• The Journal of the Acoustical Society of Korea
• /
• v.21 no.4
• /
• pp.380-386
• /
• 2002

Conventional post-processing as like confidence measure (CM) proposed by Rahim calculates phones' CM using the likelihood between phoneme model and anti-model, and then word's CM is obtained by averaging phone-level CMs[1]. In conventional method, CMs of some specific keywords are tory low and they are usually rejected. The reason is that statistics of phone-level CMs are not consistent. In other words, phone-level CMs have different probability density functions (pdf) for each phone, especially sri-phone. To overcome this problem, in this paper, we propose normalized confidence measure. Our approach is to transform CM pdf of each tri-phone to the same pdf under the assumption that CM pdfs are Gaussian. For evaluating our method we use common keyword spotting system. In that system context-dependent HMM models are used for modeling keyword utterance and contort-independent HMM models are applied to non-keyword utterance. The experiment results show that the proposed NCM reduced FAR (false alarm rate) from 0.44 to 0.33 FA/KW/HR (false alarm/keyword/hour) when MDR is about 8%. It achieves 25% improvement of FAR.

• The Journal of the Acoustical Society of Korea
• /
• v.37 no.2
• /
• pp.99-109
• /
• 2018

The precision of the vibration-sensors, contact or non-contact types, is usually satisfactory for the practical measurement applications, but a sensor is confined to the measurement of a point or a direction. Although the precision and frequency span of the low-cost camera are inferior to these sensors, it has the merits in the cost and in the capability of simultaneous measurement of a large vibrating area. Furthermore, a camera can measure multi-degrees-of-freedom of a vibrating object simultaneously. In this study, the calibration method and the dynamic characteristics of the low-cost machine vision camera as a sensor are studied with a demonstrating example of the two-dimensional vibration of a cantilever beam. The planar image of the camera shot reveals two rectilinear and one rotational motion. The rectilinear vibration motion of a single point is first measured using a camera and the camera is experimentally calibrated by calculating error referencing the LDV (Laser Doppler Vibrometer) measurement. Then, by measuring the motion of multiple points at once, the rotational vibration motion and the whole vibration motion of the cantilever beam are measured. The whole vibration motion of the cantilever beam is analyzed both in time and frequency domain.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.4C
• /
• pp.413-423
• /
• 2003

The CMA algorithmis most widely investigated blind algorithm and the most widely used one in practice. But, since nonlinear CM cost function have not closed form solution about the optimum weight. There have been difficultiesto analyze the CMA equalizer's theoretical performance. Recently, Zeng presents the notable theoretical resultabout the MSE of CM-minimizing estimators for the FIR linear channel in the presence of AWGN. Through this method, It wouldbe possible to campare the theoretical performance between CMA and Wiener equalizer in terms of MSE. In this paper, based on Zeng's method, we first calculate the theoretical MSE bound of CMA equalizer in partial response channel which is widely used in HDD, digital VCR such as high-density digital recording.playback systems. We confirmedthis result withthe computer simulation. Except this, we also performedthe theoretical and simulation analysis about the modified CMA equalizer, which was proposed to improve the performance of CMA equalizer in partial response channel. Finally, we compare and evaluate the performance analysis results between CMA and Modified CMA equalizer.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.26 no.11B
• /
• pp.1501-1509
• /
• 2001

Recently, the use of wireless communication systems has been rapidly increasing, which results in a difficult problem in efficient control of limited frequency resources. As a way of solving this problem, the ultra wideband time hopping impulse radio system attracts much attention. The impulse radio system communicates pulse position modulated data using Gaussian monocycle pulses of very short duration less than 1 nsec. Thus the transmitted signal has very low power spectral density and ultra wide bandwidth from near D.C. to a few GHz. It is blown that it hardly interferes with the existing communication systems because of its very low power spectral density. The purpose of this paper is to characterize multipath propagation of the impulse radio signal and to evaluate the performance of the correlator-based receiver for the multipath environments. In this paper, we consider the deterministic two-path model and the statistical indoor multipath model of Saleh and Valenzuela. For the two-path model the output of the correlator with the ideal reference waveform varies according to the relative difference between the indirect path delay and the time interval of PPM, and to the indirect path gains. In addition, the characteristics of bit error rates is measured for the two models through computer simulation. The simulation results indicate that the performance of the impulse radio system depends both on the relative difference between the indirect path delay and the time interval of PPM, and on the indirect path gains. Furthermore, it is observed that the reference signal designed for the AWGN channel can not be applied to the multipath channels.

• The KIPS Transactions:PartB
• /
• v.18B no.3
• /
• pp.147-156
• /
• 2011

This paper proposes a 3-stage (preprocessing, feature extraction, and classification) fault detection and classification algorithm for induction motors. In the first stage, a low-pass filter is used to remove noise components in the fault signal. In the second stage, a discrete cosine transform (DCT) and a statistical method are used to extract features of the fault signal. Finally, a back propagation neural network (BPNN) method is applied to classify the fault signal. To evaluate the performance of the proposed algorithm, we used one second long normal/abnormal vibration signals of an induction motor sampled at 8kHz. Experimental results showed that the proposed algorithm achieves about 100% accuracy in fault classification, and it provides 50% improved accuracy when compared to the existing fault detection algorithm using a cross-covariance method. In a real-world data acquisition environment, unnecessary noise components are usually included to the real signal. Thus, we conducted an additional simulation to evaluate how well the proposed algorithm classifies the fault signals in a circumstance where a white Gaussian noise is inserted into the fault signals. The simulation results showed that the proposed algorithm achieves over 98% accuracy in fault classification. Moreover, we developed a testbed system including a TI's DSP (digital signal processor) to implement and verify the functionality of the proposed algorithm.

