• Journal of Periodontal and Implant Science
• /
• v.48 no.2
• /
• pp.114-123
• /
• 2018

Purpose: The aim of the current study was to develop a computer-assisted detection system based on a deep convolutional neural network (CNN) algorithm and to evaluate the potential usefulness and accuracy of this system for the diagnosis and prediction of periodontally compromised teeth (PCT). Methods: Combining pretrained deep CNN architecture and a self-trained network, periapical radiographic images were used to determine the optimal CNN algorithm and weights. The diagnostic and predictive accuracy, sensitivity, specificity, positive predictive value, negative predictive value, receiver operating characteristic (ROC) curve, area under the ROC curve, confusion matrix, and 95% confidence intervals (CIs) were calculated using our deep CNN algorithm, based on a Keras framework in Python. Results: The periapical radiographic dataset was split into training (n=1,044), validation (n=348), and test (n=348) datasets. With the deep learning algorithm, the diagnostic accuracy for PCT was 81.0% for premolars and 76.7% for molars. Using 64 premolars and 64 molars that were clinically diagnosed as severe PCT, the accuracy of predicting extraction was 82.8% (95% CI, 70.1%-91.2%) for premolars and 73.4% (95% CI, 59.9%-84.0%) for molars. Conclusions: We demonstrated that the deep CNN algorithm was useful for assessing the diagnosis and predictability of PCT. Therefore, with further optimization of the PCT dataset and improvements in the algorithm, a computer-aided detection system can be expected to become an effective and efficient method of diagnosing and predicting PCT.

• Journal of the Korean Solar Energy Society
• /
• v.39 no.3
• /
• pp.59-66
• /
• 2019

New and renewable energy forecasts are key technology to reduce the annual operating cost of new and renewable facilities, and accuracy of forecasts is paramount. In this study, we intend to build a model for the prediction of short-term solar power generation for 1 hour to 3 hours. To this end, this study applied two time series technique, ARIMA model without considering seasonality and SARIMA model with considering seasonality, comparing which technique has better predictive accuracy. Comparing predicted errors by MAE measures of solar power generation for 1 hour to 3 hours at four locations, the solar power forecast model using ARIMA was better in terms of predictive accuracy than the solar power forecast model using SARIMA. On the other hand, a comparison of predicted error by RMSE measures resulted in a solar power forecast model using SARIMA being better in terms of predictive accuracy than a solar power forecast model using ARIMA.

• Nutrition Research and Practice
• /
• v.13 no.3
• /
• pp.256-262
• /
• 2019

BACKGROUND/OBJECTIVES: The objectives of this study were to evaluate the accuracy of the Dietary Reference Intakes (DRI) for estimating the energy requirements of older adults, and to develop and validate new equations for predicting the energy requirements of this population group. MATERIALS/METHODS: The study subjects were 25 men and 23 women with a mean age of $72.2{\pm}3.9\;years$ and $70.0{\pm}3.3\;years$, and mean BMI of $24.0{\pm}2.1$ and $23.9{\pm}2.7$, respectively. The total energy expenditure (TEE) was measured by using the doubly labeled water (DLW) method, and used to validate the DRI predictive equations for estimated energy requirements (EER) and to develop new EER predictive equations. These developed equations were cross-validated by using the leave-one-out technique. RESULTS: In men, the DRI equation had a -7.2% bias and accurately predicted the EER (meaning EER values within ${\pm}10%$ of the measured TEE) for 64% of the subjects, whereas our developed equation had a bias of -0.1% and an accuracy rate of 84%. In women, the bias was -6.6% for the DRI equation and 0.2% for our developed equation, and the accuracy rate was 74% and 83%, respectively. The predicted EER was strongly correlated with the measured TEE, for both the DRI equations and our developed equations (Pearson's r = 0.915 and 0.908, respectively). CONCLUSIONS: The DRI equations provided an acceptable prediction of EER in older adults and these study results therefore support the use of these equations in this population group. Our developed equations had a better predictive accuracy than the DRI equations, but more studies need to be performed to assess the performance of these new equations when applied to an independent sample of older adults.

