• The Journal of Engineering Geology
• /
• v.32 no.4
• /
• pp.697-723
• /
• 2022

Data-driven models to predict groundwater levels 30 days in advance were developed for 12 groundwater monitoring stations in the middle-Jeju watershed, Jeju Island. Stacked long short-term memory (stacked-LSTM), a deep learning technique suitable for time series forecasting, was used for model development. Daily time series data from 2001 to 2022 for precipitation, groundwater usage amount, and groundwater level were considered. Various models were proposed that used different combinations of the input data types and varying lengths of previous time series data for each input variable. A general procedure for deep-learning-based model development is suggested based on consideration of the comparative validation results of the tested models. A model using precipitation, groundwater usage amount, and previous groundwater level data as input variables outperformed any model neglecting one or more of these data categories. Using extended sequences of these past data improved the predictions, possibly owing to the long delay time between precipitation and groundwater recharge, which results from the deep groundwater level in Jeju Island. However, limiting the range of considered groundwater usage data that significantly affected the groundwater level fluctuation (rather than using all the groundwater usage data) improved the performance of the predictive model. The developed models can predict the future groundwater level based on the current amount of precipitation and groundwater use. Therefore, the models provide information on the soundness of the aquifer system, which will help to prepare management plans to maintain appropriate groundwater quantities.

• Exercise Science
• /
• v.21 no.2
• /
• pp.231-242
• /
• 2012

The purpose of this study was to develop the prediction model of VO₂max using submaximal metabolic responses from the Bruce protocol, HR responses at several stages and 1,200 m running record, and to compare and analyse the validity of these prediction models. The subjects were consisted of 255 male(133 male for 1,200 m running). They were participated maximal exercise testing with Bruce protocol, and the metabolic responses were measured in the end of the first(3 minute), second stage(6 minute), and 1,200 m running record. Measurement items were VO₂(㎖/kg/min), VCO₂(㎖/kg/min), VE(L/min), HR(bpm) of 3 and 6 minute, time to HR 150 bpm and 170 bpm, HR difference between Bruce protocol 6 and 3 minute, 1,200 m running record. Analyzing with all variables using enter method, the multiple R of total variable model was 0.642(p<.01), SEE was 4.38 ㎖/kg/min, CV was 10.8 %, but multicolinearity was appeared. The multiple R of 3 minutes model 1 and model 2 were 0.341 and 0.461, SEE was 6.05 and 5.72 ㎖/kg/min, CV was 14.9 and 14.1%, and multicolinearity did not appeared. The multiple R of 6 minutes model 1 and model 2 were 0.350 and 0.456, SEE was 6.03 and 5.74 ㎖/kg/min, CV was 14.9 and 14.2%, and multicolinearity did not appeared. The R of HR 170 and HR 170 model were 0.151 and 0.154, SEE were 6.36~6.37 ㎖/kg/min, CV were 15.7%. The R of 1,200 m running model was 0.444, SEE was 4.82 ㎖/kg/min, CV were 11.9%. In conclusion, with considering usefulness and convenience through the validity of these prediction models, the prediction model of VO₂max recommended 6 and 3 minute model, and the validity of HR model and 1,200 m running model were moderately low.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.18 no.3
• /
• pp.211-226
• /
• 2023

As we transition into the post-COVID era, economic activities that were stagnant are regaining momentum. In particular, there is a growing trend of technology entrepreneurship driven by the opportunities of digital transformation in the Fourth Industrial Revolution. However, entrepreneurship education content is struggling to keep up with the rapid pace of technological change. This study aims to emphasize the importance of entrepreneurship mentoring as a crucial component of entrepreneurship education content that requires adaptation and advancement due to the increasing demand for technology entrepreneurship. This study redefines startup mentoring, which is differentiated from general mentoring, at the present time when the demand for startups, which increases with the declining employment rate, increases, and the development of quality startup education contents and securing professional startup mentors are required. According to the start-up stage, it is divided into preliminary entrepreneurs and early entrepreneurs, and the effect of entrepreneurship knowledge and self-efficacy among start-up mentoring functions on entrepreneurial will and mentoring satisfaction is improved by empirically researching the effects of start-up mentoring functions in the case of initial entrepreneurs as a moderating effect. To confirm the importance of entrepreneurship mentoring effect for. To this end, among the mentoring functions, entrepreneurship knowledge and self-efficacy were set as independent variables, and entrepreneurial will and mentoring satisfaction were set as dependent variables. The research model was designed and hypotheses were established. In addition, empirical analysis was conducted by conducting a questionnaire survey on trainees who received entrepreneurship mentoring education at ICCE Startup School and Opus Startup School. To summarize the results of the empirical analysis, first, among the entrepreneurship mentoring functions, entrepreneurship knowledge and self-efficacy were analyzed to have a significant positive (+) effect on entrepreneurial will. Second, among the entrepreneurship mentoring functions, entrepreneurship knowledge and self-efficacy were analyzed to have a significant positive (+) effect on mentoring satisfaction. Third, it was analyzed that entrepreneurship had no significant moderating effect on entrepreneurial knowledge and entrepreneurial will. Fourth, it was analyzed that entrepreneurship had no significant moderating effect on mentoring satisfaction. Fifth, it was found that entrepreneurship had a significant moderating effect between self-efficacy and will to start a business. As a result of the research analysis, the first implication is that the mentoring function in start-up education is analyzed to produce meaningful results for both the initial entrepreneurs and the prospective entrepreneurs in the will to start a business and satisfaction. . Second, it was analyzed that there was no significant relationship between whether a business was started and the mentoring function and effect. However, it was analyzed that the will to start a business through improvement of self-efficacy through mentoring was significantly related to whether or not to start a business. turned out to be helpful. Many start-up education programs currently conducted in Korea educate both early-stage entrepreneurs and prospective entrepreneurs at the same time for reasons such as convenience. However, through the results of this study, even in small-scale entrepreneurship mentoring, it is suggested that customized mentoring through detailed classification such as whether the mentee has started a business can be a method for successful entrepreneurship and high satisfaction of the mentee.