• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.8
• /
• pp.1665-1674
• /
• 2011

In this paper, we proposed an algorithm for speech enhancement of speeches corrupted by colored noise. When there is no correlation between colored noise and speech signal, the colored noise turns into white noise through whitening transformation. This transformed signal has been applied to the generalized subspace approach for speech enhancement. The speech spectral distortion, produced by the whitening transformation as pre-processing, has been restored by using the inverse whitening transformation as post-processing of the proposed algorithm. The performance of the proposed algorithm for speech enhancement has been confirmed by computer simulation. The colored noises used in this experiment were car noise and multi-talker babble. It is confirmed that the proposed algorithm shows better performance from SNR and SSD viewpoint over the previous approach with the data from the AURORA and TIMIT data base.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.1
• /
• pp.225-232
• /
• 2010

In this study, an automated ultrasonic testing system and post signal and image processing techniques are developed in order to construct ultrasonic flaw images in weldments. Image processing algorithms are built into the flaw image processing system for the automated ultrasonic testing system. The developed signal and image analysis algorithms addressed in this study include an A-Scan data compression algorithm, ultrasonic image amplification algorithm and B-scan flaw image correction algorithm(SAFT). This flaw image processing system for the automated ultrasonic testing system can be applied to various inspection fields.

• The Korean Journal of Physiology and Pharmacology
• /
• v.23 no.2
• /
• pp.131-139
• /
• 2019

Manually reviewing electroencephalograms (EEGs) is labor-intensive and demands automated seizure detection systems. To construct an efficient and robust event detector for experimental seizures from continuous EEG monitoring, we combined spectral analysis and deep neural networks. A deep neural network was trained to discriminate periodograms of 5-sec EEG segments from annotated convulsive seizures and the pre- and post-EEG segments. To use the entire EEG for training, a second network was trained with non-seizure EEGs that were misclassified as seizures by the first network. By sequentially applying the dual deep neural networks and simple pre- and post-processing, our autodetector identified all seizure events in 4,272 h of test EEG traces, with only 6 false positive events, corresponding to 100% sensitivity and 98% positive predictive value. Moreover, with pre-processing to reduce the computational burden, scanning and classifying 8,977 h of training and test EEG datasets took only 2.28 h with a personal computer. These results demonstrate that combining a basic feature extractor with dual deep neural networks and rule-based pre- and post-processing can detect convulsive seizures with great accuracy and low computational burden, highlighting the feasibility of our automated seizure detection algorithm.

• Transactions of Materials Processing
• /
• v.11 no.8
• /
• pp.724-730
• /
• 2002

Due to extremely large reduction of area or extrusion ratio in ordinary production of extruded profiles, anisotropy is naturally induced by large severe deformation during the extrusion process. Therefore, the anisotropic properties play a great role in the post processing of extruded profiles, such as in bending. Moreover, undesirable deformation will be involved when the deformation-induced anisotropy is ignored. In order to observe the deformation-induced anisotropy of the thin-walled product, the proposed algorithm is applied to some chosen industrial extrusion processes. In the present work, the method for prediction of deformation-induced anisotropy employing the Barlats six-component yield potential to the rigid-plastic finite element method is proposed. The proposed algorithm is verified with the comparison to the crystallographic texture analysis, and then applied to the C-section extrusion process using a square die. The predicted anisotropy is then compared with the experimental and computational observations for validating the proposed algorithm.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.15 no.12
• /
• pp.1031-1043
• /
• 1990

A sequential recursive Kalman filtering algorithm, using causal image model, which is designed to operate in real time in the scanning mode is developed to enhance quality of 64Kbps videocodec images via function of suppression of various noises and optimum restoration. In order to improve its performance, adapted an averaging of pixel values between processing lines and adaptive filtering strategy based on the local spatial variance. Effecttiveness of the Kalman filtering algorithm proposed has been proved in the processed test kalman filtering algorithm proposed has been proved in the processed test images and the NMSE, LOGMSE measured, therefore, it may proposes possibility of the usage in videocodec for pre- and post- processing.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.5
• /
• pp.74-82
• /
• 1995

