• The Journal of the Korea institute of electronic communication sciences
• /
• v.9 no.5
• /
• pp.543-548
• /
• 2014

Multiple-model based speech recognition framework (MMSR) has been known to be very successful in speech recognition. Since it uses multiple hidden Markov modes (HMMs) that corresponds to various noise types and signal-to-noise ratio (SNR) values, the selected acoustic model can have a close match with the test noisy speech. However, since the number of HMM sets is limited in practical use, the acoustic mismatch still remains as a problem. In this study, we experimentally determined the optimal SNR mapping between the test noisy speech and the HMM set to mitigate the mismatch between them. Improved performance was obtained by employing the SNR mapping instead of using the estimated SNR from the test noisy speech. When we applied the proposed method to the MMSR, the experimental results on the Aurora 2 database show that the relative word error rate reduction of 6.3% and 9.4% was achieved compared to a conventional MMSR and multi-condition training (MTR), respectively.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.8 no.9
• /
• pp.1343-1349
• /
• 2013

In optical fiber communications, several newly-developed signal formats are used to obtain the best performance within limited spectral bandwidth. CSRZ (carrier-suppressed return-to-zero) format is one of the new signal formats, which has better spectral efficiency and better robustness to dispersion than RZ (return-to-zero) format. Thus it is widely used for demonstrating high-speed optical communication systems. In an earlier research, we proposed a clock-extraction method of CSRZ signal to monitor chromatic dispersion. However, the clock-frequency component extracted by the clock-extraction method can be affected by the bandwidth of a transmitter or a receiver. Therefore, in this paper, we investigate the effect of bandwidth on the chromatic dispersion monitoring of CSRZ signal based on clock-frequency component. As a result, we propose a couple of robust clock-extraction methods to monitor chromatic dispersion in CSRZ signal.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.12 no.1
• /
• pp.78-84
• /
• 1998

The fluid system such as, the quantity control of raw water, chemicals control in the purification, the waste water system as well as in the feed water or circulation system of the power plant and the ventilation system is controlled with the valve and moter pump. The system's performance and the energy saving of the fluid systems depend on control of method and delicacy. Until, PI controller use in these system but it cannot control delicately because of the coupling in the system loop. In this paper we configure a single flow system to the multi variable system and suggest the application of 2-DOF PID controller and the tuning methods by the neural network to the electrical power of the flow control system. the 2-DOF controller follows to a setpoint has a robustness against the disturbance in the results of simulation. Keywords Title, Intelligent control, Neuro control, Flow control, 2 - DOF control., 2 - DOF control.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.22 no.10
• /
• pp.69-75
• /
• 2008

This paper presents an algorithm robust to error for estimating partial discharge (PD) location using acoustic emission sensors. In operating transformers, the velocity computing of the acoustic signal is difficult because the temperature of the Insulation oil is not homogeneous. So, some error occurs in the process. Therefore, the algorithm estimating PD location must consider this error to provide maintenance person with useful information. The conventional algorithm shows the PD position as a point, while the new algorithm using LookUp-Table(LUT) shows PD position as error-map visually. The error-map is more useful than the conventional result because of robustness to error. Also, we compared performance of them, by adding error to data on purpose.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.5
• /
• pp.1073-1080
• /
• 2011

In this paper, we propose a novel digital watermarking method by virtual optics which secures multimedia information such as images, videos and sounds. To secure the multimedia data, we use Fresnel transform which describes the diffraction phenomena of the waves. Also, this method attaches the random phase function to Fresnel transform so that original image and watermark image would be gaussian random vectors. The complex numbers of watermark by Fresnel transform are separated the real part and the imaginary part. The former is embedded in original image as a encoding key imperceptibly and the latter is used for detecting the watermark as a decoding key. This method for digital watermarking ensures that watermark can be successfully registered and extracted from the watermarked image. Further, it provides the robustness to signal processing operation and geometric distortion and proves the strong resilience against cropping attack. The performance evaluation of the experiment is carried out with PSNR, and the numerical simulation results show the efficiency of the proposed method.

