• The Journal of the Acoustical Society of Korea
• /
• v.42 no.6
• /
• pp.500-510
• /
• 2023

Passive sonar signals mainly contain both normal and abnormal signals. The abnormal signals mixed with normal signals are primarily detected using an AutoEncoder (AE) that learns only normal signals. However, existing AEs may perform inaccurate detection by reconstructing distorted normal signals from mixed signal. To address these limitations, we propose an abnormal signal detection model based on a Recurrent Neural Network (RNN) and vector quantization. The proposed model generates a codebook representing the learned latent vectors and detects abnormal signals more accurately through the proposed search process of code vectors. In experiments using publicly available underwater acoustic data, the AE and Variational AutoEncoder (VAE) using the proposed method showed at least a 2.4 % improvement in the detection performance and at least a 9.2 % improvement in the extraction performance for abnormal signals than the existing models.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.4
• /
• pp.337-346
• /
• 2021

Detection of abnormal signal generally can be done by using features of normal signals as main information because of data imbalance. This paper propose an efficient method for abnormal signal detection using parallel AutoEncoder (AE) which can use features of abnormal signals as well. The proposed Parallel AE (PAE) is composed of a normal and an abnormal reconstructors having identical AE structure and train features of normal and abnormal signals, respectively. The PAE can effectively solve the imbalanced data problem by sequentially training normal and abnormal data. For further detection performance improvement, additional binary classifier can be added to the PAE. Through experiments using public acoustic data, we obtain that the proposed PAE shows Area Under Curve (AUC) improvement of minimum 22 % at the expenses of training time increased by 1.31 ~ 1.61 times to the single AE. Furthermore, the PAE shows 93 % AUC improvement in detecting abnormal underwater acoustic signal when pre-trained PAE is transferred to train open underwater acoustic data.

• Journal of the Institute of Convergence Signal Processing
• /
• v.6 no.1
• /
• pp.23-26
• /
• 2005

This paper describes the algorithm for deciding the status of the operating machines in the power plants. It is very important to decide whether the status of the operating machines is good or not in the industry to protect the accidents of machines and improve the operation efficiency of the plants. There are two steps to analyze the status of the running machines. First, we extract the features from the input original data. Second, we classify those features into normal/abnormal condition of the machines using the wavelet transform and the input RMS vector through the K-means algorithm. In this paper we developed the algorithm to detect the fault operation using the K-means method from the sound of the operating machines.

• Journal of the Korean Data and Information Science Society
• /
• v.22 no.2
• /
• pp.197-206
• /
• 2011

The ability to detect online abnormal events in signals is essential in many real-world signal processing applications. In order to detect abnormal events, previously known algorithms require an explicit signal statistical model, and interpret abnormal events as statistical model abrupt changes. In general, maximum likelihood and Bayesian estimation theory to estimate well as detection methods have been used. However, the above-mentioned methods for robust and tractable model, it is not easy to estimate. More freedom to estimate how the model is needed. In this paper, we investigate a machine learning, descriptor-based approach that does not require a explicit descriptors statistical model, based on support vector machines are known to be robust statistical models and a sequential optimal algorithm online support vector machine is introduced.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.5
• /
• pp.7-13
• /
• 2020

This paper focuses on detecting abnormal patterns of respiration of humans. In this study, a contact-based device was used to acquire both normal and abnormal respiration signals. To this end, this paper reports the development of a monitoring system to investigate the respiratory status of humans in a normal environment. This work aims to classify the respiratory status, i.e., normal and abnormal status, quantitatively. The respiration signal is acquired using a contact-based medical device (BIOBPAC), and noise reduction is carried out before classifying the respiratory status. To reduce noise, a mixed filter that combines the Savitzky-Golay filter and Median filter is applied to the acquired respiration signals. The inter-class distance is maximized, and the intra-class distance is minimized. The proposed algorithm is straightforward and can be applied to a practical environment. In addition, the experimental results are provided to substantiate the proposed approach.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.06e
• /
• pp.399-402
• /
• 1998

