• Speech Sciences
• /
• v.10 no.2
• /
• pp.85-95
• /
• 2003

In speech signal processing, it is very important to detect the pitch exactly in speech recognition, synthesis and analysis. If we exactly pitch detect in speech signal, in the analysis, we can use the pitch to obtain properly the vocal tract parameter. It can be used to easily change or to maintain the naturalness and intelligibility of quality in speech synthesis and to eliminate the personality for speaker-independence in speech recognition. In this paper, we proposed a new pitch detection algorithm. First, positive center clipping is process by using the incline of speech in order to emphasize pitch period with a glottal component of removed vocal tract characteristic in time domain. And rough formant envelope is computed through peak-fitting spectrum of original speech signal infrequence domain. Using the roughed formant envelope, obtain the smoothed formant envelope through calculate the linear interpolation. As well get the flattened harmonics waveform with the algebra difference between spectrum of original speech signal and smoothed formant envelope. Inverse fast fourier transform (IFFT) compute this flattened harmonics. After all, we obtain Residual signal which is removed vocal tract element. The performance was compared with LPC and Cepstrum, ACF. Owing to this algorithm, we have obtained the pitch information improved the accuracy of pitch detection and gross error rate is reduced in voice speech region and in transition region of changing the phoneme.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.28 no.5
• /
• pp.1141-1151
• /
• 2018

In an APT attack, the communication stage between infected hosts and C&C(Command and Control) server is the key stage for intrusion into the attack target. Attackers can control multiple infected hosts by the C&C Server and direct intrusion and exploitation. If the C&C Server is exposed at this stage, the attack will fail. Therefore, in recent years, the Domain Generation Algorithm (DGA) has replaced DNS in C&C Server with a short time interval for making detection difficult. In particular, it is very difficult to verify and detect all the newly registered DNS more than 5 million times a day. To solve these problems, this paper proposes a model to judge DGA-DNS detection by the morphological similarity analysis of normal DNS and DGA-DNS, and to determine the sign of APT attack through it, then we verify its validity.

• Journal of Biomedical Engineering Research
• /
• v.29 no.6
• /
• pp.466-476
• /
• 2008

The more people use ambulatory electrocardiogram(ECG) for arrhythmia detection, the more researchers report the automatic classification algorithms. Most of the previous studies don't consider the un-balanced data distribution. Even in patients, there are much more normal beats than abnormal beats among the data from 24 hours. To solve this problem, the hierarchical classification using 21 features was adopted for arrhythmia abnormal beat detection. The features include R-R intervals and data to describe the morphology of the wave. To validate the algorithm, 44 non-pacemaker recordings from physionet were used. The hierarchical classification model with 2 stages on domain knowledge was constructed. Using our suggested method, we could improve the performance in abnormal beat classification from the conventional multi-class classification method. In conclusion, the domain knowledge based hierarchical classification is useful to the ECG beat classification with unbalanced data distribution.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.2
• /
• pp.1019-1022
• /
• 2005

As recent information communication technology is rapidly developed, a lot of researches related to speech signal processing have been processed. So pitch period is applied as important factor to many application fields such as speech recognition, speaker identification, speech analysis and synthesis. Therefore, many algorithms related to pitch detection have been proposed in time domain and frequency domain and AMDF(average magnitude difference function) which is one of pitch detection algorithms in time domain chooses time interval from valley to valley as pitch period. But, in selection of valley point to detect pitch period, complexity of the algorithm is increased. So in this paper we proposed pitch detection algorithm using rotation transform of AMDF, that taking the global minimum valley point as pitch period and established a threshold about the phoneme in beginning portion, to exclude pitch period selection. and compared existing methods with proposed method through simulation.

