• 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.

• Journal of the Korean Society of Radiology
• /
• v.12 no.3
• /
• pp.409-415
• /
• 2018

The development of smart devices has brought about significant changes in daily life and one of the most significant changes is the virtual reality zone. Virtual reality is a technology that creates the illusion that a 3D high-resolution image has already been created using a display device just like it does in itself. Unrealized subjects are forced to rely on audiovisual materials, resulting in a decline in the concentration of practices and the quality of classes. It used virtual reality to develop effective teaching materials for radiology students. In order to produce a video clip bridge using virtual reality, a radiology clinic was selected to conduct two exposures from July to September 2017. The video was produced taking into account the radiology and work flow chart and filming was carried out in two separate locations : in the computerized tomography unit and in the LINAC room. Prior to filming the scenario and the filming route were checked in advance to facilitate editing of the video. Modeling and mapping was performed in a PC environment using the Window XP operating system. Using two leading virtual reality camera Gopro Hero, CC pixels were produced using a 4K UHD, Adobe, followed by an 8 megapixel resolution of $3,840{\times}2,160/4,096{\times}2,160$. Total regeneration time was performed in about 5 minutes during the production of using virtual reality to prevent vomiting and dizziness. Currently developed virtual reality radiation and educational contents are being used to secure the market and extend the promotion process to be used by various institutions. The researchers will investigate the satisfaction level of radiation and educational contents using virtual reality and carry out supplementary tasks depending on the results.

• The Journal of Korean Society for Radiation Therapy
• /
• v.17 no.1
• /
• pp.19-31
• /
• 2005

Purpose : To supply the information of EPID system and to analyze the possibility of substitution EPID for film dosimetry. Materials & Methods : With amorphous silicon(aSi) type EPID and liquid filled lonization chamber(LC) type EPID, the reproducibility according to focus detector distance(FDD) change and gantry rotation was analyzed, and also the possible range of image acquisition was analyzed with Alderson Rando phantom. The resolution and the contrast of aSi type EPID image were analyzed through Las Vegas phantom and water phantom. DMLC image was analyzed with X-Omat V film and EPID to see wether it could be applied to the qualify assurance(QA) of IMRT. Results : The reproducibility of FDD position was within 1mm, but the reproducibility of gantry rotation was ${\pm}2,\;{\pm}3mm$ respectively. The resolution and the contrast of EPID image were affected by dose rate, image acquisition time, image acquisition method and frame number. According to the possible range of image acquisition of EPID, it is verified that the EPID is easier to use than film. There is no difference between X-Omat V film and EPID images for the QA of IMRT. Conclusion : Through various evaluation, we could obtain lots of useful information about the EPID. Because the EPID has digital data, also we found that the EPID is more useful than film dosimerty for the periodical Qualify Assurance of IMRT. Especially when it is difficult to do point dose measurement with diode or ionization chamber, the EPID could be very useful substitute. And we found that the diode and ionization chamber are difficult to evaluate the sliding window images of IMRT, but the EPID was more useful to do it.

• Journal of Hospice and Palliative Care
• /
• v.22 no.4
• /
• pp.185-197
• /
• 2019

Purpose: Hospice volunteers are serving an invisible yet pivotal role in the hospice and palliative care team. This study investigated how effectively a continuing education program could enhance hospice volunteers' competency. Methods: A total of 20 hours (four hours per week) of training was provided to 30 hospice volunteers who participated in the continuing education for hospice volunteers. Efficiency of the education was analyzed with an exploratory mixed-methods design. For quantitative analysis, the volunteers were asked, before and after the training, about their attitudes towards hospice care, what makes a meaningful life, self-efficacy and satisfaction with their volunteer service. Descriptive statistics, paired t-tests, and Wilcoxon signed-rank test were performed using SPSS Window 20.0. For qualitative research, participants were placed in three groups for a focus group interview, and data were analyzed by content analysis. Results: A quantitative study result shows that this training can significantly affect hospice volunteers' attitudes and improve their self-efficacy. A qualitative study result shows that participants wanted to receive continuous education from the physical/psychosocial/spiritual aspects to better serve end-of-life patients and their family members even though they have to spare significant time for the volunteer service. They wanted to know how to take good care of patients without getting themselves injured and how to provide spiritual care. Conclusion: The continuing education program reflecting volunteers' requests is strongly needed to improve their competency. An effective continuing education requires continuous training and support in areas where hospice volunteers are interested in. A good alternative is to combine web-based and hands-on training, thereby allowing hospice volunteers freely take training that suits their interest.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.36 no.3
• /
• pp.137-148
• /
• 2018

