• Information Systems Review
• /
• v.23 no.1
• /
• pp.23-43
• /
• 2021

Recently, many studies have been conducted to increase the accuracy of stock price prediction by analyzing candlestick charts using artificial intelligence techniques. However, these studies failed to consider the time-series characteristics of candlestick charts and to take into account the emotional state of market participants in data learning for stock price prediction. In order to overcome these limitations, this study produced input data by combining volatility index and candlestick charts to consider the emotional state of market participants, and used the data as input for a new method proposed on the basis of combining variantion autoencoder (VAE) and attention mechanisms for considering the time-series characteristics of candlestick chart. Fifty firms were randomly selected from the S&P 500 index and their stock prices were predicted to evaluate the performance of the method compared with existing ones such as convolutional neural network (CNN) or long-short term memory (LSTM). The results indicated the method proposed in this study showed superior performance compared to the existing ones. This study implied that the accuracy of stock price prediction could be improved by considering the emotional state of market participants and the time-series characteristics of the candlestick chart.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.44 no.8
• /
• pp.1194-1199
• /
• 2015

Vitamin $K_1$ (phylloquinone) content of commonly consumed foods in Korea were determined by solvent extraction followed by reversed-phase liquid chromatography using post-column derivatization and fluorescence detection. Samples were obtained in the years of 2013 and 2015. In this study, 46 vegetables, 14 fruits, and 6 legumes were analyzed. Relatively higher amounts of vitamin $K_1$ were found in sweet potato leaves, green kiwi, and mung beans among vegetables, fruits, and legumes, respectively. The content of vitamin $K_1$ in vegetables including spinach, broccoli, and potato ranged from non-detectable (ND) to $1,467.3{\mu}g/100g$. The content of vitamin $K_1$ in fruits ranged from ND to $42.7{\mu}g/100g$. The content of vitamin $K_1$ in legumes, including soybeans, mung beans and peas ranged from 1.7 to $63.4{\mu}g/100g$. In addition, the analytical method validation parameters including recovery, reproducibility, repeatability, peak purity, and linearity were calculated to ensure the method's validity. The results showed high linearity with a correlation coefficient of 0.9999. Overall recovery was close to 100% (n=5). This study revealed reliable vitamin K content in commonly consumed foods in Korea for a nutritional information and food composition database.