• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2005.04a
• /
• pp.335-339
• /
• 2005

본 논문에서는 퍼지 RBF 네트워크의 학습 성능을 개선하기 위하여 Delta-bar-Delta 알고리즘을 적용하여 학습률을 동적으로 조정하는 개선된 퍼지 RBF 네트워크를 제안한다. 제안된 학습 알고리즘은 일반화된 델타 학습 방법에 퍼지 C-Means 알고리즘을 결합한 방법으로, 중간층의 노드를 자가 생성하고 중간층과 출력충의 학습에는 일반화된 델타 학습 방법에 Delta-bar-Delta 알고리즘을 적용하여 학습률을 동적으로 조정하여 학습 성능을 개선한다. 제안된 RBF 네트워크의 학습 성능을 평가하기 위하여 컨테이너 영상에서 추출한 40개의 식별자를 학습 데이터로 적용한 결과, 기존의 ART2 기반 RBF 네트워크와 기존의 퍼지 RBF 네트워크 보다 학습 시간이 적게 소요되고, 학습의 수렴성이 개선된 것을 확인하였다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.10 no.1
• /
• pp.59-64
• /
• 2010

To improve system performance, we apply the concept of membership function to Variance Considered Machines (VCMs) which is a modified algorithm of Support Vector Machines (SVMs) proposed in our previous studies. Many classification algorithms separate nonlinear data well. However, existing algorithms have ignored the fact that probabilities of error are very high in the data-mixed area. Therefore, we make our algorithm ignore data which has high error probabilities and consider data importantly which has low error probabilities to generate system output according to the probabilities of error. To get membership function, we calculate sigmoid function from the dataset by considering means and variances. After computation, this membership function is applied to the VCMs.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.48 no.3
• /
• pp.22-33
• /
• 2020

Sign system is one of the most widely used guide media in scenic spots. It plays vital role in introducing cultural values of destinations to tourists with better visit experience. The purpose of this study is to derive the influence factors of the sign system of Mount Tai scenic area for tourists, analyze the satisfaction of tourists, and provide suggestions for the sign system of Mount Tai Mountaineering Road to improve tourists' satisfaction in the future. The evaluation items of Mount Tai Mountaineering Road sign system were derived from the previous studies and then subdivided comprehensively. Survey by questionnaires was carried out to obtain the influence factors. In order to understand the satisfaction degree of tourists, fuzzy comprehensive evaluation was implemented. The research results of this study are summarized as follows. First, four influence factors of the sign system on Mountaineering Road of Mount Tai were concluded as the interpretation content, appearance modeling, interpretation methods and layout management. Second, the order of weight values of influence factors was the interpretation content, appearance modeling, interpretation methods and layout management respectively from high to low, which means that tourists paid more attention to practicality and aesthetics. Third, the satisfaction degree of the tourists on the sign system was different. The satisfaction level for the three factors (interpretation content, appearance modeling, layout management) was good, while the satisfaction for interpretation method was medium. The reason was that it failed to deepen the understanding of tourists on the natural and cultural values of Mount Tai Mountaineering Road. These results indicate great significance to provide theoretical basis for the later readjustment and design of the sign system and to improve the overall satisfaction of tourists on tourism experience.

• Smart Structures and Systems
• /
• v.26 no.4
• /
• pp.495-506
• /
• 2020

Monitoring of complex processes faces several challenges mainly due to the lack of relevant sensory information or insufficient elaborated decision-making strategies. These challenges motivate researchers to adopt complex data processing and analysis in order to improve the process representation. This paper presents the development and implementation of quality monitoring framework based on a model-driven approach using embedded artificial intelligence strategies. In this work, the strategies are applied to the supervision of a microfabrication process aiming at showing the great performance of the framework in a very complex system in the manufacturing sector. The procedure involves two methods for modelling a representative quality variable, such as surface roughness. Firstly, the hybrid incremental modelling strategy is applied. Secondly, a generalized fuzzy clustering c-means method is developed. Finally, a comparative study of the behavior of the two models for predicting a quality indicator, represented by surface roughness of manufactured components, is presented for specific manufacturing process. The manufactured part used in this study is a critical structural aerospace component. In addition, the validation and testing are performed at laboratory and industrial levels, demonstrating proper real-time operation for non-linear processes with relatively fast dynamics. The results of this study are very promising in terms of computational efficiency and transfer of knowledge to manufacturing industry.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.9 no.11
• /
• pp.1221-1226
• /
• 2014

In an effort to improve the efficiency of the speech recognition, we investigate the effect of the number of phoneme clusters. For this purpose, codebooks of varied number of phoneme clusters are prepared by modified k-means clustering algorithm. The subsequent processing is fuzzy vector quantization (FVQ) and hidden Markov model (HMM) for speech recognition test. The result shows that there are two distinct regimes. For large number of phoneme clusters, the recognition performance is roughly independent of it. For small number of phoneme clusters, however, the recognition error rate increases nonlinearly as it is decreased. From numerical calculation, it is found that this nonlinear regime might be modeled by a power law function. The result also shows that about 166 phoneme clusters would be the optimal number for recognition of 300 isolated words. This amounts to roughly 3 variations per phoneme.

