• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.2030-2032
• /
• 2001

In recent years, many attempts have been made to predict the behavior of bonds, currencies, stock, or other economic markets. Most previous experiments used multilayer perceptrons(MLP) for stock market forecasting. The Kospi 200 Index is modeled using different neural networks and fuzzy system predictions. In this paper, a multilayer perceptron architecture, a dynamic polynomial neural network(DPNN) and a fuzzy system are used to predict the Kospi 200 index. The results of prediction is compared with the root mean squared error(RMSE) and the scatter plot. Results show that both networks can be trained to predict the index. And the fuzzy system is performing slightly better than DPNN and MLP.

• KDI Journal of Economic Policy
• /
• v.24 no.2
• /
• pp.83-119
• /
• 2002

In this paper, we study the relationship between the U.S. daily stock returns and the corresponding Korean returns. More specifically, we examine whether the previously realized U.S. stock returns would help predict the current Korean returns. We find that for dose-to-close daily stock returns, the U.S. returns would help predict the Korean returns. However, for open-to-close stock returns, the U.S. intraday stock returns would not help predict the corresponding Korean returns. After distinguishing investors by their nationality and types, we then examine whether there is a relationship between investors' net purchase of Korean stocks and the previous days' U.S. stock returns. We find that the amount of international investors' net purchase of Korean stocks today would vary significantly with the previous days' U.S. stock returns. The Korean individual investors and the Korean investment trust companies, however, would follow the opposite investment pattern.

• Journal of the Korean Society for Precision Engineering
• /
• v.22 no.5 s.170
• /
• pp.144-151
• /
• 2005

To predict the shrinkage of molded parts using numerical simulations, the mathematical model should be simplified to overcome the difficulties of formulation due to non-linearity of problems. So it is hard to predict the shrinkage exactly because of the simplification. In the present work, the neural network is used to predict the shrinkage which can implement nonlinear models very well. Comparison between the results of neural network and that of the commercial analysis software, ABAQUS, shows that the result of the neural network is in better agreement with that of the experiments.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2005.11a
• /
• pp.844-848
• /
• 2005

A method to predict the strain responses from the measurements of displacement responses is considered. The method uses a transformation matrix which is composed of a displacement modal matrix and a strain modal matrix. The method can predict strains at points where displacements are not measured as well as at displacement measuring points. One of the drawbacks of the strain prediction method is that the displacement responses must be measured at many points on a structure simultaneously. This difficulty can be overcome by measuring the FRFs between displacements at a reference point and other point in sequence with a two channel measuring equipment This procedure is based on the assumption that the characteristics of excitation applied to the structure do not vary with time.

• Proceedings of the Earthquake Engineering Society of Korea Conference
• /
• 2003.09a
• /
• pp.107-114
• /
• 2003

There are many problems in the prediction of dynamic behaviors of saturated soils because undrained excess pore water pressure builds up and then the strain softening behavior is occurred simultaneously. A few analytical constitutive models based on the effective stress concept have been proposed but most models hardly predict the excess pore water pressure and strain softening behaviors correctly In this study, the disturbed state concept (DSC) model proposed by Dr, Desai was modified to predict the saturated soil behaviors under the dynamic loads. Also, back-prediction program was developed for verification of modified DSC model. Cyclic triaxial tests were carried out to determine DSC parameters and test result was compared with the result of back-prediction. Through this research, it is proved that the proposed model based on the modified disturbed state concept can predict the realistic soil dynamic characteristics such as stress degradation and strain softening behavior according to dynamic process of excess pore water pressure.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.20 no.10
• /
• pp.9-18
• /
• 2021

The cutting force in a cutting simulation is determined by the cutting conditions, such as cutting speed, feed rate, and depth of cut. The cutting force changes, depending on the material and cutting conditions, and is affected by the heat generated during cutting. The physical properties for predicting the cutting force use constitutive equations as functions of the hardening term, rate-hardening term, and thermal-softening term. To accurately predict the thermal properties, it is necessary to accurately predict the thermal-softening coefficient. In this study, the thermal-softening coefficient was determined, and the cutting force was predicted, using the response-surface method with the cutting conditions and the thermal-softening coefficient as factors.

• Journal of the Korean Society of School Health
• /
• v.34 no.1
• /
• pp.33-41
• /
• 2021

Purpose: Exploring the variables that predict teachers' intent when referring students to mental health professionals is important. The Theory of Planned Behavio (TPB) is a theory of predicting people's intentions of performing a particular behavior; the intent to perform a certain behavior is determined by three factors. (1) attitudes toward the behavior, (2) subjective norms, and (3) perceived control. This study aimed to develop a TPB measurement to investigate what variables predict the intentions of teacher's referral behaviors. Methods: A qualitative study following standardized manuals and guidelines for developing a TPB measurement was used. As a qualitative research method, the Consensual Qualitative Research-Modified (CQR-M) was used. According to the findings from the qualitative study, the quantitative measurement to assess teachers' referral intention, attitude, subjective norm, and behavioral control was developed. Results: The reliability and validity of the newly developed measurement were tested and verified. Conclusion: The newly developed measurement would contribute to a future empirical study that will examine predictors of teachers' referral intention.

• International journal of advanced smart convergence
• /
• v.10 no.4
• /
• pp.98-103
• /
• 2021

Recently, as the need for food resources has increased both domestically and internationally, support for the agricultural sector for stable food supply and demand is expanding in Korea. However, according to recent media articles, the biggest problem in rural communities is the unstable profit structure. In addition, in order to confirm the profit structure, profit forecast data must be clearly prepared, but there is a lack of auxiliary data for farmers or future returnees to predict farm income. Therefore, in this paper we analyzed data over the past 15 years through time series analysis and proposes an artificial intelligence farm income prediction algorithm that can predict farm household income in the future. If the proposed algorithm is used, it is expected that it can be used as auxiliary data to predict farm profits.

• International Journal of Advanced Culture Technology
• /
• v.6 no.4
• /
• pp.255-261
• /
• 2018

In the field of excavation, it is important to recognize and analyze the factors that cause the ground collapse in order to predict and cope with the ground subsidence. However, it is difficult for field engineers to predict ground collapse due to insufficient knowledge of ground subsidence influence factors. Although there are many cases and studies related to the ground subsidence, there is no manual to help practitioners. In this study, we present the criteria for describing and quantifying the influential factors to help the practitioners understand the existing ground collapse cases and classification of the ground subsidence factors revealed through the research. This study aims to improve the understanding of the factors affecting the ground collapse and to provide a GSRp for the ground subsidence risk assessment which can be applied quickly in the field.

• International Journal of Computer Science & Network Security
• /
• v.21 no.8
• /
• pp.247-253
• /
• 2021

The outbreak of the deadly virus COVID-19 is said to infect 17.3Cr people around the globe since 2019. This outbreak is continuously affecting a lot of new people till this day and, most of it is said to under control. However, vaccines introduced around the world can help mitigate the risk of the virus. Apart from medical professionals, prediction models are also said to combinedly help predict the risk of infection based on given datasets. This paper is based on publication of a machine learning approach using regression models to predict the output based on dataset which have indictors grouped based on active, tested, recovered and critical cases along with regions and cities covering most of it from Dubai. Hence, the active cases are tested based on the other indicators and other attributes. The coefficient of the determination (r²) is 0.96, which is considered promising. This model can be used as an frame work, among others, to predict the resources related to the dangerous outbreak.