A comparison of model and non-model based time-frequency transforms for sperm whale click classification

We tried to find discriminating features for sperm whale clicks in order to distinguish between clicks from different whales, or to enable unique identification. We examined two different methods to obtain suitable characteristics. First, a model based on the Gabor function was used to describe the dominant frequencies in a click, and then the model parameters were used as classification features. The Gabor function model was selected because it has been used to model dolphin sonar pulses with great precision. Additionally, it has the interesting property that it has an optimal time–frequency resolution. As such, it can indicate optimal usage of the sonar by sperm whales. Second, the clicks were expressed in a wavelet packet table, from which subsequently a local discriminant basis was created. A wavelet packet basis has the advantage that it offers a highly redundant number of coefficients, which allow signals to be represented in many different ways. From the redundant signal description a representation can be selected that emphasizes the differences between classes. This local discriminant basis is more flexible than the Gabor function, which can make it more suitable for classification, but it is also more complex. Class vectors were created with both models and classification was based on the distance of a click to these vectors. We show that the Gabor function could not model the sperm whale clicks very well, due to the variability of the changing click characteristics. Best performance was reached when three subsequent clicks were averaged to smoothen the variability. Around 70% of the clicks classified correctly in both the training and validation sets. The wavelet packet table adapted better to the changing characteristics, and gave better classification. Here, also using a 3-click moving average, around 95% of the training sets classified correctly and 78% of the validation sets. These numbers lowered by only a few per cent when single clicks, instead of a moving average, were classified. This indicates that, while the features may show too much variability to enable unique identification of individual whales on a click by click basis, the wavelet approach may be capable of distinguishing between a small group of whales.

Download Full-text

Vehicle speed measurement by on-board acoustic signal processing

Measurement and Control ◽

10.1177/0020294018773777 ◽

2018 ◽

Vol 51 (5-6) ◽

pp. 138-149 ◽

Cited By ~ 2

Author(s):

Hüseyin Göksu

Keyword(s):

Relative Motion ◽

Wavelet Packet ◽

Absolute Error ◽

Frequency Resolution ◽

Vehicle Speed ◽

Air Conditioner ◽

Wavelet Packet Analysis ◽

Time Frequency ◽

Speed Sensor ◽

Frequency Domain Methods

Estimation of vehicle speed by analysis of drive-by noise is a known technique. The methods used in this kind of practice generally estimate the velocity of the vehicle with respect to the microphone(s), so they rely on the relative motion of the vehicle to the microphone(s). There are also other methods that do not rely on this technique. For example, recent research has shown that there is a statistical correlation between vehicle speed and drive-by noise emissions spectra. This does not rely on the relative motion of the vehicle with respect to the microphone(s) so it inspires us to consider the possibility of predicting velocity of the vehicle using an on-board microphone. This has the potential for the development of a new kind of speed sensor. For this purpose we record sound signal from a vehicle under speed variation using an on-board microphone. Sound emissions from a vehicle are very complex, which is from the engine, the exhaust, the air conditioner, other mechanical parts, tires, and air resistance. These emissions carry both stationary and non-stationary information. We propose to make the analysis by wavelet packet analysis, rather than traditional time or frequency domain methods. Wavelet packet analysis, by providing arbitrary time-frequency resolution, enables analyzing signals of stationary and non-stationary nature. It has better time representation than Fourier analysis and better high-frequency resolution than Wavelet analysis. Subsignals from the wavelet packet analysis are analyzed further by Norm Entropy, Log Energy Entropy, and Energy. These features are evaluated by feeding them into a multilayer perceptron. Norm entropy achieves the best prediction with 97.89% average accuracy with 1.11 km/h mean absolute error which corresponds to 2.11% relative error. Time sensitivity is ±0.453 s and is open to improvement by varying the window width. The results indicate that, with further tests at other speed ranges, with other vehicles and under dynamic conditions, this method can be extended to the design of a new kind of vehicle speed sensor.

