• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.263-286
• /
• 2022

This study acquires NBA statistical information for a total of 32 years from 1990 to 2022 using web crawling, observes variables of interest through exploratory data analysis, and generates related derived variables. Unused variables were removed through a purification process on the input data, and correlation analysis, t-test, and ANOVA were performed on the remaining variables. For the variable of interest, the difference in the mean between the groups that advanced to the playoffs and did not advance to the playoffs was tested, and then to compensate for this, the average difference between the three groups (higher/middle/lower) based on ranking was reconfirmed. Of the input data, only this year's season data was used as a test set, and 5-fold cross-validation was performed by dividing the training set and the validation set for model training. The overfitting problem was solved by comparing the cross-validation result and the final analysis result using the test set to confirm that there was no difference in the performance matrix. Because the quality level of the raw data is high and the statistical assumptions are satisfied, most of the models showed good results despite the small data set. This study not only predicts NBA game results or classifies whether or not to advance to the playoffs using machine learning, but also examines whether the variables of interest are included in the major variables with high importance by understanding the importance of input attribute. Through the visualization of SHAP value, it was possible to overcome the limitation that could not be interpreted only with the result of feature importance, and to compensate for the lack of consistency in the importance calculation in the process of entering/removing variables. It was found that a number of variables related to three points and errors classified as subjects of interest in this study were included in the major variables affecting advancing to the playoffs in the NBA. Although this study is similar in that it includes topics such as match results, playoffs, and championship predictions, which have been dealt with in the existing sports data analysis field, and comparatively analyzed several machine learning models for analysis, there is a difference in that the interest features are set in advance and statistically verified, so that it is compared with the machine learning analysis result. Also, it was differentiated from existing studies by presenting explanatory visualization results using SHAP, one of the XAI models.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.12 no.6
• /
• pp.456-464
• /
• 2007

This paper proposes a novel three-phase current-fed active clamp DC-DC converter for fuel cells. A single common active clamp branch is used to limit transient voltage across the three-phase full bridge and to realize zero-voltage switching(ZVS) in all switches. To apply for the power generation system current-fed type has been combined with the three-phase power conversion system. The proposed approach has the following advantages: an increase (by a factor of three) of input current and output voltage chopping frequencies; lower RMS current through the inverter switches with higher power transfer capability; reduction in size of reactive later components and the power conditioning system; better transformer utilization; increase of the system reliability. Therefore, the proposed three-phase current-fed active clamp DC-DC converter is appropriate for the boost type DC-DC converter for fuel cells and also applicable for the photovoltaic and battery charge system. The paper details the analysis, simulation and hardware implementation of the proposed system. Finally, experimental results with the proposed PWM strategy demonstrate the feasibility of the proposed scheme on a 500W prototype converter.

• Fire Science and Engineering
• /
• v.27 no.5
• /
• pp.19-25
• /
• 2013

The fire took place in the synthetic heat transfer fluid boiler. This study uses simulation to investigate the first, second and third passes and the temperature in the fire burner. The boiler's internal fluid is more or less unsteady due to the out of order inverter. As the operation continues, the flame's flow and speed are unsteady. The synthetic heat transfer fluid leak spouted about 120 kg/min in the form of vapor in the early period of the fire. The flame extended to the second and third passes. The highest temperature of the second and third pass is $1059^{\circ}C$ and $1007^{\circ}C$, respectively. The simulation shows that the temperature is $767^{\circ}C$ in the low part of the third pass. The synthetic heat transfer fluid spouted through the cracked part of the fire box in the first pass and accumulated on the turn table. The temperature rises to $183^{\circ}C$ in the low part of the burner. Therefore, it is expected that the temperature of the interior of the fire box is above $1200^{\circ}C$. The temperature of the burner rises to a maximum level several times in a short period. On account of that, several explosions occur in the fire burner.

• Journal of the Society of Cosmetic Scientists of Korea
• /
• v.44 no.1
• /
• pp.95-101
• /
• 2018

The epidermis which is stratified by epithelial tissue renewal based on keratinocyte differentiation protects the organism from various environmental insults by forming a physical barrier. Autophagy is a mechanism which mediates lysosomal delivery and degradation of protein aggregates, damaged organelles and intracellular microorganisms. Recent reports have shown that autophagy has critical roles for proper terminal differentiation to stratum corneum via removing metabolic organelles and nuclei. However, whether increasing autophagy can activate epidermal differentiation is unknown. Here, we screened a library of natural single compounds and discovered that betaine specifically increased the LC3 positive cytosolic punctate vesicles and LC3-I to LC3-II conversion in HaCaT human keratinocyte cell line, indicating increased autophagy flux. mTOR pathway, which negatively regulates autophagy, was not affected by betaine treatment, suggesting betaine-induced autophagy through an mTOR-independent pathway. Betaine-induced autophagy was also observed in primary human keratinocyte and skin equivalent. Furthermore, epidermal thickness was increased in skin equivalent under betaine treatment. Overall, our finding suggests that betaine as a novel regulator of autophagy may induce epidermal turnover and improve the skin barrier abnormality of the aged epidermis.