• Journal of the Korean Institute of Landscape Architecture
• /
• v.47 no.4
• /
• pp.68-80
• /
• 2019

This study is to provide basic data for the user-oriented design for a middle school meditation forest in the future by analyzing the physical environment characteristics of existing middle school meditation forests, the users' utilization behavior, and the degree of the importance satisfaction. For this purpose, 24 evaluation indices based on site characteristics, naturalness, functionality, and the effectiveness of meditation forest sites were selected for analysis of importance satisfaction. We surveyed and analyzed the students and teachers of two middle schools 'A' and 'B' in Gwangju Metropolitan City. The results of this study are as follows. First, the perception and utilization rates of the meditation forests by students was significantly lower than teachers at both schools. 'A' school has a better use and recognition rate than the 'B' school. Second, the purposes of using meditation forests were rest (49.6%), weekday lunchtime (63.6%), with friends (65.0%) or colleagues (60%), and short (less than 10 minutes) rests (68.6%). They preferred flowers (30.0%) and shading plants (28.9%), mainly using shelters (57.9%) and walking trails (37.1%). Third, as a result of the importance of satisfaction analysis, the average score of the 24 items importance (3.81), higher than the satisfaction (3.62). The 24 items positioned in 4 quadrants are as follows: Nine items are in the I quadrant for 'persistent maintenance'. Three items are in the II quadrant for 'priority correction'. Seven items are in the quadrant III for 'low priority in the management and operation'. Five items are in the quadrant IV for 'avoid over effort'. For the comparison of two middle schools' satisfaction, 'A' school satisfaction was higher than 'B' school for 16 items, which showed a statistically significant difference. It is believed that the users in 'A' school are more satisfied than 'B' school because it has more forests and trails, better accessibility, and a variety of plant types and planting areas in the A school meditation forest. The results of the overall satisfaction analysis showed a significant difference between 'A' school (68.0%) and 'B' school (47.2%) as 'A' school has better shelters and trails. The rankings of the most satisfying space are walking trails (1st place) and shelters (2nd place). The reason for the highest satisfaction was for rest (stress relief and emotional support) in both 'A' and 'B' schools.

• Korean Chemical Engineering Research
• /
• v.61 no.4
• /
• pp.523-541
• /
• 2023

As accessibility to 3D printers increases, there is a growing frequency of exposure to chemicals associated with 3D printing. However, research on the toxicity and harmfulness of chemicals generated by 3D printing is insufficient, and the performance of toxicity prediction using in silico techniques is limited due to missing molecular structure data. In this study, quantitative structure-activity relationship (QSAR) model based on data-centric AI approach was developed to predict the toxicity of new 3D printing materials by imputing missing values in molecular descriptors. First, MissForest algorithm was utilized to impute missing values in molecular descriptors of hazardous 3D printing materials. Then, based on four different machine learning models (decision tree, random forest, XGBoost, SVM), a machine learning (ML)-based QSAR model was developed to predict the bioconcentration factor (Log BCF), octanol-air partition coefficient (Log Koa), and partition coefficient (Log P). Furthermore, the reliability of the data-centric QSAR model was validated through the Tree-SHAP (SHapley Additive exPlanations) method, which is one of explainable artificial intelligence (XAI) techniques. The proposed imputation method based on the MissForest enlarged approximately 2.5 times more molecular structure data compared to the existing data. Based on the imputed dataset of molecular descriptor, the developed data-centric QSAR model achieved approximately 73%, 76% and 92% of prediction performance for Log BCF, Log Koa, and Log P, respectively. Lastly, Tree-SHAP analysis demonstrated that the data-centric-based QSAR model achieved high prediction performance for toxicity information by identifying key molecular descriptors highly correlated with toxicity indices. Therefore, the proposed QSAR model based on the data-centric XAI approach can be extended to predict the toxicity of potential pollutants in emerging printing chemicals, chemical process, semiconductor or display process.