This study introduces a novel approach for identifying potential failure risks in missile manufacturing by leveraging Quality Inspection Management (QIM) data to address the challenges presented by a dataset comprising 666 variables and data imbalances. The utilization of the SMOTE for data augmentation and Lasso Regression for dimensionality reduction, followed by the application of a Random Forest model, results in a 99.40% accuracy rate in classifying missiles with a high likelihood of failure. Such measures enable the preemptive identification of missiles at a heightened risk of failure, thereby mitigating the risk of field failures and enhancing missile life. The integration of Lasso Regression and Random Forest is employed to pinpoint critical variables and test items that significantly impact failure, with a particular emphasis on variables related to performance and connection resistance. Moreover, the research highlights the potential for broadening the scope of data-driven decision-making within quality control systems, including the refinement of maintenance strategies and the adjustment of control limits for essential test items.

Recently, there has been an increasing attempt to replace defect detection inspections in the manufacturing industry using deep learning techniques. However, obtaining substantial high-quality labeled data to enhance the performance of deep learning models entails economic and temporal constraints. As a solution for this problem, semi-supervised learning, using a limited amount of labeled data, has been gaining traction. This study assesses the effectiveness of semi-supervised learning in the defect detection process of manufacturing using the MixMatch algorithm. The MixMatch algorithm incorporates three dominant paradigms in the semi-supervised field: Consistency regularization, Entropy minimization, and Generic regularization. The performance of semi-supervised learning based on the MixMatch algorithm was compared with that of supervised learning using defect image data from the metal casting process. For the experiments, the ratio of labeled data was adjusted to 5%, 10%, 25%, and 50% of the total data. At a labeled data ratio of 5%, semi-supervised learning achieved a classification accuracy of 90.19%, outperforming supervised learning by approximately 22%p. At a 10% ratio, it surpassed supervised learning by around 8%p, achieving a 92.89% accuracy. These results demonstrate that semi-supervised learning can achieve significant outcomes even with a very limited amount of labeled data, suggesting its invaluable application in real-world research and industrial settings where labeled data is limited.

The Fourth Industrial Revolution and sensor technology have led to increased utilization of sensor data. In our modern society, data complexity is rising, and the extraction of valuable information has become crucial with the rapid changes in information technology (IT). Recurrent neural networks (RNN) and long short-term memory (LSTM) models have shown remarkable performance in natural language processing (NLP) and time series prediction. Consequently, there is a strong expectation that models excelling in NLP will also excel in time series prediction. However, current research on Transformer models for time series prediction remains limited. Traditional RNN and LSTM models have demonstrated superior performance compared to Transformers in big data analysis. Nevertheless, with continuous advancements in Transformer models, such as GPT-2 (Generative Pre-trained Transformer 2) and ProphetNet, they have gained attention in the field of time series prediction. This study aims to evaluate the classification performance and interval prediction of remaining useful life (RUL) using an advanced Transformer model. The performance of each model will be utilized to establish a health index (HI) for cutting blades, enabling real-time monitoring of machine health. The results are expected to provide valuable insights for machine monitoring, evaluation, and management, confirming the effectiveness of advanced Transformer models in time series analysis when applied in industrial settings.

Recently, the development of computer vision with deep learning has made object detection using images applicable to diverse fields, such as medical care, manufacturing, and transportation. The manufacturing industry is saving time and money by applying computer vision technology to detect defects or issues that may occur during the manufacturing and inspection process. Annotations of collected images and their location information are required for computer vision technology. However, manually labeling large amounts of images is time-consuming, expensive, and can vary among workers, which may affect annotation quality and cause inaccurate performance. This paper proposes a process that can automatically collect annotations and location information for images using eXplainable AI, without manual annotation. If applied to the manufacturing industry, this process is thought to save the time and cost required for image annotation collection and collect relatively high-quality annotation information.

