• Journal of Convergence for Information Technology
• /
• v.7 no.6
• /
• pp.159-166
• /
• 2017

In this paper, we have experimented to improve the verification performance of speaker change detection on broadcast news. It is to enhance the input noisy speech and to apply the KL distance $D_s$ using the SNR-based weighting function $w_m$. The basic experimental system is the verification system of speaker change using GMM-UBM based KL distance D(Experiment 0). Experiment 1 applies the input noisy speech enhancement using MMSE Log-STSA. Experiment 2 applies the new KL distance $D_s$ to the system of Experiment 1. Experiments were conducted under the condition of 0% MDR in order to prevent missing information of speaker change. The FAR of Experiment 0 was 71.5%. The FAR of Experiment 1 was 67.3%, which was 4.2% higher than that of Experiment 0. The FAR of experiment 2 was 60.7%, which was 10.8% higher than that of experiment 0.

• Journal of the Korean Society of Radiology
• /
• v.17 no.5
• /
• pp.663-670
• /
• 2023

In this study, we aimed to perform a comparative evaluation using quantitative factors between a region-growing based segmentation with noise reduction algorithms and a U-Net based segmentation. Initially, we applied median filter, median modified Wiener filter, and fast non-local means algorithm to computed tomography (CT) images, followed by region-growing based segmentation. Additionally, we trained a U-Net based segmentation model to perform segmentation. Subsequently, to compare and evaluate the segmentation performance of cases with noise reduction algorithms and cases with U-Net, we measured root mean square error (RMSE) and peak signal to noise ratio (PSNR), universal quality image index (UQI), and dice similarity coefficient (DSC). The results showed that using U-Net for segmentation yielded the most improved performance. The values of RMSE, PSNR, UQI, and DSC were measured as 0.063, 72.11, 0.841, and 0.982 respectively, which indicated improvements of 1.97, 1.09, 5.30, and 1.99 times compared to noisy images. In conclusion, U-Net proved to be effective in enhancing segmentation performance compared to noise reduction algorithms in CT images.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.38 no.6
• /
• pp.56-64
• /
• 2001

In this paper, we proposed the simple and selective method for the order of model that reflected the feature of the heart rate variability without the complicated calculation in the power spectral analysis of heart rate variability using autoregressive model. The power spectral analysis of short-term of heart rate variability using autoregressive have been problem to resolution of spectral estimates by the selective model order. As a result that the proposed method for the order comparative tested with the AIC and the fixed order method, the calculation process could become very simple and select the order which correspond with the feature of the time series. We verified it could removed the noisy power components by the fixed order.

• Structural Monitoring and Maintenance
• /
• v.6 no.4
• /
• pp.317-346
• /
• 2019

Performance assessment of pavements proves useful, in terms of handling the ride quality, controlling the travel time of vehicles and adequate maintenance of pavements. Roughness profiles provide a good measure of the deteriorating condition of the pavement. For the accurate estimates of pavement roughness from dynamic vehicle responses, vehicle parameters should be known accurately. Information on vehicle parameters is uncertain, due to the wear and tear over time. Hence, condition monitoring of pavement requires the identification of pavement roughness along with vehicle parameters. The present study proposes a scheme which estimates the roughness profile of the pavement with the use of accurate estimates of vehicle parameters computed in parallel. Pavement model used in this study is a two-layer Euler-Bernoulli beam resting on a nonlinear Pasternak foundation. The asphalt topping of the pavement in the top layer is modeled as viscoelastic, and the base course bottom layer is modeled as elastic. The viscoelastic response of the top layer is modeled with the help of the Burgers model. The vehicle model considered in this study is a half car model, fitted with accelerometers at specified points. The identification of the coupled system of vehicle-pavement interaction employs a coupled scheme of an unbiased minimum variance estimator and an optimization scheme. The partitioning of observed noisy quantities to be used in the two schemes is investigated in detail before the analysis. The unbiased minimum variance estimator (MVE) make use of a linear state-space formulation including roughness, to overcome the linearization difficulties as in conventional nonlinear filters. MVE gives estimates for the unknown input and fed into the optimization scheme to yield estimates of vehicle parameters. The issue of ill-posedness of the problem is dealt with by introducing a regularization equivalent term in the objective function, specifically where a large number of parameters are to be estimated. Effect of different objective functions is also studied. The outcome of this research is an overall measure of pavement condition.

• Smart Media Journal
• /
• v.7 no.4
• /
• pp.17-23
• /
• 2018

We proposed a LSTM-based RNN model that can effectively perform the automatic spacing characteristics. For those long or noisy sentences which are known to be difficult to handle within Neural Network Learning, we defined a proper input data format and decoding data format, and added dropout, bidirectional multi-layer LSTM, layer normalization, and attention mechanism to improve the performance. Despite of the fact that Sejong corpus contains some spacing errors, a noise-robust learning model developed in this study with no overfitting through a dropout method helped training and returned meaningful results of Korean word spacing and its patterns. The experimental results showed that the performance of LSTM sequence-to-sequence model is 0.94 in F1-measure, which is better than the rule-based deep-learning method of GRU-CRF.

