• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.11
• /
• pp.473-478
• /
• 2022

Evaluation learning based on code testing is becoming a popular solution in programming education via Online judge(OJ). In the recent past, many papers have been published on how to detect plagiarism through source code similarity analysis to support OJ. However, deep learning-based research to support automated tutoring is insufficient. In this paper, we propose Input & Output side FiLM models to predict whether the input code will pass or fail. By applying Feature-wise Linear Modulation(FiLM) technique to GRU, our model can learn combined information of Java byte codes and problem information that it tries to solve. On experimental design, a balanced sampling technique was applied to evenly distribute the data due to the occurrence of asymmetry in data collected by OJ. Among the proposed models, the Input Side FiLM model showed the highest performance of 73.63%. Based on result, it has been shown that students can check whether their codes will pass or fail before receiving the OJ evaluation which could provide basic feedback for improvements.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 1997.11a
• /
• pp.194-197
• /
• 1997

A hydride vapor phase epitaxy (HVPE) method was performed to prepare the thick-fi lm GaN on AIN/Si substrates. We obtained substrate-free GaN. The foul t-width at half maximum of double crystal X-ray rocking curve from 350 ${\mu}{\textrm}{m}$ thick substrate-free GaN was ~1000 arcsec. The photoluminescence spectrum (at 20 K) shows the narrow bound exiton (I$_2$) line and wealth donor-acceptor pair recombination however. there was not observed deep donor-accepter pair recombination indicate the substrate-free GaN crystal prepared in this study are of high purity and high crystalline quality.

• Asian-Australasian Journal of Animal Sciences
• /
• v.26 no.6
• /
• pp.845-855
• /
• 2013

Requirements of dietary chloride (dCl) and chloride salts were determined by using $4{\times}2$ factorial arrangement under four phase feeding program. Four levels (0.31, 0.45, 0.59 and 0.73%) and two sources ($NH_4Cl$ and $CaCl_2$) of the dCl were allocated to 1,472 chicks in eight dietary treatments in which each treatment was replicated four times with 46 birds per replicate. The four phase feeding program was comprised of four dietary phases: Prestarter (d 1 to 10), Starter (d 11 to 20), Grower (d 21 to 33) and Finisher (d 34 to 42); and diets were separately prepared for each phase. The cations, anions, pH, dissolved oxygen (DO), temperature, electrical conductivity (EC), total dissolved solids (TDS) and salinity were analyzed in drinking water and were not affected by dietary treatments. BW gain (BWG; $p{\leq}0.009$) and feed:gain (FG; $p{\leq}0.03$) were improved in $CaCl_2$ supplemented diets during d 1 to 10. The maximum response of BWG and FG was observed at 0.38% and 0.42% dCl, respectively, for d 34 to 42. However, the level of dCl for BWG during d 21 to 33 ($p{\leq}0.04$) and d 34 to 42 ($p{\leq}0.009$) was optimized at 0.60% and 0.42%, respectively. The level of dCl for optimized feed intake (FI; $p{\leq}0.006$), FG ($p{\leq}0.007$) and litter moisture (LM; $p{\leq}0.001$) was observed at 0.60%, 0.38% and 0.73%, respectively, for d 1 to 42. Water intake (DWI) was not affected by increasing dCl supplementation (p>0.05); however, the ratio between DWI and FI (DWI:FI) was found highest at 0.73% dCl during d 1 to 10 ($p{\leq}0.05$) and d 21 to 33 ($p{\leq}0.009$). Except for d 34 to 42 ($p{\leq}0.006$), the increasing level of dCl did not result in a significant difference in mortality during any phase. Blood pH and glucose, and breast and thigh weights (percentage of dressed weight) were improved while dressing percentage (DP) and gastrointestinal health were exacerbated with $NH_4Cl$ as compared to $CaCl_2$ supplemented diets ($p{\leq}0.001$). Higher plasma $Na^+$ and $HCO_3{^-}$ and lower $Cl^-$ and $Ca^{{+}{+}}$ were observed in $NH_4Cl$ supplemented diets ($p{\leq}0.001$). Increasing supplementation of dCl increased plasma $Cl^-$ ($p{\leq}0.04$; quadratically) and linearly reduced plasma $K^+$ ($p{\leq}0.001$), $Ca^{{+}{+}}$ ($p{\leq}0.003$), $HCO_3{^-}$ ($p{\leq}0.001$), and $Na^+$ ($p{\leq}0.001$; quadratically). Consequently, higher requirements of dietary chloride are suggested for feed intake; nevertheless, lower levels of dietary chloride are sufficient to support optimal BWG and FG with increasing age. The $NH_4Cl$ supplemented diets ameliorate breast and thigh meat yield along with overall energy balance (glucose).