The characterization and quantitative analysis of anthocyanins in four purple-fleshed sweet potato varieties (Borami, Mokpo 62, Shinzami, and Zami) cultivated in Korea were carried out by HPLC/diode array detector (DAD), HPLC-TOF/MS, and HPLC-MS/MS analyses. For the identification of anthocyanins, molecular formulas were first calculated by using the exact mass data of the molecular ions ([M](+)). The patterns of isotope ions of M(+) were also monitored to confirm the assignment of the molecular formulas. HPLC-MS(2) analysis was further conducted for elucidating their molecular structures. Twenty-seven different anthocyanins were tentatively identified in the sweet potatoes. Six of them are the first reported in sweet potatoes roots. The quantity and profiles of anthocyanins in sweet potatoes varied greatly with variety. Borami was found, for the first time, to be a rare sweet potato variety with an exceptionally high quantity of pelargonidin-based anthocyanins.

Compared to the traditional machine learning models, deep neural networks (DNN) are known to be highly sensitive to the choice of hyperparameters. While the required time and effort for manual tuning has been rapidly decreasing for the well developed and commonly used DNN architectures, undoubtedly DNN hyperparameter optimization will continue to be a major burden whenever a new DNN architecture needs to be designed, a new task needs to be solved, a new dataset needs to be addressed, or an existing DNN needs to be improved further. For hyperparameter optimization of general machine learning problems, numerous automated solutions have been developed where some of the most popular solutions are based on Bayesian Optimization (BO). In this work, we analyze four fundamental strategies for enhancing BO when it is used for DNN hyperparameter optimization. Specifically, diversification, early termination, parallelization, and cost function transformation are investigated. Based on the analysis, we provide a simple yet robust algorithm for DNN hyperparameter optimization-DEEP-BO (Diversified, Early-termination-Enabled, and Parallel Bayesian Optimization). When evaluated over six DNN benchmarks, DEEP-BO mostly outperformed well-known solutions including GP-Hedge, BOHB, and the speed-up variants that use Median Stopping Rule or Learning Curve Extrapolation. In fact, DEEP-BO consistently provided the top, or at least close to the top, performance over all the benchmark types that we have tested. This indicates that DEEP-BO is a robust solution compared to the existing solutions. The DEEP-BO code is publicly available at https://github.com/snu-adsl/DEEP-BO.

The characterization and quantification of anthocyanins in grape cultivars of Oll‐Meoru (Vitis coignetiae×Vitis labrusca), Neut‐Meoru (Vitis coignetiae×Vitis labrusca), Muscal Bailey A. (Vitis labruscana), and Campbell Early (Vitis labrusca×V. vinifera) cultivated in Korea were carried out by partial purification through XAD‐7 column chromatography followed by C‐18 HPLC/diode array detector (DAD), HPLC/MS, and HPLC/MS/MS analyses. The column oven temperature during the reverse phase C‐18 HPLC greatly affected the separation of individual anthocyanins. The result showed that the optimum column oven temperature was 35 °C. Sixteen different anthocyanins (11 nonacylated and 5 acylated anthocyanins) were identified in the grape juices. Oll‐Meoru, Neut‐Meoru, and Muscat Bailey A (MBA) grape juices contained only nonacylated anthocyanins. Oll‐Meoru and Neut‐Meoru grape juices had same anthocyanins, but their proportions were considerably different. Peonidin 3,5‐diglucoside and malvidin 3,5‐diglucoside were the major anthocyanins in Oll‐Meoru grape juice. Delphinidin 3‐glucoside was, however, the major anthocyanin in Neut‐Meoru grape juice. Peonidin 3‐glucoside and malvidin 3‐glucoside were the most abundant anthocyanins in Muscal Bailey A grape juice. Campbell Early grape juice contained both nonacylated and acylated anthocyanins. Cyanidin 3‐(p‐coumaroyl)glucoside‐5‐glucoside and peonidin 3‐(p‐coumaroyl)glucoside‐5‐glucoside were the most abundant anthocyanins in Campbell Early grape juice. Total anthocyanin contents were greatly different in different grape jucies, with the highest in Neut‐Meoru juice (1043.5 μg/mL), followed by Oll‐Meoru (997.7 μg/mL), MBA (390.2 μg/mL), and Campbell Early (183.9 μg/mL) juices. The total anthocyanin content in Neut‐Meoru grape juice was 5.67 times higher than that in Campbell Early grape juice. This represents the 1st report on the systematic characterization and quantification of anthocyanins in the juices of these grapes cultivated in Korea.

Internet-connected devices, especially mobile devices such as smartphones, have become widely accessible in the past decade. Interaction with such devices has evolved into frequent and short-duration usage, and this phenomenon has resulted in a pervasive popularity of casual games in the game sector. On the other hand, development of casual games has become easier than ever as a result of the advancement of development tools. With the resulting fierce competition, now both acquisition and retention of users are the prime concerns in the field. In this study, we focus on churn prediction of mobile and online casual games. While churn prediction and analysis can provide important insights and action cues on retention, its application using play log data has been primitive or very limited in the casual game area. Most of the existing methods cannot be applied to casual games because casual game players tend to churn very quickly and they do not pay periodic subscription fees. Therefore, we focus on the new players and formally define churn using observation period (OP) and churn prediction period (CP). Using the definition, we develop a standard churn analysis process for casual games. We cover essential topics such as pre-processing of raw data, feature engineering including feature analysis, churn prediction modeling using traditional machine learning algorithms (logistic regression, gradient boosting, and random forests) and two deep learning algorithms (CNN and LSTM), and sensitivity analysis for OP and CP. Play log data of three different casual games are considered by analyzing a total of 193,443 unique player records and 10,874,958 play log records. While the analysis results provide useful insights, the overall results indicate that a small number of well-chosen features used as performance metrics might be sufficient for making important action decisions and that OP and CP should be properly chosen depending on the analysis goal.

An ultrafast frequency domain optical coherence tomography system was developed at A-scan rates between 2.5 and 10 MHz, a B-scan rate of 4 or 8 kHz, and volume-rates between 12 and 41 volumes/second. In the case of the worst duty ratio of 10%, the averaged A-scan rate was 1 MHz. Two optical demultiplexers at a center wavelength of 1310 nm were used for linear-k spectral dispersion and simultaneous differential signal detection at 320 wavelengths. The depth-range, sensitivity, sensitivity roll-off by 6 dB, and axial resolution were 4 mm, 97 dB, 6 mm, and 23 μm, respectively. Using FPGAs for FFT and a GPU for volume rendering, a real-time 4D display was demonstrated at a rate up to 41 volumes/second for an image size of 256 (axial) × 128 × 128 (lateral) voxels.