• Nuclear Engineering and Technology
• /
• v.54 no.4
• /
• pp.1439-1448
• /
• 2022

Background: We investigated the feasibility of in vitro radiosensitivity prediction with gene expression using deep learning. Methods: A microarray gene expression of the National Cancer Institute-60 (NCI-60) panel was acquired from the Gene Expression Omnibus. The clonogenic surviving fractions at an absorbed dose of 2 Gy (SF2) from previous publications were used to measure in vitro radiosensitivity. The radiosensitivity prediction model was based on the convolutional neural network. The 6-fold cross-validation (CV) was applied to train and validate the model. Then, the leave-one-out cross-validation (LOOCV) was applied by using the large-errored samples as a validation set, to determine whether the error was from the high bias of the folded CV. The criteria for correct prediction were defined as an absolute error<0.01 or a relative error<10%. Results: Of the 174 triplicated samples of NCI-60, 171 samples were correctly predicted with the folded CV. Through an additional LOOCV, one more sample was correctly predicted, representing a prediction accuracy of 98.85% (172 out of 174 samples). The average relative error and absolute errors of 172 correctly predicted samples were 1.351±1.875% and 0.00596±0.00638, respectively. Conclusion: We demonstrated the feasibility of a deep learning-based in vitro radiosensitivity prediction using gene expression.

• The Korean Journal of Food And Nutrition
• /
• v.37 no.4
• /
• pp.197-210
• /
• 2024

This study aims to develop a deep learning model to monitor rice serving amounts in institutional foodservice, enhancing personalized nutrition management. The goal is to identify the best convolutional neural network (CNN) for detecting rice quantities on serving trays, addressing balanced dietary intake challenges. Both a vanilla CNN and 12 pre-trained CNNs were tested, using features extracted from images of varying rice quantities on white trays. Configurations included optimizers, image generation, dropout, feature extraction, and fine-tuning, with top-1 validation accuracy as the evaluation metric. The vanilla CNN achieved 60% top-1 validation accuracy, while pre-trained CNNs significantly improved performance, reaching up to 90% accuracy. MobileNetV2, suitable for mobile devices, achieved a minimum 76% accuracy. These results suggest the model can effectively monitor rice servings, with potential for improvement through ongoing data collection and training. This development represents a significant advancement in personalized nutrition management, with high validation accuracy indicating its potential utility in dietary management. Continuous improvement based on expanding datasets promises enhanced precision and reliability, contributing to better health outcomes.

• Korean Journal of Radiology
• /
• v.22 no.3
• /
• pp.476-488
• /
• 2021

Objective: We aimed to develop a deep neural network for segmenting lung parenchyma with extensive pathological conditions on non-contrast chest computed tomography (CT) images. Materials and Methods: Thin-section non-contrast chest CT images from 203 patients (115 males, 88 females; age range, 31-89 years) between January 2017 and May 2017 were included in the study, of which 150 cases had extensive lung parenchymal disease involving more than 40% of the parenchymal area. Parenchymal diseases included interstitial lung disease (ILD), emphysema, nontuberculous mycobacterial lung disease, tuberculous destroyed lung, pneumonia, lung cancer, and other diseases. Five experienced radiologists manually drew the margin of the lungs, slice by slice, on CT images. The dataset used to develop the network consisted of 157 cases for training, 20 cases for development, and 26 cases for internal validation. Two-dimensional (2D) U-Net and three-dimensional (3D) U-Net models were used for the task. The network was trained to segment the lung parenchyma as a whole and segment the right and left lung separately. The University Hospitals of Geneva ILD dataset, which contained high-resolution CT images of ILD, was used for external validation. Results: The Dice similarity coefficients for internal validation were 99.6 ± 0.3% (2D U-Net whole lung model), 99.5 ± 0.3% (2D U-Net separate lung model), 99.4 ± 0.5% (3D U-Net whole lung model), and 99.4 ± 0.5% (3D U-Net separate lung model). The Dice similarity coefficients for the external validation dataset were 98.4 ± 1.0% (2D U-Net whole lung model) and 98.4 ± 1.0% (2D U-Net separate lung model). In 31 cases, where the extent of ILD was larger than 75% of the lung parenchymal area, the Dice similarity coefficients were 97.9 ± 1.3% (2D U-Net whole lung model) and 98.0 ± 1.2% (2D U-Net separate lung model). Conclusion: The deep neural network achieved excellent performance in automatically delineating the boundaries of lung parenchyma with extensive pathological conditions on non-contrast chest CT images.

• Journal of Korea Society of Industrial Information Systems
• /
• v.25 no.4
• /
• pp.17-27
• /
• 2020

In this paper, we proposed verification methods to prove the effectiveness of automatic test equipment (ATE) for weapon systems. Since the test results from the unproven ATE is not reliable and its use is limited as objective data, it is essential to verify the test equipment in order to guarantee the quality level of the unit under test (UUT). Through the suggested methods, it is applied to the ATE of the tactical information communications network (TICN) system to confirm the verification results and to describe the validation results.

• International Journal of Computer Science & Network Security
• /
• v.21 no.5
• /
• pp.175-182
• /
• 2021

The greenhouse is a complex system. It is subject to multiple input disturbances that are highly dependent on meteorological conditions, which are generally nonlinear and have a great influence on the agricultural production. The objective of this paper is to study the fuzzy logic technique as one of the most efficient technologies to control the greenhouse. The fuzzy logic controller (FLC) was developed to activate the actuator based on a ventilator was installed in an experimental greenhouse to obtain a desired temperature of the microclimate despite the externals disturbances.

