Purpose: There have been some efforts to diagnose intracranial aneurysm through a non-invasive method using MRA, although the process may be difficult when the lesion is less than 3mm. The present study prospectively compares the results of high resolution, fast speed slice interpolation MRA and DSA thereby examing the potentiality of primary non-invasive screening test. Materials and Methods: A total of 26 cerebral aneurysm lesions from 14 patients with subarachnoid hemorrhage from ruptured aneurysm (RA) and 5 patients with unruptured aneurysm(UA). In all subjects, MRA was taken to confirm the vessel of origin, definition of aneurysm neck and the relationship of the aneurysm to nearby small vessels, and the results were compared with the results of DSA. The images were obtained with 1.5T superconductive machine (Vision, Siemens, Erlangen, Germany) on 4 slabs of MRA using slice interpolation. The settings include TR/TE/FA=30/6.4/25, matrix $160{\times}512$, FOV $150{\times}200$, 7minutes 42 seconds of scan time, effective thickness of 0.7 mm and an entire thickness of 102. 2mm. The images included structures from foramen magnum to A3 portion of anterior cerebral artery. MIP was used for the image analysis, and multiplanar reconstruction (MPR) technique was used in cases of intracranial aneurysm. Results: A total of 26 intracranial aneurysm lesions from 19 patients with 2 patients having 3 lesion, 3 patients having 2 lesions and the rest of 14 patients having 1 lesion each were examined. Among those, 14 were RA and 12 were UA. Eight lesions were less than 2mm in size, 9 lesions were 3-5mm, 7 were 6-9mm and 2 were larger than IOmm. On initial exams, 25 out of 26 aneurysm lesions were detected in either MRA or DSA showing 96% sensitivity. Specificity cannot be estimated since there was no true negative of false positive findings. When MRA and MPR were used concurrently for the confirmation of size and shape, the results were equivalent to those of DSA, while in the confirmation of aneurysm neck and parent vessels, the concurrent use of MRA and MPR was far superior to the sole use of either MRA or DSA. Conclusion: High resolution MRA using slice interpolation technique showed equal results as those of DSA for the detection of intracranial aneurysm, and may be used as a primary non-invasive screening test in the future.

• Journal of Chest Surgery
• /
• v.42 no.1
• /
• pp.79-86
• /
• 2009

Background: Background: Computed tomography (CT) is the main tool for detecting abnormalities of the thoracic aorta, but conventional CT only shows the cross-sectional images. These CT images have some limitations fo accuratly measuring the thoracic aortic diameters at various levels. Multidetector computed tomography (MDCT) overcomes these limitations. We measured the thoracic aortic diameter perpendicular to the loop-shaped thoracic aortic course and this was studied in relation to age, gender, height, weight, the body surface area, the body mass index and the presence of hypertension. Material and Method: Thirty hundred thirty one patients (males: 141 patients and females: 190 patients) who had no abnormalities of the thoracic aorta were investigated using MDCT aortography. They were divided into three age categories: 20~39 years old, 40~59 years old and over age 60. The image was reformed with multiplanar reconstruction and the diameter of the aorta was measured perpendicular to the aortic course at 5 anatomic segments. Level A was the mid-ascending aorta, level B was the distal ascending aorta, level C was the aortic arch, level D was the aortic isthmus and level E was the mid-descending aorta. Result: The mean age was 49.5 years old for males and 54.9 years old for females (p<0.05). The mean diameter of the thoracic aorta at level A was 31.1 mm, that at level B was 30.2 mm, that at level C was 26.5 mm, that at level D was 24.0 mm and that at level E was 22.6 mm. The diameters at all the levels were gradually increased with age. Hypertensive patients had larger diameters than did the non-hypertensive population. There was a positive correlation between the ascending aortic diameter (levels A&B) and height and the body surface area, but there were no statistical differences at the aortic arch (level C) and the descending aorta (levels D&E). There were no statistical differences of the weight and body mass index at all levels. Conclusion: The diameters of the thoracic aortas were directly correlated with gender, age and hypertension. Height and the body surface area were only correlated with the ascending aorta. Weight and the body mass index have no statistical difference at all levels. We measured the age related thoracic aortic diameters and the upper normal limits and we provide this data as reference values for the thoracic aortic diameter in the Korean population.

• Archives of design research
• /
• v.15 no.4
• /
• pp.275-284
• /
• 2002

To improve the social and economic position of the disabled people and secure their human rights, an integrated society should be buill. To build such a society, an adequate access should be provided to the movement or in using buildings or facilities. The inconveniences from social life on the part of the disabled people might not result from their impairment or disability, but from physical and social barriers in the environment surrounding them. Therefore, it is necessary to reconstruct entire systems of the society as a disabled people-friendly structure in order to remove those barriers, make them stand their own feet in our communities and freely participate in the social activities. This will eventually lead to build a society in which all people including the disabled people can use those facilities in a more convenient way. It is almost impossible for the disabled people to safely and conveniently access to and use facilities and equipments and freely move to their desired places, without any help from others in Korea. Even though, there are currently many disabled people-related convenience facilities, they have been independently built without a connection with other facilities and buildings, thus not greatly useful. Even when convenience facilities have been built, mostly they are superficially set up; therefore, in many cases, the disabled peOple cannot use those facilities. In this. research, I tried a new concept of mobile wheelchair lift design, which the disabled people can operate without restrictions, when using the public facilities. The key to this research was to develop the existing import-oriented simple functional products to a new system with functional safety and high quality orientation. Also, this research aimed at bringing an. import substitution effect, as well as preempting the mobile wheelchair lift market by advancing into overseas markets through application of new image designs in the field of disabled people aid equipments.

• Tuberculosis and Respiratory Diseases
• /
• v.54 no.2
• /
• pp.191-198
• /
• 2003

Background : The pathological features in asthmatic airway remodeling are diverse. The aim of this study was to examine the degree of airway vascularity in relation to the other remodeling parameters in asthmatics. Methods : Bronchial biopsies were done in 34 asthmatic patients, and 6 control subjects. The basement membrane thickness and the subepithelial thickness were measured in the hematoxylin-eosin stained tissue, and the degree of vascularity was measured using type IV collagen immunostaining. Results : 1) Compared to the control subjects, the asthmatics showed a significant increase in the basement membrane thickness ($6.92{\pm}2.01{\mu}m$ vs $9.67{\pm}2.84{\mu}m$, p<0.05) and the subepithelial thickness ($44.49{\pm}31.92{\mu}m$ vs $121.22{\pm}72.79{\mu}m$, p<0.05). 2) Compared to the control subjects, the asthmatics showed a significant increase in the vascular area per unit submucosal area ($4.51{\pm}2.13%$ vs $10.32{\pm}6.08%$, p<0.05). In addition, the number of vessels per unit submucosal area showed an increased tendency without statistical significance. 3) In the asthmatics, the number of vessels and the vascular area per unit submucosal area showed no correlation with the basement membrane thickness, the subepithelial thickness, the severity, the forced expiratory volume in 1 second($FEV_1$), and the methacholine provocative concentration 20($PC_{20}$). Conclusion : This study showed that vascularity was an important parameter in asthmatic airway remodeling but it was not related to the other remodeling parameters such as the basement membrane thickness and the subepithelial thickness. Each of these asthmatic remodeling parameters may have a different clinical significance. Therefore, further studies will be needed.