• Journal of KIISE:Software and Applications
• /
• v.31 no.12
• /
• pp.1569-1580
• /
• 2004

One commonly used approach to deal with uncertainty is Bayesian network which represents joint probability distributions of domain. There are some attempts to team the structure of Bayesian networks automatically and recently many researchers design structures of Bayesian network using evolutionary algorithm. However, most of them use the only one fittest solution in the last generation. Because it is difficult to combine all the important factors into a single evaluation function, the best solution is often biased and less adaptive. In this paper, we present a method of generating diverse Bayesian network structures through fitness sharing and combining them by Bayesian method for adaptive inference. In order to evaluate performance, we conduct experiments on learning Bayesian networks with artificially generated data from ASIA and ALARM networks. According to the experiments with diverse conditions, the proposed method provides with better robustness and adaptation for handling uncertainty.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38A no.9
• /
• pp.773-781
• /
• 2013

The Hough transform for line detection is widely used in many machine vision applications due to its robustness against data loss and distortion. However, it is not appropriate for real-time embedded vision systems, because it has inefficient computation structure and demands a large number of memory accesses. Thus, this paper proposes an improved voting scheme of the Hough transform, and then applies this scheme to a Hough transform hardware architecture so that it can provide real-time performance with less hardware resource. The proposed voting scheme reduces computation overhead of the voting procedure using correlation between adjacent pixels, and improves computational efficiency by increasing reusability of vote values. The proposed hardware architecture, which adopts this improved scheme, maximizes its throughput by computing and storing vote values for many adjacent pixels in parallel. This parallelization for throughput improvement is accomplished with little hardware overhead compared with sequential computation.

• Journal of Power Electronics
• /
• v.15 no.1
• /
• pp.190-201
• /
• 2015

This paper uses the switching function approach to present a simple state model of the Vienna-type rectifier. The approach introduces the relationship between the DC-link neutral point voltage and the AC side phase currents. A novel direct power control (DPC) strategy, which is based on the sliding mode control (SMC) for Vienna I rectifiers, is developed using the proposed power model in the stationary ${\alpha}-{\beta}$ reference frames. The SMC-based DPC methodology directly regulates instantaneous active and reactive powers without transforming to a synchronous rotating coordinate reference frame or a tracking phase angle of grid voltage. Moreover, the required rectifier control voltages are directly calculated by utilizing the non-linear SMC scheme. Theoretically, active and reactive power flows are controlled without ripple or cross coupling. Furthermore, the fixed-switching frequency is obtained by employing the simplified space vector modulation (SVM). SVM solves the complicated designing problem of the AC harmonic filter. The simplified SVM is based on the simplification of the space vector diagram of a three-level converter into that of a two-level converter. The dwelling time calculation and switching sequence selection are easily implemented like those in the conventional two-level rectifier. Replacing the current control loops with power control loops simplifies the system design and enhances the transient performance. The simulation models in MATLAB/Simulink and the digital signal processor-controlled 1.5 kW Vienna-type rectifier are used to verify the fast responses and robustness of the proposed control scheme.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.2
• /
• pp.529-535
• /
• 2000

In this paper, we propose a new method of designing the vector quantizer which is robustness to coding results and independent of statistical characteristics of an input image in wavelet transformed image coding processes. The most critical drawback of a conventional vector quantizer is the degradation of coding capability resulted from the discordance between quantizer objective image and statistical characteristics of training sequence which is for generating representing vector. In order to resolve the problem of conventional methods, we use independent random-variables and pseudo image to which image correlation and edge component were added, as a training sequence for generating representing vector. We have done a computer simulation in order to compare coding capability between a vector quantizer designed by the proposed method and one with the conventional method using real image as same as that is objective to coding of training sequence used in codebook generation. The results show the superiority of the proposed vector quantizer method at the aspect of coding capability compared to conventional one. They also clarify the problems of conventional methods.

• Archives of design research
• /
• v.18 no.3 s.61
• /
• pp.191-198
• /
• 2005

Menu is the most common interaction tool to select and execute a specific menu item from multiple menu options. With the very rapid increasing amount of information, various new menu designs have been developed. In this research, the pull-down menu, fisheye menu and grid menu were tested to compare the performance time, error rate, simplicity, usefulness, user friendliness, and overall user preference of each menu type. The grid menu was more efficient in selection speed than the pull-down and fisheye menus when the number of menu-items was 50 and 100. The time needed to choose a menu-item with a grid menu was less affected by the size of menu. The pull-down and the grid menus were considered to be more satisfactory, simple, user friendly, and useful than the fisheye menu. 42.3 percent of subjects indicated that the grid menu was their preferred selection tool among the menus. The grid menu is an efficient and robust alternative menu choice for small and middle size menu list. Further study is required to examine the possibility of grid menu on mobile devices.