• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.372-372
• /
• 2000

In this paper, we propose Neuro Fuzzy Polynomial Networks(NFPN) based on Polynomial Neural Network(PNN) and Neuro-Fuzzy(NF) for model identification of complex and nonlinear systems. The proposed NFPN is generated from the mutually combined structure of both NF and PNN. The one and the other are considered as the premise part and consequence part of NFPN structure respectively. As the premise part of NFPN, NF uses both the simplified fuzzy inference as fuzzy inference method and error back-propagation algorithm as learning rule. The parameters such as parameters of membership functions, learning rates and momentum coefficients are adjusted using genetic algorithms. As the consequence part of NFPN, PNN is based on Group Method of Data Handling(GMDH) method and its structure is similar to Neural Networks. But the structure of PNN is not fixed like in conventional Neural Networks and self-organizing networks that can be generated. NFPN is available effectively for multi-input variables and high-order polynomial according to the combination of NF with PNN. Accordingly it is possible to consider the nonlinearity characteristics of process and to get better output performance with superb predictive ability. In order to evaluate the performance of proposed models, we use the nonlinear function. The results show that the proposed FPNN can produce the model with higher accuracy and more robustness than any other method presented previously.

• 보건의료산업학회지
• /
• 제10권4호
• /
• pp.153-165
• /
• 2016

Objectives : Recently, concern about the ubiquitous healthcare industry has increased worldwide. This study estimated the economic effects of the ubiquitous healthcare industry by Input-Output Analysis. Methods : In this study, $384^*384$ sector statistics of the Bank of Korea were used as the initial analysis tool, after adjustments, $9^*9$ sector statistics were used as the major research method for that industry. The main analysis tools of this study included a comparison of the backward and forward linkage effects, as well as the induced effects of the self-industry and other industries and the induced coefficients including products, value-added, employee's pay, sales surplus, and employment. Results : Based on the results of the analysis, the ubiquitous healthcare industry has great economic impacts which affects major macroeconomic factors including production and the backward linkage effect. Additionally, the induced effects of the self-industry, the ubiquitous healthcare industry, are significant compared to other industries in terms of production, employee's pay and operating surplus. Conclusions : The ubiquitous healthcare industry is a growth engines for national development. This paper offers alternatives for efficient industrial policies.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2002년도 하계학술대회 논문집 D
• /
• pp.2821-2823
• /
• 2002

In this paper we propose the Multi-FNN (Fuzzy-Neural Networks) for optimal identification modeling of complex system. The proposed Multi-FNNs is based on a concept of FNNs and exploit linear inference being treated as generic inference mechanisms. In the networks learning, backpropagation(BP) algorithm of neural networks is used to updata the parameters of the network in order to control of nonlinear process with complexity and uncertainty of data, proposed model use a HCM(Hard C-Means)clustering algorithm which carry out the input-output dat a preprocessing function and Genetic Algorithm which carry out optimization of model The HCM clustering method is utilized to determine the structure of Multi-FNNs. The parameters of Multi-FNN model such as apexes of membership function, 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 abilities of the model. NOx emission process data of gas turbine power plant is simulated in order to confirm the efficiency and feasibility of the proposed approach in this paper.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2004년도 ICEIC The International Conference on Electronics Informations and Communications
• /
• pp.237-243
• /
• 2004

A multichannel smart sound sensor capable to detect and identify sound events in noisy conditions is presented in this paper. Sound information extraction is a complex task and the main difficulty consists is the extraction of high­level information from an one-dimensional signal. The input of smart sound sensor is composed of data collected by 5 microphones and its output data is sent through a network. For a real time working purpose, the sound analysis is divided in three steps: sound event detection for each sound channel, fusion between simultaneously events and sound identification. The event detection module find impulsive signals in the noise and extracts them from the signal flow. Our smart sensor must be capable to identify impulsive signals but also speech presence too, in a noisy environment. The classification module is launched in a parallel task on the channel chosen by data fusion process. It looks to identify the event sound between seven predefined sound classes and uses a Gaussian Mixture Model (GMM) method. Mel Frequency Cepstral Coefficients are used in combination with new ones like zero crossing rate, centroid and roll-off point. This smart sound sensor is a part of a medical telemonitoring project with the aim of detecting serious accidents.

• JSTS:Journal of Semiconductor Technology and Science
• /
• 제16권4호
• /
• pp.443-450
• /
• 2016

The linearization technique for low noise amplifier (LNA) has been implemented in standard $0.18-{\mu}m$ BiCMOS process. The MOS-BJT derivative superposition (MBDS) technique exploits a parallel LC tank in the emitter of bipolar transistor to reduce the second-order non-linear coefficient ($g_{m2}$) which limits the enhancement of linearity performance. Two feedback capacitances are used in parallel with the base-collector and gate-drain capacitances to adjust the phase of third-order non-linear coefficients of bipolar and MOS transistors to improve the linearity characteristics. The MBDS technique is also employed cascode configuration to further reduce the second-order nonlinear coefficient. The proposed LNA exhibits gain of 9.3 dB and noise figure (NF) of 2.3 dB at 2 GHz. The excellent IIP3 of 20 dBm and low-power power consumption of 5.14 mW at the power supply of 1 V are achieved. The input return loss ($S_{11}$) and output return loss ($S_{22}$) are kept below - 10 dB and -15 dB, respectively. The reverse isolation ($S_{12}$) is better than -50 dB.

