• KIPS Transactions on Software and Data Engineering
• /
• v.1 no.2
• /
• pp.109-114
• /
• 2012

Honeycombs are dense structures that small cysts, which generally have about 2~10 mm in diameter, are surrounded by the wall of fibrosis. When honeycomb is found in the patients, the incidence of acute exacerbation is generally very high. Thus, the observation and quantitative measurement of honeycomb are considered as a significant marker for clinical diagnosis. In this point of view, we propose an automatic segmentation method using morphological image processing and assessment of the degree of clustering techniques. Firstly, image noises were removed by the Gaussian filtering and then a morphological dilation method was applied to segment lung regions. Secondly, honeycomb cyst candidates were detected through the 8-neighborhood pixel exploration, and then non-cyst regions were removed using the region growing method and wall pattern testing. Lastly, final honeycomb regions were segmented through the extraction of dense regions which are consisted of two or more cysts using cluster analysis. The proposed method applied to 80 High resolution computed tomography (HRCT) images and achieved a sensitivity of 89.4% and PPV (Positive Predictive Value) of 72.2%.

• Journal of Convergence for Information Technology
• /
• v.8 no.3
• /
• pp.79-84
• /
• 2018

Cloud services are readily available through a variety of media, attracting a lot of attention from users. However, there are various security damages that abuse the privacy of users who use cloud services, so there is not enough technology to prevent them. In this paper, we propose a protection model to safeguard user's privacy in a cloud environment so as not to illegally exploit user's privacy. The proposed model randomly manages the user's signature to strengthen the role of the middle manager and the cloud server. In the proposed model, the user's privacy information is provided illegally by the cloud server to the user through the security function and the user signature. Also, the signature of the user can be safely used by bundling the random number of the multiplication group and the one-way hash function into the hash chain to protect the user's privacy. As a result of the performance evaluation, the proposed model achieved an average improvement of data processing time of 24.5% compared to the existing model and the efficiency of the proposed model was improved by 13.7% than the existing model because the user's privacy information was group managed.

• Journal of Korea Water Resources Association
• /
• v.54 no.5
• /
• pp.301-309
• /
• 2021

In this study, we tried to improve the performance of the existing U-net-based deep learning rainfall prediction model, which can weaken the meaning of time series order. For this, ConvLSTM2D U-Net structure model considering temporal consistency of data was applied, and we evaluated accuracy of the ConvLSTM2D U-Net model using a RainNet model and an extrapolation-based advection model. In addition, we tried to improve the uncertainty in the model training process by performing learning not only with a single model but also with 10 ensemble models. The trained neural network rainfall prediction model was optimized to generate 10-minute advance prediction data using four consecutive data of the past 30 minutes from the present. The results of deep learning rainfall prediction models are difficult to identify schematically distinct differences, but with ConvLSTM2D U-Net, the magnitude of the prediction error is the smallest and the location of rainfall is relatively accurate. In particular, the ensemble ConvLSTM2D U-Net showed high CSI, low MAE, and a narrow error range, and predicted rainfall more accurately and stable prediction performance than other models. However, the prediction performance for a specific point was very low compared to the prediction performance for the entire area, and the deep learning rainfall prediction model also had limitations. Through this study, it was confirmed that the ConvLSTM2D U-Net neural network structure to account for the change of time could increase the prediction accuracy, but there is still a limitation of the convolution deep neural network model due to spatial smoothing in the strong rainfall region or detailed rainfall prediction.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_4
• /
• pp.1925-1934
• /
• 2022

Monitoring nuclear activity for inaccessible areas using remote sensing technology is essential for nuclear non-proliferation. In recent years, deep learning has been actively used to detect nuclear-activity-related small objects. However, high-resolution satellite imagery containing small objects can result in class imbalance. As a result, there is a performance degradation problem in detecting small objects. Therefore, this study aims to improve detection accuracy by analyzing the effect of the ratio of small objects related to nuclear activity in the input data for the performance of the deep learning model. To this end, six case datasets with different ratios of small object pixels were generated and a U-Net model was trained for each case. Following that, each trained model was evaluated quantitatively and qualitatively using a test dataset containing various types of small object classes. The results of this study confirm that when the ratio of object pixels in the input image is adjusted, small objects related to nuclear activity can be detected efficiently. This study suggests that the performance of deep learning can be improved by adjusting the object pixel ratio of input data in the training dataset.

