• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.05a
• /
• pp.47-50
• /
• 2000

In this paper, an optimal identification method using Multi-FNN(Fuzzy-Neural Network) is proposed for model ins of nonlinear complex system. In order to control of nonlinear process with complexity and uncertainty of data, proposed model use a HCM clustering algorithm which carry out the input-output data preprocessing function and Genetic Algorithm which carry out optimization of model. The proposed Multi-FNN is based on Yamakawa's FNN and it uses simplified inference as fuzzy inference method and Error Back Propagation Algorithm as learning rules. HCM clustering method which carry out the data preprocessing function for system modeling, is utilized to determine the structure of Multi-FNN by means of the divisions of input-output space. Also, the parameters of Multi-FNN model such as apexes of membership function, learning rates and momentum coefficients are adjusted using genetic algorithms. Also, a performance index with a weighting factor is presented to achieve a sound balance between approximation and generalization abilities of the model, To evaluate the performance of the proposed model, we use the time series data for gas furnace and the numerical data of nonlinear function.

• Journal of Information Processing Systems
• /
• v.14 no.1
• /
• pp.176-190
• /
• 2018

This paper presents a novel convolutional neural network based multi-feature fusion learning method for non-rigid 3D model retrieval, which can investigate the useful discriminative information of the heat kernel signature (HKS) descriptor and the wave kernel signature (WKS) descriptor. At first, we compute the 2D shape distributions of the two kinds of descriptors to represent the 3D model and use them as the input to the networks. Then we construct two convolutional neural networks for the HKS distribution and the WKS distribution separately, and use the multi-feature fusion layer to connect them. The fusion layer not only can exploit more discriminative characteristics of the two descriptors, but also can complement the correlated information between the two kinds of descriptors. Furthermore, to further improve the performance of the description ability, the cross-connected layer is built to combine the low-level features with high-level features. Extensive experiments have validated the effectiveness of the designed multi-feature fusion learning method.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.1
• /
• pp.143-151
• /
• 2015

Biometric technology has been proposed as a new means to replace conventional PIN or password because it is hard to be lost and has the low possibility of illegal use. However, unlike a PIN, password, and personal information there is no way to modify the exposure if it is exposed and used illegally. Therefore, the existing single modality with single biometrics is critical when it expose. However in this paper, we use a multi-modality and multi-biometrics to authenticate between users and TTP or between users and financial institutions. Thereby, we propose a more reliable method and compared this paper with existed methods about security and performance in this paper.

• Journal of the Korean Institute of Educational Facilities
• /
• v.13 no.4
• /
• pp.24-30
• /
• 2006

There is a new demand for functional sharing between existing schools and neighbouring community facilities. This study is to find out the priority of the existing schools at Nowon District for functional sharing development. Most schools are located geographically near the highly populated residential district. The development will be a form of multi-use school complex. The process starts with selecting the schools located in the center of local community. Since the school facilities occupies the relatively enough space, it is possible to expand other functions for the neighbouring communities. Accordingly many citizens can utilize them because of their greater activities. This study is based on the investigation and the analysis of actual situations related to the complex development of school facilities. As a result the suitable candidate schools for the multi-use development are listed under the searched conditions.

• Korean Journal of Child Studies
• /
• v.29 no.1
• /
• pp.33-48
• /
• 2008

This study analyzed social development and self-efficacy in use of internet in adolescents. Subjects were 510 7th, 8th, 10th, and 11th grade students in Daegu. Instruments were the modified Activities Questionnaire for Students (Heitner & Erica, 2(02), the Personality Inventory for Youth (Heitner & Erica, 2002) and the Self-Efficacy Scale (Song, 1998). Findings were that (1) male students use more synchronous (multi-game) but female students use more asynchronous (e-mail) and asocial (web-surfing) internet activity. (2) Synchronous social internet (multi-game) users were more social and more efficient than asynchronous (e-mail) and asocial (web-surfing) internet users.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.9A
• /
• pp.1273-1281
• /
• 2000