• Smart Structures and Systems
• /
• v.18 no.3
• /
• pp.501-523
• /
• 2016

Electromechanical impedance (EMI) based structural health monitoring is performed by measuring the variation in the impedance due to the structural local damage. The impedance signals are acquired from the piezoelectric patches that are bonded on the structural surface. The impedance variation, which is directly related to the mechanical properties of the structure, indicates the presence of local structural damage. Two traditional EMI-based damage detection methods are based on calculating the difference between the measured impedance signals in the frequency domain from the baseline and the current structures. In this paper, a new structural damage detection approach by analyzing the time domain impedance responses is proposed. The measured time domain responses from the piezoelectric transducers will be used for analysis. With the use of the Time Frequency Autoregressive Moving Average (TFARMA) model, a damage index based on Singular Value Decomposition (SVD) is defined to identify the existence of the structural local damage. Experimental studies on a space steel truss bridge model in the laboratory are conducted to verify the proposed approach. Four piezoelectric transducers are attached at different locations and excited by a sweep-frequency signal. The impedance responses at different locations are analyzed with TFARMA model to investigate the effectiveness and performance of the proposed approach. The results demonstrate that the proposed approach is very sensitive and robust in detecting the bolt damage in the gusset plates of steel truss bridges.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.57 no.7
• /
• pp.1295-1297
• /
• 2008

Large-sized flat-panel displays are widely used for PC monitors and TV displays. In this paper, frequency domain pre-filter algorithms are presented for detection of defects in large-sized Thin Film Transistor-Liquid Crystal Display(TFT-LCD) panel surfaces. Frequency analysis with 1-D, 2-D FFT methods for extract the periodic patterns of lattice structures in TFT-LCD is performed. To remove this patterns, frequency domain band-stop filters were used for eliminating specific frequency components. In order to acquire only defected images, 2-D inverse FFT methods to inverse transform of frequency domain images were used.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.4C
• /
• pp.458-471
• /
• 2006

Digital watermarking of multimedia data is a very active research area that has enjoyed a considerable amount of attention in recent years. In this paper, we propose an algorithm for embedding/detecting a fragile watermark in MPEG-4 compressed video domain (Simple and Advance Simple Profiles). The watermark bits are put directly into Huffman VLC-codespace of quantized DCT domain. The advantage of watermark embedding into the compressed domain is the significant savings for a real-time implementation as it does not require a full decoding operation. The watermark embedding does not change the video file size. The algorithm demonstrates high watermarking capacity, thereby providing reliable foolproof authentication. The results of experimental testing demonstrate that watermark embedding preserves the video quality. Watermark detection is performed without using the original video.

• Journal of Korea Multimedia Society
• /
• v.21 no.3
• /
• pp.342-347
• /
• 2018

We proposed a fast detection of copy-move image forgery using four step search algorithm in the spatial domain. In the four-step search algorithm, the search area is 21 (-10 ~ +10), and the number of pixels to be scanned is 33. Our algorithm reduced computational complexity more than conventional copy move image forgery methods. The proposed method reduced 92.34 % of computational complexity compare to exhaustive search algorithm.

• Journal of Digital Convergence
• /
• v.13 no.8
• /
• pp.253-260
• /
• 2015

Because mass of activity records of individuals and organizations are accumulated in the digital space and amount of information is also increasing exponentially, the most urgent requirements of users is the tool for 'efficient' acquisition of 'useful' information. This paper try digital convergence to combine a domain specific technology with real time issue detection and grouping based on Web media. To derive core functionalities, we collect and analyze user requirements of national defense issue detection services. By utilizing linguistic resources specialized on national defence area and discovering features for measuring issue importance, we try to seek differentiation domain specific issue detection method. Finally we compare our detection results based on the development outputs of prototype.

• Journal of Broadcast Engineering
• /
• v.24 no.3
• /
• pp.472-484
• /
• 2019

This paper proposes a time-domain sound event detection algorithm using DNN (Deep Neural Network). In this system, time domain sound waveform data which is not converted into the frequency domain is used as input to the DNN. The overall structure uses CRNN structure, and GLU, ResNet, and Squeeze-and-excitation blocks are applied. And proposed structure uses structure that considers features extracted from several layers together. In addition, under the assumption that it is practically difficult to obtain training data with strong labels, this study conducted training using a small number of weakly labeled training data and a large number of unlabeled training data. To efficiently use a small number of training data, the training data applied data augmentation methods such as time stretching, pitch change, DRC (dynamic range compression), and block mixing. Unlabeled data was supplemented with insufficient training data by attaching a pseudo-label. In the case of using the neural network and the data augmentation method proposed in this paper, the sound event detection performance is improved by about 6 %(based on the f-score), compared with the case where the neural network of the CRNN structure is used by training in the conventional method.