• The Journal of Korean Institute of Next Generation Computing
• /
• v.15 no.5
• /
• pp.64-74
• /
• 2019

Although a non-rigid registration has high demands in clinical practice, it has a high computational complexity and it is very difficult for ensuring the accuracy and robustness of registration. This study proposes a method of applying a non-rigid registration to 3D magnetic resonance images of brain in an unsupervised learning environment by using a deep-learning network. A feature vector between two images is produced through the network by receiving both images from two different patients as inputs and it transforms the target image to match the source image by creating a displacement vector field. The network is designed based on a U-Net shape so that feature vectors that consider all global and local differences between two images can be constructed when performing the registration. As a regularization term is added to a loss function, a transformation result similar to that of a real brain movement can be obtained after the application of trilinear interpolation. This method enables a non-rigid registration with a single-pass deformation by only receiving two arbitrary images as inputs through an unsupervised learning. Therefore, it can perform faster than other non-learning-based registration methods that require iterative optimization processes. Our experiment was performed with 3D magnetic resonance images of 50 human brains, and the measurement result of the dice similarity coefficient confirmed an approximately 16% similarity improvement by using our method after the registration. It also showed a similar performance compared with the non-learning-based method, with about 10,000 times speed increase. The proposed method can be used for non-rigid registration of various kinds of medical image data.

• 한국노년학
• /
• v.40 no.2
• /
• pp.239-255
• /
• 2020

The purpose of this study is to examine whether family relationships of elderly single-person households affect community participation and whether these relationships differ by gender. Based on Baltes and Baltes (1990) 's selection, optimization, and compensation theory (SOC) and the argument that family members are a social capital by Prandini (2014), we test whether family relationships can affect community participation in old age. In order to verify this, single-person households were extracted from the 2017 National Survey of Living Conditions and Welfare Needs conducted by the Korea Institute for Health and Social Affairs (Male sample=370, Female sample=1770), multiple regression analysis were conducted with the dependent variables of friends·neighbors and the participation at Kyungrodang·welfare centers for the elderly. The results are as follows. In the case of men, family relations showed no significant effect on their participation in friends·neighbors, or Kyungrodang·welfare centers. However, in the case of women, the frequency of contact with family had a positive effect on the frequency of meeting friends·neighbors. Family contact frequency and child relationship satisfaction had a positive (+) effect on Kyungrodang·welfare center participation, while family meeting frequency had a negative effect on participation in Kyungrodang·welfare centers. For women, although Prandini's (2014) claim that family members are a social capital seems to be supported, it was found that the impact could vary depending on the type of community participation. In addition, practical discussions and suggestions were presented.

• Economic and Environmental Geology
• /
• v.56 no.3
• /
• pp.331-341
• /
• 2023

When creating a soil contamination map using geostatistical techniques, there are various sources that can affect prediction errors. In this study, a grid-based soil contamination map was created from the sampling data of heavy metal concentrations in soil in abandoned mine areas using Ordinary Kriging. Five factors that were judged to affect the prediction error of the soil contamination map were selected, and the variation of the root mean squared error (RMSE) between the predicted value and the actual value was analyzed based on the Leave-one-out technique. Then, using a machine learning algorithm, derived the top three factors affecting the RMSE. As a result, it was analyzed that Variogram Model, Minimum Neighbors, and Anisotropy factors have the largest impact on RMSE in the Standard interpolation. For the variogram models, the Spherical model showed the lowest RMSE, while the Minimum Neighbors had the lowest value at 3 and then increased as the value increased. In the case of Anisotropy, it was found to be more appropriate not to consider anisotropy. In this study, through the combined use of geostatistics and machine learning, it was possible to create a highly reliable soil contamination map at the local scale, and to identify which factors have a significant impact when interpolating a small amount of soil heavy metal data.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.11 no.4
• /
• pp.395-401
• /
• 2009

One of the key design factors for the ventilation and safety system at extra long tunnel is the airflow velocity induced by the natural ventilation force. Despite of the importance, it has not been widely studied due to the complicated influencing variables and the relationship among them is difficult to quantify. At this moment none of the countries in the world defines its specific value on verified ground. It is also the case in Korea. The recent worldwide disasters by tunnel fires and demands for better air quality inside tunnel by users require the optimization of the tunnel ventilation system. This indicates why the natural ventilation force is necessary to be thoroughly studied. This paper aims at predicting the natural ventilation force at a 11 km-long tunnel which is in the stage of detailed design and will be the longest vehicle tunnel in Korea. The concept of barometric barrier which can provide the maximum possible natural ventilation force generated by the topographic effect on the external wind is applied to estimate the effect of wind pressure and the chimney effect caused by the in and outside temperature difference is also analyzed.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.171-173
• /
• 2022

