• Journal of radiological science and technology
• /
• v.47 no.1
• /
• pp.29-37
• /
• 2024

This study aims to evaluate the performance of the U-Net based learning model that may vary depending on the histogram equalization algorithm. The subject of the experiment were 17 radiology students of this college, and 1,727 data sets in which the region of interest was set in the thyroid after acquiring ultrasound image data were used. The training set consisted of 1,383 images, the validation set consisted of 172 and the test data set consisted of 172. The equalization algorithm was divided into Histogram Equalization(HE) and Contrast Limited Adaptive Histogram Equalization(CLAHE), and according to the clip limit, it was divided into CLAHE8-1, CLAHE8-2. CLAHE8-3. Deep Learning was learned through size control, histogram equalization, Z-score normalization, and data augmentation. As a result of the experiment, the Attention U-Net showed the highest performance from CLAHE8-2 to 0.8355, and the U-Net and BSU-Net showed the highest performance from CLAHE8-3 to 0.8303 and 0.8277. In the case of mIoU, the Attention U-Net was 0.7175 in CLAHE8-2, the U-Net was 0.7098 and the BSU-Net was 0.7060 in CLAHE8-3. This study attempted to confirm the effects of U-Net, Attention U-Net, and BSU-Net models when histogram equalization is performed on ultrasound images. The increase in Clip Limit can be expected to increase the ROI match with the prediction mask by clarifying the boundaries, which affects the improvement of the contrast of the thyroid area in deep learning model learning, and consequently affects the performance improvement.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.1149-1151
• /
• 2003

We performed a validation study of the MODIS active fire detection algorithm using high resolution SPOT image as the reference data set. Fire with visible smoke plumes are detected in the SPOT scenes, while the hotspots in MODIS data are detected using NASA's new version 4 fire detection algorithm. The detection performance is characterized by the commission error rate (false alarms) and the omission error rate (undetected fires). In the Sumatra and Kalimantan study area, the commission rate and the omission rate are 27% and 34% respectively. False alarms are probably due to recently burnt areas with warm surfaces. False negative detection occur where there are long smoke plumes and where fires occur in densely vegetated areas.

• Nuclear Engineering and Technology
• /
• v.53 no.10
• /
• pp.3133-3150
• /
• 2021

This work deals with the validation of a high-fidelity multiphysics system coupling the Serpent 2 Monte Carlo neutron transport code with SUBCHANFLOW, a subchannel thermalhydraulics code, and TRANSURANUS, a fuel-performance analysis code. The results for a full-core pin-by-pin burnup calculation for the ninth operating cycle of the Temelín II VVER-1000 plant, which starts from a fresh core, are presented and assessed using experimental data. A good agreement is found comparing the critical boron concentration and a set of pin-level neutron flux profiles against measurements. In addition, the calculated axial and radial power distributions match closely the values reported by the core monitoring system. To demonstrate the modeling capabilities of the three-code coupling, pin-level neutronic, thermalhydraulic and thermomechanic results are shown as well. These studies are encompassed in the final phase of the EU Horizon 2020 McSAFE project, during which the Serpent-SUBCHANFLOW-TRANSURANUS system was developed.

• Journal of the Korean Data and Information Science Society
• /
• v.23 no.1
• /
• pp.39-51
• /
• 2012

Cluster analysis has proven to be a useful tool for investigating the association structure among genes and samples in a microarray data set. We applied several cluster validation measures to evaluate the performance of clustering algorithms for analyzing microarray gene expression data, including hierarchical clustering, K-means, PAM, SOM and model-based clustering. The available validation measures fall into the three general categories of internal, stability and biological. The performance of clustering algorithms is evaluated using simulated and SRBCT microarray data. Our results from simulated data show that nearly every methods have good results with same result as the number of classes in the original data. For the SRBCT data the best choice for the number of clusters is less clear than the simulated data. It appeared that PAM, SOM, model-based method showed similar results to simulated data under Silhouette with of internal measure as well as PAM and model-based method under biological measure, while model-based clustering has the best value of stability measure.

• Journal of the Korean Chemical Society
• /
• v.46 no.4
• /
• pp.309-317
• /
• 2002

A spectrofluorimetric method for the simultaneous determination of amino acids (tryptophan and tyrosine) based on the application of multivariate calibration method such as principal component regression and partial least squares (PLS) to luminescence measurements has been studied. Emission spectra of synthetic mixtures of two amino acids were obtained at excitation wavelength of 257 ㎚. The calibration model in PCR and PLS was obtained from the spectral data in the range of 280-500 ㎚ for each standard of a calibration set of 32 standards, each containing different amounts of two amino acids. The relative standard error of prediction ($RSEP_a$) was obtained to assess the model goodness in quantifying each analyte in a validation set. The overall relative standard error of prediction ($RSEP_m$) for the mixture obtained from the results of a validation set, formed by 6 independent mixtures was also used to validate the present method.

