• The Journal of Korean Society for Radiation Therapy
• /
• v.17 no.1
• /
• pp.57-71
• /
• 2005

Purpose : To evaluate radiation dose and accuracy with TLD and diode detector when treat total skin with electron beam. Materials and Methods : Using Stanford Technique, we treated patient with Mycosis Fungoides. 6 MeV electron beam of LINAC was used and the SSD was 300 cm. Also, acrylic speller(0.8 cm) was used. The patient position was 6 types and the gantry angle was 64, 90 and $116^{\circ}$. The patient's skin dose and the output were detected 5 to 6 times with TLD and diode. Result : The deviations of dose detected with TLD from tumor dose were CA $+\;6\%$, thigh $+\;8\%$, umbilicus $+\;4\%$, calf $-\;8\%$, vertex $-\;74.4\%$, deep axillae $-\;10.2\%$, anus and testis $-\;87\%$, sole $-\;86\%$ and nails shielded with 4mm lead $+4\%$. The deviations of dose detected with diode were $-4.5\%{\sim}+5\%$ at the patient center and $-1.1\%{\sim}+1\%$ at the speller. Conclusion : The deviation of total skin dose was $+\;8\%{\sim}-\;8\%$ and that deviation was within the acceptable range(${\pm}\;10\%$). The boost dose was irradiated for the low dose areas(vertex, anus, sole). The electron beam output detected at the sootier was stable. It is thought that the deviation of dose at patient center detected with diode was induced by detection point and patient position.

• Journal of Korea Technology Innovation Society
• /
• v.10 no.4
• /
• pp.654-686
• /
• 2007

To estimate and analyze an interested science and technology level in any case requires three basic informations: (1) relative positions of our technology level, (2) other relevant technology level of the world best country holding the state of the art technology, and (3) its theoretical or practical maximum level within a certain period of time. Further, additional information from analyzing its respective rate of technology changes is necessary. It seems that most previous empirical or case studies on technology level have not considered third and fourth informations seriously, and thus critically have missed important findings from a dynamic point of view on the matter. A dynamic approach considering types of development processes and paths as well as current position needs an application of a concept of technology development stages and respective growth curves. This paper proposes a new method of approach and application by implementing relatively simple types of the growth curve(S-curve) such as logistic and Comports curves and applying estimation results of these curves to ten core technologies of the growth engines for the next future generation in Korea. The study implies that Korean science and technology level in general clearly gets higher as it approaches to a recent time of period, but relative technology gap from the world best in terms of catching-up period does not get better or narrower in case of at least part of the concerned technologies such as bio new drugs and human organs, and intelligence robots. The possibility does exist that some of our concerned technologies shooting for the next future generation may not come to the world highest level in the near future. The purpose of this study is to propose possibilities of catching-up, if any, by estimating its relevant type of growth pattern by way of measuring and analyzing technology level and by analyzing the technology development process through a position analysis. At this stage this study tries to introduce a new theoretical approach of estimating technology level and its application to existing case study results(data) from Korea Institute of Science and Technology Planning and Evaluation(KISTEP) and Korea Institute of Industrial Technology Evaluation and Planing(ITEP), for years of 2004 and 2006 respectively. The study has some limitations in terms of accuracy of measuring(estimating) a relevant growth curve to a particular technology, feasibility of applying estimated results, accessing and analyzing panel experts opinions. Hence, it is recommended that further study would follow soon enough to verify practical applicability and possible expansion of the study results.

• Journal of Intelligence and Information Systems
• /
• v.22 no.4
• /
• pp.177-192
• /
• 2016