Download Full-text

Flow Measurement by Wavelet Packet Analysis of Sound Emissions

Measurement and Control ◽

10.1177/0020294018768340 ◽

2018 ◽

Vol 51 (3-4) ◽

pp. 104-112

Author(s):

Hüseyin Göksu

Keyword(s):

Flow Measurement ◽

Acoustic Analysis ◽

Wavelet Packet ◽

Flow Speed ◽

Frequency Resolution ◽

Wavelet Packet Analysis ◽

Resonance Effects ◽

Time Frequency ◽

Feature Vectors ◽

Frequency Domain Methods

Fluid, when running through pipes, makes a complex sound emission whose parameters change nonlinearly with respect to flow speed. Especially, in household pipe systems, there may be spraying effects and resonance effects which make the emission more complex. We present a novel approach for predicting flow speed based on wavelet packet analysis of sound emissions rather than traditional time and frequency domain methods. Wavelet packet analysis, by providing arbitrary time–frequency resolution, enables analyzing signals of stationary and non-stationary nature. It has better time representation than Fourier analysis and better high-frequency resolution than wavelet analysis. Wavelet packet analysis subimages are further analyzed to obtain feature vectors of norm entropy. These feature vectors are fed into a multilayer perceptron for prediction. Prediction accuracy of 98.62%, with 3.99E−04 L/s mean absolute error and its corresponding 1.85% relative error is achieved. Time sensitivity is ±0.453 s and is open to improvement by varying window width. The result indicates that the proposed method is a good candidate for flow measurement by acoustic analysis.

Download Full-text

Stochastic Modeling and Optimal Time-Frequency Estimation of Task-Related HRV

Applied Sciences ◽

10.3390/app9235154 ◽

2019 ◽

Vol 9 (23) ◽

pp. 5154

Author(s):

Rachele Anderson ◽

Peter Jönsson ◽

Maria Sandsten

Keyword(s):

Stochastic Model ◽

Frequency Estimation ◽

Optimal Time ◽

Model Parameters ◽

Inference Method ◽

Physiological Factors ◽

Time Frequency ◽

Spectral Estimates ◽

Novel Approach ◽

Spectral Estimator

In this paper, we propose a novel framework for the analysis of task-related heart rate variability (HRV). Respiration and HRV are measured from 92 test participants while performing a chirp-breathing task consisting of breathing at a slowly increasing frequency under metronome guidance. A non-stationary stochastic model, belonging to the class of Locally Stationary Chirp Processes, is used to model the task-related HRV data, and its parameters are estimated with a novel inference method. The corresponding optimal mean-square error (MSE) time-frequency spectrum is derived and evaluated both with the individually estimated model parameters and the common process parameters. The results from the optimal spectrum are compared to the standard spectrogram with different window lengths and the Wigner-Ville spectrum, showing that the MSE optimal spectral estimator may be preferable to the other spectral estimates because of its optimal bias and variance properties. The estimated model parameters are considered as response variables in a regression analysis involving several physiological factors describing the test participants’ state of health, finding a correlation with gender, age, stress, and fitness. The proposed novel approach consisting of measuring HRV during a chirp-breathing task, a corresponding time-varying stochastic model, inference method, and optimal spectral estimator gives a complete framework for the study of task-related HRV in relation to factors describing both mental and physical health and may highlight otherwise overlooked correlations. This approach may be applied in general for the analysis of non-stationary data and especially in the case of task-related HRV, and it may be useful to search for physiological factors that determine individual differences.

Download Full-text

MECHANICAL WATCH SIGNATURE ANALYSIS BASED ON WAVELET DECOMPOSITION

International Journal of Wavelets Multiresolution and Information Processing ◽

10.1142/s0219691309003057 ◽

2009 ◽

Vol 07 (04) ◽

pp. 491-512 ◽

Cited By ~ 1

Author(s):

QINGBO HE ◽

RUXU DU

Keyword(s):

