• Proceedings of the Korea Water Resources Association Conference
• /
• 2007.05a
• /
• pp.132-136
• /
• 2007

최근 지구온난화로 인한 이상기후의 영향으로 강우일수는 줄고 있으나 강수량은 예년과 비슷한 수준을 보이고 있다. 이로 인해 갈수기의 용수부족 현상은 더욱 심해지고. 장마철의 홍수피해와 게릴라성 집중호우로 인한 피해가 커지는 등 해가 갈수록 홍수 예경보의 중요성은 더욱 높아지고 있다. 그럼에도 불구하고 현재 홍수 예경보 체계는 몇 가지 문제를 가지고 있다. 기존 예경보 체계의 경우 한 번의 예측을 수행하기 위해 수반되는 전처리과정과 주계산과정을 거치는 동안 각 과정에서 발생한 오차들이 반복, 누적되어 최종 결과물(예측된 유출량) 속에 모두 포함된다. 또한 기존 체계에서는 유출모형을 적용하기 위해서 토양형. 피복상태 등에 관련된 매개변수들이 필요한데. 이러한 매개변수의 결정에 어려움이 있고. 불확실성을 갖고 있다. 본 연구에서는 불확실성을 적극적으로 인정하고 수학적으로 해석하려는 fuzzy 이론을 신경망 이론에 도입하여 홍수 예경보 시스템의 운영과정에서 발생하는 불확실성의 문제를 해결하고자 하였다. 본 연구에서 사용한 ANFIS(Adaptive Neuro-Fuzzy Inference System)은 data driven model(자료에 기반을 둔 모형)의 하나로 다음과 같은 장점을 가진다. 우선 data driven model은 유역의 물리적, 지형적 특성을 고려하지 않고(매개변수설정에서 발생하는 문제 해결 가능), 입력자료와 출력자료만을 고려하여 구축되는 모형이므로, 유역의 물리적 자료나 지형 자료와 같은 방대한 양의 자료 수집이 필요 없고, 일단 모형이 구축되면 자료의 입력만으로도 신뢰성 높은 결과를 단시간 내에 효율적으로 획득할 수 있다. 그리고 유역 내의 상황이 변화하더라도, 이들의 영향을 고려하여 쉽게 모형을 갱신할 수 있다. 마지막으로 모형의 구축 과정이 물리적 모형에 비해 비교적 간편하다는 장점이 있다. 본 연구에서는 ANFIS를 통해 탄천유역의 강수량 자료와 대곡교의 수위자료를 입력자료로 사용하여 대곡교의 수위를 예측하였다. 입력 자료는 시간차 계열의 강우량과 수위 자료를 사용하였으며 모형을 통하여 t+1, t+2, t+3 시간 후의 수위를 예측하였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.06a
• /
• pp.188-194
• /
• 2007

We propose a new ad hoc multicast routing protocol for based on the ontology scheme called inference network. Ontology knowledge-based is one of the structure of context-aware. We will have developed an algorithm that will design multi-hierarchy Layered networks to simulate a desired system.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.12B
• /
• pp.1758-1765
• /
• 2010

This paper proposes an architecture exploration methodology for the design of embedded cores exploiting design hierarchy. The proposed method performs systematic architecture exploration by taking different approaches for verifying designs and estimating performances depending on the hierarchy level in design process. Performance estimation tools generate profile having performance data related with design modules of an embedded core. Profile analyzer performs data-mining to acquire association rules between the design modules and performance parameters. Inference engine in the profile analyzer updates the association rules which will be used to improve the design performance at next exploration steps. To show the efficiency of the proposed architecture explorations methodology, experiments had been performed for JPEG encoder, Chen-DCT, and FFT application functions. The embedded cores designed by taking the proposed method show performance improvement by 60.8% in terms of clock cycles on the average when compared with the initial embedded core in MIPS R3000.

• Journal of KIISE:Computing Practices and Letters
• /
• v.11 no.3
• /
• pp.246-256
• /
• 2005

Rule-based paradigm is one of the principal types of software process modeling and enaction approaches, as they provide formality and flexibility sufficient to handle complex processes. However, the systems adopting rule-based paradigms are hard to define and understand process models, and their inference engine should be modified or redeveloped at worst according to the change of process language. In this paper, we describe a rule-based PSEE(Process-Centered Software Engineering Environment) PRAiSE that solves the above limitations of existing rule-based PSEEs as well as maintains the merits of rule-based paradigm such as the ability to incorporate the nature of software processes flexibly in which dynamic changes and parallelism are pervasive and prevalent. PRAiSE provides RAiSE, a graphical Process modeling language, and defined process models are interpreted and enacted by process engine implemented using CLiPS, a rule based expert system tool.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.47 no.9
• /
• pp.37-43
• /
• 2010

An Interference Cancellation Wireless Repeater transmitts directly amplified the RF signal input to extend the coverage of the base station. Such a repeater inevitably suffers from the feedback interferences due to the environment and the adaptive Interference Cancelling System(ICS) is necessary. In this paper, the Variable Stepsize Complex Sign -Sign(VSCSS) LMS algorithm for ICS is presented. The algorithm can be implemented without multiplication/division arithmetic operation so that the required logic resources can be dramatically reduced in FPGA implementation. The performance of the proposed algorithm was analyzed in comparison with CSS-LMS algorithm and the learning curves obtained from simulation showed an excellent agreement with the theorical prediction. The simulation result with ICS in fading feedback channel environment showed the performance of the proposed algorithm is competible with NLMS algorithm.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.1
• /
• pp.34-39
• /
• 2009

