Publish in OALib Journal

ISSN: 2333-9721

APC: Only $99


Any time

2020 ( 5 )

2019 ( 39 )

2018 ( 142 )

2017 ( 170 )

Custom range...

Search Results: 1 - 10 of 19205 matches for " Ji Won Yoon "
All listed articles are free for downloading (OA Articles)
Page 1 /19205
Display every page Item
An Efficient Model Selection for Gaussian Mixture Model in a Bayesian Framework
Ji Won Yoon
Computer Science , 2013,
Abstract: In order to cluster or partition data, we often use Expectation-and-Maximization (EM) or Variational approximation with a Gaussian Mixture Model (GMM), which is a parametric probability density function represented as a weighted sum of $\hat{K}$ Gaussian component densities. However, model selection to find underlying $\hat{K}$ is one of the key concerns in GMM clustering, since we can obtain the desired clusters only when $\hat{K}$ is known. In this paper, we propose a new model selection algorithm to explore $\hat{K}$ in a Bayesian framework. The proposed algorithm builds the density of the model order which any information criterions such as AIC and BIC basically fail to reconstruct. In addition, this algorithm reconstructs the density quickly as compared to the time-consuming Monte Carlo simulation.
Statistical Denoising for single molecule fluorescence microscopic images
Ji Won Yoon
Computer Science , 2013,
Abstract: Single molecule fluorescence microscopy is a powerful technique for uncovering detailed information about biological systems, both in vitro and in vivo. In such experiments, the inherently low signal to noise ratios mean that accurate algorithms to separate true signal and background noise are essential to generate meaningful results. To this end, we have developed a new and robust method to reduce noise in single molecule fluorescence images by using a Gaussian Markov Random Field (GMRF) prior in a Bayesian framework. Two different strategies are proposed to build the prior - an intrinsic GMRF, with a stationary relationship between pixels and a heterogeneous intrinsic GMRF, with a differently weighted relationship between pixels classified as molecules and background. Testing with synthetic and real experimental fluorescence images demonstrates that the heterogeneous intrinsic GMRF is superior to other conventional de-noising approaches.
Efficient Estimation of the number of neighbours in Probabilistic K Nearest Neighbour Classification
Ji Won Yoon,Nial Friel
Computer Science , 2013,
Abstract: Probabilistic k-nearest neighbour (PKNN) classification has been introduced to improve the performance of original k-nearest neighbour (KNN) classification algorithm by explicitly modelling uncertainty in the classification of each feature vector. However, an issue common to both KNN and PKNN is to select the optimal number of neighbours, $k$. The contribution of this paper is to incorporate the uncertainty in $k$ into the decision making, and in so doing use Bayesian model averaging to provide improved classification. Indeed the problem of assessing the uncertainty in $k$ can be viewed as one of statistical model selection which is one of the most important technical issues in the statistics and machine learning domain. In this paper, a new functional approximation algorithm is proposed to reconstruct the density of the model (order) without relying on time consuming Monte Carlo simulations. In addition, this algorithm avoids cross validation by adopting Bayesian framework. The performance of this algorithm yielded very good performance on several real experimental datasets.
How to Compare the Scientific Contributions between Research Groups
Hyoungshick Kim,Ji Won Yoon
Computer Science , 2009,
Abstract: We present a method to analyse the scientific contributions between research groups. Given multiple research groups, we construct their journal/proceeding graphs and then compute the similarity/gap between them using network analysis. This analysis can be used for measuring similarity/gap of the topics/qualities between research groups' scientific contributions. We demonstrate the practicality of our method by comparing the scientific contributions by Korean researchers with those by the global researchers for information security in 2006 - 2008. The empirical analysis shows that the current security research in South Korea has been isolated from the global research trend.
Non-degenerate quadric surfaces in Euclidean 3-space
Dae Won Yoon,Ji Soon Jun
International Journal of Mathematical Analysis , 2012,
A data mining approach using transaction patterns for card fraud detection
Chae Chang Lee,Ji Won yoon
Computer Science , 2013,
Abstract: Credit and debit cards, rather than actual money, have become the universal payment means. With these cards, it has become possible to buy expensive items easily without an additional complex authentication procedure being conducted. However, card transaction features are targeted by criminals seeking to use a lost or stolen card and looking for a chance to replicate it. Accidents, whether caused by the negligence of users or not, that lead to a transaction being performed by a criminal rather than the authorized card user should be prevented. Therefore, card companies are providing their clients with a variety of policies and standards to cover this eventuality. Card companies must therefore be able to distinguish between the rightful user and illegal users according to these standards in order to minimize damage resulting from unauthorized transactions. However, there is a limit to applying the same fixed standards to all card users, since the transaction patterns of people differ and even individuals' transaction patterns may change frequently due to changes income and consumption preference. Therefore, when only a specific threshold is applied, it is difficult to distinguish a fraudulent card transaction from a legitimate one. In this paper, we present methods for learning the individual patterns of a card user's transaction amount and the region in which he or she uses the card, for a given period, and for determining whether the specified transaction is allowable in accordance with these learned user transaction patterns. Then, we classify legitimate transactions and fraudulent transactions by setting thresholds based on the learned individual patterns.