• Imaging Science in Dentistry
• /
• v.52 no.3
• /
• pp.239-244
• /
• 2022

Purpose: Despite the proliferation of numerous morphometric and anthropometric methods for sex identification based on linear, angular, and regional measurements of various parts of the body, these methods are subject to error due to the observer's knowledge and expertise. This study aimed to explore the possibility of automated sex determination using convolutional neural networks(CNNs) based on lateral cephalometric radiographs. Materials and Methods: Lateral cephalometric radiographs of 1,476 Iranian subjects (794 women and 682 men) from 18 to 49 years of age were included. Lateral cephalometric radiographs were considered as a network input and output layer including 2 classes(male and female). Eighty percent of the data was used as a training set and the rest as a test set. Hyperparameter tuning of each network was done after preprocessing and data augmentation steps. The predictive performance of different architectures (DenseNet, ResNet, and VGG) was evaluated based on their accuracy in test sets. Results: The CNN based on the DenseNet121 architecture, with an overall accuracy of 90%, had the best predictive power in sex determination. The prediction accuracy of this model was almost equal for men and women. Furthermore, with all architectures, the use of transfer learning improved predictive performance. Conclusion: The results confirmed that a CNN could predict a person's sex with high accuracy. This prediction was independent of human bias because feature extraction was done automatically. However, for more accurate sex determination on a wider scale, further studies with larger sample sizes are desirable.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.8 no.2
• /
• pp.14-26
• /
• 2009

This study presented a novel method to estimate travel times under incident conditions. Predictive travel time information was defined and evaluated with the proposed method. The proposed method utilized individual vehicle speeds obtained from global positioning systems (GPS) and inter-vehicle communications(IVC) for more reliable real-time travel times. Individual vehicle trajectory data were extracted from microscopic traffic simulations using AIMSUN. Market penetration rates (MPR) and IVC ranges were explored with the accuracy of travel times. Relationship among travel time accuracy, IVC ranges, and MPR were further identified using regression analyses. The outcomes of this study would be useful to derive functional requirements associated with traffic information systems under forthcoming ubiquitous transportation environment

• The Journal of Korean Physical Therapy
• /
• v.19 no.3
• /
• pp.41-46
• /
• 2007

Purpose: This study was to investigate how dose the radiography findings are to magnetic resonance (MR) image findings in the L5-S1 instability patients. The subjects of this study were comprised of eleven males and fifteen females, who had Lumbago and agreed with this research. Methods: Radiography and MR images of Lumbar spine were acquired respectively from subjects in conditions of maximum flexion and extension. The horizontal and angular displacements in lumabosacral spine radiography were used to assess the instability of lumbar spine. MR images were also used to evaluate the intervertebral disc abnormalities and change of bone marrow. Results: The results are as follows. 1. In the case of flexion transitional displacement proposed by Dupuis et al, the specificity and negative predictive value were good accuracy ($0.7{\sim}0.8$), and the negative predictive value was in average. In the case of extension displacement, the negative predictive value was about average ($0.6{\sim}0.7$), but the sensitivity, specificity and positive predictive value were below the poor (<0.6). On the other side, the specificity was about average but other things were below in the case of angular displacement. 2. In the case of flexion transitional displacement proposed by Dupuis et al., compared with the intervertebral disc abnormalities, the negative prediction value was excellent, the sensitivity good, and the specificity about average. In the case of extension, the negative prediction value was about average, but the other things were poor. On the other side the specificity and negative predictive value had good accuracy and the sensitivity and positive prediction value were below average in the case of angular displacement. Conclusion: The above results show that the radiography finding is sufficiently helpful to find the lumbar spine instability as an economic point of view.