• Journal of the Institute of Convergence Signal Processing
• /
• v.5 no.2
• /
• pp.111-118
• /
• 2004

Techniques based on thresholding of wavelet coefficients are gaining popularity for denoising data because of the reasonable performance at the low complexity. The VisuShrink which removes the noise with the universal threshold is one of the techniques. The universal threshold is proportional to the noise deviation and the number of data samples. In general, because the noise deviation is not known, one needs to estimate the deviation for determining the value of the universal threshold. But, only for the finest scale wavelet coefficients, it has been known the way of estimating the noise deviation, so the noise in coarse scales cannot be removed with the VisuShrink. We propose here a new denoising method which removes the noise in each scale except the coarsest scale by Visushrink method. The noise deviation at each band is estimated by the monotonic transform and weighted deviation, the product of estimated noise deviation by the weight, is applied to the universal threshold. By making use of the universal threshold and the Soft-Threshold technique, the noise in each band is removed. The denoising characteristics of the proposed method is compared with that of the traditional VisuShrink and SureShrink method. The result showed that the proposed method is effective in denoising on Gaussian noise and quantization noise.

• Journal of Broadcast Engineering
• /
• v.24 no.6
• /
• pp.919-927
• /
• 2019

In this paper, we propose an accurate camera calibration method for acquiring multiview stereoscopic images. Generally, camera calibration is performed by using checkerboard structured patterns. The checkerboard pattern simplifies feature point extraction process and utilizes previously recognized lattice structure, which results in the accurate estimation of relations between the point on 2-dimensional image and the point on 3-dimensional space. Since estimation accuracy of camera parameters is dependent on feature matching, accurate detection of checkerboard corner is crucial. Therefore, in this paper, we propose the method that performs accurate camera calibration method through accurate detection of checkerboard corners. Proposed method detects checkerboard corner candidates by utilizing 1-dimensional gaussian filters with succeeding corner refinement process to remove outliers from corner candidates and accurately detect checkerboard corners in sub-pixel unit. In order to verify the proposed method, we check reprojection errors and camera location estimation results to confirm camera intrinsic parameters and extrinsic parameters estimation accuracy.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.5 no.4
• /
• pp.777-790
• /
• 2001

Theoretical analyses have been tried to design high power and stable operating SLD at 1.55${\mu}{\textrm}{m}$ wavelength range which is the lowest absorption wavelength in optical fiber. The materials of active layer and SCH layer were chosen as conventional In1-xGaxAsyPl-y quaternary composition systems. From the transverse mode and the lateral mode analyses of waveguide, the optical power distributions and the optical confinement factor have been studied for single-mode high power operation. According to these analyses, it was calculated the composition and the thickness of SCH layer to obtain the maximum optical confinement factor. In order to obtain low values of the reflectivity, we used the window region and the lateral tilted angle between tile active region and window region. And the reflectivity of SLD was calculated with the gaussian beam approximation and mode analysis. From these researches, it was confirmed for several results to fabricate the efficient and stable SLD. In case of using $1.3\mum$, InGaAsP SCH layer, the layer thickness was obtained $0.08\mum$, to get the maximum optical confinement factor. Using $0.2\mum$, active layer thickness and $0.08\mum$, SCH layer thickness, the window region length is about $100\mum$ without An coating, $10\mum$ in 1% AR coating to obtain about 10-4 reflectivity. When the tilted angle is about $10~15^{\circ}$, the reflectivity is about 10-3. From these results, if the window region length and tilted angle were controlled appropriately in given device structure, it was confirmed that it is possible to fabricate the stable SLD without AR coating analytically.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.3
• /
• pp.471-479
• /
• 2018

Recently, the spread of smart TV based Android iOS Set Top box has become common. This paper propose a new approach to control the TV using gestures away from the era of controlling the TV using remote control. In this paper, the AdaBoost algorithm is applied to gesture recognition by using a mono camera. First, we use Camshift-based Body tracking and estimation algorithm based on Gaussian background removal for body coordinate extraction. Using global and local feature vectors, we recognized gestures with speed change. By tracking the time interval trajectories of hand and wrist, the AdaBoost algorithm with CART algorithm is used to train and classify gestures. The principal component feature vector with high classification success rate is searched using CART algorithm. As a result, 24 optimal feature vectors were found, which showed lower error rate (3.73%) and higher accuracy rate (95.17%) than the existing algorithm.

• Journal of Korean Society of Transportation
• /
• v.27 no.5
• /
• pp.97-111
• /
• 2009

Image-based traffic information collection systems have entered widespread adoption and use in many countries since these systems are not only capable of replacing existing loop-based detectors which have limitations in management and administration, but are also capable of providing and managing a wide variety of traffic related information. In addition, these systems are expanding rapidly in terms of purpose and scope of use. Currently, the utilization of image processing technology in the field of traffic accident management is limited to installing surveillance cameras on locations where traffic accidents are expected to occur and digitalizing of recorded data. Accurately recording the sequence of situations around a traffic accident in a signal intersection and then objectively and clearly analyzing how such accident occurred is more urgent and important than anything else in resolving a traffic accident. Therefore, in this research, we intend to present a technology capable of overcoming problems in which advanced existing technologies exhibited limitations in handling real-time due to large data capacity such as object separation of vehicles and tracking, which pose difficulties due to environmental diversities and changes at a signal intersection with complex traffic situations, as pointed out by many past researches while presenting and implementing an active and environmentally adaptive methodology capable of effectively reducing false detection situations which frequently occur even with the Gaussian complex model analytical method which has been considered the best among well-known environmental obstacle reduction methods. To prove that the technology developed by this research has performance advantage over existing automatic traffic accident recording systems, a test was performed by entering image data from an actually operating crossroad online in real-time. The test results were compared with the performance of other existing technologies.