• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.12
• /
• pp.1581-1590
• /
• 1995

Recently, advanced video coding techniques using segmentation technique have been actively researched as candidates for video coding of MPEG-4 standard. The conventional segmentation techniques are unsuitable for real-time process because they have sequential structure. In this paper, we propose a new image segmentation technique using competitive learning neural network for vector quantization. The proposed segmentation procedure consist of prefiltering, primary and secondary segmentation, and a small region ellimination process. Primary segmentation segments input image in detail. Secondary segmentation merges similar region using a repetitive FSCL(Frequency sensitive competive learning) neural network. In this process, it is possible to segment an image from high resolution to low resolution by adjusting the number of repetition. Finally, small regions are merged into adjacent regions. Experimental results show that the procedure described yields reconstructed images of reasonably acceptable quality at bit rates of 0. 25 - 0.3 bit/pel.

• Research in Mathematical Education
• /
• v.15 no.2
• /
• pp.141-158
• /
• 2011

In recent years, an increasing number of viewpoints hold that students should be engaged in a learning environment where understanding and knowledge transfer take place. This study introduces Mathematics Created by You (MCY)-mentoring program, which allows students to construct artefacts that are required to learn. This program is online-based and so can be shared by several people and mathematics leaning takes place through interactions within this carefully designed environment. Also, MCY intends to provide students a series of sequential activities related to creative play, creative learning and creative inquiry based on a Constructive and interactive environment. Furthermore, a creative activity- constructing a creative product using building blocks- was presented as an example. Finally, we investigate the pedagogical implications and suggest directions for the further development.

• Journal of Educational Research in Mathematics
• /
• v.8 no.2
• /
• pp.485-494
• /
• 1998

This study is on the theory of Piaget's reflective abstraction and the mechanism of the development of knowledge and the history of algebra and its application to understand the difficulties that many students have in learning algebra. Piaget considers the development of knowledge as a linear process. The stages in the construction of different forms of knowledge are sequential and each stage begins with reorganization. The reorganization consists of the projection onto a higher level from the lower level and the reflection which reconstructs and reorganizes within a lager system that is transferred by profection. Piaget shows that the mechanisms mediating transitions from one historical period to the next are analogous to those mediating the transition from one psychogenetic stage to the next and characterizes the mechanism as the intra, inter, trans sequence. The historical development of algebra is characterized by three periods, which are intra inter, transoperational. The analysis of the history of algebra by the mechanism explains why the difficulties that students have in learning algebra occur and shows that the roles of teachers are important to help students to overcome the difficulties.

• The Mathematical Education
• /
• v.43 no.2
• /
• pp.177-186
• /
• 2004

In this paper, we introduce new functional definitions for school geometry based on DGS (dynamic geometry system) teaching-learning environment. For the vertices forming a geometric figure, we first consider the relationship between the independent vertices and dependent vertices, and using this relationship and educational considerations in DGS, we introduce functional definitions for the geometric figures in terms of its independent vertices. For this purpose, we design a new DGS called JavaMAL MicroWorld. Based on the needs of new definitions in DGS environment for the student's construction activities in learning geometry, we also design a new DGS based geometry curriculum in which the definitions of the school geometry are newly defined and reconnected in a new way. Using these funct onal definitions, we have taught the new geometry contents emphasizing the sequential expressions for the student's geometric activities.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.6 no.4
• /
• pp.282-287
• /
• 2006

This paper presents an original feature selection method for Emotion Recognition which includes many original elements. Feature selection has some merits regarding pattern recognition performance. Thus, we developed a method called thee 'Interactive Feature Selection' and the results (selected features) of the IFS were applied to an emotion recognition system (ERS), which was also implemented in this research. The innovative feature selection method was based on a Reinforcement Learning Algorithm and since it required responses from human users, it was denoted an 'Interactive Feature Selection'. By performing an IFS, we were able to obtain three top features and apply them to the ERS. Comparing those results from a random selection and Sequential Forward Selection (SFS) and Genetic Algorithm Feature Selection (GAFS), we verified that the top three features were better than the randomly selected feature set.

