• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1999년도 제14차 학술회의논문집
• /
• pp.121-124
• /
• 1999

Subspace-based state space system identification (4SID) methods have been demonstrated to per-form well in a number of applications, but the properties of these have not been fully analyzed or understood yet. For applying the methods, no assumptions on structure of realization are needed and any coordinate transformation is allowed for the estimates. This is one reason why many kinds of properties expected for identification procedures have not been clarified yet. We illustrate, by using Schur complement, an interpretation of the R matrix yielded by the QR factorization in the 4SID procedure. The results in this paper can be useful for analysis of properties of parameters obtained by 4SID methods.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2001년도 추계학술대회논문집 I
• /
• pp.409-412
• /
• 2001

Identification of systems operating in closed loop has long been of prime interest in industrial applications. The fundamental problem with closed-loop data is the correlation between the unmeasurable noise and the input. This is the reason why several methods that work in open loop fail when applied to closed-loop data. The prediction error based approaches to the closed-loop system are divided to direct method and indirect method. Both of direct and indirect methods are known to be applied to the closed-loop data without critical modification. But the direct method induces the bias error in the experimental frequency response function and this bias error may deteriorates the parameter estimation performance

• Journal of Information Processing Systems
• /
• 제14권5호
• /
• pp.1075-1086
• /
• 2018

In this paper a cross-validation algorithm for training probabilistic neural networks (PNNs) is presented in order to be applied to automatic face identification. Actually, standard PNNs perform pretty well for small and medium sized databases but they suffer from serious problems when it comes to using them with large databases like those encountered in biometrics applications. To address this issue, we proposed in this work a new training algorithm for PNNs to reduce the hidden layer's size and avoid over-fitting at the same time. The proposed training algorithm generates networks with a smaller hidden layer which contains only representative examples in the training data set. Moreover, adding new classes or samples after training does not require retraining, which is one of the main characteristics of this solution. Results presented in this work show a great improvement both in the processing speed and generalization of the proposed classifier. This improvement is mainly caused by reducing significantly the size of the hidden layer.

• 유공압시스템학회논문집
• /
• 제7권4호
• /
• pp.23-31
• /
• 2010

As the analysis and design technologies for electro-magnetic actuation has advanced over the years, proportional solenoid valve is gaining acceptance in wide range of industrial and commercial applications because of its superior characteristics over the conventional AOV or MOV, such as improved performance, reduced maintenance costs. This research deals with the position controller design of two-stage flow control solenoid valve. Investigation of steady-state characteristics and dynamic model identification for pilot disc is performed. Least square method to minimize the error magnitude of frequency response between the closed-loop and target system is applied to the design of PI-controller gains. From the experiments of step and frequency response, it is concluded that the controller meets the performance specification of target system, which verifies the usefulness of controller design method for proportional solenoid valve.

• 제어로봇시스템학회논문지
• /
• 제18권9호
• /
• pp.801-805
• /
• 2012

This paper proposes dynamic thresholding scheme for fingerprint identification. As a user authentication method by fingerprint recognition technology, verification method based on 1:1 matching was mainly used in the past, but identification method based on 1:N matching is generally used recently. The control of the value of FAR is very important in the application areas such as access control and time attendance systems. This paper proposes dynamic thresholding scheme which could properly control the value of FAR according to the field of applications and size of the fingerprints database.

• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 1990년도 봄 학술발표회 논문집
• /
• pp.37-43
• /
• 1990

This paper develops practical models and methods for the assessment of safety and rating of damaged and/or deteriorated bridges by incorporating a system identification technique for the explicit inclusion of the degree of deterioration or damage and of the actual bridge response. And, based on the proposed model, reliability-based rating methods are proposed as LRFR(Load and Resistance Factor Rating) and system reliability-index rating criteria. The proposed limit state model explicitly accounts for the degree of deterioration or damage in terms of the damage and response factors. The damage factor in the paper is proposed as the ratio of the current stiffness to the intact stiffness. Based on the observation and the results of applications to existing bridges, it may be concluded that the proposed rating models, which explicitly account for the uncertainties and the effects of degree of deterioration or damage based on the system identification technique, provide more realistic and consistent safety-assessment and capacity-rating.

• 대한전기학회논문지:전기기기및에너지변환시스템부문B
• /
• 제54권2호
• /
• pp.101-109
• /
• 2005

The newly developed speed sensorless control scheme is proposed to estimate both motor speed and rotor resistance simultaneously using variable rotor flux. The rotor flux is given as sinusoidal waveform with an amplitude and a frequency without affecting precise torque control. Especially the proposed method makes the simultaneous estimation of rotor resistance and speed with high precision even though at the low speed area including a few rpm. Moreover, on-line identification of rotor resistance can be performed simply without calculating troublesome trigonometric functions and complicated integral computation. Therefore, the proposed system can be accomplished by using very cheap microprocessors for several applications. The results of the numerical simulations and experiments demonstrate that this method is effective to estimate the speed and on-line identification of rotor resistance for sensorless induction motors.

• 대한전기학회논문지:전력기술부문A
• /
• 제48권1호
• /
• pp.68-75
• /
• 1999

Machine recognition of faces from still and video images is emerging as an active research area spanning several disciplines such as image processing, pattern recognition, computer vision and neural networks. In addition, human face identification has numerous applications such as human interface based systems and real-time video systems of surveillance and security. In this paper, we propose an algorithm that can identify a particular individual face. We consider human face identification system in color space, which hasn't often considered in conventional in conventional methods. In order to make the algorithm insensitive to luminance, we convert the conventional RGB coordinates into normalized CIE coordinates. The normalized-CIE-based facial images are KL-transformed. The transformed data are used as the input of multi-layered neural network and the network are trained using error-backpropagation methods. Finally, we verify the system performance of the proposed algorithm by experiments.

• 대한의생명과학회지
• /
• 제28권3호
• /
• pp.145-156
• /
• 2022

Over the past few decades, few technologies have had a greater impact on clinical microbiology laboratories than matrix-assisted laser desorption time-of-flight mass spectrometry (MALDI-TOF MS). The MALDI-TOF MS is a fast, accurate, and low-cost and efficient method of microbial identification. This technology generates characteristic mass spectral fingerprints that is a unique signature for each microorganism, making it an ideal method for accurate identification at the genus and species levels of both bacterial and fastidious microorganism such as anaerobes, mycobacterium and fungi etc. In addition, MALDI-TOF MS has been successfully used in microbial subtyping and susceptibility tests such as determination of resistance genes. In this study, the authors summarized the application of MALDI-TOF MS in clinical microbiology and clinical research and explored the future of MALDI-TOF MS.

• 대한임베디드공학회논문지
• /
• 제16권3호
• /
• pp.89-97
• /
• 2021

Voice interface can not only make daily life more convenient through artificial intelligence speakers but also improve the working environment of the factory. This paper presents a voice-assisted work management system that supports both speech and speaker recognition. This system is able to provide machine control and authorized worker authentication by voice at the same time. We applied two speech recognition methods, Google's Speech application programming interface (API) service, and DeepSpeech speech-to-text engine. For worker identification, the SincNet architecture for speaker recognition was adopted. We implemented a prototype of the work management system that provides voice control with 26 commands and identifies 100 workers by voice. Worker identification using our model was almost perfect, and the command recognition accuracy was 97.0% in Google API after post- processing and 92.0% in our DeepSpeech model.