Acoustic Signal ◽

Wavelet Decomposition ◽

Wavelet Packet ◽

Wide Frequency Range ◽

Frequency Resolution ◽

Signature Analysis ◽

Time Frequency ◽

Mode Decomposition ◽

Frequency Components ◽

Wavelet Techniques

The acoustic signal of mechanical watch is a distinct multi-component signal. It contains many frequency components corresponding to specific escapement motion sources with a very wide frequency range. Therefore, it is challenging for signature analysis of mechanical watch by the acoustic signal. This paper studies the time-frequency signatures of the mechanical watch based on wavelet decomposition. Two methods are proposed to improve the frequency resolution of traditional wavelet techniques by combining other beneficial techniques in the sense of decomposing specific mono- or independent components. The empirical mode decomposition (EMD) is presented to advance the wavelet packet decomposition (WPD) to decompose the mono-component signals. And the blind source separation (BSS) makes the redundancy of continuous wavelet transform (CWT) further gain good frequency resolution in the independent meaning. The decomposed signals by the two methods reveal the insight of mechanical watch movement and can contribute much simpler and clearer time-frequency signatures. Experimental results indicated the effectiveness of the two methods and the value of the time-frequency signatures in analyzing and diagnosing mechanical watch movements.

Download Full-text

Gaussian Window of Optimal Time-Frequency Resolution in Numerical Implementation of Short-Time Fourier Transform

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.48-49.555 ◽

2011 ◽

Vol 48-49 ◽

pp. 555-560 ◽

Cited By ~ 1

Author(s):

Yang Jin ◽

Zhi Yong Hao

Keyword(s):

Fourier Transform ◽

Continuous Time ◽

Gaussian Function ◽

Frequency Resolution ◽

Optimal Time ◽

Numerical Implementation ◽

Short Time Fourier Transform ◽

Time Frequency ◽

Gaussian Window ◽

Short Time

In this paper, we report the condition to keep the optimal time-frequency resolution of the Gaussian window in the numerical implementation of the short-time Fourier transform. Because of truncation and discretization, the time-frequency resolution of the discrete Gaussian window is different from that of the proper Gaussian function. We compared the time-frequency resolution performance of the discrete Gaussian window and Hanning window based on that they have the same continuous-time domain standard deviation, and generalized the condition under which the time-frequency resolution of the Gaussian window will prevail over that of the Hanning window.

Download Full-text

The Improvement of Wavelet Packet for Psychoacoustic Model

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.591-593.2491 ◽

2012 ◽

Vol 591-593 ◽

pp. 2491-2494

Author(s):

Jing Lei Zhou ◽

Ying Li

Keyword(s):

Spectrum Analysis ◽

Wavelet Packet ◽

Critical Band ◽

Frequency Resolution ◽

Wavelet Packet Decomposition ◽

Frequency Division ◽

Time Frequency ◽

Psychoacoustic Model ◽

Insufficient Time ◽

The Way

Compared with common psychoacoustic model, this article uses wavelet packet decomposition to decompose a signal. This method improves the situation of insufficient time-frequency resolution which the uniform spectrum analysis causes. In addition, frequency division by wavelet packet decomposition is much closer to human’s critical band than the way common psychoacoustic model getting, it is more suitable to human’s hearing characteristics. So we can use wavelet packet decomposition replace FFT in MPEG, and get accurate psychoacoustic model.

Download Full-text

Applications of predictive maintenance techniques in industrial systems

Serbian Journal of Electrical Engineering ◽

10.2298/sjee1103263m ◽

2011 ◽

Vol 8 (3) ◽

pp. 263-279 ◽

Cited By ~ 6

Author(s):

Aleksandra Marjanovic ◽

Goran Kvascev ◽

Predrag Tadic ◽

Zeljko Djurovic

Keyword(s):

Power Plants ◽

Hypothesis Test ◽

Moving Average ◽

Thermal Power ◽

Cost Savings ◽

Data Driven ◽

Model Parameters ◽

Model Based ◽

Level Sensor ◽

Arma Modeling

Prognostic methods represent a new methodology for system maintenance which offers significant time and cost savings. The paper offers a short overview of the available prognosis techniques and proposes the implementation of one model-based and one data-driven method. As a representative of the model-based methods the autoregressive moving average (ARMA) modeling approach is chosen. The estimated model parameters are further used for implementing the early change detector which is realized as a Neyman-Pearson hypothesis test. On the other hand, hidden Markov model (HMM) based prognosis illustrates the use of data-driven techniques. Using the cross-correlation input-output functions, HMM prognosis algorithm is proposed, as a suitable way of timely detection. Both techniques were implemented to detect performance changes of the water level sensor in a steam separator system in thermal power plants.

