• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.1
• /
• pp.16-37
• /
• 2022

Accurate liver segment segmentation based on radiological images is indispensable for the preoperative analysis of liver tumor resection surgery. However, most of the existing segmentation methods are not feasible to be used directly for this task due to the challenge of exact edge prediction with some tiny and slender vessels as its clinical segmentation criterion. To address this problem, we propose a novel deep learning based segmentation model, called Boundary-Aware Dual Attention Liver Segment Segmentation Model (BADA). This model can improve the segmentation accuracy of liver segments with enhancing the edges including the vessels serving as segment boundaries. In our model, the dual gated attention is proposed, which composes of a spatial attention module and a semantic attention module. The spatial attention module enhances the weights of key edge regions by concerning about the salient intensity changes, while the semantic attention amplifies the contribution of filters that can extract more discriminative feature information by weighting the significant convolution channels. Simultaneously, we build a dataset of liver segments including 59 clinic cases with dynamically contrast enhanced MRI(Magnetic Resonance Imaging) of portal vein stage, which annotated by several professional radiologists. Comparing with several state-of-the-art methods and baseline segmentation methods, we achieve the best results on this clinic liver segment segmentation dataset, where Mean Dice, Mean Sensitivity and Mean Positive Predicted Value reach 89.01%, 87.71% and 90.67%, respectively.

• International Journal of Computer Science & Network Security
• /
• v.22 no.9
• /
• pp.175-182
• /
• 2022

In our daily life, we come across different types of information, for example in the format of multimedia and text. We all need different types of information for our common routines as watching/reading the news, listening to the radio, and watching different types of videos. However, sometimes we could run into problems when a certain type of information is required. For example, someone is listening to the radio and wants to listen to jazz, and unfortunately, all the radio channels play pop music mixed with advertisements. The listener gets stuck with pop music and gives up searching for jazz. So, the above example can be solved with an automatic audio classification system. Deep Learning (DL) models could make human life easy by using audio classifications, but it is expensive and difficult to deploy such models at edge devices like nano BLE sense raspberry pi, because these models require huge computational power like graphics processing unit (G.P.U), to solve the problem, we proposed DL model. In our proposed work, we had gone for a low complexity model for Audio Event Detection (AED), we extracted Mel-spectrograms of dimension 128×431×1 from audio signals and applied normalization. A total of 3 data augmentation methods were applied as follows: frequency masking, time masking, and mixup. In addition, we designed Convolutional Neural Network (CNN) with spatial dropout, batch normalization, and separable 2D inspired by VGGnet [1]. In addition, we reduced the model size by using model quantization of float16 to the trained model. Experiments were conducted on the updated dataset provided by the Detection and Classification of Acoustic Events and Scenes (DCASE) 2020 challenge. We confirm that our model achieved a val_loss of 0.33 and an accuracy of 90.34% within the 132.50KB model size.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.15 no.4
• /
• pp.249-256
• /
• 2022

In the case of Drone Photogrammetry, the "pixel to point tool" module of Metashape, Pix4D Mapper, ContextCapture, and Global MapperGIS, which is a simple software, are widely used. Each SW has its own logic for the analysis of aerial triangulation, but from the user's point of view, it is necessary to select a SW by comparative analysis of the coordinate values of geospatial information for the result. Taking aerial photos for drone photogrammetry, surveying GCP reference points through VRS-GPS Survey, processing the acquired basic data using each SW to construct ortho image and DSM, and GCPSurvey performance and acquisition from each SW The coordinates (X,Y) of the center point of the GCP target on the Ortho-Image and the height value (EL) of the GCP point by DSM were compared. According to the "Public Surveying Work Regulations", the results of each SW are all within the margin of error. It turned out that there is no problem with the regulations no matter which SW is included within the scope.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.65 no.3
• /
• pp.69-82
• /
• 2023

Representative meteorological data of the rural water district, which is the spatial unit of the study, was produced using the grid-based national standard RCP scenario rainfall data provided by the Korea Meteorological Administration. The retrospective reproducibility of the climate model scenario data was analyzed, and the change in climate characteristics in the water district unit for the future period was presented. Finally the data characteristics and differences of each meteorological element according to various spatial resolution conversion and post-processing methods were examined. As a main result, overall, the distribution of average precipitation and R95p of the grid data, has reasonable reproducibility compared to the ASOS observation, but the maximum daily rainfall tends to be distributed low nationwide. The number of rainfall days tends to be higher than the station-based observation, and this is because the grid data is generally calculated using the area average concept of representative rainfall data for each grid. In addition, in the case of coastal regions, there is a problem that administrative districts of islands and rural water districts do not match. and In the case of water districts that include mountainous areas, such as Jeju, there was a large difference in the results depending on whether or not high rainfall in the mountainous areas was reflected. The results of this study are expected to be used as foundation for selecting data processing methods when constructing future meteorological data for rural water districts for future agricutural water management plans and climate change vulnerability assessments.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.43 no.2
• /
• pp.113-119
• /
• 1998

