• Journal of Intelligence and Information Systems
• /
• v.13 no.2
• /
• pp.15-26
• /
• 2007

In this study, a SOHO (Small Office Home Office) bankruptcy prediction model is proposed using Modified Bagging Predictors which is modification of traditional Bagging Predictors. There have been several studies on bankruptcy prediction for large and middle size companies. However, little studies have been done for SOHOs. In commercial banks, loan approval processes for SOHOs are usually less structured than those for large and middle size companies, and largely depend on partial information such as credit scores. In this study, we use a real SOHO loan approval data set of a Korean bank. First, decision tree induction techniques and artificial neural networks are applied to the data set, and the results are not satisfactory. Bagging Predictors which has been not previously applied for bankruptcy prediction and Modified Bagging Predictors which is proposed in this paper are applied to the data set. The experimental results show that Modified Bagging Predictors provides better performance than decision tree inductions techniques, artificial neural networks, and Bagging Predictors.

• Clinical Endoscopy
• /
• v.56 no.4
• /
• pp.479-489
• /
• 2023

Background/Aims: Accurate neoplastic prediction can significantly decrease costs associated with pathology and unnecessary colorectal polypectomies. Narrow-band imaging (NBI) and dual-focus (DF) mode are promising emerging optical technologies for recognizing neoplastic features of colorectal polyps digitally. This study aimed to clarify the clinical usefulness of NBI with and without DF assistance in the neoplastic prediction of small colorectal polyps (<10 mm). Methods: This cross-sectional study included 530 small colorectal polyps from 343 consecutive patients who underwent colonoscopy at the University Medical Center from September 2020 to May 2021. Each polyp was endoscopically diagnosed in three successive steps using white-light endoscopy (WLE), NBI, and NBI-DF and retrieved for histopathological assessment. The diagnostic accuracy of each modality was evaluated with reference to histopathology. Results: There were 295 neoplastic polyps and 235 non-neoplastic polyps. The overall accuracies of WLE, WLE+NBI, and WLE+NBI+NBI-DF in the neoplastic prediction of colorectal polyps were 70.8%, 87.4%, and 90.8%, respectively (p<0.001). The accuracy of WLE+NBI+NBI-DF was significantly higher than that of WLE+NBI in the polyp size ≤5 mm subgroup (87.3% vs. 90.1%, p<0.001). Conclusions: NBI improved the real-time neoplastic prediction of small colorectal polyps. The DF mode was especially useful in polyps ≤5 mm in size.

• The KIPS Transactions:PartA
• /
• v.16A no.5
• /
• pp.347-356
• /
• 2009

Precise branch prediction is a critical factor in the IPC Improvement of modern microprocessor architectures. In addition to the branch prediction accuracy, branch prediction delay have a profound impact on overall system performance as well. However, it tends to be overlooked when the architects design the branch predictor. To tolerate branch prediction delay, this paper proposes Early Start Prediction (ESP) technique. The proposed solution dynamically identifies the start instruction of basic block, called as Basic Block Start Address (BB_SA), and the solution uses BB_SA when predicting the branch direction, instead of branch instruction address itself. The performance of the proposed scheme can be further improved by combining short interval hiding technique between BB_SA and branch instruction. The simulation result shows that the proposed solution hides prediction latency, with providing same level of prediction accuracy compared to the conventional predictors. Furthermore, the combination with short interval hiding technique provides a substantial IPC improvement of up to 10.1%, and the IPC is actually same with ideal branch predictor, regardless of branch predictor configurations, such as clock frequency, delay model, and PHT size.

• Journal of Chest Surgery
• /
• v.20 no.4
• /
• pp.655-658
• /
• 1987

Aortic annulus size was measured by two-dimensional echocardiography [2DE] in 29 patients undergoing aortic valve replacement or double valve replacement in order to predict prosthetic aortic valve size. Fifteen patients had aortic stenoinsufficiency, eleven had aortic insufficiency, and three had aortic stenosis. 2DE measurements of aortic annulus diameter, as determined from the parasternal long-axis view, demonstrated a high correlation with actual prosthetic valve size implanted at surgery [r=0.85, p<0.05]. 2DE exactly predicted actual prosthetic valve size in 8 of 29 patients [27.6%], was within 1mm of prosthetic valve size in 11 of 29 patients [37.9%], was within 2mm of prosthetic valve size in 8 of 29 patients, and was within 3mm of prosthetic valve size in 2 patients.

• Structural Engineering and Mechanics
• /
• v.19 no.5
• /
• pp.567-580
• /
• 2005

Numerous tests on concrete structure members under local pressure demonstrated that the compressive strength of concrete at the loaded surface is increased by the confinement effect provided by the enveloping concrete. Even though most design codes propose specific criteria for preventing bearing failure, they do not take into consideration size effect which is an important phenomenon in the fracture mechanics of concrete/reinforced concrete. In this paper, six series of square prism concrete blocks with three different depths (size range = 1:4) and two different height/depth ratios of 2 and 3 are tested under concentrated load. Ultimate loads obtained from the test results are analysed by means of the modified size effect law (MSEL). Then, a prediction formula, which considers effect of both depth and height on size effect, is proposed. The developed formula is compared with experimental data existing in the literature. It is concluded that the observed size effect is in good agreement with the MSEL.

