• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.6
• /
• pp.267-275
• /
• 2023

This paper presents the development of specialized software for annotating volume-of-interest on ¹⁸F-FDG PET/CT images with the goal of facilitating the studies and diagnosis of head and neck cancer (HNC). To achieve an efficient annotation process, we employed the SE-Norm-Residual Layer-based U-Net model. This model exhibited outstanding proficiency to segment cancerous regions within ¹⁸F-FDG PET/CT scans of HNC cases. Manual annotation function was also integrated, allowing researchers and clinicians to validate and refine annotations based on dataset characteristics. Workspace has a display with fusion of both PET and CT images, providing enhance user convenience through simultaneous visualization. The performance of deeplearning model was validated using a Hecktor 2021 dataset, and subsequently developed semi-automatic annotation functionalities. We began by performing image preprocessing including resampling, normalization, and co-registration, followed by an evaluation of the deep learning model performance. This model was integrated into the software, serving as an initial automatic segmentation step. Users can manually refine pre-segmented regions to correct false positives and false negatives. Annotation images are subsequently saved along with their corresponding ¹⁸F-FDG PET/CT fusion images, enabling their application across various domains. In this study, we developed a semi-automatic annotation software designed for efficiently generating annotated lesion images, with applications in HNC research and diagnosis. The findings indicated that this software surpasses conventional tools, particularly in the context of HNC-specific annotation with ¹⁸F-FDG PET/CT data. Consequently, developed software offers a robust solution for producing annotated datasets, driving advances in the studies and diagnosis of HNC.

• Convergence Security Journal
• /
• v.24 no.1
• /
• pp.21-26
• /
• 2024

The security model in the previous network environment has a vulnerability in which resource access control for trusted users is not properly achieved using the Perimeter model based on trust. The Zero Trust is an absolute principle to assume that the users and devices accessing internal data have nothing to trust. Applying the Zero Trust principle is very successful in reducing the attack surface of an organization, and by using the Zero Trust, it is possible to minimize damage when an attack occurs by limiting the intrusion to one small area through segmentation. ZTNA is a major technology that enables organizations to implement Zero Trust security, and similar to Software Defined Boundary (SDP), ZTNA hides most of its infrastructure and services, establishing one-to-one encrypted connections between devices and the resources they need. In this study, we review the functions and requirements that become the principles of the ZTNA architecture, and also study the security requirements and additional considerations according to the construction and operation of the ZTNA solution.

• Journal of Animal Science and Technology
• /
• v.66 no.1
• /
• pp.31-56
• /
• 2024

Pig farming, a vital industry, necessitates proactive measures for early disease detection and crush symptom monitoring to ensure optimum pig health and safety. This review explores advanced thermal sensing technologies and computer vision-based thermal imaging techniques employed for pig disease and piglet crush symptom monitoring on pig farms. Infrared thermography (IRT) is a non-invasive and efficient technology for measuring pig body temperature, providing advantages such as non-destructive, long-distance, and high-sensitivity measurements. Unlike traditional methods, IRT offers a quick and labor-saving approach to acquiring physiological data impacted by environmental temperature, crucial for understanding pig body physiology and metabolism. IRT aids in early disease detection, respiratory health monitoring, and evaluating vaccination effectiveness. Challenges include body surface emissivity variations affecting measurement accuracy. Thermal imaging and deep learning algorithms are used for pig behavior recognition, with the dorsal plane effective for stress detection. Remote health monitoring through thermal imaging, deep learning, and wearable devices facilitates non-invasive assessment of pig health, minimizing medication use. Integration of advanced sensors, thermal imaging, and deep learning shows potential for disease detection and improvement in pig farming, but challenges and ethical considerations must be addressed for successful implementation. This review summarizes the state-of-the-art technologies used in the pig farming industry, including computer vision algorithms such as object detection, image segmentation, and deep learning techniques. It also discusses the benefits and limitations of IRT technology, providing an overview of the current research field. This study provides valuable insights for researchers and farmers regarding IRT application in pig production, highlighting notable approaches and the latest research findings in this field.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.26 no.6
• /
• pp.85-96
• /
• 2023

