• Economic and Environmental Geology
• /
• v.57 no.5
• /
• pp.551-562
• /
• 2024

Predicting groundwater levels with data-driven models like artificial neural networks typically requires a substantial amount of data. However, when groundwater monitoring wells are newly developed or when a significant portion of the data is invalid (for example, due to missing values or outliers), acquiring an adequate dataset for training prediction models becomes challenging, leading to diminished prediction accuracy. This study proposes a method based on transfer learning to address the issue of insufficient training data. The Gated Recurrent Unit (GRU) was used as the primary data-driven model for predictions. A GRU-based pretrained network for the transfer learning process was developed using groundwater level and corresponding rainfall data collected from 89 monitoring stations nationwide. Subsequently, this pretrained network was fine-tuned using a small amount of training data obtained from the target monitoring well to develop the final prediction model. To verify the effectiveness of the transfer learning algorithm, two different groundwater level prediction models were evaluated: 1) a GRU-based model trained with insufficient data from the target well, and 2) a GRU-based model utilizing the transfer learning algorithm. Comparative verification was conducted with groundwater level data obtained from wells at two different locations, where the model using the transfer learning algorithm demonstrated superior performance compared to the other. This study confirms that the transfer learning algorithm can significantly enhance the performance of groundwater level prediction models, irrespective of the amount of available training data.

• Journal of Korean Academy of Nursing
• /
• v.45 no.5
• /
• pp.671-683
• /
• 2015

Purpose: The purpose of this study was to understand and describe the leadership experience of clinical nurses. Methods: During 2014, data were collected using focus group interviews. Three focus group interviews were held with a total of 20 clinical nurses participating. All interviews were recorded as they were spoken and transcribed and data were analyzed using qualitative content analysis. Results: Fifteen categories emerged from the five main themes. 1) Thoughts on the leadership category: to lead others, to cope with problem situations adequately and to serve as a shield against difficulties. 2) Situations requiring leadership: situation that requires correct judgement, coping and situations that need coordination and cooperation. 3-1) Leadership behaviors: other-oriented approach and self-oriented approach. 3-2) Leadership behavior consequences: relevant compensation and unfair termination. 4-1) Facilitators of leadership: confidence and passion for nursing and external support and resources. 4-2) Barriers to leadership: non-supportive organization culture and deficiency in own leadership competencies. 5) Strategies of leadership development: strengthen leadership through self-development and organizational leadership development. Conclusion: In conclusion, the results indicate that it is necessary to enhance clinical nurses' leadership role in healthcare. Enhancement can be achieved through leadership programs focused on enlarging leadership experience, constant self-development, leadership training, and development of leadership competencies suited to the nursing environment.

• Journal of Korean Home Economics Education Association
• /
• v.23 no.1
• /
• pp.159-176
• /
• 2011

The purpose of this study was to investigate 1) how the middle school Home Economics teachers perceive the importance of the practical problem-focused instruction, 2) how often they perform the instruction, and 3) what they require for the implementation the instruction. Data were collected from 150 Home Economics teachers via e-mail survey and from 6 Home Economics teachers' face-to-face interviews. Descriptive statistics including frequency, percentage, average, and standard deviation, and the results of such analyses as ANOVA, T-test, and correlation were reported using SPSS/win 10.1. The results of this research were as follows: First, even though the majority of the respondents recognized the high need for practical problem-focused instruction, only a small portion of the respondents reported that they performed that instruction in the classroom. There was no correlation between the perception of the need for practical problem-focused instruction and the degree of performance of practical problem-focused instruction. Secondly, the of performance of practical problem-focused instruction was significantly different depending on the years of teaching experience and the subject that the teachers majored in. Job satisfaction had positive correlations with the perception of the need for practical problem-focused instruction and the degree of performance of practical problem-focused instruction. Thirdly, the more teachers shared information and materials with colleagues, the better they tended to be at practical problem-focused instruction. On the other hand, insufficient time for their instruction and a deficiency in understanding the rationale of the instruction were pointed out as barriers to classroom practice. The respondents answered that long-term training programs on the philosophical foundation of practical problem-focused instruction, materials related to the instruction as well as additional credits for Home Economics are most critical to reduce the discrepancy between the teacher perception and the classroom practice of practical problem-focused instruction.