The purpose of this study is to analyze the effect of temperature and humidity on the measured Particulate Matter (PM) concentrations recorded by PMS5003T, a low-cost light scattering type measuring tool. A regression analysis was performed on the ratio of PM concentrations measured by the light scattering method and the beta-ray absorption method according to temperature and humidity in an outdoor environment. As the temperature decreased, the PM concentration ratio increased, and this tendency intensified below 0oC. As the humidity increased, the PM concentration ratio increased, but the effect was less than the temperature effect. The coefficients of determination for temperature and humidity were R2 = 0.325 and 0.003, respectively, and the effects of temperature and humidity on the measured values w ere formulated and compensated for. As a result of the compensation, R2, relative precision, accuracy and RMSE improved from 0.927 to 0.958, from 91.183% to 96.651%, from 31.383% to 74.058%, and from 13.517 μg/m³ to 6.690 μg/m³, respectively. Finally, results from this study indicate that the reliability of the low-cost light scattering type PM sensor can be improved by applying the temperature and humidity compensation method.

Recently, the importance of preventive maintenance has been emerging since failures in a complex system are automatically detected due to the development of artificial intelligence techniques and sensor technology. Therefore, prognostic and health management (PHM) is being actively studied, and prediction of the remaining useful life (RUL) of the system is being one of the most important tasks. A lot of researches has been conducted to predict the RUL. Deep learning models have been developed to improve prediction performance, but studies on identifying the importance of features are not carried out. It is very meaningful to extract and interpret features that affect failures while improving the predictive accuracy of RUL is important. In this paper, a total of six popular deep learning models were employed to predict the RUL, and identified important variables for each model through SHAP (Shapley Additive explanations) that one of the explainable artificial intelligence (XAI). Moreover, the fluctuations and trends of prediction performance according to the number of variables were identified. This paper can suggest the possibility of explainability of various deep learning models, and the application of XAI can be demonstrated. Also, through this proposed method, it is expected that the possibility of utilizing SHAP as a feature selection method.

Recently, a study of prognosis and health management (PHM) was conducted to diagnose failure and predict the life of air craft engine parts using sensor data. PHM is a framework that provides individualized solutions for managing system health. This study predicted the remaining useful life (RUL) of aeroengine using degradation data collected by sensors provided by the IEEE 2008 PHM Conference Challenge. There are 218 engine sensor data that has initial wear and production deviations. It was difficult to determine the characteristics of the engine parts since the system and domain-specific information was not provided. Each engine has a different cycle, making it difficult to use time series models. Therefore, this analysis was performed using machine learning algorithms rather than statistical time series models. The machine learning algorithms used were a random forest, gradient boost tree analysis and XG boost. A sliding window was applied to develop RUL predictions. We compared model performance before and after applying the sliding window, and proposed a data preprocessing method to develop RUL predictions. The model was evaluated by R-square scores and root mean squares error (RMSE). It was shown that the XG boost model of the random split method using the sliding window preprocessing approach has the best predictive performance.

Control mating is important aspect in bee breeding programs. The technique of artificial insemination is the possible one that can surely control mating of the selected drones with the virgin queen. This is the first time applied artificial insemination technique to control mating of A. cerana in Korea. Altogether 18 queens were artificially inseminated, and 2,000 drones of Korean A. cerana were used to evaluate amount of semen collection. Semen of A. cerana is much difficult to separate from mucus in comparing with A. mellifera. The average amount of semen can be collected from one A. cerana drone was 0.09 μl, whereas the A. mellifera was more than 6 times (0.58 μl semen per A mellifera drone). Obtaining 1 μl of semen have to collect from 11.94 drones that successful semen ejection and have to kill 17 A. cerana drones. Queens artificially inseminated with 4 μl of semen (once insemination) or 8 μl of semen (twice insemination, each with 4 μl of semen) started laying egg later than naturally mated queens 5.3 and 2.5 days, respectively. The onsets of oviposition of artificially inseminated queens were 12.5 to 15.3 days. Queens received twice inseminations started laying eggs 2.8 days earlier than those received only once insemination. Artificially inseminated queens produced exclusively brood and were similar as the naturally mated ones. The brood production of the queens received once insemination with 4 μl of semen was insignificantly different than those received twice inseminations or naturally mated ones, suggesting that one artificial insemination with 4 μl of semen is favorable.

