• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.3
• /
• pp.77-90
• /
• 2018

Software Defect Prediction (SDP) is a field of study that identifies defective modules. With insufficient local data, a company can exploit Cross-Project Defect Prediction (CPDP), a way to build a classifier using dataset collected from other companies. Most machine learning algorithms for SDP have used more than one parameter that significantly affects prediction performance depending on different values. The objective of this study is to propose a parameter selection technique to enhance the performance of CPDP. Using a Harmony Search algorithm (HS), our approach tunes parameters of cost-sensitive boosting, a method to tackle class imbalance causing the difficulty of prediction. According to distributional characteristics, parameter ranges and constraint rules between parameters are defined and applied to HS. The proposed approach is compared with three CPDP methods and a Within-Project Defect Prediction (WPDP) method over fifteen target projects. The experimental results indicate that the proposed model outperforms the other CPDP methods in the context of class imbalance. Unlike the previous researches showing high probability of false alarm or low probability of detection, our approach provides acceptable high PD and low PF while providing high overall performance. It also provides similar performance compared with WPDP.

• Clinical and Experimental Pediatrics
• /
• v.56 no.6
• /
• pp.247-253
• /
• 2013

Purpose: In children with acute leukemia, bone marrow genetic abnormalities (GA) have prognostic significance, and may be the basis for minimal residual disease monitoring. Since April 2007, we have used a multiplex reverse transcriptase-polymerase chain reaction tool (HemaVision) to detect of GA. Methods: In this study, we reviewed the results of HemaVision screening in 270 children with acute leukemia, newly diagnosed at The Catholic University of Korea from April 2007 to December 2011, and compared the results with those of fluorescence in situ hybridization (FISH), and G-band karyotyping. Results: Among the 270 children (153 males, 117 females), 187 acute lymphoblastic leukemia and 74 acute myeloid leukemia patients were identified. Overall, GA was detected in 230 patients (85.2%). HemaVision, FISH, and G-band karyotyping identified GA in 125 (46.3%), 126 (46.7%), and 215 patients (79.6%), respectively. TEL-AML1 (20.9%, 39/187) and AML1-ETO (27%, 20/74) were the most common GA in ALL and AML, respectively. Overall sensitivity of HemaVision was 98.4%, with false-negative results in 2 instances: 1 each for TEL-AML1 and MLL-AF4. An aggregate of diseases-specific FISH showed 100% sensitivity in detection of GA covered by HemaVision for actual probes utilized. G-band karyotype revealed GA other than those covered by HemaVison screening in 133 patients (49.3%). Except for hyperdiplody and hypodiploidy, recurrent GA as defined by the World Health Organizationthat were not screened by HemaVision, were absent in the karyotype. Conclusion: HemaVision, supported by an aggregate of FISH tests for important translocations, may allow for accurate diagnosis of GA in Korean children with acute leukemia.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.5
• /
• pp.451-457
• /
• 2020

Format recognition and OCR techniques are widely used as methods for detecting and protecting personal information from electronic documents. However, due to the poor recognition rate of the OCR engine, personal information cannot be detected or false positives commonly occur. It also takes a long time to analyze a large amount of electronic documents. In this paper, we propose a method to improve the speed of image analysis of electronic documents, character recognition rate of the OCR engine, and detection rate of personal information by improving the existing method. The analysis speed was increased using the format recognition method while the analysis speed and character recognition rate of the OCR engine was improved by image correction. An algorithm for analyzing personal information from images was proposed to increase the reconnaissance rate of personal information. Through the experiments, 1755 image format recognition samples were analyzed in an average time of 0.24 seconds, which was 0.5 seconds higher than the conventional PAID system format recognition method, and the image recognition rate was 99%. The proposed method in this paper can be used in various fields such as public, telecommunications, finance, tourism, and security as a system to protect personal information in electronic documents.