Download Full-text

Design and Optimization of ECG Modeling for Generating Different Cardiac Dysrhythmias

Sensors ◽

10.3390/s21051638 ◽

2021 ◽

Vol 21 (5) ◽

pp. 1638

Author(s):

Md. Abdul Awal ◽

Sheikh Shanawaz Mostafa ◽

Mohiuddin Ahmad ◽

Mohammad Ashik Alahe ◽

Mohd Abdur Rashid ◽

...

Keyword(s):

Gaussian Function ◽

Model Performance ◽

Clinical Importance ◽

Optimization Methods ◽

Model Parameters ◽

Search Technique ◽

Time Frequency ◽

Model Based ◽

Cardiac Dysrhythmias ◽

Ecg Morphology

The electrocardiogram (ECG) has significant clinical importance for analyzing most cardiovascular diseases. ECGs beat morphologies, beat durations, and amplitudes vary from subject to subject and diseases to diseases. Therefore, ECG morphology-based modeling has long-standing research interests. This work aims to develop a simplified ECG model based on a minimum number of parameters that could correctly represent ECG morphology in different cardiac dysrhythmias. A simple mathematical model based on the sum of two Gaussian functions is proposed. However, fitting more than one Gaussian function in a deterministic way has accuracy and localization problems. To solve these fitting problems, two hybrid optimization methods have been developed to select the optimal ECG model parameters. The first method is the combination of an approximation and global search technique (ApproxiGlo), and the second method is the combination of an approximation and multi-start search technique (ApproxiMul). The proposed model and optimization methods have been applied to real ECGs in different cardiac dysrhythmias, and the effectiveness of the model performance was measured in time, frequency, and the time-frequency domain. The model fit different types of ECG beats representing different cardiac dysrhythmias with high correlation coefficients (>0.98). Compared to the nonlinear fitting method, ApproxiGlo and ApproxiMul are 3.32 and 7.88 times better in terms of root mean square error (RMSE), respectively. Regarding optimization, the ApproxiMul performs better than the ApproxiGlo method in many metrics. Different uses of this model are possible, such as a syntactic ECG generator using a graphical user interface has been developed and tested. In addition, the model can be used as a lossy compression with a variable compression rate. A compression ratio of 20:1 can be achieved with 1 kHz sampling frequency and 75 beats per minute. These optimization methods can be used in different engineering fields where the sum of Gaussians is used.

Download Full-text

Engine Speed–Independent Acoustic Signature for Vehicles

Measurement and Control ◽

10.1177/0020294018769080 ◽

2018 ◽

Vol 51 (3-4) ◽

pp. 94-103 ◽

Cited By ~ 2

Author(s):

Hüseyin Göksu

Keyword(s):

Multilayer Perceptron ◽

Engine Speed ◽

Wavelet Packet ◽

Frequency Resolution ◽

Wavelet Packet Analysis ◽

Time Frequency ◽

Feature Vectors ◽

Energy Entropy ◽

Acoustic Signature ◽

Frequency Domain Methods

A vehicle, when running, makes a complex sound emission from the engine, the exhaust, the air conditioner, and other mechanical parts. Analysis of this sound for the purpose of vehicle identification is an interesting practice which has security- and transportation-related applications. Engine speed variation, which causes shifts in the frequency content of the emissions, makes Fourier-based methods ineffective in terms of providing a stable signature for the vehicle. We search for an engine speed–independent acoustic signature for the vehicle, and for this purpose, we propose wavelet packet analysis rather than traditional time- or frequency-domain methods. Wavelet packet analysis, by providing arbitrary time–frequency resolution, enables analyzing signals of stationary and non-stationary nature. It has better time representation than Fourier analysis and better high-frequency resolution than wavelet analysis. Under varying engine speed, sound emissions are recorded from four cars and analyzed by wavelet packet analysis. Wavelet packet analysis subimages are further analyzed to obtain feature vectors in the form of log energy entropy, norm entropy, and energy. These feature vectors are fed into a classifier, multilayer perceptron, for evaluation. While norm entropy achieves a classification rate of 100%, log energy entropy and energy achieves classification rates of 99.26% and 97.79%, respectively. These results indicate that, wavelet packet analysis along with norm entropy and multilayer perceptron provides an accurate vehicle-specific acoustic signature independent of the engine speed.

Download Full-text