Machine learning is a field of artificial intelligence. It refers to an area of computer science related to providing machines the ability to perform their own data analysis, decision making and forecasting. For example, one of the representative machine learning models is artificial neural network, which is a statistical learning algorithm inspired by the neural network structure of biology. In addition, there are other machine learning models such as decision tree model, naive bayes model and SVM(support vector machine) model. Among the machine learning models, we use SVM model in this study because it is mainly used for classification and regression analysis that fits well to our study. The core principle of SVM is to find a reasonable hyperplane that distinguishes different group in the data space. Given information about the data in any two groups, the SVM model judges to which group the new data belongs based on the hyperplane obtained from the given data set. Thus, the more the amount of meaningful data, the better the machine learning ability. In recent years, many financial experts have focused on machine learning, seeing the possibility of combining with machine learning and the financial field where vast amounts of financial data exist. Machine learning techniques have been proved to be powerful in describing the non-stationary and chaotic stock price dynamics. A lot of researches have been successfully conducted on forecasting of stock prices using machine learning algorithms. Recently, financial companies have begun to provide Robo-Advisor service, a compound word of Robot and Advisor, which can perform various financial tasks through advanced algorithms using rapidly changing huge amount of data. Robo-Adviser's main task is to advise the investors about the investor's personal investment propensity and to provide the service to manage the portfolio automatically. In this study, we propose a method of forecasting the Korean volatility index, VKOSPI, using the SVM model, which is one of the machine learning methods, and applying it to real option trading to increase the trading performance. VKOSPI is a measure of the future volatility of the KOSPI 200 index based on KOSPI 200 index option prices. VKOSPI is similar to the VIX index, which is based on S&P 500 option price in the United States. The Korea Exchange(KRX) calculates and announce the real-time VKOSPI index. VKOSPI is the same as the usual volatility and affects the option prices. The direction of VKOSPI and option prices show positive relation regardless of the option type (call and put options with various striking prices). If the volatility increases, all of the call and put option premium increases because the probability of the option's exercise possibility increases. The investor can know the rising value of the option price with respect to the volatility rising value in real time through Vega, a Black-Scholes's measurement index of an option's sensitivity to changes in the volatility. Therefore, accurate forecasting of VKOSPI movements is one of the important factors that can generate profit in option trading. In this study, we verified through real option data that the accurate forecast of VKOSPI is able to make a big profit in real option trading. To the best of our knowledge, there have been no studies on the idea of predicting the direction of VKOSPI based on machine learning and introducing the idea of applying it to actual option trading. In this study predicted daily VKOSPI changes through SVM model and then made intraday option strangle position, which gives profit as option prices reduce, only when VKOSPI is expected to decline during daytime. We analyzed the results and tested whether it is applicable to real option trading based on SVM's prediction. The results showed the prediction accuracy of VKOSPI was 57.83% on average, and the number of position entry times was 43.2 times, which is less than half of the benchmark (100 times). A small number of trading is an indicator of trading efficiency. In addition, the experiment proved that the trading performance was significantly higher than the benchmark.

• Nuclear Medicine and Molecular Imaging
• /
• v.41 no.3
• /
• pp.234-240
• /
• 2007

Purpose: In this study we propose a block-iterative method for reconstructing Compton scattered data. This study shows that the well-known expectation maximization (EM) approach along with its accelerated version based on the ordered subsets principle can be applied to the problem of image reconstruction for Compton camera. This study also compares several methods of constructing subsets for optimal performance of our algorithms. Materials and Methods: Three reconstruction algorithms were implemented; simple backprojection (SBP), EM, and ordered subset EM (OSEM). For OSEM, the projection data were grouped into subsets in a predefined order. Three different schemes for choosing nonoverlapping subsets were considered; scatter angle-based subsets, detector position-based subsets, and both scatter angle- and detector position-based subsets. EM and OSEM with 16 subsets were performed with 64 and 4 iterations, respectively. The performance of each algorithm was evaluated in terms of computation time and normalized mean-squared error. Results: Both EM and OSEM clearly outperformed SBP in all aspects of accuracy. The OSEM with 16 subsets and 4 iterations, which is equivalent to the standard EM with 64 iterations, was approximately 14 times faster in computation time than the standard EM. In OSEM, all of the three schemes for choosing subsets yielded similar results in computation time as well as normalized mean-squared error. Conclusion: Our results show that the OSEM algorithm, which have proven useful in emission tomography, can also be applied to the problem of image reconstruction for Compton camera. With properly chosen subset construction methods and moderate numbers of subsets, our OSEM algorithm significantly improves the computational efficiency while keeping the original quality of the standard EM reconstruction. The OSEM algorithm with scatter angle- and detector position-based subsets is most available.

