• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.35 no.6
• /
• pp.357-365
• /
• 2022

Refrigerant mischarging is one of the most frequently occurring failure modes in air conditioners, and both undercharging and overcharging degrade cooling performance. Therefore, it is important to accurately determine the amount of charged refrigerant. In this study, a support vector machine (SVM) model was developed to multi-classify the refrigerant mischarge through steady-state identification via fuzzy clustering techniques. For steady-state identification, a fuzzy clustering algorithm was applied to the air conditioner operation data using the difference between moving averages. The identification results using the proposed method were compared with those using existing steady-state determination techniques studied through the inversed Fisher's discriminant ratio (IFDR). Subsequently, the main features were selected using minimum redundancy maximum relevance (mRMR) considering the correlation among candidate features, and an SVM multi-classification model was devised using the derived features. The proposed method achieves satisfactory accuracy and robustness from test data collected in the new domain.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.64 no.4
• /
• pp.441-451
• /
• 2019

This study was conducted to investigate the crop characteristics of 181 sweetpotato germplasms collected from Korea and overseas. The longest shoot vine length was observed in IT232211 (354.8 cm) and the shortest shoot vine length was observed in IT232185 (32 cm). The maximum numbers of shoot branches and nodes were produced by IT232091 (23.0) and IT232174 (67.8), respectively. Differences in Rapid Visco Analyser profiles were observed for pasting parameters such peak, trough, final, breakdown, and setback viscosities; and pasting temperature. The peak and breakdown viscosities were highest in IT232050 and IT232010, at 338.3 and 207.2 Rapid Visco Unit (RVU), respectively. The trough viscosity was lowest in IT232019 at 103.8 RVU. IT232101 had the highest final viscosity (284.6 RVU), and IT232192 had the highest setback viscosity (81.7 RVU). IT232197 had the highest pasting temperature at 86.8℃, and that of IT232134 was lowest at 72.7℃. To evaluate functional substance content, we analyzed 2,2-diphenyl-1-picrylhydrazyl (DPPH) radical scavenging activity and total polyphenol content. The highest frequency proportion of starch was in the 10%-15% range (50.8% of the plants), followed by the 5%-10% range (38.1% of the germplasms). Sugar content ranged from 13.5 to 33.3% (23.2% on average); the highest frequency proportion of sugar was in the 20%-25% range (56.9% of the germplasms), followed by the 25%-30% range (25.4% of the germplasms). The highest frequency proportion of water was in the 70%-80% range (52.5% of the germplasms), followed by the 60%-70% range (44.2% of the germplasms). Our results provide basic data for the selection of useful resources and for the development of new sweetpotato varieties.