Image mosaicking is one of the basic and important technologies in the field of application using images. The key of image mosaicking is to extract seamlines from a joint image. The method proposed in this paper for image mosaicking is as follows. The feature points of the images to be joined are extracted and the joining form between the two images is identified. A reference position for detection the seamlines were selected according to the joint form, and an image pyramid was created for efficient image processing. The outlines of the image including buildings and roads are extracted from the overlapping area with low resolution, and the seamlines are determined by considering the components of the outlines. Based on this, the seamlines in the high-resolution image was re-searched and finally the seamline for image mosaicking was determined. In addition, in order to minimize color distortion of the image with the determined seamline, a method of improving the quality of the mosaic image by fine correction of the mosaic area was applied. It was confirmed that the quality of the seamline extraction results applying the method proposed was reasonable.

In the realm of dental prosthesis fabrication, obtaining accurate impressions has historically been a challenging and inefficient process, often hindered by hygiene concerns and patient discomfort. Addressing these limitations, Company D recently introduced a cutting-edge solution by harnessing the potential of intraoral scan images to create 3D dental models. However, the complexity of these scan images, encompassing not only teeth and gums but also the palate, tongue, and other structures, posed a new set of challenges. In response, we propose a sophisticated real-time image segmentation algorithm that selectively extracts pertinent data, specifically focusing on teeth and gums, from oral scan images obtained through Company D's oral scanner for 3D model generation. A key challenge we tackled was the detection of the intricate molar regions, common in dental imaging, which we effectively addressed through intelligent data augmentation for enhanced training. By placing significant emphasis on both accuracy and speed, critical factors for real-time intraoral scanning, our proposed algorithm demonstrated exceptional performance, boasting an impressive accuracy rate of 0.91 and an unrivaled FPS of 92.4. Compared to existing algorithms, our solution exhibited superior outcomes when integrated into Company D's oral scanner. This algorithm is scheduled for deployment and commercialization within Company D's intraoral scanner.

Freshwater jellyfish, a type of jellyfish exclusively found in freshwater, has a limited number of species but is found globally. However, their ecology and causes of occurrence are largely unknown. Therefore, understanding the distribution of polyps, which produce the larvae of freshwater jellyfish, can provide important data for comprehending their ecology. This study aims to explore the COI gene of freshwater jellyfish using environmental DNA from the microbial film in the Miho River system. Among the 12 survey points in the Miho River watershed, genetic material of freshwater jellyfish was detected in 8 points, mainly located upstream near reservoirs. These genetic materials were identified as genes of the well-known freshwater jellyfish species, Craspedacusta sowerbii. Notably, the C. sowerbii genes found in the Miho River watershed survey points were closely related to a species previously discovered in Italy. Consequently, utilizing environmental DNA to explore the genetic traces of freshwater jellyfish enables rapid screening of areas with a high likelihood of freshwater jellyfish occurrence. This approach is deemed to provide crucial information for understanding the distribution and ecology of freshwater jellyfish in Korea.

On pig farms, the highest mortality rate is observed among nursing piglets. To reduce this mortality rate, farmers need to carefully observe the piglets to prevent accidents such as being crushed and to maintain a proper body temperature. However, observing a large number of pigs individually can be challenging for farmers. Therefore, our aim was to detect the behavior of piglets and sows in real-time using deep learning models, such as YOLOv4-CSP and YOLOv7-E6E, that allow for real-time object detection. YOLOv4-CSP reduces computational cost by partitioning feature maps and utilizing Cross-stage Hierarchy to remove redundant gradient calculation. YOLOv7-E6E analyzes and controls gradient paths such that the weights of each layer learn diverse features. We detected standing, sitting, and lying behaviors in sows and lactating and starving behaviors in piglets, which indicate nursing behavior and movement to colder areas away from the group. We optimized the model parameters for the best object detection and improved reliability by acquiring data through experts. We conducted object detection for the five different behaviors. The YOLOv4-CSP model achieved an accuracy of 0.63 and mAP of 0.662, whereas the YOLOv7-E6E model showed an accuracy of 0.65 and mAP of 0.637. Therefore, based on mAP, which includes both class and localization performance, YOLOv4-CSP showed the superior performance. Such research is anticipated to be effectively utilized for the behavioral analysis of fattening pigs and in preventing piglet crushing in the future.

