• Korean Journal of Radiology
• /
• v.22 no.1
• /
• pp.118-130
• /
• 2021

Objective: This study aimed to investigate the blood-brain barrier (BBB) disruption in mild traumatic brain injury (mTBI) patients with post-concussion syndrome (PCS) using dynamic contrast-enhanced (DCE) magnetic resonance (MR) imaging and automatic whole brain segmentation. Materials and Methods: Forty-two consecutive mTBI patients with PCS who had undergone post-traumatic MR imaging, including DCE MR imaging, between October 2016 and April 2018, and 29 controls with DCE MR imaging were included in this retrospective study. After performing three-dimensional T1-based brain segmentation with FreeSurfer software (Laboratory for Computational Neuroimaging), the mean K^trans and v_p from DCE MR imaging (derived using the Patlak model and extended Tofts and Kermode model) were analyzed in the bilateral cerebral/cerebellar cortex, bilateral cerebral/cerebellar white matter (WM), and brainstem. K^trans values of the mTBI patients and controls were calculated using both models to identify the model that better reflected the increased permeability owing to mTBI (tendency toward higher K^trans values in mTBI patients than in controls). The Mann-Whitney U test and Spearman rank correlation test were performed to compare the mean K^trans and v_p between the two groups and correlate K^trans and v_p with neuropsychological tests for mTBI patients. Results: Increased permeability owing to mTBI was observed in the Patlak model but not in the extended Tofts and Kermode model. In the Patlak model, the mean K^trans in the bilateral cerebral cortex was significantly higher in mTBI patients than in controls (p = 0.042). The mean v_p values in the bilateral cerebellar WM and brainstem were significantly lower in mTBI patients than in controls (p = 0.009 and p = 0.011, respectively). The mean K^trans of the bilateral cerebral cortex was significantly higher in patients with atypical performance in the auditory continuous performance test (commission errors) than in average or good performers (p = 0.041). Conclusion: BBB disruption, as reflected by the increased K^trans and decreased v_p values from the Patlak model, was observed throughout the bilateral cerebral cortex, bilateral cerebellar WM, and brainstem in mTBI patients with PCS.

• Proceedings of the KIEE Conference
• /
• 2002.07a
• /
• pp.169-171
• /
• 2002

The western route of KEPCO's 765kV transmission line has been tentatively operating as 345kV voltage before commercial operation. After finishing the test operation of 765kV substation in 2002. KEPCO decided to operate the 765kV line for commercial operation. During the applying of 765kV voltage to the transmission line, double circuit transmission line will be operated with two voltage grades of 765kV and 345kV. Because the earthing switch is installed on both end of transmission line, we had estimated the electrostatic induction voltage and electromagnetic induction current before the line energizing in order to confirm the ratings of earthing switch. The induced voltage and current is very important for the maintenance of parallel circuit. This paper describes the simulation study of electrical phenomena such as electrostatic induction voltage from the parallel line and electromagnetic induction current from the parallel circuit. The transmission line model was developed by EMTP (Electro-Magnetic Transient Program).

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.399-401
• /
• 2022

A definitive diagnosis to classify the breast malignancy status may be achieved by microscopic analysis using surgical open biopsy. However, this procedure requires experts in the specializing of histopathological image analysis directing to time-consuming and high cost. To overcome these issues, deep learning is considered practically efficient to categorize breast cancer into benign and malignant from histopathological images in order to assist pathologists. This study presents a pre-trained convolutional neural network model architecture with a 100% fine-tuning scheme and Adagrad optimizer to classify the breast cancer histopathological images into benign and malignant using a 40× magnification BreaKHis dataset. The pre-trained architecture was constructed using the InceptionResNetV2 model to generate a modified InceptionResNetV2 by substituting the last layer with dense and dropout layers. The results by demonstrating training loss of 0.25%, training accuracy of 99.96%, validation loss of 3.10%, validation accuracy of 99.41%, test loss of 8.46%, and test accuracy of 98.75% indicated that the modified InceptionResNetV2 model is reliable to predict the breast malignancy type from histopathological images. Future works are necessary to focus on k-fold cross-validation, optimizer, model, hyperparameter optimization, and classification on 100×, 200×, and 400× magnification.

