• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.11
• /
• pp.1489-1495
• /
• 1995

In this paper, we propose recurrent neural prediction models (RNPM), recurrent neural networks trained as a nonlinear predictor of speech, as a new connectionist model for speech recognition. RNPM modulates its mapping effectively by internal representation, and it requires no time alignment algorithm. Therefore, computational load at the recognition stage is reduced substantially compared with the well known predictive neural networks (PNN), and the size of the required memory is much smaller. And, RNPM does not suffer from the problem of deciding the time varying target function. In the speaker dependent and independent speech recognition experiments under the various conditions, the proposed model was comparable in recognition performance to the PNN, while retaining the above merits that PNN doesn't have.

• Clinical and Experimental Pediatrics
• /
• v.62 no.8
• /
• pp.301-306
• /
• 2019

Purpose: Coronary artery abnormalities (CAA) are the most important complications of Kawasaki disease (KD). Iron deficiency anemia (IDA) is a prevalent micronutrient deficiency and its association with KD remains unknown. We hypothesized that presence of IDA could be a predictor of CAA. Methods: This retrospective study included 173 KD patients, divided into 2 groups according to absence (group 1) and presence (group 2) of CAA. Odds ratios (ORs) with 95% confidence intervals (CIs) were calculated using a logistic regression model to estimate the association between CAA and other indicators. Due to collinearity between indicators of IDA, each indicator was paired with anemia in 3 models. Results: Serum iron, iron saturation, and ferritin concentration, the 3 indicators of IDA, were significantly higher in group 1 than in group 2. Three sets of models including anemia with iron indicators produced the OR of CAA of 3.513, 3.171, and 2.256, respectively. The 3 indicators of IDA were negatively associated with CAA, by OR of 0.965, 0.914, and 0.944, respectively. The areas under the curve (AUCs) of ferritin concentration, iron saturation, serum iron, anemia, and Kobayashi score were 0.907 (95% CI, 0.851-0.963), 0.729 (95% CI, 0.648-0.810), 0.711 (95% CI, 0.629-0.793), 0.638 (95% CI, 0.545-0.731), and 0.563 (95% CI, 0.489-0.636), respectively. Conclusion: Indicators of IDA, especially ferritin, were highly associated with CAA; therefore, they were stronger predictors of CAA than Kobayashi scores. IDA indicators can be used to predict CAA development and to suggest requirements for early interventions.

• Journal of Oral Medicine and Pain
• /
• v.46 no.2
• /
• pp.21-32
• /
• 2021

Purpose: The purpose of the present study was to investigate the correlation between age and 34 radiomorphometric parameters on panoramic radiographs, and to provide generalized linear models (GLMs) as a non-invasive, inexpensive, and accurate method to the forensic judgement of living individual's age. Methods: The study included 417 digital panoramic radiographs of Korean individuals (178 males and 239 females, mean age: 32.57±17.81 years). Considering the skeletal differences between the sexes, GLMs were obtained separately according to sex, as well as across the total sample. For statistical analysis and to predict the accuracy of the new GLMs, root mean squared error (RMSE) and adjusted R-squared (R²) were calculated. Results: The adjusted R²-values of the developed GLMs in the total sample, and male and female groups were 0.623, 0.637, and 0.660, respectively (p<0.001), while the allowable RMSE values were 8.80, 8.42, and 8.53 years, respectively. In the GLM of the total sample, the most influential predictor of greater age was decreased pulp area in the #36 first molar (beta=-26.52; p<0.01), followed by the presence of periodontitis (beta=10.24; p<0.01). In males, the most influential factor was the presence of periodontitis (beta=9.20; p<0.05), followed by the number of full veneer crowns (beta=2.19; p<0.001). In females, the most influential predictor was the presence of periodontitis (beta=18.10; p<0.001), followed by the tooth area of the #16 first molar (beta=-11.57; p<0.001). Conclusions: We established acceptable GLM for each sex and found out the predictors necessary to age estimation which can be easily found in panoramic radiographs. Our study provides reference that parameters such as the area of tooth and pulp, the number of teeth treated, and the presence of periodontitis should be considered in estimating age.