Phytohormones (plant hormones) are a class of small-molecule organic compounds synthesized de novo in plants. Although phytohormones are present in trace amounts, they play a key role in regulating plant growth and development, and in response to external stresses. Therefore, the analysis and monitoring of phytohormones have become an important research topic in precision agriculture. Among the various detection methods, electrochemical analysis is favored because of its simplicity, rapidity, high sensitivity, and in-situ monitoring. Graphene and graphene-like carbon materials have abundant sources, exhibiting large specific surface area, and excellent physicochemical properties. Thus, they have been widely used in the preparation of electrochemical biosensors for phytohormone detection. In this paper, the research advances of electrochemical sensors based on graphene and graphene-like carbon materials for phytohormone detection have been reviewed. The properties of graphene and graphene-like carbon materials are first introduced. Then, the research advances of electrochemical biosensors (including conventional electrochemical sensors, photoelectrochemical sensors, and electrochemiluminescence sensors) based on graphene and graphene-like carbon materials for phytohormone detection is summarized, with emphasis on their sensing strategies and the roles of graphene and graphene-like carbon materials in them. Finally, the development of electrochemical sensors based on graphene and graphene-like carbon materials for phytohormone detection is prospected.

In factory automation, efforts are being made to increase productivity while maintaining high-quality products. In this study, a CNN network structure was designed to quickly and accurately recognize a cigarette located in the opposite direction or a cigarette with a loose end in an automated facility rotating at high speed for cigarette production. Tobacco inspection requires a simple network structure and fast processing time and performance. The proposed network has an excellent accuracy of 96.33% and a short processing time of 0.527 msec, showing excellent performance in learning time and performance compared to other CNN networks, confirming its practicality. In addition, it was confirmed that efficient learning is possible by increasing a small number of image data through a rotation conversion method.

Fishing gear used in coastal fishing should be equipped with fishing buoys, indicating their locations, thus enabling their constant monitoring and detection by other ships to avoid collision. However, common fishing buoys fabricated using Styrofoam, bamboo, or PVC have short detection ranges owing to their weak radar radio wave reflection. Although research on improving the performance of radar equipment is in progress, studies on early detection of fishing gear to reduce collisions with ships sailing nearby are limited. In this study, we conducted experiments to determine methods to prevent collisions between ships and fishing gear by improving both the fishing buoy material and installation method for the reflector to increase the radar detection range of the fishing buoys.

딥러닝을 이용하여 항공 및 위성 영상 속의 다양한 공간객체를 탐지하는 연구들이 증가하고 있다. 매년 급속하게 증가하는 위성 및 항공사진과 같은 원격탐사의 자료 속에서 특정 공간객체들을 수작업으로 탐지하는 것은 한계를 갖는다. 본 연구에서는 딥러닝의 객체 탐지기법을 이용하여 토지피복도 내 공간객체들에 대한 탐지를 시도하였다. 데이터는 국토지리정보원의 항공사진을 활용하였고 농경지에 해당하는 논, 밭, 하우스 재배지 등의 객체들을 탐지하였다. 토지피복을 구성하는 다양한 공간객체들에 대한 탐지를 통해 YOLOv5 모델의 활용 가능성을 탐색하였다.

This research proposes a novel approach to tackle the challenge of categorizing unstructured customer complaints in the automotive industry. The goal is to identify potential vehicle defects based on the findings of our algorithm, which can assist automakers in mitigating significant losses and reputational damage caused by mass claims. To achieve this goal, our model uses the Word2Vec method to analyze large volumes of unstructured customer complaint data from the National Highway Traffic Safety Administration (NHTSA). By developing a score dictionary for eight pre-selected criteria, our algorithm can efficiently categorize complaints and detect potential vehicle defects. By calculating the score of each complaint, our algorithm can identify patterns and correlations that can indicate potential defects in the vehicle. One of the key benefits of this approach is its ability to handle a large volume of unstructured data, which can be challenging for traditional methods. By using machine learning techniques, we can extract meaningful insights from customer complaints, which can help automakers prioritize and address potential defects before they become widespread issues. In conclusion, this research provides a promising approach to categorize unstructured customer complaints in the automotive industry and identify potential vehicle defects. By leveraging the power of machine learning, we can help automakers improve the quality of their products and enhance customer satisfaction. Further studies can build upon this approach to explore other potential applications and expand its scope to other industries.