본 논문에서는 환자의 음성을 정상, 양성종양, 악성종양으로 분류하는 실험을 켑스트럼 파라미터를 통한 음원분리와 신경회로망을 이용하여 수행하고 그 결과를 보고한다. 기존의 장애음성 데이터베이스에는 정상음성과 양성종양의 경우만 수록되어 있었고 외국의 환자들을 대상으로 한 경우만 있었기 때문에 국내의 환자들에게 직접 적용할 경우 어떠한 결과가 나올지 예측하기가 어려웠다. 최근 부산대학교 이비인후과팀에서 수집한 국내의 정상, 양성, 악성종양의 경우에 대한 데이터베이스를 분석하고 신경회로망에 의해 분류함으로써 사람의 음성신호만에 의한 후두질환이 식별이 가능하였다. 본 실험에서는 식별 파라미터로 음성신호의 선형예측오차신호에 관한 켑스트럼으로부터 음원비인 HNRR을 구하여 Jitter, Shimmer와 함께 사용하였다. 신경회로망은 입, 출력 층과 한 개의 은닉층을 갖는 다층신경망을 이용하였으며, 식별은 두단계로 나누어 정상과 비정상을 분류한 후 다시 비정상을 양성과 악성으로 분류하였다[1].

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.1
• /
• pp.8-15
• /
• 2005

The analysis of Rader signal that have non-linearity variable phase is signal that contact easily in several fields such as radar, telecommunication, seismic, sonar and biomedical applications. In generally, Non-stationary signal means that spectral characteristics are varying with time and instantaneous frequency is only one frequency or narrow range of frequencies varying as a function of time. Therefore, Instantaneous frequency is vary important variable that understanding physical characteristic of signal. This paper was describes continuous wavelet transform to determine instantaneous frequency at non-staionary signal and compare to existing method. When white noise or various frequency is overlapped each other in sign, existing method was can not decide corrected instantaneous frequency, but when used continuous wavelet transform, very well decide correctly frequency regardless of component of signal.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.2 no.2
• /
• pp.29-36
• /
• 2009

The analysis of Radar signal, telecommunication, bioengineering, seismic, and acoustic signal is consist of the Non-stationary signal which has non-linear phase variation. Non-stationary signal means that the physical properties of signal depend on time variation and the instantaneous frequency represents physical property of these type of signal. Thus estimation of the instantaneous frequency of non-stationary signal is important subject in signal processing. In this work, the instantaneous frequency analysis method utilizing continuous wavelets transform is represented and compared with Hilbert Transform method.

• KEPCO Journal on Electric Power and Energy
• /
• v.4 no.2
• /
• pp.101-105
• /
• 2018

In this paper, the kernel regression model is applied for the case study of gas turbine abnormal state analysis. In addition to vibration analysis at the remote site, the kernel regression model technique can is useful for analyzing abnormal state of rotor vibration signals of gas turbine in power plant. In monitoring based on data-driven techniques correlated measurements, the fault free training data of shaft vibration obtained during normal operations of gas turbine are used to develop a empirical model based on auto-associative kernel regression. This data-driven model can be used to predict virtual measurements, which are compared with real-time data, generating residuals. Any faults in the system may cause statistically abnormal changes in these residuals and could be detected. As the result, the kernel regression model provides information that can distinguish anomalies such as sensor failure in a shaft vibration signal.

• Journal of Biomedical Engineering Research
• /
• v.16 no.1
• /
• pp.95-100
• /
• 1995

In this study, we have evaluated the effect of amplitude and frequency perturbation of EGG signal for single vowels associated with laryngeal pathology. The normal EGG signal was properly characterized by an autoregressive model which has an optimal order of ninth using the parametric method. This can be analyzed by determining the transfer function. Perturbations in the fundamental pitch and in the peak amplitude of EGG signal measured with a four-electrode system using the modulation/demodulation techniques were investigated for the purpose of developing a decision criteria for the laryngeal function analysis. The abnormal EGG signal has nonperiodic and unstable characteristics. It can be discriminated by the calculation of opening and closing time of glottis using the EGG signal. In case of normal and abnormal subjects, m$\pm$0.5*sd was discriminating line for frequency perturbation and m$\pm$2*sd for normal amplitude perturbations, respectively. Also, The normal and abnormal cases of the subjects can be discriminated effectively using the pattern of attractor derived with Hilbert transform of EGG signal.