• International Journal of Advanced Culture Technology
• /
• v.9 no.4
• /
• pp.268-273
• /
• 2021

In this paper, we propose a sentiment analysis model that improves performance on small-scale data. A sentiment analysis model for small-scale data is proposed and verified through experiments. To this end, we propose Bagging-Bi-GRU, which combines Bi-GRU, which learns GRU, which is a variant of LSTM (Long Short-Term Memory) with excellent performance on sequential data, in both directions and the bagging technique, which is one of the ensembles learning methods. In order to verify the performance of the proposed model, it is applied to small-scale data and large-scale data. And by comparing and analyzing it with the existing machine learning algorithm, Bi-GRU, it shows that the performance of the proposed model is improved not only for small data but also for large data.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.1268-1271
• /
• 2022

Since it is common to have touch-screen devices, it is less challenging to draw sketches anywhere and save them in vector form. Current research on sketches considers coordinate sequence data and adopts sequential models for learning sketch representation in sketch understanding. In the sketch dataset, it has become customary that the dataset is in vector coordinate format. Moreover, the popular dataset does not consider real-life sketches, sketches from pencil, pen, and paper. Art psychology uses real-life sketches to analyze patients. ETRI presents a unique sketch dataset for sketch recognition of autism spectrum disorder in pixel format. We present a method to formulate the dataset for better generalization of sketch data. Through experiments, we show that pixel-based models can produce a good performance.

• Communications for Statistical Applications and Methods
• /
• v.30 no.6
• /
• pp.551-560
• /
• 2023

Recently, there has been significant research into the recognition of human activities using three-dimensional sequential skeleton data captured by the Kinect depth sensor. Many of these studies employ deep learning models. This study introduces a novel feature selection method for this data and analyzes it using machine learning models. Due to the high-dimensional nature of the original Kinect data, effective feature extraction methods are required to address the classification challenge. In this research, we propose using the first four moments as predictors to represent the distribution of joint sequences and evaluate their effectiveness using two datasets: The exergame dataset, consisting of three activities, and the MSR daily activity dataset, composed of ten activities. The results show that the accuracy of our approach outperforms existing methods on average across different classifiers.

• ETRI Journal
• /
• v.45 no.6
• /
• pp.929-938
• /
• 2023

The detection of all the symbols transmitted simultaneously in multiuser systems using limited wireless resources is challenging. Traditional model-based methods show high performance with perfect channel state information (CSI); however, severe performance degradation will occur if perfect CSI cannot be acquired. In contrast, data-driven methods perform slightly worse than model-based methods in terms of symbol error ratio performance in perfect CSI states; however, they are also able to overcome extreme performance degradation in imperfect CSI states. This study proposes a novel deep learning-based method by improving a state-of-the-art data-driven technique called deep soft interference cancellation (DSIC). The enhanced DSIC (EDSIC) method detects multiuser symbols in a fully sequential manner and uses an efficient neural network structure to ensure high performance. Additionally, error-propagation mitigation techniques are used to ensure robustness against channel uncertainty. The EDSIC guarantees a performance that is very close to the optimal performance of the existing model-based methods in perfect CSI environments and the best performance in imperfect CSI environments.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.37 no.1
• /
• pp.32-42
• /
• 2000

This paper presents an on-line learning algorithm for sequential construction of generalized radial basis function networks (GRBFNs) to model nonlinear systems from empirical data. The GRBFN, an extended from of standard radial basis function (RBF) networks with constant weights, is an architecture capable of representing nonlinear systems by smoothly integrating local linear models. The proposed learning algorithm has a two-stage learning scheme that performs both structure learning and parameter learning. The structure learning stage constructs the GRBFN model using two construction criteria, based on both training error criterion and Mahalanobis distance criterion, to assign new hidden units and the linear local models for given empirical training data. In the parameter learning stage the network parameters are updated using the gradient descent rule. To evaluate the modeling performance of the proposed algorithm, simulations and their results applied to two well-known benchmarks are discussed.