• Journal of Animal Science and Technology
• /
• 제65권2호
• /
• pp.365-376
• /
• 2023

Pig breeding management directly contributes to the profitability of pig farms, and pregnancy diagnosis is an important factor in breeding management. Therefore, the need to diagnose pregnancy in sows is emphasized, and various studies have been conducted in this area. We propose a computer-aided diagnosis system to assist livestock farmers to diagnose sow pregnancy through ultrasound. Methods for diagnosing pregnancy in sows through ultrasound include the Doppler method, which measures the heart rate and pulse status, and the echo method, which diagnoses by amplitude depth technique. We propose a method that uses deep learning algorithms on ultrasonography, which is part of the echo method. As deep learning-based classification algorithms, Inception-v4, Xception, and EfficientNetV2 were used and compared to find the optimal algorithm for pregnancy diagnosis in sows. Gaussian and speckle noises were added to the ultrasound images according to the characteristics of the ultrasonography, which is easily affected by noise from the surrounding environments. Both the original and noise added ultrasound images of sows were tested together to determine the suitability of the proposed method on farms. The pregnancy diagnosis performance on the original ultrasound images achieved 0.99 in accuracy in the highest case and on the ultrasound images with noises, the performance achieved 0.98 in accuracy. The diagnosis performance achieved 0.96 in accuracy even when the intensity of noise was strong, proving its robustness against noise.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권2호
• /
• pp.311-326
• /
• 2024

The rapid development of neural network technology promotes the neural network model driven by big data to overcome the texture effect of complex objects. Due to the limitations in complex scenes, it is necessary to establish custom template matching and apply it to the research of many fields of computational vision technology. The dependence on high-quality small label sample database data is not very strong, and the machine learning system of deep feature connection to complete the task of texture effect inference and speculation is relatively poor. The style transfer algorithm based on neural network collects and preserves the data of patterns, extracts and modernizes their features. Through the algorithm model, it is easier to present the texture color of patterns and display them digitally. In this paper, according to the texture effect reasoning of custom template matching, the 3D visualization of the target is transformed into a 3D model. The high similarity between the scene to be inferred and the user-defined template is calculated by the user-defined template of the multi-dimensional external feature label. The convolutional neural network is adopted to optimize the external area of the object to improve the sampling quality and computational performance of the sample pyramid structure. The results indicate that the proposed algorithm can accurately capture the significant target, achieve more ablation noise, and improve the visualization results. The proposed deep convolutional neural network optimization algorithm has good rapidity, data accuracy and robustness. The proposed algorithm can adapt to the calculation of more task scenes, display the redundant vision-related information of image conversion, enhance the powerful computing power, and further improve the computational efficiency and accuracy of convolutional networks, which has a high research significance for the study of image information conversion.

• Korean Journal of Radiology
• /
• 제24권12호
• /
• pp.1179-1189
• /
• 2023

Objective: We aimed to evaluate the reporting quality of research articles that applied deep learning to medical imaging. Using the Checklist for Artificial Intelligence in Medical Imaging (CLAIM) guidelines and a journal with prominence in Asia as a sample, we intended to provide an insight into reporting quality in the Asian region and establish a journal-specific audit. Materials and Methods: A total of 38 articles published in the Korean Journal of Radiology between June 2018 and January 2023 were analyzed. The analysis included calculating the percentage of studies that adhered to each CLAIM item and identifying items that were met by ≤ 50% of the studies. The article review was initially conducted independently by two reviewers, and the consensus results were used for the final analysis. We also compared adherence rates to CLAIM before and after December 2020. Results: Of the 42 items in the CLAIM guidelines, 12 items (29%) were satisfied by ≤ 50% of the included articles. None of the studies reported handling missing data (item #13). Only one study respectively presented the use of de-identification methods (#12), intended sample size (#19), robustness or sensitivity analysis (#30), and full study protocol (#41). Of the studies, 35% reported the selection of data subsets (#10), 40% reported registration information (#40), and 50% measured inter and intrarater variability (#18). No significant changes were observed in the rates of adherence to these 12 items before and after December 2020. Conclusion: The reporting quality of artificial intelligence studies according to CLAIM guidelines, in our study sample, showed room for improvement. We recommend that the authors and reviewers have a solid understanding of the relevant reporting guidelines and ensure that the essential elements are adequately reported when writing and reviewing the manuscripts for publication.