• 한국전산유체공학회:학술대회논문집
• /
• 2010.05a
• /
• pp.320-325
• /
• 2010

A multiphase CFD analysis is performed to investigate the effect of near-wall grid for simulating a subcooled boiling flow in vertical tube. The multiphase flow model used in this CFD analysis is the two-fluid model in which liquid(water) and vapor(steam) are considered as continuous and dispersed fluids, respectively. A wall boiling model is also used to simulate the subcooled boiling heat transfer at the heated wall boundary. The diameter and heated length of tube are 0.0154 m and 2 m, respectively. The system pressure in tube is 4.5 MPa and the inlet subcooling is 60 K. The near-wall grid size in the non-dimensional wall unit ($y_{w}^{+}$) was examined from 64 to 172 at the outlet boundary. The CFD calculations predicted the void distributions as well as the liquid and wall temperatures in tube. The predicted axial variations of the void fraction and the wall temperature are compared with the measured ones. The CFD prediction of the wall temperature is shown to slightly depend on the near-wall grid size but the axial void prediction has somewhat large dependency. The CFD prediction was found to show a better agreement with the measured one for the large near-wall grid, e.g., $y_{w}^{+}$ > 100.

• Journal of computational fluids engineering
• /
• v.15 no.3
• /
• pp.24-31
• /
• 2010

boiling flow in vertical tube. The multiphase flow model used in this CFD analysis is the two-fluid model in which liquid(water) and gas(vapour) are considered as continuous and dispersed fluids, respectively. A wall boiling model is also used to simulate the subcooled boiling heat transfer at the heated wall boundary. The diameter and heated length of tube are 0.0154 m and 2 m, respectively. The system pressure in tube is 4.5 MPa and the inlet subcooling is 60 K. The near-wall grid size in the non-dimensional wall unit for lqiuid phase ($y^+_{w,l}$) was examined from 101 to 313 at the outlet boundary. The CFD calculations predicted the void distributions as well as the liquid and wall temperatures in tube. The predicted axial variations of the void fraction and the wall temperature are compared with the measured ones. The CFD prediction of the wall temperature is shown to slightly depend on the near-wall grid size but the axial void prediction has somewhat large dependency. The CFD prediction was found to show a better agreement with the measured one for the large near-wall grid, e.g., $y^+_{w,l}$ > 300 at the tube exit.

• Proceedings of the ESK Conference
• /
• 1993.10a
• /
• pp.124-132
• /
• 1993

This study compared two prediction methods-regression and artificial neural network (ANN) on the visual search performance when monitoring a multi-parameter screen with different occurrence frequencies. Under the highlighting condition for the highest occurrence frequency parameter as a search cue, it was found from the requression analysis that variations of mean search time (MST) could be expained almost by three factors such as the number of parameters, the target occurrence frequency of a highlighted parameter, and the highlighted parameter size. In this study, prediction performance of ANN was evaluated as an alternative to regression method. Backpropagation method which was commonly used as a pattern associator was employed to learn a search behavior of subjects. For the case of increased number of parameters and incresed target occurrence frequency of a highlighted parameter, ANN predicted MST's moreaccurately than the regression method (p<0.000). Only the MST's predicted by ANN did not statistically differ from the true MST's. For the case of increased highlighted parameter size. both methods failed to predict MST's accurately, but the differences from the true MST were smaller when predicted by ANN than by regression model (p=0.0005). This study shows that ANN is a good predictor of a visual search performance and can substitute the regression method under certain circumstances.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.12
• /
• pp.2647-2654
• /
• 2009

In this paper, we propose H.264 Encoder integrating Intra Prediction, Deblocking Filter, Context-Based Adaptive Variable Length Coding, and Motion Estimation encoder module. This designed module can be operated in 440 cycle for one-macroblock. To verify the Encoder architecture, we developed the reference C from JM 9.4 and verified the our developed hardware using test vector generated by reference C. The designed circuit can be operated in 166MHz clock system, and has 1800K gate counts using Charterd 0.18 um process including SRAM memory. Manufactured chip has the size of $6{\times}6mm$ and 208 pins package.

• Structural Engineering and Mechanics
• /
• v.69 no.3
• /
• pp.243-255
• /
• 2019

Utilization of fiber beam-column element has gained considerable attention in recent years due mainly to its ability to model distributed plasticity over the length of the element through a number of integration points. However, the relatively high sensitivity of the method to modeling parameters as well as material behavior models can pose a significant challenge. Residual drift is one of the seismic demands which is highly sensitive to modeling parameters and material behavior models. Permanent deformations play a prominent role in the post-earthquake evaluation of serviceability of bridges affected by a near-fault ground shaking. In this research, the influence of distributed plasticity modeling parameters using both force-based and displacement-based fiber elements in the prediction of internal forces obtained from the nonlinear static analysis is studied. Having chosen suitable type and size of elements and number of integration points, the authors take the next step by investigating the influence of material behavioral model employed for the prediction of permanent deformations in the nonlinear dynamic analysis. The result shows that the choice of element type and size, number of integration points, modification of cyclic concrete behavior model and reloading strain of concrete significantly influence the fidelity of fiber element method for the prediction of permanent deformations.