The rapid detection of bacteria in the oral cavity, its species identification, and bacterial count determination are important to diagnose oral diseases caused by pathogenic bacteria. The existing clinical microbial diagnosis methods are time-consuming as they involve observing patients’ samples under a microscope or culturing and confirming bacteria using polymerase chain reaction (PCR) kits, making the process complex. Therefore, it is required to analyze the development status of substances and systems that can rapidly detect and analyze pathogenic microorganisms in the oral cavity. With research advancements, a close relationship between oral and systemic diseases has been identified, making it crucial to identify the changes in the oral cavity bacterial composition. Additionally, an early and accurate diagnosis is essential for better prognosis in periodontal disease. However, most periodontal diseasecausing pathogens are anaerobic bacteria, which are difficult to identify using conventional bacterial culture methods. Further, the existing PCR method takes a long time to detect and involves complicated stages. Therefore, to address these challenges, the concept of point-of-care (PoC) has emerged, leading to the study and implementation of various chair-side test methods. This study aims to investigate the different PoC diagnostic methods introduced thus far for identifying pathogenic microorganisms in the oral cavity. These are classified into three categories: 1) microbiological tests, 2) microchemical tests, and 3) genetic tests. The microbiological tests are used to determine the presence or absence of representative causative bacteria of periodontal diseases, such as A. actinomycetemcomitans , P. gingivalis , P. intermedia , and T. denticola . However, the quantitative analysis remains impossible, and detecting pathogens other than the specific ones is challenging. The microchemical tests determine the activity of inflammation or disease by measuring the levels of biomarkers present in the oral cavity. Although this diagnostic method is based on increase in the specific biomarkers proportional to inflammation or disease progression in the oral cavity, its commercialization is limited due to low sensitivity and specificity. The genetic tests are based on the concept that differences in disease vulnerability and treatment response are caused by the patient’s DNA predisposition. Specifically, the IL-1 gene is used in such tests. PoC diagnostic methods developed to date serve as supplementary diagnostic methods and tools for patient education, in addition to existing diagnostic methods, although they have limitations in diagnosing oral diseases alone. Research on various PoC test methods that can analyze and manage the oral cavity bacterial composition is expected to become more active, aligning with the shift from treatmentoriented to prevention-oriented approaches in healthcare.

To make semiconductor chips, a number of complex semiconductor manufacturing processes are required. Semiconductor chips that have undergone complex processes are subjected to EDS(Electrical Die Sorting) tests to check product quality, and a wafer bin map reflecting the information about the normal and defective chips is created. Defective chips found in the wafer bin map form various patterns, which are called defective patterns, and the defective patterns are a very important clue in determining the cause of defects in the process and design of semiconductors. Therefore, it is desired to automatically and quickly detect defective patterns in the field, and various methods have been proposed to detect defective patterns. Existing methods have considered simple, complex, and new defect patterns, but they had the disadvantage of being unable to provide field engineers the evidence of classification results through deep learning. It is necessary to supplement this and provide detailed information on the size, location, and patterns of the defects. In this paper, we propose an anomaly detection framework that can be explained through FCDD(Fully Convolutional Data Description) trained only with normal data to provide field engineers with details such as detection results of abnormal defect patterns, defect size, and location of defect patterns on wafer bin map. The results are analyzed using open dataset, providing prominent results of the proposed anomaly detection framework.