• The KIPS Transactions:PartD
• /
• v.14D no.1 s.111
• /
• pp.57-66
• /
• 2007

Organizations of Software development are very important issue on enhancement of a software quality as rapid progress of software industry. Especially there are diverse attempts for enhancement of test maturity of the software organization through some kinds of the test maturity model. But the current test maturity models based on CMM(Capability Maturity Model) lack part of actual testing measurement and only measure level of test maturity. To solve these problems, we suggest 'double V-model' to execute both software development process and test process simultaneously, and also 'test attributes to Maturity Levels Correlation Matrix' for evaluating level of test maturity included with definitions of test attribute and level. That is, we enhance TMM(Test Maturity Model) adopted with 'Improvement Suggestion' of TPI(Test Process Improvement) which is easy the evaluation of test maturity of organization and gives the direction of improvement to level up the test maturity for the measured organization. As a result, we will contribute to level up the test maturity of the organization.

• Proceedings of the Korean Society of Crop Science Conference
• /
• 2022.10a
• /
• pp.80-80
• /
• 2022

Estimation of heading date of paddy rice is laborious and time consuming. Therefore, automatic estimation of heading date of paddy rice is highly essential. In this experiment, deep learning classification models were used to classify two difference categories of rice (vegetative and reproductive stage) based on the panicle initiation of paddy field. Specifically, the dataset includes 444 slanted view images belonging to two categories and was then expanded to include 1,497 images via IMGAUG data augmentation technique. We adopt two transfer learning strategies: (First, used transferring model weights already trained on ImageNet to six classification network models: VGGNet, ResNet, DenseNet, InceptionV3, Xception and MobileNet, Second, fine-tuned some layers of the network according to our dataset). After training the CNN model, we used several evaluation metrics commonly used for classification tasks, including Accuracy, Precision, Recall, and F1-score. In addition, GradCAM was used to generate visual explanations for each image patch. Experimental results showed that the InceptionV3 is the best performing model in terms of the accuracy, average recall, precision, and F1-score. The fine-tuned InceptionV3 model achieved an overall classification accuracy of 0.95 with a high F1-score of 0.95. Our CNN model also represented the change of rice heading date under different date of transplanting. This study demonstrated that image based deep learning model can reliably be used as an automatic monitoring system to detect the heading date of rice crops using CCTV camera.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.12
• /
• pp.2243-2251
• /
• 2016

In this paper, we propose a theoretical model for characterization and upper bounds of [1,2]-domination set of network which has tree structure. In detail, we propose a theoretic model for upper bounds on [1,2]-domination set of a tree network which has some typical constrains. To that purpose, we introduce a graph theory to model and analyze the characteristics of tree structure networks. We assume a node subset D of a graph G=(V,E). We define that D is a [1,2]-dominant set if for any node v in set V which is not an element of a set D is adjacent to a node or two nodes of an element in a set D (that is, $1{\leq}{\mid}N({\upsilon}){\bigcap}D{\mid}{\leq}2$ for every node $v{\in}V-D$). The minimum cardinality of a [1,2]-dominating set of G, which is denoted by ${\gamma}_{[1,2]}(G)$, is called the [1,2]-domination number of G. In this paper, we show new upper bounds and characteristics about the [1,2]-domination number of tree.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.37 no.6
• /
• pp.24-33
• /
• 2000