The 4th industrial revolution technology is developing people's lives more efficiently. GIS provided on the Internet services such as traffic information and time information makes people getting more quickly to destination. National geographic information service(NGIS) and each local government are making basic data to investigate SOC accessibility for analyzing optimal point. To construct the shortest distance, the accessibility from the starting point to the arrival point is analyzed. Applying road network map, the starting point and the ending point, the shortest distance, the optimal accessibility is calculated by using Dijkstra algorithm. The analysis information from multiple starting points to multiple destinations was required more than 3 steps of manual analysis to decide the position for the optimal point, within about 0.1% error. It took more time to process the many-to-many (M×N) calculation, requiring at least 32G memory specification of the computer. If an optimal proximity analysis service is provided at a desired location more versatile, it is possible to efficiently analyze locations that are vulnerable to business start-up and living facilities access, and facility selection for the public.

• Information Systems Review
• /
• v.16 no.3
• /
• pp.161-177
• /
• 2014

Corporate credit rating assessment consists of complicated processes in which various factors describing a company are taken into consideration. Such assessment is known to be very expensive since domain experts should be employed to assess the ratings. As a result, the data-driven corporate credit rating prediction using statistical and artificial intelligence (AI) techniques has received considerable attention from researchers and practitioners. In particular, statistical methods such as multiple discriminant analysis (MDA) and multinomial logistic regression analysis (MLOGIT), and AI methods including case-based reasoning (CBR), artificial neural network (ANN), and multiclass support vector machine (MSVM) have been applied to corporate credit rating.2) Among them, MSVM has recently become popular because of its robustness and high prediction accuracy. In this study, we propose a novel optimized MSVM model, and appy it to corporate credit rating prediction in order to enhance the accuracy. Our model, named 'GAMSVM (Genetic Algorithm-optimized Multiclass Support Vector Machine),' is designed to simultaneously optimize the kernel parameters and the feature subset selection. Prior studies like Lorena and de Carvalho (2008), and Chatterjee (2013) show that proper kernel parameters may improve the performance of MSVMs. Also, the results from the studies such as Shieh and Yang (2008) and Chatterjee (2013) imply that appropriate feature selection may lead to higher prediction accuracy. Based on these prior studies, we propose to apply GAMSVM to corporate credit rating prediction. As a tool for optimizing the kernel parameters and the feature subset selection, we suggest genetic algorithm (GA). GA is known as an efficient and effective search method that attempts to simulate the biological evolution phenomenon. By applying genetic operations such as selection, crossover, and mutation, it is designed to gradually improve the search results. Especially, mutation operator prevents GA from falling into the local optima, thus we can find the globally optimal or near-optimal solution using it. GA has popularly been applied to search optimal parameters or feature subset selections of AI techniques including MSVM. With these reasons, we also adopt GA as an optimization tool. To empirically validate the usefulness of GAMSVM, we applied it to a real-world case of credit rating in Korea. Our application is in bond rating, which is the most frequently studied area of credit rating for specific debt issues or other financial obligations. The experimental dataset was collected from a large credit rating company in South Korea. It contained 39 financial ratios of 1,295 companies in the manufacturing industry, and their credit ratings. Using various statistical methods including the one-way ANOVA and the stepwise MDA, we selected 14 financial ratios as the candidate independent variables. The dependent variable, i.e. credit rating, was labeled as four classes: 1(A1); 2(A2); 3(A3); 4(B and C). 80 percent of total data for each class was used for training, and remaining 20 percent was used for validation. And, to overcome small sample size, we applied five-fold cross validation to our dataset. In order to examine the competitiveness of the proposed model, we also experimented several comparative models including MDA, MLOGIT, CBR, ANN and MSVM. In case of MSVM, we adopted One-Against-One (OAO) and DAGSVM (Directed Acyclic Graph SVM) approaches because they are known to be the most accurate approaches among various MSVM approaches. GAMSVM was implemented using LIBSVM-an open-source software, and Evolver 5.5-a commercial software enables GA. Other comparative models were experimented using various statistical and AI packages such as SPSS for Windows, Neuroshell, and Microsoft Excel VBA (Visual Basic for Applications). Experimental results showed that the proposed model-GAMSVM-outperformed all the competitive models. In addition, the model was found to use less independent variables, but to show higher accuracy. In our experiments, five variables such as X7 (total debt), X9 (sales per employee), X13 (years after founded), X15 (accumulated earning to total asset), and X39 (the index related to the cash flows from operating activity) were found to be the most important factors in predicting the corporate credit ratings. However, the values of the finally selected kernel parameters were found to be almost same among the data subsets. To examine whether the predictive performance of GAMSVM was significantly greater than those of other models, we used the McNemar test. As a result, we found that GAMSVM was better than MDA, MLOGIT, CBR, and ANN at the 1% significance level, and better than OAO and DAGSVM at the 5% significance level.