Li Yu's Xian Qing Ou Ji was written during the late Ming and early Qing Dynasty when material culture flourished due to the development of the commercial economy. Xian Qing Ou Ji is considered a retrospective work that reflects the rich material society at that time. This study focuses on his gardening theories through the interpretation and analysis of these two texts of 'Jushibu(居室部)' and 'Zhongzhibu(種植部)' in Xian Qing Ou Ji. The results are summarized as follows. First, he explained the method of garden configuration and orientation according to the topography utilizing the theory of 'suiting one's measures to local conditions(因地制宜)'. He emphasized the detailed understanding of topography as the starting point for all the gardening theories. It stated that he tried to adjust the height of the terrain artificially to create an ideal form of 'anterior high and posterior low(前低後高)'. The successful arrangement of houses, pavilions, rockery and waterways et al. was able to be achieved because of his accurate understanding of topography. Second, 'borrowing scenery(取景在借)' means 'borrowing the outside scenery to the inside'. He applied this theory by 'viewing in motion(動觀)' and 'viewing in repose(靜觀)'. 'Viewing in motion' is seen as a positive methodology for landscape enjoyment. For example, the view through a window changes with movements of the boat, and it can portray thousands of landscape paintings which can be seen through the windows. In the case of 'viewing in repose', the window is regarded as a means of attracting outside garden views to the inside. Third, he emphasized 'the firmness of objects(制體宜堅)', where the design of windows and railings must be considered ahead of others. Fourth, he interpreted the contents of 'the pursuit of novelty(創異標新)'. This generalizes the characteristics of his gardening theory. The contents included 'hall wall(廳壁)', 'variable sun visor(活?)', 'hanging boards and couplets(聯?)' and 'method of supporting vines with bamboo screen(竹屛扶植法)'.

• The Journal of Korean Society for Radiation Therapy
• /
• v.33
• /
• pp.25-33
• /
• 2021

Purpose : The purpose of this study is to evaluate the accuracy and usefulness of the Trigger mode for the Respiratory Gated Radiation Therapy (RGRT) Materials and methods : A QUASAR respiratory phantom that inserted a 3 mm fiducial marker (a gold marker) was used to estimate the accuracy of the Trigger mode. And the 20 bpm was used as reference respiration rate in this study. The marker that placed at the center of the phantom was contoured, and the lower threshold of a gating window was fixed at 2.0 mm using an OBI with Truebeam STx^TM. The upper threshold was measured every 0.5 mm from 1.0 mm to 3.0 mm. The respiration rates were changed every 10 bpm from 10 bpm to 60 bpm. We repeatedly measured five times to check the error rate of the trigger mode in the same condition. Result : The differences of a distance from a peak phase to upper threshold, 1.0 to 3.0 mm at a 20 bpm as a reference for 3 days in a row were 0.68±0.05 mm, 0.91±0.03 mm, 1.23±0.03 mm, 1.42±0.04 mm, and 1.66±0.06 mm, respectively. Measurement result of changes in respiratory rate compared to baseline respiratory rate in maximum absolute difference. The coefficient of determination (R2) to estimate the correlation between the respiration velocity and variation of absolute difference was on average 0.838, 0.887, 0.770, 0.850, and 0.906. The p-values of all the variables were below 0.05. Conclusion : Using Trigger mode during respiratory gated radiation therapy (RGRT), accuracy and usefulness of trigger mode at reference breathing rate were confirmed. However, inaccuracies depending on the rate of breathing it could be uncertain in case of respiration rate is faster than 20 bpm as a standard respiration rate compared to slower than 20 bpm. Consequently, when conducting a RGRT using the trigger mode, real time monitoring is required with well educated respiration.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.31 no.4
• /
• pp.84-94
• /
• 2013