• The Journal of Korea Robotics Society
• /
• v.19 no.2
• /
• pp.188-195
• /
• 2024

This paper proposes a photorealistic real-time dense 3D mapping system that utilizes a neural network-based image enhancement method and mesh-based map representation. Due to the characteristics of the underwater environment, where problems such as hazing and low contrast occur, it is hard to apply conventional simultaneous localization and mapping (SLAM) methods. At the same time, the behavior of Autonomous Underwater Vehicle (AUV) is computationally constrained. In this paper, we utilize a neural network-based image enhancement method to improve pose estimation and mapping quality and apply a sliding window-based mesh expansion method to enable lightweight, fast, and photorealistic mapping. To validate our results, we utilize real-world and indoor synthetic datasets. We performed qualitative validation with the real-world dataset and quantitative validation by modeling images from the indoor synthetic dataset as underwater scenes.

• Journal of the Korean Data and Information Science Society
• /
• v.15 no.2
• /
• pp.499-506
• /
• 2004

The Unscented Kalman Filter is known to outperform the Extended Kalman Filter for the nonlinear state estimation with a significance advantage that it does not require the computation of Jacobian but EKF has a competitive advantage to the UKF on the performance time. We compare both algorithms on training the artificial neural network. The validation data set is used to estimate parameters which are supposed to result in better fitting for the test data set. Experimental results are presented which indicate the performance of both algorithms.

• Korean Journal of Biological Psychiatry
• /
• v.12 no.2
• /
• pp.165-172
• /
• 2005

Objectives:The purpose of this study is to 1) conduct a discrimination analysis of schizophrenia and bipolar affective disorder using MMPI profile through artificial neural network analysis and logistic regression analysis, 2) to make a comparison between advantages and disadvantages of the two methods, and 3) to demonstrate the usefulness of artificial neural network analysis of psychiatric data. Procedure:The MMPI profiles for 181 schizophrenia and bipolar affective disorder patients were selected. Of these profiles, 50 were randomly placed in the learning group and the remaining 131 were placed in the validation group. The artificial neural network was trained using the profiles of the learning group and the 131 profiles of the validation group were analyzed. A logistic regression analysis was then conducted in a similar manner. The results of the two analyses were compared and contrasted using sensitivity, specificity, ROC curves, and kappa index. Results:Logistic regression analysis and artificial neural network analysis both exhibited satisfactory discriminating ability at Kappa index of greater than 0.4. The comparison of the two methods revealed artificial neural network analysis is superior to logistic regression analysis in its discriminating capacity, displaying higher values of Kappa index, specificity, and AUC(Area Under the Curve) of ROC curve than those of logistic regression analysis. Conclusion:Artificial neural network analysis is a new tool whose frequency of use has been increasing for its superiority in nonlinear applications. However, it does possess insufficiencies such as difficulties in understanding the relationship between dependent and independent variables. Nevertheless, when used in conjunction with other analysis tools which supplement it, such as the logistic regression analysis, it may serve as a powerful tool for psychiatric data analysis.

• Korean Journal of Remote Sensing
• /
• v.15 no.2
• /
• pp.107-117
• /
• 1999

A comparison of a neural network approach with the conventional statistical methods, multiple regression and band ratio analyses, for the estimation of water quality parameters in presented in this paper. The Landsat TM image of Lake Daechung acquired on March 18, 1996 and the thirty in-situ sampling data sets measured during the satellite overpass were used for the comparison. We employed a three-layered and feedforward network trained by backpropagation algorithm. A cross validation was applied because of the small number of training pairs available for this study. The neural network showed much more successful performance than the conventional statistical analyses, although the results of the conventional statistical analyses were significant. The superiority of a neural network to statistical methods in estimating water quality parameters is strictly because the neural network modeled non-linear behaviors of data sets much better.

• Korean Journal of Remote Sensing
• /
• v.38 no.1
• /
• pp.103-110
• /
• 2022

Since satellite images generally include clouds in the atmosphere, it is essential to detect or mask clouds before satellite image processing. Clouds were detected using physical characteristics of clouds in previous research. Cloud detection methods using deep learning techniques such as CNN or the modified U-Net in image segmentation field have been studied recently. Since image segmentation is the process of assigning a label to every pixel in an image, precise pixel-based dataset is required for cloud detection. Obtaining accurate training datasets is more important than a network configuration in image segmentation for cloud detection. Existing deep learning techniques used different training datasets. And test datasets were extracted from intra-dataset which were acquired by same sensor and procedure as training dataset. Different datasets make it difficult to determine which network shows a better overall performance. To verify the effectiveness of the cloud detection network such as Cloud-Net, two types of networks were trained using the cloud dataset from KOMPSAT-3 images provided by the AIHUB site and the L8-Cloud dataset from Landsat8 images which was publicly opened by a Cloud-Net author. Test data from intra-dataset of KOMPSAT-3 cloud dataset were used for validating the network. The simulation results show that the network trained with KOMPSAT-3 cloud dataset shows good performance on the network trained with L8-Cloud dataset. Because Landsat8 and KOMPSAT-3 satellite images have different GSDs, making it difficult to achieve good results from cross-sensor validation. The network could be superior for intra-dataset, but it could be inferior for cross-sensor data. It is necessary to study techniques that show good results in cross-senor validation dataset in the future.