• Journal of the Korea Society of Computer and Information
• /
• v.27 no.9
• /
• pp.1-12
• /
• 2022

Traditional methods of measuring corneal ulcers were difficult to present objective basis for diagnosis because of the subjective judgment of the medical staff through photographs taken with special equipment. In this paper, we propose a method to detect the ulcer area on a pixel basis in corneal ulcer images using a semantic segmentation model. In order to solve this problem, we performed the experiment to detect the ulcer area based on the DeepLab model which has the highest performance in semantic segmentation model. For the experiment, the training and test data were selected and the backbone network of DeepLab model which set as Xception and ResNet, respectively were evaluated and compared the performances. We used Dice similarity coefficient and IoU value as an indicator to evaluate the performances. Experimental results show that when 'crop & resized' images are added to the dataset, it segment the ulcer area with an average accuracy about 93% of Dice similarity coefficient on the DeepLab model with ResNet101 as the backbone network. This study shows that the semantic segmentation model used for object detection also has an ability to make significant results when classifying objects with irregular shapes such as corneal ulcers. Ultimately, we will perform the extension of datasets and experiment with adaptive learning methods through future studies so that they can be implemented in real medical diagnosis environment.

• Bulletin of the Korean Chemical Society
• /
• v.31 no.8
• /
• pp.2147-2150
• /
• 2010

c-Jun N-terminal kinase 1 (JNK1) is involved in apoptosis, cell differentiation and proliferation. It has been reported that a flavonol, quercetin, induces cell apoptosis and JNK inhibition. In order to understand the interactions of quercetin and JNK1, we performed receptor-oriented pharmacophore based in silico screening and determined a binding model of human JNK1 and quercetin at the ATP binding site of JNK1. 5-OH of A-ring and carbonyl oxygen of C-ring of quercetin participated in hydrogen bonding interactions with backbone of E109 and M111. Additionally, 3'-OH of quercetin formed a hydrogen bond with backbone of I32. One hydrophobic interaction is related on the binding of quercetin to JNK1 with I32, N114, and V158. Based on this model, we conducted a docking study with other 8 flavonols to find possible flavonoids inhibitors of JNK1. We proposed that one flavonols, rhamnetin, can be a potent inhibitor of JNK and 5-OH of A-ring and 3'-OH of B-ring of flavonols are the essential features for JNK1 inhibition.

• Mass Spectrometry Letters
• /
• v.4 no.4
• /
• pp.71-74
• /
• 2013

In the present study, we report that the charge-directed (assisted) peptide dissociation products, such as b- and y-type peptide backbone fragments, were the major products in MS/MS and $MS^3$ applications of some o-TEMPO-Bz-C(O)-peptide ions, while radical-driven dissociation products, such as a/x and c/z-type fragments, were previously shown to be the major products in the free radical initiated peptide sequencing mass spectrometry (FRIPS MS). Those o-TEMPO-Bz-C(O)-peptides share a common feature in their sequences, that is, the peptides do not include an arginine residue that has the highest proton affinity among free amino acids. The appearance of b- and y-type fragments as major products in FRIPS MS can be understood in terms of the so-called "mobile-proton model". When the proton is highly mobilized by the absence of arginine, the chare-directed peptide dissociation pathways appear to be more competitive than the radical-driven dissociation pathways, in our FRIPS experiments.

• Proceedings of the PSK Conference
• /
• 2002.10a
• /
• pp.330.2-330.2
• /
• 2002

The conformational study on cyclic Ac-Cys-Pro-Xaa-Cys-NHMe (Ac-CPXC-NHMe: X = Ala, Val. Leu. Aib. Gly. His. Phe, Tyr. Asn. and Ser) peptides has been carried out using the ECEPP/3 force field and the hydration shell model in the unhydrated and hydrated states. This work has been undertaken to investigate structural implications of the CPXC sequence as the chain reversal for the initiation of protein folding and as the motif for active site of disulfide oxidoreductases. The backbone conformation DAAA is in common the most feasible for cyclic CPXC peptides in the hydrated state. which has a type 1${\beta}$-turn at the Pro-Xaa sequence. The proline residue and the hydrogen bond between backbones of two cystines appear to play a role in stabilizing this preferred conformation of cycilc CPXC peptides. However. the distributions of backbone conformations and ${\beta}$-turns may indicate that the cyclic CPXC peptide seems to exist as an ensemble of ${\beta}$-turns and coiled conformations. The intirnsic stability of the cyclic CPXC motif itself the active conformation appears to play a role in determining electrochemical properties of disulfide oxidoreductases.

