• Journal of Information Processing Systems
• /
• v.16 no.1
• /
• pp.6-29
• /
• 2020

Biometrics identification using multiple modalities has attracted the attention of many researchers as it produces more robust and trustworthy results than single modality biometrics. In this paper, we present a novel multimodal recognition system that trains a deep learning network to automatically learn features after extracting multiple biometric modalities from a single data source, i.e., facial video clips. Utilizing different modalities, i.e., left ear, left profile face, frontal face, right profile face, and right ear, present in the facial video clips, we train supervised denoising auto-encoders to automatically extract robust and non-redundant features. The automatically learned features are then used to train modality specific sparse classifiers to perform the multimodal recognition. Moreover, the proposed technique has proven robust when some of the above modalities were missing during the testing. The proposed system has three main components that are responsible for detection, which consists of modality specific detectors to automatically detect images of different modalities present in facial video clips; feature selection, which uses supervised denoising sparse auto-encoders network to capture discriminative representations that are robust to the illumination and pose variations; and classification, which consists of a set of modality specific sparse representation classifiers for unimodal recognition, followed by score level fusion of the recognition results of the available modalities. Experiments conducted on the constrained facial video dataset (WVU) and the unconstrained facial video dataset (HONDA/UCSD), resulted in a 99.17% and 97.14% Rank-1 recognition rates, respectively. The multimodal recognition accuracy demonstrates the superiority and robustness of the proposed approach irrespective of the illumination, non-planar movement, and pose variations present in the video clips even in the situation of missing modalities.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.1 no.2
• /
• pp.1-15
• /
• 1997

This paper presents substructural identification methods for the assessment of local damages in complex and large structural systems. For this purpose, an auto-regressive and moving average with stochastic input (ARMAX) model is derived for a substructure to process the measurement data impaired by noises. Using the substructural methods, the number of unknown parameters for each identification can be significantly reduced, hence the convergence and accuracy of estimation can be improved. Secondly, the damage index is defined as the ratio of the current stiffness to the baseline value at each element for the damage assessment. The indirect estimation method was performed using the estimated results from the identification of the system matrices from the substructural identification. To demonstrate the proposed techniques, several simulation and experimental example analyses are carried out for structural models of a 2-span truss structure, a 3-span continuous beam model and 3-story building model. The results indicate that the present substructural identification method and damage estimation methods are effective and efficient for local damage estimation of complex structures.

• Journal of Intelligence and Information Systems
• /
• v.14 no.2
• /
• pp.45-61
• /
• 2008

Previous U-Commerce researches have dealt with the business support systems for traditional commerce space such as real world shopping malls. This paper investigates U-Commerce business models in service space. The McDonald's Touch-Order case is analyzed from business model perspective and the Media-Embedded Place business model is introduced as a U-Commerce business model for value creation in service space. The media-embedded place business model attaches auto-identification tags to tables or billboards, triggers commercial transaction through the tags, and shares the revenues and the incentives among the place owners and commerce/content providers. This paper analyzes its scenario and applications and illustrates the profitability analysis using so-called 'tag evaluation model'.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.32 no.3
• /
• pp.45-50
• /
• 2004

The design of reaction wheel control logic is critical to achieve the spacecraft attitude stabilization and performance requirements for the successful mission. Due to various uncertainties on orbit there exist limitation to obtain the model parameters through the ground tests and to design the associated control logic. Thus, the model parameter correction using on-orbit data is essential to the control performance on orbit. This paper performs the system identification using KOMPSAT-1 telemetry data and extracts the model parameters of the reaction wheel. Moreover, the reaction wheel is remodeled and compared with the ground test results.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.15 no.6
• /
• pp.1819-1830
• /
• 1991

The problems associated with noise/energy source identification using multiple input/single output model in linear systems are investigated. Partial coherence function is formulated for the model introducing a virtual force and extraneous noises into the conventional two input/single output system. The analytical results show that the partial coherence function in two input/single output linear system is the function of noise/signal ratios when multiple inputs are mutually coherent and extraneous noises exist. Parametric studies for ordinary and partial coherence functions are carried out to demonstrate the effects of noise/signal ratios for these functions.