• Korean Journal of Radiology
• /
• v.21 no.6
• /
• pp.660-669
• /
• 2020

Objective: To evaluate the accuracy of a deep learning-based automated segmentation of the left ventricle (LV) myocardium using cardiac CT. Materials and Methods: To develop a fully automated algorithm, 100 subjects with coronary artery disease were randomly selected as a development set (50 training / 20 validation / 30 internal test). An experienced cardiac radiologist generated the manual segmentation of the development set. The trained model was evaluated using 1000 validation set generated by an experienced technician. Visual assessment was performed to compare the manual and automatic segmentations. In a quantitative analysis, sensitivity and specificity were calculated according to the number of pixels where two three-dimensional masks of the manual and deep learning segmentations overlapped. Similarity indices, such as the Dice similarity coefficient (DSC), were used to evaluate the margin of each segmented masks. Results: The sensitivity and specificity of automated segmentation for each segment (1-16 segments) were high (85.5-100.0%). The DSC was 88.3 ± 6.2%. Among randomly selected 100 cases, all manual segmentation and deep learning masks for visual analysis were classified as very accurate to mostly accurate and there were no inaccurate cases (manual vs. deep learning: very accurate, 31 vs. 53; accurate, 64 vs. 39; mostly accurate, 15 vs. 8). The number of very accurate cases for deep learning masks was greater than that for manually segmented masks. Conclusion: We present deep learning-based automatic segmentation of the LV myocardium and the results are comparable to manual segmentation data with high sensitivity, specificity, and high similarity scores.

• Annals of Hepato-Biliary-Pancreatic Surgery
• /
• v.27 no.2
• /
• pp.195-200
• /
• 2023

Backgrounds/Aims: We aimed to build a machine learning tool to help predict low-grade intraductal papillary mucinous neoplasms (IPMNs) in order to avoid unnecessary surgical resection. IPMNs are precursors to pancreatic cancer. Surgical resection remains the only recognized treatment for IPMNs yet carries some risks of morbidity and potential mortality. Existing clinical guidelines are imperfect in distinguishing low-risk cysts from high-risk cysts that warrant resection. Methods: We built a linear support vector machine (SVM) learning model using a prospectively maintained surgical database of patients with resected IPMNs. Input variables included 18 demographic, clinical, and imaging characteristics. The outcome variable was the presence of low-grade or high-grade IPMN based on post-operative pathology results. Data were divided into a training/validation set and a testing set at a ratio of 4:1. Receiver operating characteristics analysis was used to assess classification performance. Results: A total of 575 patients with resected IPMNs were identified. Of them, 53.4% had low-grade disease on final pathology. After classifier training and testing, a linear SVM-based model (IPMN-LEARN) was applied on the validation set. It achieved an accuracy of 77.4%, with a positive predictive value of 83%, a specificity of 72%, and a sensitivity of 83% in predicting low-grade disease in patients with IPMN. The model predicted low-grade lesions with an area under the curve of 0.82. Conclusions: A linear SVM learning model can identify low-grade IPMNs with good sensitivity and specificity. It may be used as a complement to existing guidelines to identify patients who could avoid unnecessary surgical resection.

• The Bulletin of The Korean Astronomical Society
• /
• v.36 no.2
• /
• pp.64-64
• /
• 2011

We present a new quasi-stellar object (QSO) selection algorithm using a Support Vector Machine, a supervised classification method, on a set of extracted time series features including period, amplitude, color, and autocorrelation value. We train a model that separates QSOs from variable stars, non-variable stars, and microlensing events using 58 known QSOs, 1629 variable stars, and 4288 non-variables in the MAssive Compact Halo Object (MACHO) database as a training set. To estimate the efficiency and the accuracy of the model, we perform a cross-validation test using the training set. The test shows that the model correctly identifies ~80% of known QSOs with a 25% false-positive rate. The majority of the false positives are Be stars. We applied the trained model to the MACHO Large Magellanic Cloud (LMC) data set, which consists of 40 million lightcurves, and found 1620 QSO candidates. During the selection, none of the 33,242 known MACHO variables were misclassified as QSO candidates. In order to estimate the true false-positive rate, we crossmatched the candidates with astronomical catalogs including the Spitzer Surveying the Agents of a Galaxy's Evolution (SAGE) LMC catalog and a few X-ray catalogs. The results further suggest that the majority of the candidates, more than 70%, are QSOs.

• 한국전산유체공학회:학술대회논문집
• /
• 2005.04a
• /
• pp.202-206
• /
• 2005

A new numerical scheme for two-phase flows, the Hybrid VOF method has been developed for improved free surface capturing. The present new method is a volume capturing based VOF method coupled with a reinitialization procedure of a Level-set method. For validation, the proposed method is applied to two test cases: spherical bubble rising and dam breaking. The calculated results by using the Hybrid VOF method with the two previously applied VOF formulations are compared with available numerical and experimental data. It is found that the new method provides more accurate results than the two previous ones.

• Journal of the Society of Naval Architects of Korea
• /
• v.42 no.2 s.140
• /
• pp.88-97
• /
• 2005

A new numerical scheme solving two-phase flow, the Hybrid VOF method for improved free surface capturing has been developed by combining a volume capturing VOF method with the Level-Set reinitialization procedure. For validation, the proposed method is applied to 3-D bubble rising problem, dam breaking and the free surface flow around a commercial container ship. The calculated results by using the Hybrid VOF method with the two previously applied VOF formulations are compared with available numerical and experimental data. It is found that the new method provides more reasonable results than the two previous ones.