• Current Optics and Photonics
• /
• 제8권4호
• /
• pp.355-365
• /
• 2024

Wavefront coding (WFC) imaging systems can redistribute the energy of an interference laser spot on an image plane sensor by wavefront phase modulation and reduce the peak intensity, realizing laser protection while maintaining imaging functionality by leveraging algorithmic post-processing. In this paper, a spiral axicon WFC imaging system is proposed, and the performance for laser protection is investigated by constructing a laser transmission model. An Airy disk on an image plane sensor is refactored into a symmetrical hollow ring by a spiral axicon phase mask, and the maximum intensity can be reduced to lower than 1% and single-pixel power to 1.2%. The spiral axicon phase mask exhibits strong robustness to the position of the interference laser source and can effectively reduce the risk of sensor damage for an almost arbitrary lase propagation distance. Moreover, we revealed that there is a sensor hazard distance for both conventional and WFC imaging systems where the maximum single-pixel power reaches a peak value under irradiation of a power-fixed laser source. Our findings can offer guidance for the anti-laser reinforcement design of photoelectric imaging systems, thereby enhancing the adaptability of imaging systems in a complex laser environment. The laser blinding-resistant imaging system has potential applications in security monitoring, autonomous driving, and intense-laser-pulse experiments.

• 분석과학
• /
• 제37권5호
• /
• pp.280-294
• /
• 2024

This study introduces a novel analytical method for the assessment of pralsetinib impurities and degradation products (DPs), addressing critical gaps in existing methodologies. This research aims to develop a robust HPLC method for impurity analysis, characterize degradation products using LC-MS, and evaluate the environmental impact of the method. The study began by optimizing HPLC conditions with various columns and buffers, ultimately achieving successful separation using an XBridge^® RP-C18 column with ethanol as solvent A and 50 mM formic acid at pH 2.9. This setup provided excellent peak resolution and symmetry, essential for reliable stability studies. The developed HPLC method was then adapted for HPLC-MS/MS, enhancing sensitivity and detection efficiency of DPs. Stress degradation studies of pralsetinib under different conditions (acidic, basic, oxidative, thermal, and photolytic) revealed significant degradation under acidic (29.3 %) and basic (21.5 %) conditions, with several DPs identified. Oxidative stress resulted in 19.8 % degradation, while thermal and photolytic conditions caused minimal degradation. HPLC-MS/MS analysis identified structures of five degradation products, providing detailed insights into pralsetinib's stability and degradation pathways. Method validation followed ICH guidelines Q2(R1), confirming method's specificity, selectivity, sensitivity, linearity, accuracy, precision, and robustness. The method exhibited strong linearity with a coefficient of determination (r²) greater than 0.999 for pralsetinib and its impurities. This method advances impurity detection and DPs characterization, ensuring the quality and safety of pralsetinib. Additionally, method's environmental impact was assessed, aligning with sustainable analytical practices. These findings provide essential data on pralsetinib's stability, guiding storage conditions and ensuring its efficacy and safety in pharmaceutical applications.

• Journal of Advanced Marine Engineering and Technology
• /
• 제39권6호
• /
• pp.633-641
• /
• 2015

선박, 발전소, 석유화학 등의 분야에서 운전되고 있는 많은 프로세스들은 강한 비선형성을 보일 뿐만 아니라 동시에 시변 특성도 가지고 있다. 이런 프로세스에 기존의 고정-파라미터 PID 제어기를 적용하면 성능이 나빠지고 경우에 따라서는 불안정해질 수도 있다. 따라서 본 연구에서는 복잡한 프로세스를 제어하기 위한 비선형 PID 제어기를 제안한다. 제안되는 제어기의 이득은 오차와 오차의 변화율의 비선형 함수로 기술되며, 사용자 파라미터들은 ITAE를 최소로 하는 관점에서 유전알고리즘으로 동조된다. 제안된 방법은 열분해반응 또는 촉매를 이용한 고분자합성에 널리 사용되는 연속 교반탱크반응기를 대상으로 시뮬레이션을 실시하며, 그 유효성을 보이기 위해 다른 두 비선형/적응 제어법과 비교한다.