We have surveyed the current status of insect pollinator use for horticultural crops in 2016. The use rate and farmnumber of insect pollinators for 26 horticultural crops were 25.8% and 55,208, respectively. The colony number of insectpollinators used in this survey was 479,777, which include 344,690 for honeybees, 119,104 for bumblebees, 2,415 formason bees, 1,317 for flies, and 2,415 for the combination of bumblebees, honeybees, and mason bees. The use rateof insect pollinators was 59.4% for 11 vegetable crops and the colony number of insect pollinators used for 11 vegetablecrops was 449,287. The colony number of insect pollinators used for 15 fruit tree crops was 30,290, which include honeybees(66.3%), bumblebees (20.2%), mason bees (8.0%), flies (1.6%), and the combination (3.9%) of bumblebees, honeybees,and mason bees. Together, farms of 98% showed positive effect for the use of insect pollinators and most of farms (97.0%)planed for the continuous use of insect pollinators

경수로 원전을 대상으로 원전 내 방사화 대상 물질인 스테인리스강, 탄소강 및 콘크리트의 불순물 정보 적용여부에 따른 방 사화 핵종 재고량을 계산하였다. 본 연구에서 탄소강은 압력용기 물질에 사용되었고, 스테인리스강은 압력용기 내부 물질에 사용되었으며, 일반 콘크리트가 생체 차폐체에 사용되었다. 금속 물질에 대해서는 참고자료 1개의 불순물 함량 정보를 적용 하였고, 콘크리트 물질에서는 참고자료 5개의 불순물 함량 정보를 적용하여 평가를 수행하였다. 방사화 핵종 재고량 전산해 석 시 중성자속 계산에는 MCNP 전산코드를, 방사화 계산에는 FISPACT 전산코드를 각각 사용하였다. 계산 결과, 금속 물질 에서 불순물을 포함한 경우가 그렇지 않은 경우보다 비방사능이 2배 이상 높았으며, 특히 콘크리트에서는 불순물을 포함한 경우가 그렇지 않은 경우보다 최대 30배 이상 비방사능이 높게 계산되었다. 방사화 핵종의 생성반응과 재고량을 분석한 결 과, 금속 구조물에서는 불순물 중 Co원소와 중성자에 의해 생성되는 방사화 핵종인 Co-60이, 콘크리트에서는 불순물 중 Co, Eu 원소와 중성자에 의해 생성되는 방사화 핵종인Co-60, Eu-152, Eu-154 이 방사성폐기물 준위 결정에 큰 영향을 미치고 있 음을 확인하였다. 본 연구의 결과는 원전 해체 계획 수립 시 방사화 핵종 재고량 평가 및 규제에 활용될 수 있을 뿐 아니라, 해체를 고려한 원전 또는 원자력시설의 설계 단계에서도 참고자료로 활용 될 것으로 판단된다.

In this study, a novel and flexible recommender system was developed, based on product taxonomy and usage patterns of users. The proposed system consists of the following four steps : (i) estimation of the product-preference matrix, (ii) construction of the product-preference matrix, (iii) estimation of the popularity and similarity levels for sought-after products, and (iv) recom- mendation of a products for the user. The product-preference matrix for each user is estimated through a linear combination of clicks, basket placements, and purchase statuses. Then the preference matrix of a particular genre is constructed by computing the ratios of the number of clicks, basket placements, and purchases of a product with respect to the total. The popularity and similarity levels of a user’s clicked product are estimated with an entropy index. Based on this information, collaborative and content-based filtering is used to recommend a product to the user. To assess the effectiveness of the proposed approach, an empirical study was conducted by constructing an experimental e-commerce site. Our results clearly showed that the proposed hybrid method is superior to conventional methods.

Currently, R&D investment of government is increased dramatically. However, the budget of the government is different depend- ing on the size of ministry and priorities, and then it is difficult to obtain consensus on the budget. They did not establish decision support systems to evaluate and execute R&D budget. In this paper, we analyze factors affecting research funds by linear regression and decision tree analysis in order to increase investment efficiency in national research project. Moreover, we suggested strategies that budget is estimated reasonably.