• Clinical and Experimental Reproductive Medicine
• /
• v.30 no.3
• /
• pp.223-231
• /
• 2003

Objective: The aim of the present study was to evaluate the clinical efficiency of fluorescent in situ hybridization (FISH) in the prenatal diagnosis of chromosomal aneuploidy. Methods: We reviewed data of 268 cases to identify women undergoing genetic amniocentesis at cytogenetic laboratory, from January 2000 to December 2002. Amniotic fluid was submitted for both rapid FISH on uncultured interphase amniocytes using a commercially available DNA probe for chromosome 13, 18, 21, X, Y and standard karyotyping on cultured metaphase amniocytes. Results from FISH and full karyotype were compared. Results: There were 251 cases (84%) normal and 17 cases (16%) abnormal in FISH results. All 17 cases of trisomy 13, 18, 21 including two cases of mosaicism and sex chromosome aneuploidies which are detected by FISH were confirmed with conventional cytogenetics and there was no false positive result. Twenty two cases had karyotypically proven abnormalities that could not have been detected by the targeted FISH. Conclusion: Interphase FISH analysis of uncultured amniotic fluid cells has been shown to be an effective and reliable technique for rapid fetal aneuploidy screening during pregnancy as an adjunctive test to conventional cytogenetics.

• Korean Journal of Cognitive Science
• /
• v.25 no.4
• /
• pp.385-416
• /
• 2014

In this study, memory for emotional words was compared between extraverts and introverts, employing signal detection analysis to distinguish differences in discriminative memory and response bias. Subjects were presented with a study list of emotional words in an encoding session, followed by a recognition session. Effects of task difficulty were examined by varying the nature of the encoding task and the intervals between study and test. For an easy task, with a retention interval of 5 minutes (Study I), introverts exhibited better memory (i.e., higher d') than extraverts, particularly for low-frequency words, and response biases did not differ between these two groups. For a difficult task, with a one-month retention period (Study II), performance was poor overall, and only high-frequency words were remembered; also extraverts adopted a more liberal criterion for 'old' responses (i.e., more hits and more false alarms) for positive emotional-valence words. These results suggest that as task difficulty drives down performance, effects of internal control processes become more apparent, revealing differences in response biases for positive words between extraverts and introverts. These results show that extraversion can distort memory performance for words, depending on their emotional valence.

• Journal of Korea Multimedia Society
• /
• v.11 no.5
• /
• pp.610-622
• /
• 2008

Moving object segmentation is an essential technique for various video surveillance applications. The result of moving object segmentation often contains shadow regions caused by the color difference of shadow pixels. Hence, moving object segmentation is usually followed by a shadow elimination process to remove the false detection results. The common assumption adopted in previous works is that, under the illumination variation, the value of chromaticity components are preserved while the value of intensity component is changed. Hence, color transforms which separates luminance component and chromaticity component are usually utilized to remove shadow pixels. In this paper, various color spaces (YCbCr, HSI, normalized rgb, Yxy, Lab, c1c2c3) are examined to find the most appropriate color space for shadow elimination. So far, there have been some research efforts to compare the influence of various color spaces for shadow elimination. However, previous efforts are somewhat insufficient to compare the color distortions under illumination change in diverse color spaces, since they used a specific shadow elimination scheme or different thresholds for different color spaces. In this paper, to relieve the limitations of previous works, (1) the amount of gradients in shadow boundaries drawn to uniform colored regions are examined only for chromaticity components to compare the color distortion under illumination change and (2) the accuracy of background subtraction are analyzed via RoC curves to compare different color spaces without the problem of threshold level selection. Through experiments on real video sequences, YCbCr and normalized rgb color spaces showed good results for shadow elimination among various color spaces used for the experiments.

