This study suggests a machine learning model for predicting the production quality of free-machining 303-series stainless steel small rolling wire rods according to the manufacturing process's operation condition. The operation condition involves 37 features such as sulfur, manganese, carbon content, rolling time, and rolling temperature. The study procedure includes data preprocessing (integration and refinement), exploratory data analysis, feature selection, machine learning modeling. In the preprocessing stage, missing values and outlier are removed, and variables for the interaction between processes and quality influencing factors identified in existing studies are added. Features are selected by variable importance index of lasso regression, extreme gradient boosting (XGBoost), and random forest models. Finally, logistic regression, support vector machine, random forest, and XGBoost is developed as a classifier to predict good or defective products with new operating condition. The hyper-parameters for each model are optimized using k-fold cross validation. As a result of the experiment, XGBoost showed relatively high predictive performance compared to other models with accuracy of 0.9929, specificity of 0.9372, F1-score of 0.9963 and logarithmic loss of 0.0209. In this study, the quality prediction model is expected to be able to efficiently perform quality management by predicting the production quality of small rolling wire rods in advance.

Background : Cirsium setidens is a perennial wild herb that belongs to the Asteraceae family. It grows in the mountainous region of Gangwon-do in Korea and is also called gondre. The bioconversion technology applied in this study has the same meaning as biosynthesis, biocatalyst, etc., and refers to a technique for producing desired products from precursors using enzymatic functions of microorganisms. Therefore, useful microorganisms having immunological activity were selected and Cirsium setidens fermentation products were prepared by applying bioconversion technology. And fermented product extracts were prepared to consider as a good sources of natural immune enhancement and functional food ingredients. Methods and Results : Lactobacillus fermentum, Lactobacillus plantarum, Saccharomyces cerevisiae, Weissella cibaria, and Lactobacillus plantarum were used as isolates from traditional foods. The fermentation product was set to a condition that the inherent physical properties did not change and did not generate a unique odor during fermentation. Cirsium setidens was fermented at 37℃ for 24 hours. And the fermented material was sterilized at 9 0℃ for 1 hour and then dried at 70℃ and pulverized. The contents of pectolinarin and pectolinarigenin, which are non - glycosides, were analyzed before and after fermentation using HPLC. Also NO production was measured in RAW264.7 cells after extract treatment at various concentrations using Griess reagent kit . The content of pectolinarin was increased in fermented Crisium setidens before fermentation, but the content of pectolinarigenin was increased after fermentation. In addition, the water extract of the fermented material accelerated the NO production compared to the pre - fermented material. Conclusion : As a result, relatively high immunostimulating effect were observed in dried Crisium setidens after fermentation, and it was confirmed that it could be a ingredient material for health functional food.

Background : We studied the anti-oxidant activity and anti-inflammatory effects of Spiraea fritschiana Schneid extract (SFSE). Methods and Results : The SFSE was prepared using methanol and was evaluated for its total phenol and flavonoid content, DPPH (1,1-diphenyl-2-picrylhydrazyl) free-radical scavenging activity, reducing power, and effect on nitric oxide (NO) production, and cell viability by using real-time polymerase chain reaction (PCR). The total phenol content was 212.78 ㎍• gallic acid equivalent (GAE)/㎎ and the total flavonoid content was 66.84 ㎍• quercetin equivalent (QE)/㎎. The extract showed antioxidant activity (DPPH free-radical scavenging activity) with RC50 value of 76.61 ㎍/㎖. The reducing power of the extract was Abs 0.58 at 250 ㎍/㎖. Cell viability was determined using the MTT 3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyltetrazolium bromide assay. To evaluate anti-inflammatory activity, we examined the inhibitory effects on lipopolysaccharide-(LPS)-induced NO production in RAW 264.7 cells. The NO inhibition rate was 90% at 200 ㎍/㎖ SFSE. At the same concentration, the expression of pro-inflammatory genes such as inducible nitric oxide synthase (iNOS) and cyclooxygenase (COX)-2 also decreased. Conclusions : Our results suggest that SFSE is a novel resource for the development of foods and drugs that possess anti-oxidant and anti-inflammatory activity.