• Journal of Trauma and Injury
• /
• v.18 no.2
• /
• pp.141-147
• /
• 2005

Purpose: Recently, The new Injury Severity Score (NISS) has become a more accurate predictor of mortality than the traditional Injury Severity Score (ISS) in the trauma population. Trauma Score Injury Severity Score (TRISS) method, regarded as the gold standard for mortality prediction in trauma patients, still contains the ISS as an essential factor within its formula. The purpose of this study was to determine whether a simple modification of the TRISS by replacing the ISS with the NISS would improve the prediction of in-hospital mortality in a trauma population with blunt head and neck trauma. Objects and Methods: The study population consisted of 641 patients from a regional emergency medical center in Kyoungsangnam-do. Demographic data, clinical information, the final diagnosis, and the outcome for each patient were collected in a retrospective manner. the ISS, NISS, TRISS, and modified TRISS were calculated for each patients. The discrimination and the calibration of the ISS, NISS, modified TRISS and conventional TRISS models were compared using receiver operator characteristic (ROC) curves, areas under the ROC curve (AUC) and Hosmer-Lemeshow statistics. Results: The AUC of the ISS, NISS, modified TRISS, and conventional TRISS were 0.885, 0.941, 0.971, and 0.918 respectively. Statistical differences were found between the ISS and the NISS (p=0.008) and between the modified TRISS and the conventional TRISS (p=0.009). Hosmer-Lemeshow chi square values were 13.2, 2.3, 50.1, and 13.8, respectively; only the conventional TRISS failed to achieve the level of and an excellent calibration model (p<0.001). Conclusion: The modified TRISS is a more accurate predictor of in-hospital mortality than the conventional TRISS in a trauma population of blunt head and neck trauma.

• The Journal of Information Systems
• /
• v.17 no.2
• /
• pp.49-72
• /
• 2008

Today, the World Wide Web (WWW) impacts many facets of our lives, including communication, entertainment, social activities, shopping, etc. The web portal is the most accessed type of site and is advertising-supported the more users who visit the site, the more income it generates. User perception to a web site is very important much research has focused on the internet users' behavior. Some well-known theories, such as the technology acceptance model have been used to examine variables that motivate individuals to accept and use an IS. But Understanding continued use is the goal of this study. We focus on user beliefs (specifically, perceived usefulness) and attitude because pier studies of IT usage, predominantly based on the technology acceptance model (TAM) and similar models, have established these perceptions as the dey determinants of both initial IT usage (acceptance) and long-term usage (continuance) intention and behavior (Bhattacherjee 2001; Davis et al. 1989). Any change in beliefs or attitudes will likely have a corresponding impact on, and may even revers, users' continuance intention and behavior. Also, continuance use have some features which are prior use, habit, feature-centric view of technology. So this research reflected continuance use features. Examination of the paths in the model revealed several interesting results. First, Perceived usefulness was a stronger predictor of acceptance intention in TAM than attitude, But attitude was a stronger predictor of continuance intention in this study than perceive usefulness. Second, confirmation was not affect directly to attitude. Last, Habit was strongest predictor of continuance intention in this study.

• Journal of the Korean Society of Hazard Mitigation
• /
• v.10 no.1
• /
• pp.103-109
• /
• 2010

In this study, a three-dimensional non-hydrostatic pressure model based on a normalized vertical coordinate system for free surface flows is presented. To strongly couple the free surface and non-hydrostatic pressure with the momentum equations, a double predictor-corrector method is employed. The study is especially focused on implementing the dynamic boundary condition (a zero pressure condition) at the free surface with ignoring of the atmospheric pressure. It is shown that the boundary condition can be specified easily with a slight modification to existing models.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.6B
• /
• pp.691-696
• /
• 2008

In this paper, a three-dimensional non-hydrostatic pressure model for free surface flows using a normalized vertical coordinate system is presented. To strongly couple the free surface and non-hydrostatic pressure in the momentum equations, a double predictor-corrector method is employed. This research is especially focused on implementing the dynamic boundary condition (a zero pressure condition) at the free surface. This boundary condition can be specified accurately with a small modification to existing models. Numerical results with and without this modification clearly show that a precise implementation of the dynamic boundary condition is paramountly important.