• Journal of dental hygiene science
• /
• v.24 no.1
• /
• pp.22-28
• /
• 2024

Background: Particulate matter (PM) has been extensively observed due to its negative association with human health. Previous research revealed the possible negative effect of air pollutant exposure on oral health. However, the predictive model between air pollutant exposure and the prevalence of periodontitis has not been observed yet. Therefore, this study aims to propose a predictive model for the number of patients with periodontitis exposed to PM and atmospheric factors in South Korea using deep learning. Methods: This study is a retrospective cohort study utilizing secondary data from the Korean Statistical Information Service and the Health Insurance Review and Assessment database for air pollution and the number of patients with periodontitis, respectively. Data from 2015 to 2022 were collected and consolidated every month, organized by region. Following data matching and management, the deep neural networks (DNN) model was applied, and the mean absolute percentage error (MAPE) value was calculated to ensure the accuracy of the model. Results: As we evaluated the DNN model with MAPE, the multivariate model of air pollution including exposure to PM_2.5, PM₁₀, and other atmospheric factors predict approximately 85% of the number of patients with periodontitis. The MAPE value ranged from 12.85 to 17.10 (mean±standard deviation=14.12±1.30), indicating a commendable level of accuracy. Conclusion: In this study, the predictive model for the number of patients with periodontitis is developed based on air pollution, including exposure to PM_2.5, PM₁₀, and other atmospheric factors. Additionally, various relevant factors are incorporated into the developed predictive model to elucidate specific causal relationships. It is anticipated that future research will lead to the development of a more accurate model for predicting the number of patients with periodontitis.

• Asian Pacific Journal of Cancer Prevention
• /
• v.13 no.8
• /
• pp.3611-3615
• /
• 2012

Objective: The objective of this study was to establish the diagnostic accuracy, specificity and sensitivity of fine needle aspiration cytology(FNAC) for intra-oral tumors, comparing with histopathology as the gold standard. Materials and methods: Forty cases of FNA cytology from intraoral tumors was performed in AFID along with the demographic data and clinical information and then diagnosed at AFIP, Rawalpindi. Then the cytology results obtained per FNAC were compared with the histopathological biopsy results of the same lesions. The following variables were recorded for each patient: Age, gender, site of biopsy, diagnosis. The data were entered and analyzed using Open-epi version 2.0. Diagnostic accuracy, sensitivity, specificity, positive predictive value and negative predictive value were calculated. Cohen Kappa was further applied to compare the agreement between the biopsy and FNAC diagnoses. A p-value of < 0.05 was considered as statistically significant. Results: Among the total patients included in the study there were 24 males and 16 females, with a ratio of 1.5:1. Age of the patients ranged from 24 to 80 years with a mean of 52 years. A total of six sites were aspirated from the oral cavity with maximum (11) aspirates taken from alveolar ridge. The results of FNAC revealed that there were 32 malignant and 8 benign aspirates. Confirmation through histopathological analysis came for 31/32 malignant cases while one was falsely given positive for malignancy on FNAC. Among a total of 40 cases, 31(77%) cases diagnosed were found to be malignant and remaining 9(23%) were benign. The FNAC results revealed 32 malignant and 8 benign lesions. Histopathology of the subsequent surgically excised specimen showed malignant lesions in 31(77%) and benign in 9(23%) patients. As a whole, it was found that the absolute sensitivity for introral FNAC was 100% and specificity 89% with positive predictive value of 97% and negative predictive value of 100%. Conclusion: Cytological diagnosis was almost corroborative with final histopathological diagnosis in all cases, with very few exceptions, exhibiting high diagnostic accuracy.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.2521-2525
• /
• 2005

In this paper, we presented a predictive control technique, which is based on wavelet neural network (WNN), for the control of chaotic systems whose precise mathematical models are not available. The WNN is motivated by both the multilayer feedforward neural network definition and wavelet decomposition. The wavelet theory improves the convergence of neural network. In order to design predictive controller effectively, the WNN is used as the predictor whose parameters are tuned by error between the output of actual plant and the output of WNN. Also the training method for the finding a good WNN model is the Extended Kalman algorithm which updates network parameters to converge to the reference signal during a few iterations. The benefit of EKF training method is that the WNN model can have better accuracy for the unknown plant. Finally, through computer simulations, we confirmed the performance of the proposed control method.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.12 no.1
• /
• pp.768-783
• /
• 2020

Typically, a Dynamic Positioning System (DPS) uses a PID feed-back system, and it often adopts a wind feed-forward system because of its easier implementation than a feed-forward system based on current or wave. But, because a ship's drifting motion is caused by wind, current, and wave drift loads, all three environmental loads should be considered. In this study, a motion predictive control for the PID feedback system of the DPS is proposed, which considers the three environmental loads by utilizing predicted drifted ship positions in the future since it contains information about the three environmental loads from the moment to the future. The prediction accuracy for the future drifted ship position is ensured by adopting deep learning algorithms and a replay buffer. Finally, it is shown that the proposed motion predictive system results in better station-keeping performance than the wind feed-forward system.