• Journal of Korea Multimedia Society
• /
• v.14 no.1
• /
• pp.54-75
• /
• 2011

PoC(Push-to-talk Over Cellular) is an integrated technology of group voice calls, video calls and internet based multimedia services. If a PoC user can not participate in the PoC session for various reasons such as an emergency situation, lack of battery capacity, then the user can use the PoC Box which has a similar functionality to the MM Box in the MMS(Multimedia Messaging Service). The RTSP(Real-Time Streaming Protocol) method is recommended to be used when there is a transmission session between the PoC box and a terminal. Since the existing VOD service uses a wired network, the packet size of RTSP-based VOD service is huge, however, the PoC service has wireless communication environments which have general characteristics to be used in RTSP method. Packet loss in a wired communication environments is relatively less than that in wireless communication environment, therefore, a buffering latency occurs in PoC service due to a play-out delay which means an asynchronous play of audio & video contents. Those problems make a user to be difficult to find the information they want when the media contents are played-out. In this paper, the following techniques and methods were proposed and their performance and superiority were verified through testing: cross-over dual reception buffering technique, advance partition multi-reception buffering technique, and on-demand multi-reception buffering technique, which are designed for effective picking up of information in media content being transmitted in short amount of time using RTSP when a user searches for media, as well as for reduction in playback delay; and same-priority packetization transmission method and priority-based packetization transmission method, which are media data packetization methods for transmission. From the simulation of functional evaluation, we could find that the proposed multiple receiving buffering and packetizing methods are superior, with respect to the media retrieval inclination, to the existing single receiving buffering method by 6-9 points from the viewpoint of effectiveness and excellence. Among them, especially, on-demand multiple receiving buffering technology with same-priority packetization transmission method is able to manage the media search inclination promptly to the requests of users by showing superiority of 3-24 points above compared to other combination methods. In addition, users could find the information they want much quickly since large amount of informations are received in a focused media retrieval period within a short time.

• The Journal of Korean Academy of Prosthodontics
• /
• v.57 no.2
• /
• pp.102-109
• /
• 2019

Purpose: The purpose of this study was to evaluate the accuracy of three types of intraoral scanners and the accuracy of the single abutment and bridge abutment model. Materials and methods: In this study, a single abutment, and a bridge abutment with missing first molar was fabricated and set as the reference model. The reference model was scanned with an industrial three-dimensional scanner and set as reference scan data. The reference model was scanned five times using the three intraoral scanners (CS3600, CS3500, and EZIS PO). This was set as the evaluation scan data. In the three-dimensional analysis (Geomagic control X), the divided abutment region was selected and analyzed to verify the scan accuracy of the abutment. Statistical analysis was performed using SPSS software (${\alpha}=.05$). The accuracy of intraoral scanners was compared using the Kruskal-Wallis test and post-test was performed using the Pairwise test. The accuracy difference between the single abutment model and the bridge abutment model was analyzed by the Mann-Whitney U test. Results: The accuracy according to the intraoral scanner was significantly different (P < .05). The trueness of the single abutment model and the bridge abutment model showed a statistically significant difference and showed better trueness in the single abutment (P < .05). There was no significant difference in the precision (P = .616). Conclusion: As a result of comparing the accuracy of single and bridge abutments, the error of abutment scan increased with increasing scan area, and the accuracy of bridge abutment model was clinically acceptable in three types of intraoral scanners.

• Journal of Korea Water Resources Association
• /
• v.45 no.8
• /
• pp.795-804
• /
• 2012

Recently, changes in rainfall intensity and patterns have been causing increasing soil loss worldwide. As a result, the water ecosystem becomes worse and crops yield are reduced with soil loss and nutrient loss with it. Many studies have been proposed to estimate runoff and soil loss to predict or decrease non-point source pollution. Although the USLE has been used for many years in estimating soil losses, the USLE cannot reflect effects on soil loss of changes in rainfall intensity and patterns. The WEPP, physically based model, is capable of predicting soil loss and runoff using various rainfall intensity. In this study, the WEPP model was simulated for sediment yield, runoff and peak runoff using data of 5, 10, 30, 60 minute term rainfall, Huff's method and design rainfall. In case of rainfall interval of 5 minutes and 60 minutes, the sediment and runoff values decreased by 24% and 19%, respectively. The peak rate runoff values decreased by 16% when rainfall interval changed from 5 minutes to 60 minutes, indicating the peak rate runoff values are affected by rainfall intensity to some degrees. As a result of simulating using Huff's method, all values (sediment yield, runoff, peak runoff) were found to be the greatest at third quartile. According to the analysis under various design rainfall conditions (2, 3, 5, 10, 20, 30, 50, 100, 200, 300 years frequency), sediment yield, runoff, and peak runoff of 906.2%, 249.4% and 183.9% were estimated using 2 year to 300 year frequency rainfall data.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.21 no.2
• /
• pp.74-79
• /
• 2017

