• The Journal of Korea Robotics Society
• /
• v.19 no.2
• /
• pp.203-212
• /
• 2024

Simultaneous motion is essential in the activities of daily living (ADL). For motion intention recognition, surface electromyogram (sEMG) and corresponding motion label is necessary. However, this process is time-consuming and it may increase the burden of the user. Therefore, we propose a simultaneous motion recognition framework using data augmentation based on muscle activation model. The model consists of multiple point sources to be optimized while the number of point sources and their initial parameters are automatically determined. From the experimental results, it is shown that the framework has generated the data which are similar to the real one. This aspect is quantified with the following two metrics: structural similarity index measure (SSIM) and mean squared error (MSE). Furthermore, with k-nearest neighbor (k-NN) or support vector machine (SVM), the classification accuracy is also enhanced with the proposed framework. From these results, it can be concluded that the generalization property of the training data is enhanced and the classification accuracy is increased accordingly. We expect that this framework reduces the burden of the user from the excessive and time-consuming data acquisition.

• Journal of the Korean Society of Radiology
• /
• v.83 no.6
• /
• pp.1208-1218
• /
• 2022

In the medical field, artificial intelligence has been used in various ways with many developments. However, most artificial intelligence technologies are developed so that one model can perform only one task, which is a limitation in designing the complex reading process of doctors with artificial intelligence. Multi-task learning is an optimal way to overcome the limitations of single-task learning methods. Multi-task learning can create a model that is efficient and advantageous for generalization by simultaneously integrating various tasks into one model. This study investigated the concepts, types, and similar concepts as multi-task learning, and examined the status and future possibilities of multi-task learning in the medical research.

• International Journal of Computer Science & Network Security
• /
• v.22 no.5
• /
• pp.31-38
• /
• 2022

The article highlights the educational potential of information and communication technologies in the study of philological disciplines in higher education institutions. The study aims to analyze the didactic potential of ICT in the study of philological disciplines, as well as to check the scientific hypothesis that the use of ICT in HEIs in the study of philological disciplines will intensify and enhance the effectiveness of the learning process. To confirm the validity of the hypothesis, experimental testing was carried out and the results are illustrated in the article. The above-mentioned goal of the study determined the use of theoretical and empirical methods: analysis, synthesis, generalization, and systematization of pedagogical and scientific-methodological literature to clarify the state of research problem development and to identify pedagogical foundations on which the process of ICT use is based, comparison and prediction; questioning and testing of educational process participants to understand the effectiveness of ICT use in their training in HEIs. The research results showed positive changes in all analyzed criteria in the experimental group, which is due to the introduction of additional ICT tools into the educational process of the mentioned group. The scientific novelty of the study consists in highlighting the main characteristics and didactic functions of ICT in the learning process of philological students; in covering the classification of ICT, ICT tools, and typology of training sessions using ICT in the study of philological disciplines. In the conclusion it is summarized that the introduction of modern ICT in the educational process allows intensifying the learning process, implementation of a variety of ideas, increases the pace of classes and material assimilation, influencing the motivation for learning, increases the amount of independent work of students.

• The KIPS Transactions:PartD
• /
• v.12D no.6 s.102
• /
• pp.837-848
• /
• 2005

A multi-scale database is a set of spatial database, covering same geographic area with different scales and it can be derived from pre-existing databases. In the derivation processes of a new multi-scale spatial database, the geometries and topological relations on the source database can be transformed and the transformation can be the cause of the lack of integrity Therefore, it is necessary to assess the transformation whether it is consistent or not after the derivation process of a new multi-scale database. Thus, we propose assessment methods for the topological consistency between a source database and a derived multi-scale database in this paper. In particular, we focus on the case that 2-dimensional objects are collapsed to 1-dimensional ones in the derivation process of a multi-scale database. We also describe implementation of the assessment methods and show the results of the implementation with experimental data.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.53 no.1
• /
• pp.40-49
• /
• 2004

In this paper, we propose a new architecture of Genetic Algorithms(GAs)-based Self-Organizing Polynomial Neural Networks(SOPNN), discuss a comprehensive design methodology and carry out a series of numeric experiments. The conventional SOPNN is based on the extended Group Method of Data Handling(GMDH) method and utilized the polynomial order (viz. linear, quadratic, and modified quadratic) as well as the number of node inputs fixed (selected in advance by designer) at Polynomial Neurons (or nodes) located in each layer through a growth process of the network. Moreover it does not guarantee that the SOPNN generated through learning has the optimal network architecture. But the proposed GA-based SOPNN enable the architecture to be a structurally more optimized network, and to be much more flexible and preferable neural network than the conventional SOPNN. In order to generate the structurally optimized SOPNN, GA-based design procedure at each stage (layer) of SOPNN leads to the selection of preferred nodes (or PNs) with optimal parameters- such as the number of input variables, input variables, and the order of the polynomial-available within SOPNN. An aggregate performance index with a weighting factor is proposed in order to achieve a sound balance between approximation and generalization (predictive) abilities of the model. A detailed design procedure is discussed in detail. To evaluate the performance of the GA-based SOPNN, the model is experimented with using two time series data (gas furnace and NOx emission process data of gas turbine power plant). A comparative analysis shows that the proposed GA-based SOPNN is model with higher accuracy as well as more superb predictive capability than other intelligent models presented previously.