This study scrutinizes the titles of serial poems on Japanese Apricot, which have lucid characters on season and time changes, having been appreciated and recited by the scholars in the Choseon Dynasty era and analyses the records of Zhang zi(1153~1235), a writer in Song(宋) Dynasty in China, having presented the objects harmonizing perfectly with Japanese Apricot. The results of this study categorizes the objects of Japanese Apricot appreciation and establishes the landscape characteristics on Japanese Apricot appreciation affiliated with as follows. First, the objects of Japanese Apricot appreciation are categorized into 'form of blossoms', 'natural feature(景物)', 'place of tree planting', 'the picturesque scene(景色)' and 'behavior'. Second, the scholars regarded the single trees whose branches are grotesque as the objects of appreciation and enjoyed them. They preferred white and single petal Japanese Apricot and admired red Japanese Apricot which has Taoism images. Third, they admired pines and camelias which represent fidelity and strength and valued Japanese Apricot with cranes which remind themselves of solitary scholars. Fourth, they appreciated the images of Japanese Apricot reflected on the water, and the poetically inspiring atmosphere where the trees are planted by the window. Fifth, the moon and snow were crucial weather conditions for appreciating. cold weather and time from night to dawn were ideally suited for enjoying. Sixth, they enjoyed blossoms in various fashions like bottling(甁梅), potting(盆梅), green-housing(龕梅), searching(龕梅) and black-and-white painting(墨梅) with a view to seeing blossoms earlier than the usual flowering time. Moreover, they used paper drapes, bead curtains, mirrors and ice lamps for active appreciation. They also listened to the sound of Piri(wind) and Geomungo(string), played go and drew tea with noble and elegant beauties when they enjoyed Japanese Apricot. The scholars influenced by the neo-Confucianism, which contemplates the objects, attached the specific sentiments like memories, grieves, dreams and farewells to Japanese Apricot and appreciated them. As stated above the scholars enjoyed the landscape including the picturesque scene like climate-weather, time-season and human behaviors not to mention the physical beauty of Japanese Apricot themselves and objects in company with Japanese Apricot including animals and plants.

• The Korean Journal of Nuclear Medicine
• /
• v.38 no.4
• /
• pp.318-324
• /
• 2004