Purpose Proton therapy can deliver an optimal dose to tumor while reducing unnecessary dose to normal tissue as compared the conventional photon therapy. As proton beams are irradiated into tissue, various positron emitters are produced via nuclear fragmentation reactions. These positron emitters could be used for the dose verification by using PET. However, the short half-life of the radioisotopes makes it hard to obtain the enough amounts of events. The aim of this study is to investigate the effect of off-line PET imaging scan time on the PET image quality. Materials and Methods The various diameters of spheres (D=37, 28, 22 mm) filled with distilled water were inserted in a 2001 IEC body phantom. Then proton beams (100 MU) were irradiated into the center of the each sphere using the wobbling technique with the gantry angle of $0^{\circ}$. The modulation widths of the spread out bragg peak were 16.4, 14.7 and 9.3 cm for the spheres of 37, 28 and 22 mm in diameters respectively. After 5 min of the proton irradiation, the PET images of the IEC body phantom were obtained for 50 min. The PET images with different time courses (0-10 min, 11-20 min, 21-30 min, 31-40 min and 41-50 min) were obtained by dividing the frame with a duration of 10 min. In order to evaluate the off-line PET image quality with the different time courses, the contrast-to-noise ratio (CNR) of the PET image calculated for each sphere. Results The CNRs of the sphere (D=37 mm) were 0.43, 0.42, 0.40, 0.31 and 0.21 for the time courses of 0-10 min, 11-20 min, 21-30 min, 31-40 min and 41-50 min respectively. The CNRs of the sphere (D=28 mm) were 0.36, 0.32, 0.27, 0.19 and 0.09 for the time courses of 0-10 min, 11-20 min, 21-30 min, 31-40 min and 41-50 min respectively. The CNR of 37 mm sphere was decreased rapidly after 30 min of the proton irradiation. In case of the spheres of 28 mm and 22 mm, the CNR was decreased drastically after 20 min of the irradiation. Conclusion The off-line PET imaging time is an important factor for the monitoring of the proton therapy. In case of the lesion diameter of 22 mm, the off-line PET image should be obtained within 25 min after the proton irradiation. When it comes to small size of tumor, the long PET imaging time will be beneficial for the proton therapy treatment monitoring.

• Journal of the Korean Society for Marine Environment & Energy
• /
• v.13 no.3
• /
• pp.187-197
• /
• 2010

Carbon dioxide Capture and Storage(CCS) is regarded as one of the most promising options to response climate change. CCS is a three-stage process consisting of the capture of carbon dioxide($CO_2$), the transport of $CO_2$ to a storage location, and the long term isolation of $CO_2$ from the atmosphere for the purpose of carbon emission mitigation. Up to now, process design for this $CO_2$ marine geological storage has been carried out mainly on pure $CO_2$. Unfortunately the $CO_2$ mixture captured from the power plants and steel making plants contains many impurities such as $N_2$, $O_2$, Ar, $H_2O$, $SO_2$, $H_2S$. A small amount of impurities can change the thermodynamic properties and then significantly affect the compression, purification, transport and injection processes. In order to design a reliable $CO_2$ marine geological storage system, it is necessary to analyze the impact of these impurities on the whole CCS process at initial design stage. The purpose of the present paper is to compare and analyse the relevant physical property models including BWRS, PR, PRBM, RKS and SRK equations of state, and NRTL-RK model which are crucial numerical process simulation tools. To evaluate the predictive accuracy of the equation of the state for $CO_2-SO_2$ mixture, we compared numerical calculation results with reference experimental data. In addition, optimum binary parameter to consider the interaction of $CO_2$ and $SO_2$ molecules was suggested based on the mean absolute percent error. In conclusion, we suggest the most reliable physical property model with optimized binary parameter in designing the $CO_2-SO_2$ mixture marine geological storage process.

• The KIPS Transactions:PartA
• /
• v.11A no.7 s.91
• /
• pp.555-562
• /
• 2004

Both global volume reduction and local shape changes of hippocampus within the brain indicate their abnormal neurological states. Hippocampal shape analysis consists of two main steps. First, construct a hippocampal shape representation model ; second, compute a shape similarity from this representation. This paper proposes a novel method for the analysis of hippocampal shape using integrated Octree-based representation, containing meshes, voxels, and skeletons. First of all, we create multi-level meshes by applying the Marching Cube algorithm to the hippocampal region segmented from MR images. This model is converted to intermediate binary voxel representation. And we extract the 3D skeleton from these voxels using the slice-based skeletonization method. Then, in order to acquire multiresolutional shape representation, we store hierarchically the meshes, voxels, skeletons comprised in nodes of the Octree, and we extract the sample meshes using the ray-tracing based mesh sampling technique. Finally, as a similarity measure between the shapes, we compute $L_2$ Norm and Hausdorff distance for each sam-pled mesh pair by shooting the rays fired from the extracted skeleton. As we use a mouse picking interface for analyzing a local shape inter-actively, we provide an interaction and multiresolution based analysis for the local shape changes. In this paper, our experiment shows that our approach is robust to the rotation and the scale, especially effective to discriminate the changes between local shapes of hippocampus and more-over to increase the speed of analysis without degrading accuracy by using a hierarchical level-of-detail approach.