• 지능정보연구
• /
• 제1권2호
• /
• pp.103-121
• /
• 1995

This study proposes a artificial neural network method to predict the time to buy and sell the stocks listed on the Korea Composite Stock Price Index(KOSPI). Four types (NN1, NN2, NN3, NN4) of independent networks were developed to predict KOSPIs up/down direction after four weeks. These networks have a difference only in the length of learning period. NN5 - arithmetic average of four networks outputs - shows an higher accuracy than other network types and Multiple Linear Regression (MLR), and buying and selling simulation using systems outputs produces higher reture than buy-and-hold strategy.

• 한국환경과학회지
• /
• 제7권4호
• /
• pp.451-460
• /
• 1998

The objectives of this study Is to evaluate the total runoff yield, peak flow and peak flow travel time depending on the urbanization, return period and rainfall patterns at the downstream of Manchon urban watershed in TaeGu City. SWM(Storm Water Management Model) is used for runog analysis based on 5 different steps of urbanization and 4 different types of Hufrs quartile according to 8 return periods. It is analyzed that the order of total runoff yield according to raiun patterns is Huffs 4, Huffs 2. Huffs 3 and Huffs 1 quartile, that of peak flow magnitude is Huffs 2, Huffs 1, Huffs 4 and Huffs 3 quartile at present development ratio. under the 60, 70, 80 and 90ft of urbanization to the 50% of urbanization by means of the rainfall patterns, the mean Increasing ratio of total runoff yield for each case is 4.55, 11.43, 16.07 and 20.02%, that of peak flow is 5.82, 13.61, 17.15 and 18.83%, the mean decreasing ratio of peak flow travel time Is 0.00, 2.44, 5.07 and 6.26%, the mean increasing ratio of runoff depth Is 4.51, 11.42, 16.02 and 20.05% respectively. the mean increasing ratio of total runoff yield by means of each and 19.71%. Therefore, as the result of this study. it can be used for principal data as to storm sewage treatment and flood damage protection planning in urban small watershed.