Spatial patterns of soil temperature on sloping lands are related to the amount of solar irradiance at the surface. Since soil temperature is a critical determinant of many biological processes occurring in the soil, an accurate prediction of soil temperature distribution could be beneficial to agricultural and environmental management. However, at least two problems are identified in soil temperature prediction over natural sloped surfaces. One is the complexity of converting solar irradiances to corresponding soil temperatures, and the other, if the first problem could be solved, is the difficulty in handling large volumes of geo-spatial data. Recent developments in geographic information systems (GIS) provide the opportunity and tools to spatially organize and effectively manage data for modeling. In this paper, a simple model for conversion of solar irradiance to soil temperature is developed within a GIS environment. The irradiance-temperature conversion model is based on a geophysical variable consisting of daily short- and long-wave radiation components calculated for any slope. The short-wave component is scaled to accommodate a simplified surface energy balance expression. Linear regression equations are derived for 10 and 50 cm soil temperatures by using this variable as a single determinant and based on a long term observation data set from a horizontal location. Extendability of these equations to sloped surfaces is tested by comparing the calculated data with the monthly mean soil temperature data observed in Iowa and at 12 locations near the Tennessee - Kentucky border with various slope and aspect factors. Calculated soil temperature variations agreed well with the observed data. Finally, this method is applied to a simulation study of daily mean soil temperatures over sloped corn fields on a 30 m by 30 m resolution. The outputs reveal potential effects of topography including shading by neighboring terrain as well as the slope and aspect of the land itself on the soil temperature.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.213-215
• /
• 2021

With the development of IoT technology, various technologies such as artificial intelligence and automation are being grafted into industrial sites, and accordingly, the importance of data processing is increasing. In particular, a system based on a digital image may cause a malfunction due to noise in the image due to a sensor defect or a communication environment problem. Therefore, research on image processing has been continued as a pre-processing process, and an effective noise reduction technique is required depending on the type of noise and the characteristics of the image. In this paper, we propose a modified spatial weight filter to protect edge components in the impulse noise reduction process. The proposed algorithm divides the filtering mask into four regions and calculates the standard deviation of each region. The final output was filtered by applying a spatial weight to the region with the lowest standard deviation value. Simulation was conducted to evaluate the performance of the proposed algorithm, and it showed superior impulse noise reduction performance compared to the existing method.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.11
• /
• pp.43-52
• /
• 2023

Rubber produced by rubber companies is subjected to quality suitability inspection through rheometer test, followed by secondary processing for automobile parts. However, rheometer test is being conducted by humans and has the disadvantage of being very dependent on experts. In order to solve this problem, this paper proposes a deep learning-based rheometer quality inspection system. The proposed system combines LSTM(Long Short-Term Memory) and CNN(Convolutional Neural Network) to take advantage of temporal and spatial characteristics from the rheometer. Next, combination materials of each rubber was used as an auxiliary input to enable quality conformity inspection of various rubber products in one model. The proposed method examined its performance with 30,000 validation datasets. As a result, an F1-score of 0.9940 was achieved on average, and its excellence was proved.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.27 no.2
• /
• pp.19-33
• /
• 2024

CCTV for crime prevention is expanding; however, due to the absence of guidelines for determining installation locations, CCTV is being installed in locations unrelated to areas with frequent crime occurrences. In this study, we developed a CCTV Priority Installation Index and applied it in a case study area. The index consists of crime vulnerability and surveillance vulnerability indexes, calculated using machine learning algorithms to predict crime incident counts per grid and the proportion of unmonitored area per grid. We tested the index in a pilot area and found that utilizing the Viewshed function in CCTV visibility analysis resolved the problem of overestimating surveillance area. Furthermore, applying the index to determine CCTV installation locations effectively improved surveillance coverage. Therefore, the CCTV Priority Installation Index can be utilized as an effective decision-making tool for establishing smart and safe cities.

• Nuclear Engineering and Technology
• /
• v.56 no.9
• /
• pp.3571-3584
• /
• 2024

Reactor core transient calculation is very important for the reactor safety analysis, in which the kernel is neutron kinetics calculation by simulating the variation of neutron density or thermal power over time. Compared with the point kinetics method, the time-space neutron kinetics calculation can provide accurate variation of neutron density in both space and time domain. But it consumes a lot of resources. It is necessary to develop a surrogate model that can quickly obtain the temporal and spatial variation information of neutron density or power with acceptable calculation accuracy. This paper uses the time-varying characteristics of power to construct a time function, parameterizes the time-varying characteristics which contains the information about the spatial change of power. Thereby, the amount of targets to predict in the space domain is compressed. A surrogate method using the machine learning is proposed in this paper. In the construction of a neural network, the input is processed by a convolutional layer, followed by a fully connected layer or a deconvolution layer. For the problem of time sequence disturbance, a structure combining convolutional neural network and recurrent neural network is used. It is verified in the tests of a series of 1D, 2D and 3D reactor models. The predicted values obtained using the constructed neural network models in these tests are in good agreement with the reference values, showing the powerful potential of the surrogate models.

• Journal of Korean Association for Spatial Structures
• /
• v.11 no.1
• /
• pp.121-130
• /
• 2011

Space frame structures have the advantage of constructing a large space structures without column and it may be considered as a shell structure. Nevertheless, with the characteristics of thin and long term of spacing, the unstable problem of space structure could not be set up clearly, and there is a huge difference between theory and experiment. Therefore, in this work, the tangential stiffness matrix of space frame structures is studied to solve the instability problem, and the nonlinear incremental analysis of the structures considering rise-span ratio(${\mu}$) and the ratio of load($R_L$) is performed for searching unstable points. Basing on the results of the example, global buckling can be happened by low rise-span ratio(${\mu}$), nodal buckling can be occurred by high rise-span ratio(${\mu}$). And in case of multi node space structure applying the ratio of load($R_L$), the nodal buckling phenomenon occur at low the ratio of load($R_L$), the global buckling occur a1 high the ratio of load($R_L$). In case of the global buckling, the load of bifurcation is about from 50% to 70% of perfect one's snap-through load.