• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.63-83
• /
• 2019

Investors prefer to look for trading points based on the graph shown in the chart rather than complex analysis, such as corporate intrinsic value analysis and technical auxiliary index analysis. However, the pattern analysis technique is difficult and computerized less than the needs of users. In recent years, there have been many cases of studying stock price patterns using various machine learning techniques including neural networks in the field of artificial intelligence(AI). In particular, the development of IT technology has made it easier to analyze a huge number of chart data to find patterns that can predict stock prices. Although short-term forecasting power of prices has increased in terms of performance so far, long-term forecasting power is limited and is used in short-term trading rather than long-term investment. Other studies have focused on mechanically and accurately identifying patterns that were not recognized by past technology, but it can be vulnerable in practical areas because it is a separate matter whether the patterns found are suitable for trading. When they find a meaningful pattern, they find a point that matches the pattern. They then measure their performance after n days, assuming that they have bought at that point in time. Since this approach is to calculate virtual revenues, there can be many disparities with reality. The existing research method tries to find a pattern with stock price prediction power, but this study proposes to define the patterns first and to trade when the pattern with high success probability appears. The M & W wave pattern published by Merrill(1980) is simple because we can distinguish it by five turning points. Despite the report that some patterns have price predictability, there were no performance reports used in the actual market. The simplicity of a pattern consisting of five turning points has the advantage of reducing the cost of increasing pattern recognition accuracy. In this study, 16 patterns of up conversion and 16 patterns of down conversion are reclassified into ten groups so that they can be easily implemented by the system. Only one pattern with high success rate per group is selected for trading. Patterns that had a high probability of success in the past are likely to succeed in the future. So we trade when such a pattern occurs. It is a real situation because it is measured assuming that both the buy and sell have been executed. We tested three ways to calculate the turning point. The first method, the minimum change rate zig-zag method, removes price movements below a certain percentage and calculates the vertex. In the second method, high-low line zig-zag, the high price that meets the n-day high price line is calculated at the peak price, and the low price that meets the n-day low price line is calculated at the valley price. In the third method, the swing wave method, the high price in the center higher than n high prices on the left and right is calculated as the peak price. If the central low price is lower than the n low price on the left and right, it is calculated as valley price. The swing wave method was superior to the other methods in the test results. It is interpreted that the transaction after checking the completion of the pattern is more effective than the transaction in the unfinished state of the pattern. Genetic algorithms(GA) were the most suitable solution, although it was virtually impossible to find patterns with high success rates because the number of cases was too large in this simulation. We also performed the simulation using the Walk-forward Analysis(WFA) method, which tests the test section and the application section separately. So we were able to respond appropriately to market changes. In this study, we optimize the stock portfolio because there is a risk of over-optimized if we implement the variable optimality for each individual stock. Therefore, we selected the number of constituent stocks as 20 to increase the effect of diversified investment while avoiding optimization. We tested the KOSPI market by dividing it into six categories. In the results, the portfolio of small cap stock was the most successful and the high vol stock portfolio was the second best. This shows that patterns need to have some price volatility in order for patterns to be shaped, but volatility is not the best.

• Korean Journal of Weed Science
• /
• v.12 no.3
• /
• pp.200-222
• /
• 1992

The results of recent researches for improvement of seedling stand in direct seeded rice on the dry paddy in Korea were summarized as the following ; a variety to be cultivated should be chosen the characteristics of high percentage germination under low temperature, shorter period of shoot emergence, and better growth of the mesocotyl and shoots. Meanwhile, there was 40% increase in seedling stand at the treatment of removal of the seed awn under using the drill seeder. After seeding the rice seed covered with soil of 3cm depth was better seedling emergence and also there was the hightest seedling emergence at the 70% of moisture content of the soil. In addition, the application of the Release containing GA 10% enabled to increase the seedling stand and furthermore it was effective under deep seeding depth. The optimum seeding date should be seeded around May 10 when mean air temperature is above 12-13$^{\circ}C$ so that may establish more less 70% in seedling stand. Based on an appropriate seedling stand of 150/$m^2$, the optimum seeding rate was 5kg/10a. It was the best in seeding method using drill seeder and the most desirable recommended seeding method was the drill seeder in terms of seedling stand. In order to improve seedling stand water management was more effective in canal irrigation and in drainage at 6hr after irrigation following by the seeding process. On the other hand, for the increase of seedling stand under flooded condition a variety might have characters being better germination at low concentration of dissolved oxygen and vertically deeper growing of the crown root. Also, seedling stand was able to increase with the seed coating of $CaO_2$in the flooded soil. It was possible to be seeded on the early part of May being mean air temperature of avove 10$^{\circ}C$ and the optimum seeding rate was 5kg/10a. For an effective water management water would be flooded up to 3cm depth for 2-3 weeks after seeding. The rice plant grown under the direct seeded cultivation might be not so much strong in lodging resistance compared to that grown under the transplanting and moreover direct seeded rice cultivation under flooded condition would be more weak growth of the rice plant than that on dry paddy. Meanwhile, the lodging would be affected by the seeding rate, the soil depth after seeding. and seeding method even in the same variety. In particular, roots in the lodging pattern of direct seeded rice cultivation under flooded condition were largely distributed on the soil surface so that resulted easily in the lodging. In general, the lodging resistance would be greater as seeding rate and amount of N fertilizer application are lower and soil depth after seeding is higher. Among the introduction of different seeding method the high ridged drill seeding method on dry paddy soil resulted in the lowest in the lodging index and also it was lower in the drill seeding method than in the scattering seeding method under flooded condition. In case of more than 150 seedlings per $m^2$ there was a severe lodging due to high lodging index at the 3rd and 4th internodes. The effective lodging prevention was able to at the treatment of the Inabenfide at 45 days before heading and the Uniconazol at 15 days before heading which caused the shortage by 10-15cm in culm length. Also, fertilizer management using split application of nitrogen would be contributed the reduction of lodging at the rate of 20-30-20-20-10%(basal-5th leaf stage-7th leaf stage-panicle initiation stage-heading stage) on the dry paddy soil.

• Journal of Korean Society of Forest Science
• /
• v.108 no.4
• /
• pp.592-599
• /
• 2019

This study aimed to develop an equation for estimating stem volume for Larix kaempferiin South Korea using independent variables, diameter at breast height (DBH), and height as being closely associated with stem volume. Analysis was conducted on the growth performance of 2,840 Larix kaempferi samples across South Korea after felling them and gleaning diameter data according to both stem height and stem analyses. In order to test the fitness of six different stem taper equations, empirical assessment was conducted for fitness index (FI), bias, mean, and absolute deviation (MAD), and coefficient variation (%CV). The two selectedmodels found to be optimal were the following: model one (V=a+bDBH²), established by employing DBH only; and model four (V=a+bDBH²H), established by utilizing DBH and height, respectively. The findings of non-linear regression indicated statistical significance (p < 0.05) in a and b, which were the coefficients for the intercepts and slopes of the models. The FI of the models ranged between 94% and 99%, and the bias was close to zero, while MAD ranged from 0.01 to 0.05, and %CV from 5.97 to 14.43, indicating a high level of fitness. Thus, using the suggested models, the basic information necessary for forest management was obtained, and an estimation of the stem volume was effected without delay soon after effecting DBH and height measurements.