• Journal of Broadcast Engineering
• /
• v.17 no.5
• /
• pp.838-850
• /
• 2012

In this paper, we propose a novel algorithm that generates multi-view images by using various image features obtained from the given stereoscopic images. In the proposed algorithm, we first create an intensity gradient saliency map from the given stereo images. And then we calculate a block-based optical flow that represents the relative movement(disparity) of each block with certain size between left and right images. And we also obtain the disparities of feature points that are extracted by SIFT(scale-invariant We then create a disparity saliency map by combining these extracted disparity features. Disparity saliency map is refined through the occlusion detection and removal of false disparities. Thirdly, we extract straight line segments in order to minimize the distortion of straight lines during the image warping. Finally, we generate multi-view images by grid mesh-based image warping algorithm. Extracted image features are used as constraints during grid mesh-based image warping. The experimental results show that the proposed algorithm performs better than the conventional DIBR algorithm in terms of visual quality.

• Journal of the Korean Society of Radiology
• /
• v.10 no.5
• /
• pp.299-305
• /
• 2016

Despite of the development of medical equipments and technology. Pancreatic cancer has maked high false positive rate and low survival rate compared to other cancers. Therefore, early catch of pancreatic cancer is the only way to enhance the viability. It is important to find the exact location of the pancreas cancer in early stage. The method of optimum scan for early detection of pancreatic cancer on PET/CT exam is proposed. Examined the anatomical region that potentially can be missing from the supine position of ordinary pet/ct exam. The characteristics and usefulness of angle variation ($0^{\circ}$, $30^{\circ}$, $45^{\circ}$, $60^{\circ}$, $90^{\circ}$) of patients scan position is analyzed. The proposed scan method (named JJ-projection) is bringing advantage of anatomical discrimination by separating stomach, liver, gallbladder duodenum and pancreas. ROC curve analysis is shows to advantage of the JJ-Projection method. The sensitivity has increased 4.6% than the supine delay scan method, the results sensitivity has increased from 91% to 95.2%. The specificity has increased from 75.1% to 84%. Compared with the results observed in cancer by biological biopsy, The accuracy has increased from 86.8% to 94.1%.

• Journal of Genetic Medicine
• /
• v.6 no.2
• /
• pp.146-154
• /
• 2009

Multiplex ligation dependent probe amplification (MLPA) is a PCR-based method to detect gene dosage. Since its introduction, MLPA has been used to test a large number of genes for major deletions or duplications. Genetic testing, as a diagnostic tool for genetic disease, has been used primarily to identify point mutations, including base substitutions and small insertions/deletions, using PCR and sequence analysis. However, it is difficult to identify large deletions or duplications using routine PCR- gel based assays, especially in heterozygotes. The MLPA is a more feasible method for identification of gene dosage than another routine PCR-based methods, and better able to detect deleterious deletions or duplications. In addition to detection of gene dosage, MLPA can be applied to identify methylation patterns of target genes, aneuploidy during prenatal diagnoses, and large deletions or duplications that may be associated with various cancers. The MLPA method offers numerous advantages, as it requires only a small amount of template DNA, is applicable to a wide variety of applications, and is high-throughput. On the other hand, this method suffers from disadvantages including the possibility of false positive results affected by template DNA quality, difficulties identifying SNPs located in probe sequences, and analytical complications in quantitative aspects.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.4
• /
• pp.107-115
• /
• 2011

In this paper, we proposed fast and efficient algorithm for detecting near-duplication based on content based retrieval in large scale video database. For handling large amounts of video easily, we split the video into small segment using scene change detection. In case of video services and copyright related business models, it is need to technology that detect near-duplicates, that longer matched video than to search video containing short part or a frame of original. To detect near-duplicate video, we proposed motion distribution and frame descriptor in a video segment. The motion distribution descriptor is constructed by obtaining motion vector from macro blocks during the video decoding process. When matching between descriptors, we use the motion distribution descriptor as filtering to improving matching speed. However, motion distribution has low discriminability. To improve discrimination, we decide to identification using frame descriptor extracted from selected representative frames within a scene segmentation. The proposed algorithm shows high success rate and low false alarm rate. In addition, the matching speed of this descriptor is very fast, we confirm this algorithm can be useful to practical application.