This study proposes a method for forest vegetation monitoring using high-resolution aerial imagery captured by unmanned aerial vehicles(UAV) and deep learning technology. The research site was selected in the forested area of Mountain Dogo, Asan City, Chungcheongnam-do, and the target species for monitoring included Pinus densiflora, Quercus mongolica, and Quercus acutissima. To classify vegetation species at the pixel level in UAV imagery based on characteristics such as leaf shape, size, and color, the study employed the semantic segmentation method using the prominent U-net deep learning model. The research results indicated that it was possible to visually distinguish Pinus densiflora Siebold & Zucc, Quercus mongolica Fisch. ex Ledeb, and Quercus acutissima Carruth in 135 aerial images captured by UAV. Out of these, 104 images were used as training data for the deep learning model, while 31 images were used for inference. The optimization of the deep learning model resulted in an overall average pixel accuracy of 92.60, with mIoU at 0.80 and FIoU at 0.82, demonstrating the successful construction of a reliable deep learning model. This study is significant as a pilot case for the application of UAV and deep learning to monitor and manage representative species among climate-vulnerable vegetation, including Pinus densiflora, Quercus mongolica, and Quercus acutissima. It is expected that in the future, UAV and deep learning models can be applied to a variety of vegetation species to better address forest management.

• Journal of Drive and Control
• /
• v.21 no.2
• /
• pp.53-64
• /
• 2024

Global population growth has resulted in an increased demand for food production. Simultaneously, aging rural communities have led to a decrease in the workforce, thereby increasing the demand for automation in agriculture. Drones are particularly useful for unmanned pest control fields. However, the current method of uniform spraying leads to environmental damage due to overuse of pesticides and drift by wind. To address this issue, it is necessary to enhance spraying performance through precise performance evaluation. Therefore, as a foundational study aimed at optimizing drone-based pest control technologies, this research evaluated water-sensitive paper (WSP) via density map estimation using convolutional neural networks (CNN) with a encoder-decoder structure. To achieve more accurate estimation, this study implemented multi-task learning, incorporating an additional classifier for image segmentation alongside the density map estimation classifier. The proposed model in this study resulted in a R-squared (R²) of 0.976 for coverage area in the evaluation data set, demonstrating satisfactory performance in evaluating WSP at various density levels. Further research is needed to improve the accuracy of spray result estimations and develop a real-time assessment technology in the field.

• Journal of Korea Water Resources Association
• /
• v.53 no.7
• /
• pp.545-555
• /
• 2020

A feasibility modeling for potential hydroelectric dam site selection was suggested using 1 sec ASTGTM (ASTER Global Digital Elevation Model) and Terra/Aqua MODIS (Moderate Resolution Imaging Spectroradiometer) derived land use (MCD12Q1) data. The modeling includes DEM pre-processing of peak, sink, and flat, river network generation, watershed delineation and segmentation, terrain analysis of stream cross section and reservoir storage, and estimation of submerged area for compensation. The modeling algorithms were developed using Python and as an open source GIS. When a user-defined stream point is selected, the model evaluates potential hydroelectric head, reservoir surface area and storage capacity curve, watershed time of concentration from DEM, and compensation area from land use data. The model was tested for 4 locations of already constructed Buhang, BohyunMountain, Sungdeok, and Yeongju dams. The modeling results obtained maximum possible heads of 37.0, 67.0, 73.0, 42.0 m, surface areas of 1.81, 2.4, 2.8, 8.8 ㎢, storages of 35.9, 68.0, 91.3, 168.3×10⁶ ㎥ respectively. BohyunMountain and Sungdeok show validity but in case of Buhang and Yeongju dams have maximum head errors. These errors came from the stream generation error due to ASTGTM. So, wrong dam watershed boundary limit the head. This study showed a possibility to estimate potential hydroelectric dam sites before field investigation especially for overseas project.

• Journal of Korea Water Resources Association
• /
• v.47 no.8
• /
• pp.671-684
• /
• 2014

Change point analysis is a efficient tool to understand the fundamental information in hydro-meteorological data such as rainfall, discharge, temperature etc. Especially, this fundamental information to change points to future rainfall data identified by reasonable detection skills can affect the prediction of flood and drought occurrence because well detected change points provide a key to resolve the non-stationary or inhomogeneous problem by climate change. Therefore, in this study, the comparative study to assess the performance of the 3 change point detection skills, cumulative sum (CUSUM) method, Bayesian change point (BCP) method, and segmentation by dynamic programming (DP) was performed. After assessment of the performance of the proposed detection skills using the 3 types of the synthetic series, the 2 reasonable detection skills were applied to the observed and future rainfall data at the 5 rainfall gauges in South Korea. Finally, it was suggested that BCP (with 0.9 posterior probability) could be best detection skill and DP could be reasonably recommended through the comparative study. Also it was suggested that BCP (with 0.9 posterior probability) and DP detection skills to find some change points could be reasonable at the North-eastern part in South Korea. In future, the results in this study can be efficiently used to resolve the non-stationary problems in hydrological modeling considering inhomogeneity or nonstationarity.