• Wind and Structures
• /
• v.27 no.6
• /
• pp.381-397
• /
• 2018

Nonlinear behavior in fluid-structure interaction (FSI) of bridge decks becomes increasingly significant for modern bridges with increasing spans, larger flexibility and new aerodynamic deck configurations. Better understanding of the nonlinear aeroelasticity of bridge decks and further development of reduced-order nonlinear models for the aeroelastic forces become necessary. In this paper, the amplitude-dependent and neutral angle dependent nonlinearities of the motion-induced loads are further highlighted by series of computational fluid dynamics (CFD) simulations. An effort has been made to investigate a semi-analytical time-domain model of the nonlinear motion induced loads on the deck, which enables nonlinear time domain simulations of the aeroelastic responses of the bridge deck. First, the computational schemes used here are validated through theoretically well-known cases. Then, static aerodynamic coefficients of the Great Belt East Bridge (GBEB) cross section are evaluated at various angles of attack, leading to the so-called nonlinear backbone curves. Flutter derivatives of the bridge are identified by CFD simulations using forced harmonic motion of the cross-section with various frequencies. By varying the amplitude of the forced motion, it is observed that the identified flutter derivatives are amplitude-dependent, especially for $A^*_2$ and $H^*_2$ parameters. Another nonlinear feature is observed from the change of hysteresis loop (between angle of attack and lift/moment) when the neutral angles of the cross-section are changed. Based on the CFD results, a semi-analytical time-domain model for describing the nonlinear motion-induced loads is proposed and calibrated. This model is based on accounting for the delay effect with respect to the nonlinear backbone curve and is established in the state-space form. Reasonable agreement between the results from the semi-analytical model and CFD demonstrates the potential application of the proposed model for nonlinear aeroelastic analysis of bridge decks.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.3
• /
• pp.367-373
• /
• 2022

As deep learning-based autonomous driving technology develops, artificial intelligence models for various purposes have been studied. Based on these studies, several models were used simultaneously to develop autonomous driving systems. It can occur by increasing hardware resource consumption. We propose a multi-tasks model using a shared backbone to solve this problem. This can solve the increase in the number of backbones for using AI models. As a result, in the proposed lightweight model, the model parameters could be reduced by more than 50% compared to the existing model, and the speed could be improved. In addition, each lane can be classified through lane detection using the instance segmentation method. However, further research is needed on the decrease in accuracy compared to the existing model.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.7
• /
• pp.1841-1857
• /
• 2023

CenterNet, a novel object detection algorithm without anchor based on key points, regards the object as a single center point for prediction and directly regresses the object's height and width. However, because the objects have different sizes, directly regressing their height and width will make the model difficult to converge and lose the intrinsic relationship between object's width and height, thereby reducing the stability of the model and the consistency of prediction accuracy. For this problem, we proposed an algorithm based on the regression of the diagonal half-length and the center angle, which significantly compresses the solution space of the regression components and enhances the intrinsic relationship between the decoded components. First, encode the object's width and height into the diagonal half-length and the center angle, where the center angle is the angle between the diagonal and the vertical centreline. Secondly, the predicted diagonal half-length and center angle are decoded into two length components. Finally, the position of the object bounding box can be accurately obtained by combining the corresponding center point coordinates. Experiments show that, when using CenterNet as the improved baseline and resnet50 as the Backbone, the improved model achieved 81.6% and 79.7% mAP on the VOC 2007 and 2012 test sets, respectively. When using Hourglass-104 as the Backbone, the improved model achieved 43.3% mAP on the COCO 2017 test sets. Compared with CenterNet, the improved model has a faster convergence rate and significantly improved the stability and prediction accuracy.

• Korea Journal of Hospital Management
• /
• no.spc
• /
• pp.39-50
• /
• 2016

This paper discusses the strategic concepts applied to integrated delivery system(IDS). IDS is rooted in vertical integration(VI) and strategic alliance(SA), but only few knows about the theoretical backbone of the IDS. The paper explains how VI and SA applies to IDS, then provides cases of IDS rooted in strategic concepts; Kaiser Permanante Model, Mayo Clinic Model, and ACO(Accountable Care Organizations). Finally the paper provides the implication of IDS on Korean healthcare delivery system.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.04a
• /
• pp.1264-1266
• /
• 2009

We introduce a location-based routing model applied for grid backbone nodes in wireless mesh network. The number of paths with nearest distance between two nodes is calculated and used as key parameter to execute routing algorithm. Node will increase the transmission range that makes a trade off with data rate to reach its neighbors when node itself is isolated. The routing model is lightweight and oriented thanks to the simple but efficient routing algorithm.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.1
• /
• pp.57-64
• /
• 2006

Multiprocessor system on chip (MPSoC) platforms has set a new innovative trend for the SoC design. Quality of service parameters and performance matrix are leading to the adoption of new design methodology for SoC, which will incorporate highly scalable, reusable, predictable, cost and energy efficient platform not only for underlying communication backbone but also for the entire system architecture of NOC. Like the layered architecture for the communication backbone of NOC, we have proposed the entire system architecture for NOC to be a seven layered architecture in itself. Such a platform can separate the domain specific issues which will model concurrency along with the synchronization issues more effectively. For such a layered architecture, model of computation will provide a framework to that can model concurrency and synchronization issues which are natural for any application. Therefore it becomes extremely important to use a right computation model in a specific NOC region.