본 연구에서는 수산물 시료 중 Salmonella spp. 검출을 위해 단시간의 전배양(2시간 이내)과 탈염과정을 포함한 DNA 추출법을 사용하여 분자생물학적 검출을 위한 수산 물 전처리 방법에 대해 연구하였다. 배양 시간에 따른 증 균 효율을 탐색하기 위해 100, 101 및 102 CFU/mL농도 의 Salmonella spp. 5종을 NB 0.5에 접종하여 증균 전, 1시간 및 2시간 동안의 증균 효율을 비교하였다. 그 결 과, 2시간 동안 모든 농도에서 약 1 log CFU/mL가 증균 되어 초기 농도와 유의적인 차이가 나타났다. 또한 지역 별 패류시료에 S. Typhimurium을 인위적으로 감염시킨 뒤 DNA를 추출하여 염농도를 측정한 결과, 모든 시료의 염농도가 0%로 DNA 추출과 동시에 탈염이 이루어진 것 을 확인하였다. 이후 추출한 DNA를 사용하여 PCR을 수 행한 결과 모든 시료에서 S. Typhimurium의 특이적 양성 밴드가 확인되었다. 다음으로 수산물 시료 중 Salmonella spp. 검출을 위한 증균 과정과 탈염을 포함한 DNA 추출 방법의 검증을 위해 멸균 홍합시료 및 비멸균 홍합시료 에 Salmonella spp. 5종을 인공적으로 약 100, 101, 102 CFU/g의 농도로 오염시켜 전배양과 DNA를 추출하여 PCR로 특이적 증폭 밴드의 여부를 확인한 결과, 모든 농 도의 Salmonella spp. 5종에서 특이적 밴드가 확인되었다 . 결과적으로 본 연구에서 제시한 전배양 및 DNA 추출 방법을 포함한 전처리 방법과 PCR을 사용하여 수산물 시 료에서 10 CFU/g 미만의 Salmonella spp.를 검출하였으 며, 시간과 비용면에서 효율적이며 과정이 복잡하기 않기 때문에 수산물의 처리 현장에 활용될 수 있을 것으로 기 대된다.

This study assessed the measurement technique of odorous substances using a GC/MOS system with MOS sensor at the detector and the method detection limits were determined for odorous substances such as hydrogen sulfide, acetaldehyde, toluene, m,pxylene, and o-xylene. The portable GC/MOS system was able to separate and measure about 16 out of 22 odorous substances including sulfur compounds, aldehydes, and VOCs. The peak values for hydrogen sulfide, acetaldehyde, toluene, m,p-xylene, and o-xylene showed a nonlinear relationship with concentration and a correlation coefficient of 0.95 or higher was confirmed. The method detection limits for hydrogen sulfide, acetaldehyde, toluene, m.pxylene, and o-xylene using the portable GC/MOS system were determined to be 0.005, 0.023, 0.016, 0.004, and 0.051 ppm, respectively. It is expected that the system can measure odor samples with concentrations of least 50 ppb without additional pretreatment or concentration processes.

Graphene-derived materials are an excellent electrode for electrochemical detection of heavy metals. In this study, a MnO2/ graphene supported on Ni foam electrode was prepared via ultrasonic impregnation and electrochemical deposition. The resulting electrode was used to detect Pb(II) in the aquatic environment. The graphene and MnO2 deposited on the Ni foam not only improved active surface area, but also promoted the electron transfer. The electrochemical performance towards Pb(II) was evaluated by cyclic voltammetry (CV) and square wave anodic stripping voltammetry (SWASV). The prepared electrode exhibited lower limit of detection (LOD, 0.2 μM (S/N = 3)) and good sensitivity (59.9 μAμM−1) for Pb(II) detection. Moreover, the prepared electrodes showed good stability and reproducibility. This excellent performance can be attributed to the strong adhesion force between graphene and MnO2, which provides compact structures for the enhancement of the mechanical stability. Thus, these combined results provide some technical considerations and scientific insights for the detection of heavy metal ions using composite electrodes.

In this study, we evaluate artificial neural network (ANN) models that estimate the positions of gamma-ray sources from plastic scintillating fiber (PSF)-based radiation detection systems using different filtering ratios. The PSF-based radiation detection system consists of a single-stranded PSF, two photomultiplier tubes (PMTs) that transform the scintillation signals into electric signals, amplifiers, and a data acquisition system (DAQ). The source used to evaluate the system is Cs-137, with a photopeak of 662 keV and a dose rate of about 5 μSv/h. We construct ANN models with the same structure but different training data. For the training data, we selected a measurement time of 1 minute to secure a sufficient number of data points. Conversely, we chose a measurement time of 10 seconds for extracting time-difference data from the primary data, followed by filtering. During the filtering process, we identified the peak heights of the gaussian-fitted curves obtained from the histogram of the time-difference data, and extracted the data located above the height which is equal to the peak height multiplied by a predetermined percentage. We used percentage values of 0, 20, 40, and 60 for the filtering. The results indicate that the filtering has an effect on the position estimation error, which we define as the absolute value of the difference between the estimated source position and the actual source position. The estimation of the ANN model trained with raw data for the training data shows a total average error of 1.391 m, while the ANN model trained with 20%-filtered data for the training data shows a total average error of 0.263 m. Similarly, the 40%-filtered data result shows a total average error of 0.119 m, and the 60%-filtered data result shows a total average error of 0.0452 m. From the perspective of the total average error, it is clear that the more data are filtered, the more accurate the result is. Further study will be conducted to optimize the filtering ratio for the system and measuring time by evaluating stabilization time for position estimation of the source.