• 해양환경안전학회지
• /
• 제26권5호
• /
• pp.437-444
• /
• 2020

본 논문에서는 불규칙 선수파랑 조건에서 선박계류시스템의 전후동요를 억제하는 연구를 수행하였다. 두점식 계류시스템은 비선형복원력의 특성으로 인하여 규칙파 조건에서도 강한 비선형 응답 특성을 보인다. 종방향 불규칙 장파가 외란으로 선박계류시스템에 작용하게 되면 규칙파 외력이 입사하는 경우보다 변위와 속도에서 더욱 복잡한 비선형 거동이 발생한다. 계의 종동요 변위와 속도를 동시에 억제하기 위하여 슬라이딩모드 제어법(SMC)을 적용하였다. SMC는 매개변수의 불확실성 및 외란에 대한 강인성을 갖는 폐루프 시스템을 제공하지만, 채터링은 이 제어법을 사용할 때 큰 단점이 된다. 본 연구에서는 준 슬라이딩모드의 시그모이드 함수를 이용하여 불규칙 해양파의 외란 조건에서 채터링을 줄이고. 수렴의 정확성에 도달하는 목표를 달성하였다. 제어법의 유효성은 수치시뮬레이션을 통해 증명하였다.

• 유통과학연구
• /
• 제14권6호
• /
• pp.75-80
• /
• 2016

Purpose - A growing demand for sustainability reporting has placed pressure on firms with non-financial information that affects firm valuation, growth, and development. In particular, a number of researchers have investigated various topics in Corporate Social Responsibility (CSR), non-financial information. Prior studies suggest that CSR may affect corporate outcomes like corporate reporting, financial performance, and disclosures. However, the results from prior studies are not clear whether CSR affects corporate outcomes. This is partially due to the measurement issues with CSR. In this study, we examine whether CSR affects the quality of corporate reporting, one of the popular measures in corporate outcomes. We find an evidence that CSR positively affects the quality of corporate reporting. Research design, data, and methodology - In this study, we collected a unique dataset of CSR from MSCI. Total 169 firms listed in the Korean Stock Exchange from 2011 to 2014 were collected and analysed with the detailed CSR reports. Using a correlation test, we found a weak association between CSR and the quality of corporate reporting. However, the regression tests provided a strong relationship between CSR and the quality of corporate reporting after controlling for other variables that may affect the quality of corporate reporting. Additionally, we calculated the t-statistics based on heteroskedaticity-consistent standard errors (White, 1980). Results - Before we run the regression test, we sort the measures of the two dependent variables into each rating of CSR (from AAA to CCC). The results indicate that the quality of corporate reporting measured by discretionary accruals and performance-matched discretionary accruals monotonically decrease as the CSR ratings increase. This supports our hypothesis. In the regression tests, the coefficient on MJDA (PMDA) is -0.183 (-0.173) and significant at the 5% level. We can interpret the results as CSR affecting the quality of corporate reporting in positive ways. Other coefficients on control variables are consistent with prior studies. For example, the coefficients on both LOSS and LEV are positive and significant at conventional level, meaning that firms with financial difficulty may harm their quality of corporate reporting. Conclusion - We found an evidence that CSR is positively associated with the quality of corporate reporting. This study contributes to the literature in various ways. First, this study extends the line of CSR research by providing additional evidence in the setting of ethical behaviors by managements. This is consistent with the hypothesis and supports the results of prior studies. Second, to the best of my knowledge, this is the first study using the MSCI CSR ratings. In contrast with prior studies using different measures of CSR, the MSCI CSR ratings allow us to provide in-depth analysis. Third, the additional measure of dependent variable (PMDA) allows us to improve the robustness of our results. Overall, the results provided this study to extend the findings in prior studies by providing incremental evidence.