• Journal of radiological science and technology
• /
• v.31 no.4
• /
• pp.389-399
• /
• 2008

Corrections of attenuation, scatter and resolution are important in order to improve the accuracy of single photon emission computed tomography (SPECT) image reconstruction. Especially, the heart movement by respiration and beating cause the errors in the corrections. Myocardial phantom is used to verify the correction methods, but there are many different parts in the current phantoms in actual human body. Therefore the results using a phantom are often considered apart from the clinical data. We developed a new phantom that implements the human body structure around the thorax more faithfully. The new phantom has the small mediastinum which can simulate the structure in which the lung adjoins anterior, lateral and apex of myocardium. The container was made of acrylic and water-equivalent material was used for mediastinum. In addition, solidified polyurethane foam in epoxy resin was used for lung. Five different sizes of myocardium were developed for the quantitative gated SPECT (QGS). The septa of all different cardiac phantoms were designed so that they can be located at the same position. The proposed phantom was attached with liver and gallbladder, the adjustment was respectively possible for the height of them. The volumes of five cardiac ventricles were 150.0, 137.3, 83.1, 42.7 and 38.6ml respectively. The SPECT were performed for the new phantom, and the differences between the images were examined after the correction methods were applied. The three-dimensional tomography of myocardium was well reconstructed, and the subjective evaluations were done to show the difference among the various corrections. We developed the new cardiac and torso phantom, and the difference of various corrections was shown on SPECT images and QGS results.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.19 no.1
• /
• pp.95-107
• /
• 2017

In this study, a preliminary study was undertaken for development of a tunnel incident automatic detection system based on a machine learning algorithm which is to detect a number of incidents taking place in tunnel in real time and also to be able to identify the type of incident. Two road sites where CCTVs are operating have been selected and a part of CCTV images are treated to produce sets of training data. The data sets are composed of position and time information of moving objects on CCTV screen which are extracted by initially detecting and tracking of incoming objects into CCTV screen by using a conventional image processing technique available in this study. And the data sets are matched with 6 categories of events such as lane change, stoping, etc which are also involved in the training data sets. The training data are learnt by a resilience neural network where two hidden layers are applied and 9 architectural models are set up for parametric studies, from which the architectural model, 300(first hidden layer)-150(second hidden layer) is found to be optimum in highest accuracy with respect to training data as well as testing data not used for training. From this study, it was shown that the highly variable and complex traffic and incident features could be well identified without any definition of feature regulation by using a concept of machine learning. In addition, detection capability and accuracy of the machine learning based system will be automatically enhanced as much as big data of CCTV images in tunnel becomes rich.

• The korean journal of orthodontics
• /
• v.33 no.1 s.96
• /
• pp.1-9
• /
• 2003

The purpose of this study was to find out and evaluate discrepancies between preorthodontic prediction values and actual postorthodontic values and factors contributing to it in 45 patients(17 male, 28 female) who were diagnosed as skeletal Class III ma)occlusion and received presurgical orthodontic treatment and orthognathic surgery at Yonsei university dental hospital. Lateral cephalograms were analysed at pretreatment(T1), orthodontic Prediction(T2), immediately before surgery(T3) and designated the landmark as coordinates or X and Y axes. The samples were divided according to ALD, upper and lower incisor inclination(Ul to SN, IMPA), COS, extraction, the position of extracted teeth and the statistical significance was tested to find out the factors contributing to the prediction. The results were as follows: 1. Differences between preorthodontic prediction values and actual postorthodontic values(T2-T3) were statistically significant(p<0.05) in the x coordinates of U6mbc, L1x and in y coordinates of U1i, U1x, U6me, U6mbc, L6mbc 2. The accuracy of prediction is relatively higher in horizontal changes compared to vortical changes. 3. The statistical significance(p<0.05) between prediction and actual values is observed more in the landmarks of the maxilla than the mandible. 4. Differences between prediction and actual values of incisor and first molar were statistically significant(p<0.05) according to extraction vs non-extraction, extraction type, ALD in the maxilla and according to ALD, IMPA in the mandible. Discrepancies between preorthodontic prediction values and actual postorthodontic values and factors contributing to the prediction must be considered in treatment planning of Cl III surgical patients to increase the accuracy of prediction. Furthermore future investigations are needed on the prediction of vortical changes.