• 대한전기학회논문지
• /
• 제35권1호
• /
• pp.26-35
• /
• 1986

In this paper, non-linear state equations for a 3-phase, 220V, 0.4 KW, squirrel cage induction motor have been derived using the d-q transformation and then these equations have been linearized around an operating point by a small perturbation method. Root loci on the s-plane with repect to the changes of slip S and supply frequency f have been studied. Based on the above results, the derived linear state equations have been augmented to the 6th order, including the output velocity feedback and a discrete PI speed controller. Using the new state equations, stability regions on the Kp-Kl plane have been investigated for slip S and sampling time T. In designing a discrete PI controller, the coefficients Kp and Kl around the normal operating point (220V,1,692rpm,60Hz)have been chosen under the assumptions that each response to a perturbation input of reference speed and load torque be underdamped and dominated by a pair of complex poles. Step responses in the experimental system using an Intel SDK-86 and an optimized PWM inverter show satisfactory results that the maximum overshoots and damped frequency are well coincided with ones from the computer simulation.

• 대한전자공학회논문지SD
• /
• 제45권3호
• /
• pp.22-28
• /
• 2008

비 정렬된 입출력단자를 갖는 능동 방향성 결합기에서 최대 전력결합 특성을 얻기 위한 새로운 설계조건을 제안하였다. 제안한 설계방법의 타당성 및 정확성을 분석하기 위하여 불연속 입출력 경계면에서 발생하는 반사감도를 고려한 새로운 결합효율을 정의하였다. 분석 결과, 지금까지 방향성 결합기를 설계하기 위하여 사용되어 왔던 위상정합조건과 최소간격조건들은 불연속 특성과 이득을 갖는 능동 방향성 결합기의 설계조건에 적합하지 않으며, 새로운 전력 등가분배조건이 필요함을 알 수 있었다.

• 한국산학기술학회논문지
• /
• 제9권6호
• /
• pp.1632-1638
• /
• 2008

본 논문은 종래의 CPW 월킨슨 발룬을 이용하여 CPW 평형증폭기를 구성하는 방법을 제안한다. 평형증폭기 구성에 필요한 전력분배/결합구조에 CPW 월킨슨 발룬 구조가 이용된다. 일반적인 경향처럼 CPW 단일증폭기의 정합 특성이 매우 나빴음에 비하여, 제안한 CPW 평형증폭기는 입출력측 모두 우수한 정합특성 개선을 보인다. CPW 단일 증폭기의 정합특성이 매우 나쁜 것에 비하여, -10dB 이하의 입,출력 정합특성을 보이는 CPW 평형증폭기의 주파수 대역은 각각 $1.2{\sim}2.75GHz$, $1{\sim}3.25GHz$이다.

• 전기학회논문지
• /
• 제61권5호
• /
• pp.744-752
• /
• 2012

In this study, the Polynomial-based Radial Basis Function Neural Networks is proposed as an one of the recognition part of overall face recognition system that consists of two parts such as the preprocessing part and recognition part. The design methodology and procedure of the proposed pRBFNNs are presented to obtain the solution to high-dimensional pattern recognition problems. In data preprocessing part, Principal Component Analysis(PCA) which is generally used in face recognition, which is useful to express some classes using reduction, since it is effective to maintain the rate of recognition and to reduce the amount of data at the same time. However, because of there of the whole face image, it can not guarantee the detection rate about the change of viewpoint and whole image. Thus, to compensate for the defects, Linear Discriminant Analysis(LDA) is used to enhance the separation of different classes. In this paper, we combine the PCA&LDA algorithm and design the optimized pRBFNNs for recognition module. The proposed pRBFNNs architecture consists of three functional modules such as the condition part, the conclusion part, and the inference part as fuzzy rules formed in 'If-then' format. In the condition part of fuzzy rules, input space is partitioned with Fuzzy C-Means clustering. In the conclusion part of rules, the connection weight of pRBFNNs is represented as two kinds of polynomials such as constant, and linear. The coefficients of connection weight identified with back-propagation using gradient descent method. The output of the pRBFNNs model is obtained by fuzzy inference method in the inference part of fuzzy rules. The essential design parameters (including learning rate, momentum coefficient and fuzzification coefficient) of the networks are optimized by means of Differential Evolution. The proposed pRBFNNs are applied to face image(ex Yale, AT&T) datasets and then demonstrated from the viewpoint of the output performance and recognition rate.

• 한국음향학회지
• /
• 제28권5호
• /
• pp.483-490
• /
• 2009

본 논문에서는 배경잡음과 반향이 존재하는 차량환경에서 음성인식 성능을 향상시키기 위해 상관계수를 이용한 동시통화 검출 알고리즘을 적용한 음향 반향제거기와 barge-in 기능을 갖는 음성 인터페이스를 구현하였다. 상관계수를 이용한 동시통화 검출 알고리즘은 임계치 설정 및 배경잡음의 영향 등으로 인해 검출 오류가 발생한다. 이를 보완하기 위해 동시통화 검출 조건으로 매 샘플마다 입력신호에서 추정한 배경잡음 및 반향신호의 평균 전력을 이용하여 동시통화 검출 오류를 줄였으며, 시변의 임계치를 적용한 후처리 단을 통해 시변의 잔여 잡음 성분을 제거하였다. 또한 안내음성 중에 음성입력이 가능하도록 barge-in 기능을 적용한 음성 인터페이스 시스템을 구현하였다. 제안한 음성 인터페이스 시스템은 동시통화 검출 오류와 이로 인해 발생되는 문제점을 효율적으로 해결할 수 있음을 실험을 통하여 확인하였다.