Purpose: Philips GEMINI is a newly introduced whole-body GSO PET/CT scanner. In this study, performance of the scanner including spatial resolution, sensitivity, scatter fraction, noise equivalent count ratio (NECR) was measured utilizing NEMA NU2-2001 standard protocol and compared with performance of LSO, BGO crystal scanner. Methods: GEMINI is composed of the Philips ALLEGRO PET and MX8000 D multi-slice CT scanners. The PET scanner has 28 detector segments which have an array of 29 by 22 GSO crystals ($4{\times}6{\times}20$ mm), covering axial FOV of 18 cm. PET data to measure spatial resolution, sensitivity, scatter fraction, and NECR were acquired in 3D mode according to the NEMA NU2 protocols (coincidence window: 8 ns, energy window: $409[\sim}664$ keV). For the measurement of spatial resolution, images were reconstructed with FBP using ramp filter and an iterative reconstruction algorithm, 3D RAMLA. Data for sensitivity measurement were acquired using NEMA sensitivity phantom filled with F-18 solution and surrounded by $1{\sim}5$ aluminum sleeves after we confirmed that dead time loss did not exceed 1%. To measure NECR and scatter fraction, 1110 MBq of F-18 solution was injected into a NEMA scatter phantom with a length of 70 cm and dynamic scan with 20-min frame duration was acquired for 7 half-lives. Oblique sinograms were collapsed into transaxial slices using single slice rebinning method, and true to background (scatter+random) ratio for each slice and frame was estimated. Scatter fraction was determined by averaging the true to background ratio of last 3 frames in which the dead time loss was below 1%. Results: Transverse and axial resolutions at 1cm radius were (1) 5.3 and 6.5 mm (FBP), (2) 5.1 and 5.9 mm (3D RAMLA). Transverse radial, transverse tangential, and axial resolution at 10 cm were (1) 5.7, 5.7, and 7.0 mm (FBP), (2) 5.4, 5.4, and 6.4 mm (3D RAMLA). Attenuation free values of sensitivity were 3,620 counts/sec/MBq at the center of transaxial FOV and 4,324 counts/sec/MBq at 10 cm offset from the center. Scatter fraction was 40.6%, and peak true count rate and NECR were 88.9 kcps @ 12.9 kBq/mL and 34.3 kcps @ 8.84 kBq/mL. These characteristics are better than that of ECAT EXACT PET scanner with BGO crystal. Conclusion: The results of this field test demonstrate high resolution, sensitivity and count rate performance of the 3D PET/CT scanner with GSO crystal. The data provided here will be useful for the comparative study with other 3D PET/CT scanners using BGO or LSO crystals.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.18 no.12
• /
• pp.1870-1883
• /
• 1993

In this paper, in order to build up the User Network Interface based on ATM, a study on traffic control techniques which should be performed by main function groups-B 75,5 NT2, LEX-is discussed. The structure of B-NT2 which is the most important function group In the User Network Interface is defined in quite a simple manner in addition, the functional blocks of LEX are defined in a similar manner as those of B NT2. It is possible to distribute total traffic control functions by using the similarities between B-NT2 and LEX and by allocating virtual path identifiers fixedly according to the characteristics of the traffics. For the traffic control techniques of ATM, relations among Connection Admtsslon Control, Usage Parameter Control and Bandwidth Allocation Control are defined and Multi Rule Base structure to realize optimal control functions according to the characteristics of the source traffics is proposed. And the Real-time Variable Window algorithmsimply designed to be suitable for the Multi Rule Base architecture is also proposed. The performances of the proposed algorithm are analyzed through the computer simulation by generating on-off source traffic in a virtual system that has the form of the proposed hardware. The analyzed results show that the distributed control is possible and that the implementation of the proposed architecture and algorithm is possible.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.11A
• /
• pp.867-875
• /
• 2003

Current end-to-end congestion control depends only on the information of end points (using three duplicate ACK packets) and generally responds slowly to the network congestion. This mechanism can't avoid TCP global synchronization in which TCP congestion window size is fluctuated during congestion period. Furthermore, if RTT(Round Trip Time) is increased, three duplicate ACK packets are not correct congestion signals because congestion might already disappear and the host may send more packets until it receives three duplicate ACK packets. Recently there are increasing interests in solving end-to-end congestion control using AQM(Active Queue Management) to improve the performance of TCP protocols. AQM is a variation of RED-based congestion control. In this paper, we first evaluate the effectiveness of the current AQM schemes such as RED, CHOKe, ARED, FRED and SRED, over traffic with different rates and over traffic with mixed responsive and non-responsive flows, respectively. In particular, CHOKe mechanism shows greater unfairness, especially when more unresponsive flows exist in a shared link. We then propose a new AQM scheme using CHOKe mechanism, called DQC(Double Queue CHOKe), which uses two FIFO queues before applying CHOKe mechanism to adaptive congestion control. Simulation shows that it works well in protecting congestion-sensitive flows from congestion-causing flows and exhibits better performances than other AQM schemes. Also we use partial state information, proposed in LRURED, to improve our mechanism.