• Journal of Sensor Science and Technology
• /
• v.17 no.3
• /
• pp.229-235
• /
• 2008

In order to monitor the anticancer drug in stable conditions, the Web based anticancer drug management system and alarm services were constructed and assessed in this study. Anticancer drug should be exact to the correct patient in the right environment. To overcome the restriction of existing equipment that only monitors fragmentarily, temperature and humidity were continuously monitored to maintain stable environments using sensor networks and RFID for the monitoring and management of anticancer drug. Construction drug identification and the effect of normal air outside the anticancer dispensary with obstacles were evaluated in working hour. Pre-installed control system in the dispensary could be alternated with auto sensing and alarming. We expected that the efficiency of anticancer drug management and the reliability of drug medication by handwork would be increase accordingly.

• 제어로봇시스템학회:학술대회논문집
• /
• 1999.10a
• /
• pp.45-48
• /
• 1999

Model predictive control algorithm requires a relevant model of the system to be controlled. Unfortunately, the first principle model describing a polymerization reaction system has a large number of parameters to be estimated. Thus there is a need for the identification and control of a polymerization reactor system by using available input-output data. In this work, the polynomial auto-regressive moving average (ARMA) models are employed as the input-output model and combined into the nonlinear model predictive control algorithm based on the successive linearization method. Simulations are conducted to identify the continuous styrene polymerization reactor system. The input variables are the jacket inlet temperature and the feed flow rate whereas the output variables are the monomer conversion and the weight-average molecular weight. The polynomial ARMA models obtained by the system identification are used to control the monomer conversion and the weight-average molecular weight in a continuous styrene polymerization reactor It is demonstrated that the nonlinear model predictive controller based on the polynomial ARMA model tracks the step changes in the setpoint satisfactorily. In conclusion, the polynomial ARMA model is proven effective in controlling the continuous styrene polymerization reactor.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.46 no.3
• /
• pp.8-14
• /
• 2009

In this paper, it is proposed that the design of the PID controller with the internal model control structure for improved performance. Internal model was identification that is second-order plus dead time structure using final-value theorem and genetic algorithm The parameters of Controller are determined to minimize IAE(Integral of the Absolute value of the Error) and ITAE(Integral of the Time multiplied by the Absolute value of the Error) of performance index by internal model and numerical method. Simulation examples are given to show the better performance of the proposed method than conventional methods.

• Journal of the Korean Society of Safety
• /
• v.7 no.2
• /
• pp.71-79
• /
• 1992

This paper presents a least-square algorithms of lattice structures and their use for adaptive prediction of time series generated from the dynamic system. As the view point of adaptive prediction, a new method of Identification of dynamic characteristics by means of estimating the parameters of linear auto regressive model is proposed. The fast convergence of adaptive lattice algorithms is seen to be due to the orthogonalization and decoupling properties of the lattice. The superiority of the least-square lattice is verified by computer simulation, then predictor coefficients are computed from the linear sequential time data. For the application to the dynamic characteristic analysis of unknown system, the transfer function of ideal system represented in frquency domain and the estimated one obtained by predicted coefficients are compared. Using the proposed method, the damping ratio and the natural frequency of a dynamic structure subjected to random excitations can be estimated. It is expected that this method will be widely applicable to other technical dynamic problem in which estimation of damping ratio and fundamental vibration modes are required.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.21 no.6
• /
• pp.988-994
• /
• 1997

The demands for robotic and automatic system are continually increasing in manufacturing fields. There have been many studies to monitor and predict the system, but they have mainly focused upon measuring cutting force, and current of motor spindle, and upon using acoustic sensor, etc. In this study, digital image of time series sequence was acquired by taking advantage of optical technique. Mean square error was obtained from it and was available for useful observation data. The parameter was estimated using PAA(parameter adaptation algorithm) from observation data. AR(auto regressive) model was selected for system model and fifth order was decided according to parameter estimation. Uncorrelation test was also carried out to verify convergence of parameter. Through the proceedings, it was found that there was a system stability.