• The Journal of Korean Society for Radiation Therapy
• /
• v.19 no.1
• /
• pp.1-5
• /
• 2007

Purpose: The accuracy and advantages of OBI(On Board Imager) against the conventional method like film and EPID for the setup error correction were evaluated with the analysis of the accumulated data which were produced in the process of setup error correction using OBI. Materials and Methods: The results of setup error correction using OBI system were analyzed for the 130 patients who had been planned for 3 dimensional conformal radiation therapy during March 2006 and May 2006. Two kilo voltage images acquired in the orthogonal direction were fused and compared with reference setup images. The setup errors in the direction of vertical, lateral, longitudinal axis were recorded and calculated the distance from the isocenter. The corrected setup error were analyzed according to the lesion and the degree of shift variations. Results: There was no setup error in the 41.5% of total analyzed patients and setup errors between 1mm and 5mm were found in the 52.3%. 6.1% patients showed the more than 5mm shift and this error were verified as a difference of setup position and the movement of patient in a treatment room. Conclusion: The setup error analysis using OBI in this study verified that the conventional setup process in accordance with the laser and field light was not enough to get rid of the setup error. The KV images acquired using OBI provided good image quality for comparing with simulation images and much lower patients' exposure dose compared with conventional method of using EPID. These advantages of OBI system which were confirmed in this study proved the accuracy and priority of OBI system in the process of IGRT(Image Guided Radiation Therapy).

• Radiation Oncology Journal
• /
• v.26 no.3
• /
• pp.189-194
• /
• 2008

Purpose: We designed a water-based bolus device for radiation therapy in Kaposi's sarcoma. This study evaluated the usefulness of this new device and compared it with the currently used rice-based bolus. Materials and Methods: We fashioned a polystyrene box and cut a hole in order to insert patient's extremities while the patient was in the supine position. We used a vacuum-vinyl based polymer to reduce water leakage. Next, we eliminated air using a vacuum pump and a vacuum valve to reduce the air gap between the water and extremities in the vacuum-vinyl box. We performed CT scans to evaluate the density difference of the fabricated water-based bolus device when the device in which the rice-based bolus was placed directly, the rice-based bolus with polymer-vinyl packed rice, and the water were all put in. We analyzed the density change with the air gap volume using a planning system. In addition, we measured the homogeneity and dose in the low-extremities phantom, attached to six TLD, and wrapped film exposed in parallel-opposite fields with the LINAC under the same conditions as the set-up of the CT-simulator. Results: The density value of the rice-based bolus with the rice put in directly was 14% lower than that of the water-based bolus. Moreover, the value of the other experiments in the rice-based bolus with the polymer-vinyl packed rice showed an 18% reduction in density. The analysis of the EDR2 film revealed that the water-based bolus shows a more homogeneous dose plan, which was superior by $4{\sim}4.4%$ to the rice-base bolus. The mean TLD readings of the rice-based bolus, with the rice put directly into the polystyrene box had a 3.4% higher density value. Moreover, the density value in the case of the rice-based bolus with polymer-vinyl packed rice had a 4.3% higher reading compared to the water-based bolus. Conclusion: Our custom-made water-based bolus device increases the accuracy of the set-up by confirming the treatment field. It also improves the accuracy of the therapy owing to the reduction of the air gap using a vacuum pump and a vacuum valve. This set-up represents a promising alternative device for delivering a homogenous dose to the target volume.

• Journal of Nuclear Fuel Cycle and Waste Technology(JNFCWT)
• /
• v.18 no.1
• /
• pp.51-62
• /
• 2020

This study was conducted to develop a method for depth assessment of embedded sources using gamma-spectrum ratio and for the evaluation of field applicability. To this end, Peak to Compton and Peak to valley ratio changes were evaluated according to ¹³⁷Cs, ⁶⁰Co, ¹⁵²Eu point source depth using HPGe detector and MCNP simulation. The effects of measurement distance of PTV and PTC methods were evaluated. Using the results, the source depth assessment equation using the PTC and PTV methods was derived based on the detection distance of 50 cm. In addition, the sensitivity of detection distance changes was assessed when using PTV and PTC methods, and error increased by 3 to 4 cm when detection distance decreased by 20 cm based on 50 cm. However, it was confirmed that if the detection distance was increased to 100 cm, the effects of detection distance were small. And PTV and PTC methods were compared with the two distance measurement method which evaluates the depth of source by the change of net peak counting rate according to the detection distance. As a result of source depth assessment, the PTV and PTC showed a maximum error of 1.87 cm and the two distance measurement method showed maximum error of 2.69 cm. The results of the experiment confirmed that the accuracy of the PTV and PTC methods was higher than two distance measurement. In addition, Sensitivity evaluation by horizontal position error of source has maximum error of less than 25.59 cm for the two distance measurement method. On the other hand, PTV and PTC method showed high accuracy with maximum error of less than 8.04 cm. In addition, the PTC method has lowest standard deviation for the same time measurement, which is expected to enable rapid measurement.