In this paper we studied for multi-user detection system, which hold the merit of CDMA system and can enhance the system capacity. We designed actually realizable quasi-optimal multiuser detection system by use of linear equalizer on the concept that multiuser detection algorithm can be reduced by combining TDMA with CDMA. we call this the hybrid TDMA/CDMA system. And we proposed multiuser detection system, which can use PSAD and MSDD channel estimation method. As a result of performance analysis we acquired equal or much better performance by use of linear multichannel equalizer in the case of not so many user. And on the occasion of many user within cell we can also acquired much better performance in comparison with conventional single user detection system by use of hybrid TDMA/CDMA system.

• Journal of Information Technology Services
• /
• v.12 no.2
• /
• pp.243-256
• /
• 2013

Recently, due to the proliferation of smartphones, users of mobile multimedia services which are based on wireless internet without constraint of the time and places are significantly increased. In this study, considering the characteristics of mobile multimedia and the user behavior, we analyse the factors which have an effect on the behavioral intention to use the mobile multimedia services. For this purpose, we use the model which is based on Technology Accepted Model (TAM) and add two constructs; the perceived enjoyment and the perceived risk. A survey data for 280 students at the K cyber university is used for statistical analysis As a result, the perceived ease of use affects the perceived usefulness and the perceived enjoyment, and the perceived ease of use. And the perceived usefulness and perceived enjoyment affect continuous intention to use. On the other hand, the hypothesis which the perceived risk would affect adversely the continuous intention to use is rejected. Through this study, we expect to provide the useful implications for the mobile multimedia services and contribute to the development of strategy for them.

• Proceedings of the IEEK Conference
• /
• 1998.06a
• /
• pp.773-776
• /
• 1998

In this paper, we propose an efficient multi-view images coding algorithm which finds the optimal texture from the restricted number of multi-view images. The X-Y plane of the normalized object space is divided into triangular patches. The depth value of the node is determined by applying the block based disparity compensation method and then the texture of the each patch is extracted by applying the affine transformation patch is extracted by applying the affine transformation based disparity compensation method to the multi-view images. We restricted the number of images contributed to determining the texture comapred to traditional methods which use all the multi-view images in the texture extraction. Experimental results show that the SNR of images encoded by the proposed algorithm is better than that of imaes encoded by the traditional method by the amount about 0.2dB for the test sets of multi-view images called dragon, kid, city and santa. The recovered images from the encoded data by the proposed method show the better visual images than the recovered images from the encoded data by the traditional methods.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.24 no.6A
• /
• pp.855-863
• /
• 1999

Recently a number of multi-rate CDMA systems have been proposed for the third generation mobile communication system. Multi-Code CDMA (MC-CDMA) offers the system construction advantage of being able to use a single-rate receiver. But MC-CDMA suffers from the distortion due to the nonlinearity of the power amplifier. In this paper, we analyze the effect of the nonlinearity on the bit error rate performance of MC-CDMA systems. A polynomial model is used to represent the amplifier amplitude nonlinearities.

• Proceedings of the KSME Conference
• /
• 2000.11a
• /
• pp.413-419
• /
• 2000

An efficient method for calculating the nonlinear stiffness of the Progressive Multi-Leaf Spring is developed and evaluated. It utilizes the interaction between the main and help spring that induces the nonlinearity. The main and the help springs are modeled as multi-leaf cantilever beams, and, then, they are integrated as one by connecting the two models for each side of the Progressive Multi-Leaf Spring at the center-bolt. The results from the developed model are evaluated by use of the commercial FEA program, ABAQUS. The nonlinear spring coefficients calculated by FEM analysis yield the numbers very close to the numbers calculated for the spring coefficients by used of the developed method. From the comparative evaluations, the developed method is accurate enough and very efficient in calculation time for evaluating the nonlinear spring property of the Progressive Multi-Leaf Spring.