• Journal of Korea Water Resources Association
• /
• v.51 no.12
• /
• pp.1217-1227
• /
• 2018

This paper aims to evaluate the applicability of dam inflow prediction model using recurrent neural network theory. To achieve this goal, the Artificial Neural Network (ANN) model and the Elman Recurrent Neural Network(RNN) model were applied to hydro-meteorological data sets for the Soyanggang dam and the Chungju dam basin during dam operation period. For the model training, inflow, rainfall, temperature, sunshine duration, wind speed were used as input data and daily inflow of dam for 10 days were used for output data. The verification was carried out through dam inflow prediction between July, 2016 and June, 2018. The results showed that there was no significant difference in prediction performance between ANN model and the Elman RNN model in the Soyanggang dam basin but the prediction results of the Elman RNN model are comparatively superior to those of the ANN model in the Chungju dam basin. Consequently, the Elman RNN prediction performance is expected to be similar to or better than the ANN model. The prediction performance of Elman RNN was notable during the low dam inflow period. The performance of the multiple hidden layer structure of Elman RNN looks more effective in prediction than that of a single hidden layer structure.

• Korean Journal of Social Welfare Studies
• /
• v.41 no.3
• /
• pp.135-162
• /
• 2010

The Purpose of this study is to get basic material about voluntary association in local community and its utilization. In order to achieve the purpose of this study, it was considered that trust of social capital plays a leading part in voluntary association to maintain or strengthen its role and activities. For this reason we attempt to find the process of trust building in voluntary association. The revised ground theory that is complementary weaknesses of ground theory is used in this study and in 11months, four times researches have investigated. As a result, it was analyzed that the structure of building trust can be categorized into three structure, building up relationship, dynamic interaction and structural stabilization in voluntary association. In the space that is structured spatially and temporal, role, activity, accomplishment, attitude, conflict and environment acted as basic attributes. These attributes can be found in every building process of trust and influence on continuance and growth of voluntary association. The fact that this study offers in-depth understanding of voluntary association and empirical directivity regarding the community welfare services is of great significant.

• Journal of the Korean Geographical Society
• /
• v.42 no.5
• /
• pp.808-834
• /
• 2007

This study attempts to elucidate manifold dimensions of gendered accessibility experiences. How gender roles(household responsibilities) differentiate accessibility experiences between women and men is explored through the comparison of married dual-earner couples' parental status, using the US Portland activity-travel diary dataset with GIS-based geocomputation results of(time-geography based) space-time accessibility. First, this study shows how gender division of labor within the household still permeates current society, despite the widespread belief of the social change toward a gender-egalitarian society. Then, the study pays special attention to the way gender roles structure individual accessibility experiences of women and men differently, and, in turn, the way such accessibility experiences take a form of gendered spatiality. Gendered spatiality is examined through the analysis of accessibility space as well as activity space in order to ascertain women's home-attached and spatially entrapped characteristics. More household responsibilities throughout a day and, even more, the time constraint of picking up children at the daycare centers after work lead women's possible activity space to be more home-centered. The analysis of the spatio-temporal context of accessibility space makes gendered spatiality visible. However, the findings suggest that behavioral outcomes should be understood with an explicit awareness of constraints individuals face. It is because the revealed activity spaces can be not only an outcome of constraint but also an outcome of choice. Behavioral outcomes should not be treated as a straightforward expression of the level of constraints. It is problematic to expect that behavioral outcomes directly mirror the level of constraints. It is also problematic to suppose that the level of constraints can be straightforwardly elicited from revealed behavioral outcomes.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.253-266
• /
• 2018

This paper proposes a methodology applying sequence tagging methodology to improve the performance of NER(Named Entity Recognition) used in QA system. In order to retrieve the correct answers stored in the database, it is necessary to switch the user's query into a language of the database such as SQL(Structured Query Language). Then, the computer can recognize the language of the user. This is the process of identifying the class or data name contained in the database. The method of retrieving the words contained in the query in the existing database and recognizing the object does not identify the homophone and the word phrases because it does not consider the context of the user's query. If there are multiple search results, all of them are returned as a result, so there can be many interpretations on the query and the time complexity for the calculation becomes large. To overcome these, this study aims to solve this problem by reflecting the contextual meaning of the query using Bidirectional LSTM-CRF. Also we tried to solve the disadvantages of the neural network model which can't identify the untrained words by using ontology knowledge based feature. Experiments were conducted on the ontology knowledge base of music domain and the performance was evaluated. In order to accurately evaluate the performance of the L-Bidirectional LSTM-CRF proposed in this study, we experimented with converting the words included in the learned query into untrained words in order to test whether the words were included in the database but correctly identified the untrained words. As a result, it was possible to recognize objects considering the context and can recognize the untrained words without re-training the L-Bidirectional LSTM-CRF mode, and it is confirmed that the performance of the object recognition as a whole is improved.