• Journal of the Korean Geotechnical Society
• /
• v.22 no.12
• /
• pp.33-43
• /
• 2006

Driving tests using model plastic piles with different hammer cushion materials were performed in order to evaluate the efficiency of energy transfer ratio from the hammer, degree of vibration of the surrounding ground and noise due to impacting. A small pile driving analyzer (PDA) was composed using straingages and Hopkinson bar which is measuring force signal and pile-head velocity. The hammer cushion (cap block) materials used for the model driving tests were commercial Micarta, plywood, polyurethane, rubber (SBR) and silicone rubber. The highest energy transfer ratio was obtained from Micarta in the same soil and driving conditions. Micarta was followed by polyurethane, plywood, rubber and silicone in descending order. The more efficient energy transfdr ratio of the hammer cushion materials became, the bigger average noisy (sound) level was found. In addition, Micarta and polyurethane provided bigger bearing capacities than other materials compared in the same soil and driving conditions in which the static loading tests were performed at the end of driving.

• The Journal of the Acoustical Society of Korea
• /
• v.27 no.7
• /
• pp.372-378
• /
• 2008

Voice activity detectors (VAD) are important in wireless communication and speech signal processing, In the conventional VAD methods, an expression for the likelihood ratio test (LRT) based on statistical models is derived in discrete Fourier transform (DFT) domain, Then, speech or noise is decided by comparing the value of the expression with a threshold, This paper presents a new statistical VAD method based on a signal subspace approach, The probabilistic principal component analysis (PPCA) is employed to obtain a signal subspace model that incorporates probabilistic model of noisy signal to the signal subspace method, The proposed approach provides a novel decision rule based on LRT in the signal subspace domain, Experimental results show that the proposed signal subspace model based VAD method outperforms those based on the widely used Gaussian distribution in DFT domain.

• The Journal of Korea Robotics Society
• /
• v.15 no.1
• /
• pp.8-15
• /
• 2020

This research is a case study of underwater object tracking based on real-time recurrent regression networks (Re³). Re³ has the concept of generic object tracking. Because of these characteristics, it is very effective to apply this model to unclear underwater sonar images. The model also an pursues object tracking method, thus it solves the problem of calculating load that may be limited when object detection models are used, unlike the tracking models. The model is also highly intuitive, so it has excellent continuity of tracking even if the object being tracked temporarily becomes partially occluded or faded. There are 4 types of the dataset using multi-beam sonar images: including (a) dummy object floated at the testbed; (b) dummy object settled at the bottom of the sea; (c) tire object settled at the bottom of the testbed; (d) multi-objects settled at the bottom of the testbed. For this study, the experiments were conducted to obtain underwater sonar images from the sea and underwater testbed, and the validity of using noisy underwater sonar images was tested to be able to track objects robustly.

• Journal of KIISE:Software and Applications
• /
• v.36 no.12
• /
• pp.1016-1023
• /
• 2009

A license plate recognition system consists of image processing in which characters and features are extracted, and pattern recognition in which extracted characters are classified. Feature extraction plays an important role in not only the level of data reduction but also performance of recognition. Thus, in this paper, we focused on the recognition of numeral characters especially on the feature extraction of numeral characters which has much effect in the result of plate recognition. We suggest a hybrid statistical feature model which assures the best dispersion of input data by reassignment of clustering property of input data. And we verify the effectiveness of suggested model using multi-layer perceptron and learning vector quantization neural networks. The results show that the proposed feature extraction method preserves the information of a license plate well and also is robust and effective for even noisy and external environment.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.3
• /
• pp.323-329
• /
• 2002

This paper proposes a frame reliability weighting method to compensate for a time-selective noise that occurs at random positions of speech signal contaminating certain parts of the speech signal. Speech frames have different degrees of reliability and the reliability is proportional to SNR (signal-to noise ratio). While it is feasible to estimate frame Sl? by using the noise information from non-speech interval under a stationary noisy situation, it is difficult to obtain noise spectrum for a time-selective noise. Therefore, we used statistical models of clean speech for the estimation of the frame reliability. The proposed MFR (model-based frame reliability) approximates frame SNR values using filterbank energy vectors that are obtained by the inverse transformation of input MFCC (mal-frequency cepstral coefficient) vectors and mean vectors of a reference model. Experiments on various burnt noises revealed that the proposed method could represent the frame reliability effectively. We could improve the recognition performance by using MFR values as weighting factors at the likelihood calculation step.