• Structural Engineering and Mechanics
• /
• v.36 no.6
• /
• pp.759-783
• /
• 2010

In this paper, compressive strength of carbon fiber reinforced polymer (CFRP) confined concrete cylinders is formulated using a hybrid method coupling genetic programming (GP) and simulated annealing (SA), called GP/SA, and a robust variant of GP, namely multi expression programming (MEP). Straightforward GP/SA and MEP-based prediction equations are derived for the compressive strength of CFRP-wrapped concrete cylinders. The models are constructed using two sets of predictor variables. The first set comprises diameter of concrete cylinder, unconfined concrete strength, tensile strength of CFRP laminate, and total thickness of CFRP layer. The most widely used parameters of unconfined concrete strength and ultimate confinement pressure are included in the second set. The models are developed based on the experimental results obtained from the literature. To verify the applicability of the proposed models, they are employed to estimate the compressive strength of parts of test results that were not included in the modeling process. A sensitivity analysis is carried out to determine the contributions of the parameters affecting the compressive strength. For more verification, a parametric study is carried out and the trends of the results are confirmed via some previous studies. The GP/SA and MEP models are able to predict the ultimate compressive strength with an acceptable level of accuracy. The proposed models perform superior than several CFRP confinement models found in the literature. The derived models are particularly valuable for pre-design purposes.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.6 no.2
• /
• pp.13-21
• /
• 1996

The necessity and usefulness of higher-order neural networks have been well-known since early days of neurocomputing. However the explosive number of terms has hampered the design and training of such networks. In this paper we present an evolutionary learning method for efficiently constructing problem-specific higher-order neural models. The crux of the method is the neural tree representation employing both sigma and pi units, in combination with the use of an MDL-based fitness function for learning minimal models. We provide experimental results in classification and prediction problems which demonstrate the effectiveness of the method. I. Introduction topology employs one hidden layer with full connectivity between neighboring layers. This structure has One of the most popular neural network models been very successful for many applications. However, used for supervised learning applications has been the they have some weaknesses. For instance, the fully mutilayer feedforward network. A commonly adopted connected structure is not necessarily a good topology unless the task contains a good predictor for the full *d*dWs %BH%W* input space.

• Atmosphere
• /
• v.24 no.4
• /
• pp.533-540
• /
• 2014

Statistical forecast models for the prediction of the summertime Changma precipitation have been developed in this study. As effective predictors for the Changma precipitation, the springtime sea surface temperature (SST) anomalies over the North Atlantic (NA1), the North Pacific (NPC) and the tropical Pacific Ocean (CNINO) has been suggested in Lee and Seo (2013). To further improve the performance of the statistical prediction scheme, we select other potential predictors and construct 2 additional statistical models. The selected predictors are the Northern Indian Ocean (NIO) and the Bering Sea (BS) SST anomalies, and the spring Eurasian snow cover anomaly (EUSC). Then, using the total three statistical prediction models, a simple ensemble-mean prediction is performed. The resulting correlation skill score reaches as high as ~0.90 for the last 21 years, which is ~16% increase in the skill compared to the prediction model by Lee and Seo (2013). The EUSC and BS predictors are related to a strengthening of the Okhotsk high, leading to an enhancement of the Changma front. The NIO predictor induces the cyclonic anomalies to the southwest of the Korean peninsula and southeasterly flows toward the peninsula, giving rise to an increase in the Changma precipitation.