• Journal of the Korean Society of Radiology
• /
• v.6 no.4
• /
• pp.281-290
• /
• 2012

The difference of radiation dose of MDCT due to different protocols between hospitals was analyzed by CTDI, DLP, the number of Slice and the number of DLP/Slice in 30 cases of the head, the abdomen and the chest that have 10 cases each from MDCT examination of the department of diagnostic imaging of three general hospitals in Gyeongsangbuk-do. The difference of image quality, CTDI, DLP, radiation dose in the eye and radiation dose in thyroid was analyzed after both helical scan and normal scan for head CT were performed because a protocol of head CT is relatively simple and head CT is the most frequent case. Head CT was significantly higher in two-thirds of hospitals compared to A hospital that does not exceed a CTDI diagnostic reference level (IAEA 50mGy, Korea 60mGy) (p<0.001). DLP was higher in one-third of hospitals than a diagnostic reference level of IAEA 1,050mGy.cm and Korea 1,000mGy.cm and two-thirds exceeded the recommendation of Korea and those were significantly higher than A hospital that does not exceed a diagnostic reference level (p<0.001). Abdomen CT showed 119mGy that was higher than a diagnostic reference level of IAEA 25mGy and Korea 20mGy in one-third. DLP in all hospitals was higher that Korea recommendation of 700mGy.cm. Among target hospitals, C hospital showed high radiation dose in all tests because MPR and 3D were of great importance due to low pitch and high Tube Curren. To analyze the difference of radiation dose by scan methods, normal scan and helical scan for head CT of the same patient were performed. In the result, CTDI and DLP of helical CT were higher 63.4% and 93.7% than normal scan (p<0.05, p<0.01). However, normal scan of radiation dose in thyroid was higher 87.26% (p<0.01). Beam of helical CT looked like a bell in the deep part and the marginal part so thyroid was exposed with low radiation dose deviated from central beam. In addition, helical scan used Gantry angle perpendicularly and normal scan used it parallel to the orbitomeatal line. Therefore, radiation dose in thyroid decreased in helical scan. However, a protocol in this study showed higher radiation dose than diagnostic reference level of KFDA. To obey the recommendation of KFDA, low Tube Curren and high pitch were demanded. In this study, the difference of image quality between normal scan and helical scan was not significant. Therefore, a standardized protocol of normal scan was generally used and protective gear for thyroid was needed except a special case. We studied a part of CT cases in the local area. Therefore, the result could not represent the entire cases. However, we confirmed that patient's radiation dose in some cases exceeded the recommendation and the deviation between hospitals was observed. To improve this issue, doctors of diagnostic imaging or technologists of radiology should perform CT by the optimized protocol to decrease a level of CT radiation and also reveal radiation dose for the right to know of patients. However, they had little understanding of the situation. Therefore, the effort of relevant agencies with education program for CT radiation dose, release of radiation dose from CT examination and addition of radiation dose control and open CT contents into evaluation for hospital services and certification, and also the effort of health professionals with the best protocol to realize optimized CT examination.

• Journal of Intelligence and Information Systems
• /
• v.25 no.4
• /
• pp.53-65
• /
• 2019