• Journal of the Korea Society of Computer and Information
• /
• v.4 no.2
• /
• pp.120-134
• /
• 1999

Image processing steps consist of image acquisition, pre-processing, region segmentation and recognition, and the images are easily corrupted by noise during the data transmission, data capture, and data processing. Impulse noise and gaussian noise are major noises, which can occur during the process. Many filters such as mean filter, median filter, weighted median filter, Cheikh filter, and Kyu-cheol Lee filter were proposed as spatial noise reduction filters so far. Many researches have been focused on the reduction of impulse noise, but comparatively the research in the reduction of gaussian noise has been neglected. For the reduction of gaussian noise, subset averaged median filter, using median information and subset average information of pixels in a window. was proposed. At this time, consider of the window size as 3$^{*}$3 pixel. The window is divided to 4 subsets consisted of 4 pixels. First of all, we calculate the average value of each subset, and then find the median value by sorting the average values and center pixel's value. In this paper, a better reduction of gaussian noise was proved. The proposed algorithms were implemented by ANSI C language on a Sun Ultra 2 for testing purposes and the effects and results of the filter in the various levels of noise and images were proposed by comparing the values of PSNR, MSE, and RMSE with the value of the other existing filtering methods.thods.

• Investigative Magnetic Resonance Imaging
• /
• v.14 no.1
• /
• pp.56-63
• /
• 2010

Purpose : DIR image is relatively free from susceptibility artifacts therefore, DIR image can make it possible to reliably measure cortical thickness/volume. One drawback of the DIR acquisition is the long scan time to acquire the fully sampled 3D data set. To solve this problem, we applied a parallel imaging method (GRAPPA) and verify the reliability of using the volumetric study. Materials and methods : Six healthy volunteers (3 males and 3 females; age $25.33{\pm}2.25$ years) underwent MRI using the 3D DIR sequence at a 3.0T Siemens Tim Trio MRI scanner. GRAPPA simulation was performed from the fully sampled data set for reduction factor 2. Data reconstruction was performed using MATLAB R2009b. Freesurfer v.4.3.0 was used to evaluate the cortical thickness of the entire brain, and to extract white matter information from the DIR image, Analyze 9.0 was used. The global cortical thickness estimated from the reconstructed image was compared with reference image by using a T-test in SPSS. Results : Although reduced SNR and blurring are observed from the reconstructed image, in terms of segmentation the effect was not so significant. The volumetric result was validated that there were no significant differences in many cortical regions. Conclusion : This study was performed with DIR image for a volumetric MRI study. To solve the long scan time of 3D DIR imaging, we applied GRAPPA algorithm. According to the results, fast imaging can be done with reduction factor 2 with little loss of image quality at 3.0T.

• Journal of Korea Water Resources Association
• /
• v.48 no.10
• /
• pp.807-816
• /
• 2015

In general, the water stage-discharge relationship curve is established based on the assumptions of linearity and homoscedasticity. However, the relationship between the water stage and discharge is affected from geomorphological factors, which violates the basic assumptions of the water stage-discharge relationship curve. In order to reduce the error due to the violations, the curve is divided into several sections based on the manager's judgement considering change of cross-sectional shape. In this research, the objective-splitting criteria of the curve is proposed based on the measured data without the subjective decision. First, it is assumed that the coefficient of variation follows the normal distribution. Then, if the newly calculated coefficient of variation is outside of the 95% confidential interval, the curve is divided. Namely, the groups is divided by the characteristics of the coefficient of variation and the reasonable criteria is provided for establishing a multi-segmented rating curve. To validate the proposed method, it was applied to the data generated by three artificial power functions. In addition, to confirm the applicability of the proposed method, it is applied to the water stage and discharge data of the Muju water stage gauging station and Sangegyo water stage gauging station. As a result, it is found that the automatically divided rating curve improves the accuracy and extrapolation accuracy of the rating curve. Finally, through the residual analysis using Shapiro-Wilk normality test, it is confirmed that the residual of water stage-discharge relationship curve tends to follow the normal distribution.