As a subjective recognition effect, human's emotion has impulsive characteristic and it expresses intentions and needs unconsciously. These are pregnant with information of the context about the ubiquitous computing environment or intelligent robot systems users. Such indicators which can aware the user's emotion are facial image, voice signal, biological signal spectrum and so on. In this paper, we generate the each result of facial and voice emotion recognition by using facial image and voice for the increasing convenience and efficiency of the emotion recognition. Also, we extract the feature which is the best fit information based on image and sound to upgrade emotion recognition rate and implement Multi-Modal Emotion recognition system based on feature fusion. Eventually, we propose the possibility of the ubiquitous computing service reasoning method based on Bayesian Network and ubiquitous context scenario in the ubiquitous computing environment by using result of emotion recognition.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.60 no.1
• /
• pp.184-192
• /
• 2011

In this study, we introduce a identification methodology for FCM-based fuzzy model. The two underlying design mechanisms of such networks involve Fuzzy C-Means (FCM) clustering method and Particle Swarm Optimization(PSO). The proposed algorithm is based on FCM clustering method for efficient processing of data and the optimization of model was carried out using PSO. The premise part of fuzzy rules does not construct as any fixed membership functions such as triangular, gaussian, ellipsoidal because we build up the premise part of fuzzy rules using FCM. As a result, the proposed model can lead to the compact architecture of network. In this study, as the consequence part of fuzzy rules, we are able to use four types of polynomials such as simplified, linear, quadratic, modified quadratic. In addition, a Weighted Least Square Estimation to estimate the coefficients of polynomials, which are the consequent parts of fuzzy model, can decouple each fuzzy rule from the other fuzzy rules. Therefore, a local learning capability and an interpretability of the proposed fuzzy model are improved. Also, the parameters of the proposed fuzzy model such as a fuzzification coefficient of FCM clustering, the number of clusters of FCM clustering, and the polynomial type of the consequent part of fuzzy rules are adjusted using PSO. The proposed model is illustrated with the use of Automobile Miles per Gallon(MPG) and Boston housing called Machine Learning dataset. A comparative analysis reveals that the proposed FCM-based fuzzy model exhibits higher accuracy and superb predictive capability in comparison to some previous models available in the literature.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.8 no.6
• /
• pp.483-490
• /
• 2015

There are many software reliability models that are based on the times of occurrences of errors in the debugging of software. It is shown that it is possible to do likelihood inference for software reliability models based on finite failure model and non-homogeneous Poisson Processes (NHPP). For someone making a decision about when to market software, the conditional failure rate is an important variables. The infinite failure model are used in a wide variety of practical situations. Their use in characterization problems, detection of outlier, linear estimation, study of system reliability, life-testing, survival analysis, data compression and many other fields can be seen from the many study. Statistical process control (SPC) can monitor the forecasting of software failure and thereby contribute significantly to the improvement of software reliability. Control charts are widely used for software process control in the software industry. In this paper, proposed a control mechanism based on NHPP using mean value function of Musa-Okumo and Power law type property.

• Smart Structures and Systems
• /
• v.17 no.2
• /
• pp.209-230
• /
• 2016

The Canton Tower is a high-rise slender structure with a height of 610 m. A structural health monitoring system has been instrumented on the structure, by which data is continuously monitored. This paper presents an investigation on the identified modal properties of the Canton Tower using ambient vibration data collected during a whole day (24 hours). A recently developed Fast Bayesian FFT method is utilized for operational modal analysis on the basis of the measured acceleration data. The approach views modal identification as an inference problem where probability is used as a measure for the relative plausibility of outcomes given a model of the structure and measured data. Focusing on the first several modes, the modal properties of this supertall slender structure are identified on non-overlapping time windows during the whole day under normal wind speed. With the identified modal parameters and the associated posterior uncertainty, the distribution of the modal parameters in the future is predicted and assessed. By defining the modal root-mean-square value in terms of the power spectral density of modal force identified, the identified natural frequencies and damping ratios versus the vibration amplitude are investigated with the associated posterior uncertainty considered. Meanwhile, the correlations between modal parameters and temperature, modal parameters and wind speed are studied. For comparison purpose, the frequency domain decomposition (FDD) method is also utilized to identify the modal parameters. The identified results obtained by the Bayesian method, the FDD method and a finite element model are compared and discussed.

• Journal of Institute of Control, Robotics and Systems
• /
• v.8 no.2
• /
• pp.126-135
• /
• 2002

The study is concerned with an approach to the design of new architectures of fuzzy neural networks and the discussion of comprehensive design methodology supporting their development. We propose an Adaptive Fuzzy Polynomial Neural Networks(APFNN) based on Fuzzy Neural Networks(FNN) and Self-organizing Networks(SON) for model identification of complex and nonlinear systems. The proposed AFPNN is generated from the mutually combined structure of both FNN and SON. The one and the other are considered as the premise and the consequence part of AFPNN, respectively. As the premise structure of AFPNN, FNN uses both the simplified fuzzy inference and error back-propagation teaming rule. The parameters of FNN are refined(optimized) using genetic algorithms(GAs). As the consequence structure of AFPNN, SON is realized by a polynomial type of mapping(linear, quadratic and modified quadratic) between input and output variables. In this study, we introduce two kinds of AFPNN architectures, namely the basic and the modified one. The basic and the modified architectures depend on the number of input variables and the order of polynomial in each layer of consequence structure. Owing to the specific features of two combined architectures, it is possible to consider the nonlinear characteristics of process system and to obtain the better output performance with superb predictive ability. The availability and feasibility of the AFPNN are discussed and illustrated with the aid of two representative numerical examples. The results show that the proposed AFPNN can produce the model with higher accuracy and predictive ability than any other method presented previously.