• Journal of Intelligence and Information Systems
• /
• v.11 no.2
• /
• pp.47-57
• /
• 2005

In this research, the main theme is the system integration of driving simulator and unmanned vehicle. The total system is composed of the mater system and the slave system. The master system has a cockpit system and the driving simulator. The slave system means an unmanned vehicle, which is composed of the actuator system the sensory system and the vision system. The communication system is composed of RS-232C serial communication system which combines the master system with the slave system. To integrate both systems, the signal classification and system characteristics considered DSP(Digital Signal Processing) filter is designed with signal sampling and measurement theory. In addition, to simulate the motion of tele-operated unmanned vehicle on the driving simulator, the classical washout algorithm is applied to this filter, because the unmanned vehicle does not have a limited working space, while the driving simulator has a narrow working space and it is difficult to cover all the motion of the unmanned vehicle. Because the classical washout algorithm has a defect of fixed high pass later, fuzzy logic is applied to reimburse it through an adaptive filter and scale factor for realistic motion generation on the driving simulator.

• International Journal of Control, Automation, and Systems
• /
• v.4 no.6
• /
• pp.705-713
• /
• 2006

For the analysis of multiunit extracellular neural signals as multiple spike trains, neural spike sorting is essential. Existing algorithms for the spike sorting have been unsatisfactory when the signal-to-noise ratio(SNR) is low, especially for implementation of fully-automated systems. We present a novel method that shows satisfactory performance even under low SNR, and compare its performance with a recent method based on principal component analysis(PCA) and fuzzy c-means(FCM) clustering algorithm. Our system consists of a spike detector that shows high performance under low SNR, a feature extractor that utilizes projection pursuit based on negentropy maximization, and an unsupervised classifier based on Gaussian mixture model. It is shown that the proposed feature extractor gives better performance compared to the PCA, and the proposed combination of spike detector, feature extraction, and unsupervised classification yields much better performance than the PCA-FCM, in that the realization of fully-automated unsupervised spike sorting becomes more feasible.

• 한국HCI학회:학술대회논문집
• /
• 2007.02a
• /
• pp.494-499
• /
• 2007

실제 영상과 가상의 오브젝트 또는 가상의 환경에 오브젝트를 합성하는 경우 등 사실적인 합성을 결과를 얻기 위해서는 실제 환경과 같은 배경 영상의 정확한 광원 정보가 필요하다. 본 논문에서는 실내 환경을 배경으로 영상을 합성 하는 과정에 필요한 광원정보를 카메라와 Light Probe를 이용하여 촬영된 단일 영상으로부터 추정하는 기법을 제안한다. 실내에 존재하는 광원들은 정확한 위치정보를 알 수 없는 실외환경에서와 달리 제한된 공간의 원점으로부터 3차원 공간에 위치한 좌표로 나타낼 수 있다. 광원을 추정하기 위해 먼저 실내 공간에 반사도가 높은 Light Probe를 위치하고 디지털 카메라의 적정 노출을 이용하여 광원 추정에 사용할 영상을 획득한다. 광원으로 존재하는 오브젝트의 경우 짧은 노출시간에도 카메라의 영상에 획득된다. 그렇기 때문에 단일 영상에서 광원의 영역을 추정하기 위해 영상처리를 통해 노출 시간을 짧게 하여 촬영한 영상과 비슷하게 밝은 영역만 표현되도록 처리를 한다. 전 처리된 영상으로부터 밝은 영역과 어두운 영역으로 구분을 하고 밝은 영역으로부터 광원의 정보를 추정한다. 추정된 광원들은 실제 렌더링에 곧바로 적용이 가능하며, 이를 통해 배경에 적합한 렌더링 결과를 얻을 수 있다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.5 no.1
• /
• pp.21-28
• /
• 2005

This paper proposes a new method for accelerating the search speed of genetic algorithms by taking derivative evaluation and conditional random selection into account in their evolution process. Derivative evaluation makes genetic algorithms focus on the individuals whose fitness is rapidly increased. This accelerates the search speed of genetic algorithms by enhancing exploitation like steepest descent methods but also increases the possibility of a premature convergence that means most individuals after a few generations approach to local optima. On the other hand, derivative evaluation under a premature convergence helps genetic algorithms escape the local optima by enhancing exploration. If GAs fall into a premature convergence, random selection is used in order to help escaping local optimum, but its effects are not large. We experimented our method with one combinatorial problem and five complex function optimization problems. Experimental results showed that our method was superior to the simple genetic algorithm especially when the search space is large.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.1 no.1
• /
• pp.104-112
• /
• 2001

Simply, Nonlinear dynamics theory means the complicated and noise-like phenomena originated form nonlinearity involved in deterministic dynamical system. An almost all the natural signals have nonlinear property. However, there exist few analysis software tool or package for a research and development of applications. We develop nonlinear time series analysis simulator is to provide a common and useful tool for this purpose and to promote research and development of nonlinear dynamics theory. This simulator is consists of the following four modules such as generation module, preprocessing module, analysis module and ICA module. In this paper, we applied to Electroencephalograph (EEG), as it turned out, our simulator is able to analyze nonlinear time series. Besides, we could get the useful results using the various parameters. These results are used to diagnostic the brain diseases.