Object tracking is one of important steps to achieve video-based surveillance systems. Object tracking is considered as an essential task similar to object detection and recognition. In order to perform object tracking, various machine learning methods (e.g., least-squares, perceptron and support vector machine) can be applied for different designs of tracking systems. In general, generative methods (e.g., principal component analysis) were utilized due to its simplicity and effectiveness. However, the generative methods were only focused on modeling the target object. Due to this limitation, discriminative methods (e.g., binary classification) were adopted to distinguish the target object and the background. Among the machine learning methods for binary classification, total error rate minimization can be used as one of successful machine learning methods for binary classification. The total error rate minimization can achieve a global minimum due to a quadratic approximation to a step function while other methods (e.g., support vector machine) seek local minima using nonlinear functions (e.g., hinge loss function). Due to this quadratic approximation, the total error rate minimization could obtain appropriate properties in solving optimization problems for binary classification. However, this total error rate minimization was based on a batch mode setting. The batch mode setting can be limited to several applications under offline learning. Due to limited computing resources, offline learning could not handle large scale data sets. Compared to offline learning, online learning can update its solution without storing all training samples in learning process. Due to increment of large scale data sets, online learning becomes one of essential properties for various applications. Since object tracking needs to handle data samples in real time, online learning based total error rate minimization methods are necessary to efficiently address object tracking problems. Due to the need of the online learning, an online learning based total error rate minimization method was developed. However, an approximately reweighted technique was developed. Although the approximation technique is utilized, this online version of the total error rate minimization could achieve good performances in biometric applications. However, this method is assumed that the total error rate minimization can be asymptotically achieved when only the number of training samples is infinite. Although there is the assumption to achieve the total error rate minimization, the approximation issue can continuously accumulate learning errors according to increment of training samples. Due to this reason, the approximated online learning solution can then lead a wrong solution. The wrong solution can make significant errors when it is applied to surveillance systems. In this paper, we propose an exactly reweighted technique to recursively update the solution of the total error rate minimization in online learning manner. Compared to the approximately reweighted online total error rate minimization, an exactly reweighted online total error rate minimization is achieved. The proposed exact online learning method based on the total error rate minimization is then applied to object tracking problems. In our object tracking system, particle filtering is adopted. In particle filtering, our observation model is consisted of both generative and discriminative methods to leverage the advantages between generative and discriminative properties. In our experiments, our proposed object tracking system achieves promising performances on 8 public video sequences over competing object tracking systems. The paired t-test is also reported to evaluate its quality of the results. Our proposed online learning method can be extended under the deep learning architecture which can cover the shallow and deep networks. Moreover, online learning methods, that need the exact reweighting process, can use our proposed reweighting technique. In addition to object tracking, the proposed online learning method can be easily applied to object detection and recognition. Therefore, our proposed methods can contribute to online learning community and object tracking, detection and recognition communities.

• Korean Journal of Remote Sensing
• /
• v.36 no.6_1
• /
• pp.1465-1483
• /
• 2020

Evapotranspiration is a concept that includes the evaporation from soil and the transpiration from the plant leaf. It is an essential factor for monitoring water balance, drought, crop growth, and climate change. Actual evapotranspiration (AET) corresponds to the consumption of water from the land surface and the necessary amount of water for the land surface. Because the AET is derived from multiplying the crop coefficient by the reference evapotranspiration (ET0), an accurate calculation of the ET0 is required for the AET. To date, many efforts have been made for gridded ET0 to provide multiple products now. This study presents a comparison between the ET0 products such as FAO56-PM, LDAPS, PKNU-NMSC, and MODIS to find out which one is more suitable for the local-scale hydrological and agricultural applications in Korea, where the heterogeneity of the land surface is critical. In the experiment for the period between 2016 and 2019, the daily and 8-day products were compared with the in-situ observations by KMA. The analyses according to the station, year, month, and time-series showed that the PKNU-NMSC product with a successful optimization for Korea was superior to the others, yielding stable accuracy irrespective of space and time. Also, this paper showed the intrinsic characteristics of the FAO56-PM, LDAPS, and MODIS ET0 products that could be informative for other researchers.

• Journal of Appropriate Technology
• /
• v.7 no.2
• /
• pp.127-135
• /
• 2021

To respond to the threat of global warming, countries around the world are promoting the spread of renewable energy and reduction of carbon emissions. In accordance with the United Nation's Sustainable Development Goal to combat climate change and its impacts, global automakers are pushing for a full transition to electric vehicles within the next 10 years. Electric vehicles can be a useful means for reducing carbon emissions, but in order to reduce carbon generated in the stage of producing electricity for charging, a power generation system using eco-friendly renewable energy is required. In this study, we propose a smart electric mobility operating system integrated with off-grid solar power plants established in Tanzania, Africa. By applying smart monitoring and communication functions based on Arduino-based computing devices, information such as remaining battery capacity, battery status, location, speed, altitude, and road conditions of an electric vehicle or electric motorcycle is monitored. In addition, we present a scenario that communicates with the surrounding independent solar power plant infrastructure to predict the drivable distance and optimize the charging schedule and route to the destination. The feasibility of the proposed system was verified through test runs of electric motorcycles. In considering local environmental characteristics in Tanzania for the operation of the electric mobility system, factors such as eco-friendliness, economic feasibility, ease of operation, and compatibility should be weighed. The smart electric mobility operating system proposed in this study can be an important basis for implementing the SDGs' climate change response.