• Kyungpook Mathematical Journal
• /
• v.33 no.2
• /
• pp.163-171
• /
• 1993

• Proceedings of the Korean Nuclear Society Conference
• /
• 2005.10a
• /
• pp.125-126
• /
• 2005

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2012.06a
• /
• pp.85-86
• /
• 2012

e-Navigation strategy IMO promotes is defined as it is necessary to network to provide various maritime safety information to in land and on board users, and it is expected to provide a large amount and diverse kinds of maritime spatial information services to them frequently. However, as there are some limits to transmit that by current mobile maritime communication technologies, it is required to simplify and optimize the information. In this study, tree node and convex hull method is applied to S-100 SD spatial information to generalize and we arranged the efficiency and effect of generalization by storing in XML form which can be used in general.

• Journal of the Korean School Mathematics Society
• /
• v.15 no.3
• /
• pp.565-584
• /
• 2012

This study investigates how the GSP helps gifted and talented students understand geometric principles and concepts during the inquiry process in the generalization of the internal triangle, and how the students logically proceeded to visualize the content during the process of generalization. Four mathematically gifted students were chosen for the study. They investigated the pattern between the area of the original triangle and the area of the internal triangle with the ratio of each sides on m:n respectively. Digital audio, video and written data were collected and analyzed. From the analysis the researcher found four results. First, the visualization used the GSP helps the students to understand the geometric principles and concepts intuitively. Second, the GSP helps the students to develop their inductive reasoning skills by proving the various cases. Third, the lessons used GSP increases interest in apathetic students and improves their mathematical communication and self-efficiency.

• Journal of Intelligence and Information Systems
• /
• v.10 no.2
• /
• pp.53-63
• /
• 2004

Recurrent-Cascade-Correlation(RCC) is a supervised teaming algorithm that automatically determines the size and topology of the network. RCC adds new hidden neurons one by one and creates a multi-layer structure in which each hidden layer has only one neuron. By second order RCC, new hidden neurons are added to only one hidden layer. These created neurons are not connected to each other. We present a generalization of the RCC Architecture by combining the standard RCC Architecture and the second order RCC Architecture. Whenever a hidden neuron has to be added, the new RCC teaming algorithm automatically determines whether the network topology grows vertically or horizontally. This new algorithm using sigmoid, tanh and new activation functions was tested with the morse-benchmark-problem. Therefore we recognized that the number of hidden neurons was decreased by the experiments of the RCC network generalization which used the activation functions.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.1
• /
• pp.451-458
• /
• 2011

In order to provide the optimal location based services such as the optimal moving path search or the scheduling pattern prediction, the extraction of significant moving pattern which is considered the temporal and spatial properties of the location-based historical data of the moving objects is essential. In this paper, for the extraction of significant moving pattern we propose the location generalization method which translates the location attributes of moving object into the spatial scope information based on $R^*$-tree for more efficient patterning the continuous changes of the location of moving objects and for indexing to the 2-dimensional spatial scope. The proposed method generates the moving sequences which is satisfied the constraints of the time interval between the spatial scopes using the generalized spatial data, and extracts the significant moving patterns using them. And it can be an efficient method for the temporal pattern mining or the analysis of moving transition of the moving objects to provide the optimal location based services.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.5
• /
• pp.1044-1051
• /
• 2003

This paper surveys the EBP(Error Back Propagation) learning, the Cross Entropy function and the LBL(Layer By Layer) learning, which are used for learning the MLP(Multi Layer Perceptrons). We compare the merits and demerits of each learning method in the handwritten digit recognition. Although the speed of EBP learning is slower than other learning methods in the initial learning process, its generalization capability is better. Also, the speed of Cross Entropy function that makes up for the weak points of EBP learning is faster than that of EBP learning. But its generalization capability is worse because the error signal of the output layer trains the target vector linearly. The speed of LBL learning is the fastest speed among the other learning methods in the initial learning process. However, it can't train for more after a certain time, it has the lowest generalization capability. Therefore, this paper proposes the standard of selecting the learning method when we apply the MLP.

• Journal of Intelligence and Information Systems
• /
• v.14 no.4
• /
• pp.1-18
• /
• 2008

By using previous similar case plans, the case-based planning (CBP) systems can generate efficiently plans for new problems. However, most existing CBP systems show limited functionalities for case retrieval and case generalization. Moreover, they do not allow their users to participate in the process of plan generation. To support efficient memory use and case retrieval, the proposed case-based planning system, JCBP, groups the set of cases sharing the same goal in each domain into individual case bases and maintains indexes to these individual case bases. The system applies the heuristic knowledge automatically extracted from the problem model to the case adaptation phase. It provides a sort of case generalization through goal regression. Also JCBP can operate in an interactive mode to support a mixed-initiative planning. Since it considers and utilizes user's preference and knowledge for solving the given planning problems, it can generate solution plans satisfying more user's needs and reduce the complexity of plan generation.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.12
• /
• pp.573-580
• /
• 2017

Deep Neural Network (DNN) is a large layered neural network which is consisted of a number of layers of non-linear units. Deep Learning which represented as DNN has been applied very successfully in various applications. However, many issues in DNN have been identified through past researches. Among these issues, generalization is the most well-known problem. A Recent study, Dropout, successfully addressed this problem. Also, Dropout plays a role as noise, and so it helps to learn robust feature during learning in DNN such as Denoising AutoEncoder. However, because of a large computations required in Dropout, training takes a lot of time. Since Dropout keeps changing an inter-layer representation during the training session, the learning rates should be small, which makes training time longer. In this paper, using mutation operation, we reduce computation and improve generalization performance compared with Dropout. Also, we experimented proposed method to compare with Dropout method and showed that our method is superior to the Dropout one.

• Journal of Educational Research in Mathematics
• /
• v.27 no.2
• /
• pp.171-189
• /
• 2017

By designing and applying the lesson helping to discover the power laws, we tried to investigate the characteristics on the class. To do this, we designed a discovery lesson on the power laws and applied to 54 8th grade students. As results, we could observe the overproduction of monotonous laws, tendency to vary the type of development and increase error to students without prior learning experience, and various errors. All participants failed to express the generalization of $a^m{\div}a^n$ and some participants expressed an incomplete generalization using variables partially for the base or power. We could also observe an error of limited generality or a representation error which did not use the equal sign or variables. In the survey of students, there were two contradictory positions to appeal to the enjoyment of the creation and to talk about the difficulty of creation. Based on such results, we discussed the pedagogical implications relating to the discovery of power laws.