This paper is study on the voice dialing using HMM and post processing of the connected digits. HMM algorithm is widely used in the speech recognition with a good result. But, the maximum likelihood estimation of HMM(Hidden Markov Model) training in the speech recognition does not lead to values which maximize recognition rate. To solve the problem, we applied the post processing to segmental K-means procedure are in the recognition experiment. Korea connected digits are influenced by the prolongation more than English connected digits. To decrease the segmentation error in the level building algorithm some word models which can be produced by the prolongation are added. Some rules for the added models are applied to the recognition result and it is updated. The recognition system was implemented with DSP board having a TMS320C30 processor and IBM PC. The reference patterns were made by 3 male speakers in the noisy laboratory. The recognition experiment was performed for 21 sort of telephone number, 252 data. The recognition rate was $6\%$ in the speaker dependent, and $80.5\%$ in the speaker independent recognition test.

• Proceedings of the Korean Institute of Communication Sciences Conference
• /
• 2004.07a
• /
• pp.217-217
• /
• 2004

• Journal of the Institute of Convergence Signal Processing
• /
• v.12 no.3
• /
• pp.176-180
• /
• 2011

Even though algorithms for watermark embedding and extraction step are important issue for digital watermarking, watermark selection and post-processing can give us an opportunity to improve our algorithms and achieve higher performance. For this reason, we summarized the possibilities of improvements for digital watermarking by referring to the watermark merging techniques rather than embedding and extraction algorithms in this paper. We chose Cox's function as main embedding and extraction algorithm, and multiple barcode watermarks as a watermark. Each bit of the multiple copies of barcode watermark was embedded into a gray-scale image with Cox's embedding function. After extracting the numbers of watermark, we applied the watermark merging techniques; including the simple merging, N-step iterated merging, recover merging and combination of iterated-recover merging. Main consequence of our paper was the fact of finding out how multiple barcode watermarks and merging techniques can give us opportunities to improve the performance of algorithm.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.8 no.4
• /
• pp.185-194
• /
• 2013

Abstract- In distant-talking environments, speech recognition performance degrades significantly due to noise and reverberation. Recent work of Michael L. Selzer shows that in microphone array speech recognition, the word error rate can be significantly reduced by adapting the beamformer weights to generate a sequence of features which maximizes the likelihood of the correct hypothesis. In this approach, called Likelihood Maximizing Beamforming algorithm (Limabeam), one of the method to implement this Limabeam is an UnSupervised Limabeam(USL) that can improve recognition performance in any situation of environment. From our investigation for this USL, we could see that because the performance of optimization depends strongly on the transcription output of the first recognition step, the output become unstable and this may lead lower performance. In order to improve recognition performance of USL, some post-filter techniques can be employed to obtain more correct transcription output of the first step. In this work, as a post-filtering technique for first recognition step of USL, we propose to add a Wiener-Filter combined with Feature Weighted Malahanobis Distance to improve recognition performance. We also suggest an alternative way to implement Limabeam algorithm for Hidden Markov Network (HM-Net) speech recognizer for efficient implementation. Speech recognition experiments performed in real distant-talking environment confirm the efficacy of Limabeam algorithm in HM-Net speech recognition system and also confirm the improved performance by the proposed method.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.15 no.2
• /
• pp.83-96
• /
• 2011

This work proposes a binomial method for pricing the cliquet options, which provide a guaranteed minimum annual return. The proposed binomial tree algorithm simplifies the standard binomial approach, which is problematic for cliquet options in the computational point of view, or other recent methods, which may be of intricate algorithm or require pre- or post-processing computations. Our method is simple, efficient and reliable in a Black-Scholes framework with constant interest rates and volatilities.