Recently, the spent fuel pools withdrawn from nuclear power plants in Korea have been saturated. Therefore, specific regulations on the management of spent fuel pools, such as transportation and intermediate storage are needed. The burnup history is directly related to the management of spent nuclear fuel. This is because the decision to handle nuclear fuel may vary depending on the initial concentration of nuclear fuel, the degree to which nuclear fuel is irradiated and radioisotope nuclides are decayed, and the cooling state in the spent nuclear fuel storage tank. The purpose of this study is to determine the burnup of fuel based on the value obtained by scanning the surface of spent nuclear fuel through a neutron detector. Conversely, a database of neutron signals that scan bundles of spent nuclear fuel with an instrument with an already identified combustion history needs to be completed. First of all, the correlation between burnup history and nuclides was identified in previous studies. By setting the burnup history as the input value in the ORIGEN-ARP code, it was possible to identify the radioactive isotopes remaining in the bundle of nuclear fuel. Neutrons can finally be measured based on the amount of nuclide inventory that constitutes spent nuclear fuel. Through MCNP, the neutron detector was simulated and signals were measured to confirm how it correlates with the previously acquired burnup history database. In addition, the M (sub-critical multiplication) value, which is essential for neutron measurement, was checked to confirm the degree to which additional neutrons were generated in spent nuclear fuel in a subcritical state. The target nuclear fuel assembly was CE16×16, WH14×14, and WH17×17, which confirmed the correlation (1) between burnup, enrichment, and cooling time with the previous research topic, TNSI (Total neutron source intensity). 􀜤􀜷􁈺􀜩􀜹􀝀/􀜯􀜶􀜷􁈻 = 0.83􁈺􀜵􀯇􁈻􀬴.􀬶􀬷􀬼 ∙ 􁈺􀜫􀜧􁈻􀬴.􀬸􀬺􀬶􀬻 ∙ 􀝁􀬴.􀬴􀬴􀬼􀬷∙􀯧 􁈺1􁈻 A neutron signal will be obtained from the case according to each burnup history constituting this database. In particular, PAR=SF, a function that calculates the production amount of the fission product, was used. To confirm the computational logic of SF, it was confirmed whether a reasonable calculation was made by calculating with a nuclide spectrum.

With the introduction and implementation of the National Research and Development Innovation Act in 2021, researchers are required to have a greater understanding of research ethics and to comply more strictly. The range of misconduct in research and the standards for sanctions have been expanded with the introduction of the National Research and Development Innovation Act. In addition, researchperforming institutions and specialized agencies have been obligated to establish their own research management systems and standards according to the changed criteria. The Korea Institute of Nuclear Nonproliferation and Control (KINAC), a nuclear regulatory authority that is conducting national R&D in related fields, has sought to strengthen research ethics by revising related regulations, introducing a plagiarism detection system, and expanding related education in accordance with these policies. In this study, we analyzed the effectiveness of the plagiarism detection system as a basic quality control measure for research results and a tool for enhancing research ethics, which was introduced. KINAC did not simply introduce a plagiarism detection program but established institutional improvements and other regulatory measures to support it, with the aim of more effectively managing research results. To analyze the effectiveness of this system, we calculated the plagiarism rate by sampling 30 papers each year for the three years before the introduction of the plagiarism detection system. When comparing the plagiarism rates before and after the introduction of the plagiarism detection system, no exceptional cases of high plagiarism rates were found in papers published after the introduction of the system. Although most of the papers before the introduction of the system showed a satisfactory plagiarism rate, some cases showed high plagiarism rates. We analyzed the cause of such cases in detail. Some exceptional cases were also found to be included in the range of misconduct regulated by the National Research and Development Innovation Act. As no such cases were found after the introduction of the system, we could infer that the system is effectively functioning as a tool for basic quality control and enhancing research ethics. In the future, we plan to expand the sample qualitatively and quantitatively by including other forms of outcomes published by the institution, not just papers, and conduct a more detailed analysis. Based on the results, we will develop various improvement plans for enhancing the quality and research ethics of the institution’s research results.