Switching behaviour of the ferroelectric thin film and device characteristics of the MFSFET(Metal-Ferroelectric-Semiconductor FET) are simulated with taking into account the accumulation of oxygen vacancies near interface between the ferroelectric thin film and the bottom electrode caused by the progress of fatigue. In our switching model, relative switched charge is 0.74 nC before fatigue, but after the progress of fatigue it reduces to 0.15 nC with the generation of oxygen vacancies. It indicates that the generation of oxygen vacancies strongly suppresses polarization reversal. $C-V_G\;and\;I_D-V_G$ curves in our MFSFET device model exhibit the memory window of 2 V and show the accumulation, the depletion and the inversion regions in capacitance characteristic clearly. The difference of saturation drain current of the device before fatigue in shown by the dual threshold voltages in $I_D-V_G$ curve as 6nA/$cm^2$ and decreases as much as 50% after fatigue. Decrease of the difference of saturation drain currents by fatigue implies that the accumulation of oxygen vacancies with the fatigue should be avoided in the device application. Our simulation model is expected to play an important role in estimation of the behavior of MFSFET device with various ferroelectric thin films.

• Journal of the Institute of Convergence Signal Processing
• /
• v.7 no.3
• /
• pp.108-115
• /
• 2006

In this paper, a recognition algorithm of the straight line components of lane markings and an obstacle in the travelling lane region is proposed. This algorithm also involve the pitching error correction algorithm due to traveling vehicle's fluctuation. In order to reduce their error a practical road image modelling algorithm using V.F. model and camera calibration procedure are suggested to adapt the geometric variations. It is obtained the 3D world coordinate data by the 2D road images. In experimental test, we showed that this algorithm is available to recognize lane markings and an obstacle in the traveling lane.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.20 no.2
• /
• pp.114-118
• /
• 1987

The authors carried out a model experiment to examine the hydrodynamic charactristics of the simple camber and the super-V otter board. The model otter boards are made of 1 mm thick iron plate. The simple camber otter board is made to have $12\%$ camber ratio and $432\;cm^2$ plane projected area, and the super-V otter board to have the same camber ratio as the former in every latitudinal section and almost the same plane projected area. The experiment had been done in a circular flow tank in the speed range of $0.1\~1.2m/sec$. As a result, it is examined that in the simple camber otter board the most effective angle of attack is about $25^{\circ}$, the shearing coefficient 1.47 and the drag coefficient 0.42, while in the super-V otter board they are about $20^{\circ}$, 1.40 and 0.40 respectively, so that the simple camber otter board performs a little better efficiency than the super-V otter board.

• Journal of Information Processing Systems
• /
• v.19 no.1
• /
• pp.67-79
• /
• 2023

In the image field, data augmentation refers to increasing the amount of data through an editing method such as rotating or cropping a photo. In this study, a generative adversarial network (GAN) image was created using CycleGAN, and various colors of dogs were reflected through data augmentation. In particular, dog data from the Stanford Dogs Dataset and Oxford-IIIT Pet Dataset were used, and 10 breeds of dog, corresponding to 300 images each, were selected. Subsequently, a GAN image was generated using CycleGAN, and four learning groups were established: 2,000 original photos (group I); 2,000 original photos + 1,000 GAN images (group II); 3,000 original photos (group III); and 3,000 original photos + 1,000 GAN images (group IV). The amount of data in each learning group was augmented using existing data augmentation methods such as rotating, cropping, erasing, and distorting. The augmented photo data were used to train the MobileNet_v3_Large, ResNet-152, InceptionResNet_v2, and NASNet_Large frameworks to evaluate the classification accuracy and loss. The top-3 accuracy for each deep neural network model was as follows: MobileNet_v3_Large of 86.4% (group I), 85.4% (group II), 90.4% (group III), and 89.2% (group IV); ResNet-152 of 82.4% (group I), 83.7% (group II), 84.7% (group III), and 84.9% (group IV); InceptionResNet_v2 of 90.7% (group I), 88.4% (group II), 93.3% (group III), and 93.1% (group IV); and NASNet_Large of 85% (group I), 88.1% (group II), 91.8% (group III), and 92% (group IV). The InceptionResNet_v2 model exhibited the highest image classification accuracy, and the NASNet_Large model exhibited the highest increase in the accuracy owing to data augmentation.