• Journal of Elementary Mathematics Education in Korea
• /
• v.16 no.2
• /
• pp.253-267
• /
• 2012

In this paper, we primarily focus on the perspectives about creative process, which is how mathematical creativity emerged, as one aspect of mathematical creativity and then present a desirable task characteristic to measure and program characteristics to develop mathematical creativity. At first, we describe domain-generality perspective and domain-specificity perspective on creativity. The former regard divergent thinking skill as a key cognitive process embedded in creativity of various discipline domain involving language, science, mathematics, art and so on. In contrast the researchers supporting later perspective insist that the mechanism of creativity is different in each discipline. We understand that the issue on this two perspective effect on task and program to foster and measure creativity in mathematics education beyond theoretical discussion. And then, based on previous theoretical review, we draw a desirable characteristic on instruction program and task to facilitate and test mathematical creativity, and present an applicable task and instruction cases based on Geneplor model at the mathematics class in elementary school. In conclusion, divergent thinking is necessary but sufficient to develop mathematical creativity and need to consider various mathematical reasoning such as generalization, ion and mathematical knowledge.

• Journal of Educational Research in Mathematics
• /
• v.21 no.1
• /
• pp.67-86
• /
• 2011

This study aimed to examine first graders' recognition and thinking about mathematical patterns. To attain the goal, this paper analyzed 116 students' response with regard to repeating, growing, and changing patterns represented in both picture and number, and also analyzed four students' thinking process of the patterns through interview. It was found that students showed high recognition in repeating, growing, and changing patterns in order. Whereas there was no significant difference between picture and number representation in both repeating and growing patterns, pictures gained a bit higher scores than numbers in changing patterns. Also, according to the result of examining the thinking process by the patterns, students tended to consider the patterns as a bundle and tried to solve problems with counting strategies. The result of this paper provides an empirical foundation on how first graders recognize and think of various patterns.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 1999.05a
• /
• pp.163-167
• /
• 1999

The relational data model can't be applied to CAD/CAM, CE, and CIM since it can't support the semantic model concept such as complex object, random data definition, manipulation, version control, generalization, aggregation and so on. In this paper, the IPCS(Integrated Production Control System) for hand-rail of ship is parted into several module according to process function. further more, the object oriented data model is designed with UML(Unified Modeling Language). UML is the object oriented design methodology of industrial standard that combines the Booch's methodology, the Rumbaugh's On(Object Modeling Technique), and the Jacobson's OOSE(Object-Oriented Software Engineering) methodology. The efficient management is expected with object-oriented data model construction, since this developed system can achieve efficient process control, system maintenance, repair and extension.

• International Journal of Control, Automation, and Systems
• /
• v.1 no.2
• /
• pp.194-202
• /
• 2003

In this paper, we introduce a category of Multi-FNN (Fuzzy-Neural Networks) models, analyze the underlying architectures and propose a comprehensive identification framework. The proposed Multi-FNNs dwell on a concept of fuzzy rule-based FNNs based on HCM clustering and evolutionary fuzzy granulation, and exploit linear inference being treated as a generic inference mechanism. By this nature, this FNN model is geared toward capturing relationships between information granules known as fuzzy sets. The form of the information granules themselves (in particular their distribution and a type of membership function) becomes an important design feature of the FNN model contributing to its structural as well as parametric optimization. The identification environment uses clustering techniques (Hard C - Means, HCM) and exploits genetic optimization as a vehicle of global optimization. The global optimization is augmented by more refined gradient-based learning mechanisms such as standard back-propagation. The HCM algorithm, whose role is to carry out preprocessing of the process data for system modeling, is utilized to determine the structure of Multi-FNNs. The detailed parameters of the Multi-FNN (such as apexes of membership functions, learning rates and momentum coefficients) are adjusted using genetic algorithms. An aggregate performance index with a weighting factor is proposed in order to achieve a sound balance between approximation and generalization (predictive) abilities of the model. To evaluate the performance of the proposed model, two numeric data sets are experimented with. One is the numerical data coming from a description of a certain nonlinear function and the other is NOx emission process data from a gas turbine power plant.

• Journal of the Korean School Mathematics Society
• /
• v.16 no.1
• /
• pp.241-263
• /
• 2013

The purpose of this paper is to investigate high school students' reasoning characteristics in problem solving. To do this, we selected five high school students as participants and presented them some open problems which allow diverse solving approaches, and recorded their problem solving process. Through analyzing their problem solving process relate to their solution, we found the followings: First, students quickly try to calculate without understanding the given problem. Second, students concern whether their solution is right or not rather than consider mathematical warrants for the results of their strategies. Third, students have difficulties to consider more than two conditions at the same time necessary to solve problem. Forth, students are not familiar to use precedence knowledge relate to given tasks. Fifth, students could have difficulties in problem solving because of easy generalization.