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.

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.

Enforcement of the beef traceability system can block the sale of imported beef disguised Hanwoo and help customers to know detailed information of the Hanwoo beef while purchase. This study was carried out to investigate the possibilities of identifying DNA upon various ripening and roasting methods (soy sauce, gochujang sauce, 10% vinegar, 10% coke, 10% Cheongha, 10% Soju, completely burned out, raw, normal roasted, dried, and boiled) employed for beef traceability system. Completely burned out meat could not yied useful DNA in the sample, hence wa not analysed. The amplified peaks in most of the samples appeared equally barring completely burned out meat. However, roasted beef after ripened in soy sauce showed new peaks or deletion of a peaks with two markers. The DNA allele height and the amount of extracted DNA in roasted beef after ripening in 10% Cheongha was found to be higher than those in the raw beef. No significant correlations between DNA allele height and the amount of extracted DNA within the samples was noticed. Also, these results suggest that beef traceability using microsatellite (MS) markers is possible in various roasting beef because of bovine specific MS markers. Therefore, beef traceability system by DNA identify test would give the confidence in food safety and beef distribution system to customers.

The regeneration of periodontium is the goal of periodontal therapy. Many periodontologists try to achieve this goal by using guided tissue regeneration(GTR) method. However, these procedures always include several disadvantages. Recombinant human bone morphogenetic protein-2 (rhBMP-2) stimulated ectopic bone formation when it was implanted in rat muscles with insoluble bone matrix by differentiating muscle cells into chondrocytes and osteoblasts. The purpose of this study was to evaluate the osteoinductive potential of the mixture of rhBMP-2 (5 μg/ml) and heparin (0.25 or 25 μg/ml ) at the critically sized rabbit calvarial defects. And this study aimed to reveal that heparin also acts to enhance the bone forming activity of rhBMP-2. The 12 rabbits (4-month-old; NewZealand White) were used in the present study. 5 μg/ml of rhBMP-2 and 0, 0.25 or 25 μg/ml of heparin were mixed and blotted into anorganic bovine bone and filled cranial defects. The animals were sacrificed following a time schedule (1, 3, and 6 weeks). Sections were made in 7 μm thicknesses, stained with H&E and Masson's trichrome method, and examined under a light microscope. The differences among each obtained percent value were evaluated by one-way analysis of variance. A p value of p<0.05 was considered statistically significant and an ANOVA test was performed to verify significant differences. To adjust for multiple comparisons when one-way analysis of variance showed a significant difference between groups (p<0.05), Scheffe`s post hoc test was used to identify which group differences accounted for the significant p-value. In control group, osteoinduction was not outstanding, however, in experimental groups, osteoinduction was significantly outstanding, and as the concentration of heparin mixed with rhBMP-2 increased, osteoinduction was increased. Mixtures of rhBMP-2 and heparin affect bone formation at initial bone formation, but that effect disappeared following a time lapse.

Bone morphogenetic proteins (BMPs) are known to promote osteogenesis, and clinical trials are currently underway evaluating the ability of BMPs to promote bone formation in grafting procedures and fracture healing. Some studies, have independently reported that sulfated polysaccharides particularly heparin, enhance the osteoblastic differentiation induced by BMPs in vitro, and another study demonstrated that heparin enhanced the bone formation induced by BMP‐2 in vivo. This study was performed to examine adipose stem cell responses to rhBMP‐2 alone and rhBMP‐2 with heparin at 0.25, and 25 μg/㎖ concentrations, respectively, in culture media. Adipose stem cells were cultured for 2, 4, and 8 days toward the osteoblastic differentiation in rhBMP‐2 alone and rhBMP‐2 with heparin at 0.25, and 25 μg/㎖ concentrations, respectively, in culture media. Verification of the stem cell lineage was performed in two ways. The first method was a continuous sequential culture until 5th generation. The second method was using monoclonal antibodies for STRO‐1 and CD 90. Naphthol AS phosphate‐fast blue BB staining for alkaline phosphatase was used for verifying osteoblastic differentiation because Alkaline phosphatase activity had been used as an osteoblastic differentiation marker and degree of osteoblastic activity. Alizarin red staining was also used as an osteoblastic differentiation marker because it quantifies the calcium levels in cells or tissues. During the 5th generation culture, cultured cells actively proliferated, and these cultured cells showed a positive reaction to STRO‐1 and CD90 cell surface molecules. Naphthol AS phosphate‐fast blue BB staining and Alizarin red staining were positive in most samples of each group at 2, and 4 days and positive reaction was proportioned to degree of morphological differentiation. In the concentration of 25 μg/ml of heparin, the ALP activity was highest at the 2nd day in the culture, and then the activities of ALP were decreased significantly at 4, and 8 days. The ALP activity was greatest at the 4th day of the culture, and then decreased significantly at the 8th day in 0 μ g/ml and 0.25 μg/ml of heparin concentrations, Adipose stem cells could be differentiated in rhBMP‐2 in culture media, and the addition of heparin to BMP‐2 promoted differentiation of osteoblasts. Moreover, morphological differentiation was associated with the activity of osteoblasts. This study was shown that, when heparin concentration increases, the early differentiation of the cells was brought about, but the early differentiated cells were rapidly progressed to degenerative changes

Beef traceability, a system that provides all the records of beef production, helps customers purchase that they get to know detailed information of the Hanwoo beef. This study was carried out to investigate the DNA identity possibility in various cooking methods to ripen meat (soy sauce, gochujang sauce, 10% vinegar, 10% coke, 10% Cheongha, 10% Soju, raw, dried, and decayed) for beef traceability. The DNA content of decayed beef was higher than those of other cooking methods. It is thought that result of mixed pollutant, it did not affect amplified DNA allele height because of bovine specific microsatellite (MS) markers. The ripened sample in 10% vinegar 3 days was lowest a mount of extracted DNA (156 ng) and amplified DNA allele height (based on the raw samples to 38%) by MS markers compared with the other cooking methods. There are no significant correlation between amplified DNA allele height and the amount of extracted DNA. Therefore, beef DNA identity test in various cooking methods to ripen meat can used by bovine specific MS markers. Beef traceability system by DNA identify test will give more confidence in food safety to customers