Hybrid Spam Filtering for Mobile Communication
Ji Won Yoon,Hyoungshick Kim,Jun Ho Huh
Computer Science , 2009,
Abstract: Spam messages are an increasing threat to mobile communication. Several mitigation techniques have been proposed, including white and black listing, challenge-response and content-based filtering. However, none are perfect and it makes sense to use a combination rather than just one. We propose an anti-spam framework based on the hybrid of content-based filtering and challenge-response. There is the trade-offs between accuracy of anti-spam classifiers and the communication overhead. Experimental results show how, depending on the proportion of spam messages, different filtering %%@ parameters should be set.
Metastasis to the gallbladder: A single-center experience of 20 cases in South Korea
Won Jae Yoon, Yong Bum Yoon, Youn Joo Kim, Ji Kon Ryu, Yong-Tae Kim
World Journal of Gastroenterology , 2009,
Abstract: AIM: To evaluate the clinicopathologic characteristics of patients with metastases to the gallbladder (MGBs).METHODS: We performed a single-center retrospective study of 20 patients with MGBs diagnosed pathologically from 1999 to 2007.RESULTS: Among 417 gallbladder (GB) malignancies, 20 (4.8%) were MGBs. The primary malignancies originated from the stomach (n = 8), colorectum (n = 3), liver (n = 2), kidney (n = 2), skin (n = 2), extrahepatic bile duct (n = 1), uterine cervix (n = 1), and appendix (n = 1). Twelve patients were diagnosed metachronously, presenting with cholecystitis (n = 4), abdominal pain (n = 2), jaundice (n = 1), weight loss (n = 1), and serum CA 19-9 elevation (n = 1); five patients were asymptomatic. The median survival after the diagnosis of MGB was 8.7 mo. On Cox regression analysis, R0 resection was the only factor associated with a prolonged survival [hazard ratio (HR): 0.01, P = 0.002]; presentation with cholecystitis was associated with poor survival (HR: 463.27, P = 0.006).CONCLUSION: MGBs accounted for 4.8% of all pathologically diagnosed GB malignancies. The most common origin was the stomach. The median survival of MGB was 8.7 mo.
Endoscopic management of occluded metal biliary stents: Metal versus 10F plastic stents
Won Jae Yoon, Ji Kon Ryu, Jung Won Lee, Dong-Won Ahn, Yong-Tae Kim, Yong Bum Yoon, Sang Myung Woo, Woo Jin Lee
World Journal of Gastroenterology , 2010,
Abstract: AIM: To compare the efficacy of self-expandable metal stents (SEMSs) with 10F plastic stents (PSs) in the endoscopic management of occluded SEMSs.METHODS: We retrospectively reviewed the medical records of 56 patients who underwent SEMS insertion for palliation of unresectable malignant biliary obstruction between 2000 and 2007 and subsequent endoscopic retrograde biliary drainage (ERBD) with SEMS or PS for initial SEMS occlusion between 2000 and 2008.RESULTS: Subsequent ERBD with SEMS was performed in 29 patients and with PS in 27. The median time to stent occlusion after subsequent ERBD was 186 d in the SEMS group and 101 d in the PS group (P = 0.118). Overall median stent patency was 79 d for the SEMS group and 66 d for the PS group (P = 0.379). The mean number of additional biliary drainage procedures after subsequent ERBD in patients that died (n = 50) during the study period was 2.54 ± 4.12 for the SEMS group and 1.85 ± 1.95 for the PS group (P = 0.457). The mean total cost of additional biliary drainage procedures after the occlusion of subsequent SEMS or PS was $410.04 ± 692.60 for the SEMS group and $630.16 ± 671.63 for the PS group (P = 0.260). Tumor ingrowth as the cause of initial SEMS occlusion was the only factor associated with a shorter time to subsequent stent occlusion (101 d for patients with tumor ingrowth vs 268 d for patients without tumor ingrowth, P = 0.008).CONCLUSION: Subsequent ERBD with PSs offered similar patency and number of additional biliary drainage procedures compared to SEMSs in the management of occluded SEMS.
Hypofractionated radiotheapy using helical tomotherapy for advanced hepatocellular carcinoma with portal vein tumor thrombosis
Kim Ji-Yoon,Yoo Eun-Jung,Jang Jeong-Won,Kwon Jung-Hyun
Radiation Oncology , 2013, DOI: 10.1186/1748-717x-8-15
Abstract: Background We want to evaluate the efficacy of helical tomotherapy (HT) for treating advanced hepatocellular carcinoma (HCC) with portal vein tumor thrombosis (PVTT). Methods We treated 35 patients for unresectable HCC combined with PVTT in whom other treatment modalities were not indicated. The tumor thrombi involved the main trunk of the portal vein in 18 patients (51.4%) and the first or second order branches in 17 patients (48.6%). A median dose of 50 Gy (range: 45–60 Gy) was delivered in 10 fractions. Capecitabine was given concomitantly at a dose of 600 mg/m2 twice daily during radiotherapy. Results The responses were evaluated via computed tomography. There was a complete response (CR) in 5 patients (14.3%), partial response (PR) in 10 patients (28.6%), stable disease (SD) in 18 patients (51.4%) and progressive disease (PD) in 2 patients (5.7%). The Child-Pugh classification (A vs B) and the Japan integrated staging (JIS) score (2 vs 3) were statistically significant parameters that predicted the response of PVTT (p = 0.010 and p = 0.026, respectively). The median survival, one and two year survival rate of all patients was 12.9 months, 51.4% and 22.2%, respectively. The patients with tumor thrombi in the main portal trunk showed statistically inferior overall survival than patients with tumor thrombi in the portal vein branches (9.8 versus 16.6 months, respectively, p = 0.036). The responders’ median survival was 13.9 months, double 6.9 months as the median survival of the non-responders. No radiation induced liver disease or treatment related mortality was not appeared. Conclusions Hypofractionated radiotherapy with HT was effective not only for tumor response but also for survival in the advanced HCC patients with PVTT. And stricter patient selection by Child-Pugh classification and JIS score may maximize the potential benefits of this treatment.
Page 1 /19205
Display every page Item

Copyright © 2008-2017 Open Access Library. All rights reserved.