• 한국전산구조공학회논문집
• /
• 제29권6호
• /
• pp.583-590
• /
• 2016

본 논문은 강형식 기반의 MLS 차분법에 Rayleigh 감쇠효과를 적용한 동적균열진전 해석기법을 제시한다. Rayleigh 감쇠 효과가 반영된 동적 평형방정식과 구성방정식을 도출하고, MLS 미분근사식을 이용하여 지배방정식들을 이산화하였다. 평형방정식뿐만 아니라 구성방정식에서도 감쇠효과를 적절하게 고려하여 기존의 무요소 강정식화 기법에서 고려하지 못했던 비례감쇠 알고리즘을 구현하였다. 시간관련 항을 포함한 동적 평형방정식은 중앙차분법(central difference method)을 이용하여 시간적분 하였고, 속도에 대한 차분식을 lagging시켜 이산화 방정식을 간소화시켰다. 균열의 기하학적 특성은 표면력 '0'인 자연경계 조건을 균열면에 놓인 절점들에 부과하여 묘사하였으며, 균열성장으로 인해 해석단계마다 변하는 절점의 생성 및 이동 효과를 계방정식 구성에 반영하였다. 단일균열과 다중균열을 갖는 수치예제를 통해서 제안된 수치기법의 정확성을 검증하였으며, 비례감쇠 효과의 고려가 동적균열진전 해석결과에 미치는 영향을 보였다.

• 생명과학회지
• /
• 제26권7호
• /
• pp.855-867
• /
• 2016

말은 인류에 의해 상대적으로 일찍 가축화된 종 중 하나로써, 경주능력, 강건성 및 항병성 등과 같은 능력을 위해 인공적으로 선택되었다. 그 결과, 현재 경주마로 많이 쓰이고 있는 서러브레드의 게놈은 운동 능력에 특화된 유전자형을 많이 갖고 있다. 최근 NGS 기술의 도래와 함께 전장게놈을 대상으로 경주마의 우수한 유전형질을 찾는 연구가 유전체학의 관점에서 진행되고 있다. 그 결과 말의 게놈에 대해서도 GWAS (Genome-wide Association study)가 적용되고 있고, 우수 경주능력을 나타내는 유전자 마커가 발굴되고 있다. 아울러, 특정 샘플의 전장 전사체를 NGS 기법으로 분석할 수 있는 RNA-Seq 기법 역시 활용되고 있는데, 이를 통하여 각 개체별, 운동 전후, 한 개체의 조직별 특정 유전자의 발현 양상과 함께 전사체의 서열 등을 확인할 수 있다. DNA 서열의 변화 없이 유전자 발현을 조절하는 강력한 인자로써 DNA methylation이 주목받고 있다. 말의 게놈에 있어서도 운동 특이적 또는 개체 특이적 DNA methylation 패턴을 보여 주었고, 이는 우수 개체 선정을 위한 마커 개발에 좋은 단서를 제공해 줄 것이다. 유전자 발현을 억제하는 miRNA와, 포유동물의 유전체 내 절반 정도를 차지하고 있는 이동성 유전인자는 기능유전체 연구에 있어서 중요한 인자들이다. 이들은 인간의 게놈에서 많이 연구가 되어 왔으나, 말에서의 연구는 현재 미미한 실정이다. 하지만, 현재까지 말에서 되어 있는 위의 두 인자에 대한 연구 현황을 알아보고, 차후 우수 마 선별 연구에 적용될 가능성을 제시하였다. 기능유전체 및 후성유전체 분석 기법이 발전함에 따라 말에서도 본 연구에서 소개된 여러 가지 분석 기법이 적용되고, 우수한 경주마를 선정하는 데 많은 도움을 줄 것으로 기대하고 있다. 이에 현재까지의 우수한 경주마를 선택하기 위한 많은 연구들 및, 말 연구에 대한 앞으로의 발전 가능성에 대해 고찰하고 토의하였다.