To address global climate change, various governments are investing in electric vehicle research and, especially in Korea, the application of electric vehicles to public transportation. The lithium batteries used in electric vehicles typically have an exp

This study was performed to investigate the effects of Needle Electrode Electrical Stimulation(NEES) on ischemia-induced cere˗ brovascular accidents. After obstruction and reperfusion of arteries in white mice, the amounts of necrosis and inflammation related sub˗ stances Bax, IL-6, Caspase-3, and COX-2 were measured in neurons of the fore-brain. The following results were obtained. This study used 21 male specific pathogen free(SPF) SD rats, 8 weeks of age and approximately 300g in weight. Each exposed artery was completely occluded with non-absorbent suture thread and kept in that state for 5 minutes. The sutures were then removed to allow reperfusion of blood. Test group is control group(common carotid artery occlusion models), a GI(underwent common carotid artery occlusion), and NEES(underwent NEES after artery occlusion). The GI and NEES groups were given 12, 24, or 48 hours of reperfusion before NEES. NEES device(PG6, ITO, Japan, 9V, current, 2Hz) was used to stimulate the bilateral acupoint ST36 of the SD rats for 30 minutes while they were sedated with 3% isoflurane. An immuno-his˗ tochemistry test was done on the forebrains of the GI induced rats. Both Bax and Caspase-3 immuno-reactive cells, related to apoptosis, were greater in the GI than the NEES group. Cox-2 and IL-6 immuno-reactive cells, related to inflammation, were greater in the GI and NEES groups than the control group. We can expect that applying NEES after ischemic CVA is effective for preventing brain cells from being destroyed. And we can conclude NEES should be applyed on early stage of ischemic CVA.

Root knot nematode species, such as Meloidogyne hapla, M. incognita, M. arenaria and M. javanica are economically most notorious nematode pests, causing serious damage to the various crops throughout world. In this study, DNA sequence analyses of the D1-D3 expansion segments of the 28S gene in the ribosomal DNA were conducted to characterize genetic variation of the four Meloidogyne species obtained from Korea and United States. PCR-RFLP (Polymerase Chain Reaction-Restriction Fragment Length Polymorphism), SCAR (Sequence Characterized Amplified Region) marker and RAPD (Random Amplification of Polymorphic DNA) also were used to develop the methods for exact and rapid species identification. In the sequence analysis of the D1-D3 expansion segments, only a few nucleotide sequence variation were detected among M. incognita, M. arenaria, and M. javanica, except for M. hapla. The PCR-RFLP analysis that involves amplification of the mitochondrial COII and lrRNA region yielded one distinct amplicon for M. hapla at 500 bp, enabling us to distinguish M. hapla from M. incognita, M. arenaria, M. javanica reproduced by obligate mitotic parthenogenesis. SCAR markers successfully identified the four root knot nematode species tested. We are under development of RAPD primers specific to the three root knot nematodes found in Korea.

이 연구에서는 플라즈마 제염 기술의 실용화를 위해 , , 등의 반응성 플라즈마 기체를 이용하여 원자력 시설의 주요 오염원인 코발트 핵종에 대한 표면 제염 모의실험을 수행하였다. 디스크 형태의 금속코발트에 대하여 시편 표면 온도를 변수로 플라즈마 식각 실험을 수행한 결과 반응율은 에서 기체의 경우 그리고 와 기체의 경우 각각 과 이었으며, 이들 반응의 활성화에너지는 각각 39.4 kJ/mol, 42.1 kJ/mol, 116.0 kJ/mol이었다. 이와 함께 AES (Auger Electron Spectroscopy)를 이용하여 반응 생성물 성분 분석 결과 이들 반응의 주요 반응 기구는 코발트의 불화 반응임이 밝혀졌다. 이 연구를 통해 확보된 의 금속 표면 식각율은 주요 반도체 공정의 식각율을 뛰어넘는 높은 식각율로 플라즈마 제 염 기술의 실용화를 앞당길 수 있는 고무적인 결과라 할 수 있을 것이다.