Wavelet Transform Based Abnormality Analysis of Heart Sound

Any sudden change in power line produces high frequency electromagnetic impulse called travelling wave (TW). Continuous Wavelet Transform (CWT) can detect transmission line abnormalities. CWT has several advantages over Discrete Wavelet Transform (DWT) since CWT is continuous in terms of shifting and it can operate on any scale. Bewley's lattice method, which is a method of detection of fault location from TW, does not consider the noises and interferences. Noises and interferences modify the TW signals. In this paper a novel CWT based Bewley's lattice method of transmission lines-fault detection is presented. The main difference between the conventional CWT method and the method described in this paper is the accumulation of CWT coefficients at all scales. In the proposed method, the coefficients related to transmission line abnormalities are enlarged while the coefficients of noises at different scales counteract one another. The proposed CWT based Bewley's lattice method is more accurate than conventional Bewley's lattice or DWT/CWT based methods.

Analyzing the condition and function of the heart is very important because cardiovascular diseases (CVDs) are responsible for high mortality rates worldwide and can lead to strokes and heart attacks; thus, early diagnosis and treatment are important. Phonocardiogram (PCG) signals can be used to analyze heart rate characteristics to detect heart health and detect heart-related diseases. In this paper, we propose a method for designing using wavelet analysis techniques and an ensemble of deep learning models from phonocardiogram (PCG) for heart sound classification. For this purpose, we use wavelet scattering transform (WST) and continuous wavelet transform (CWT) as the wavelet analysis approaches for 1D-convolutional neural network (CNN) and 2D-CNN modeling, respectively. These features are insensitive to translations of the input on an invariance scale and are continuous with respect to deformations. Furthermore, the ensemble model is combined with 1D-CNN and 2D-CNN. The proposed method consists of four stages: a preprocessing stage for dividing signals at regular intervals, a feature extraction stage through wavelet scattering transform (WST) and continuous wavelet transform (CWT), a design stage of individual 1D-CNN and 2D-CNN, and a classification stage of heart sound by the ensemble model. The datasets used for the experiment were the PhysioNet/CinC 2016 challenge dataset and the PASCAL classifying heart sounds challenge dataset. The performance evaluation is performed by precision, recall, F1-score, sensitivity, and specificity. The experimental results revealed that the proposed method showed good performance on two datasets in comparison to the previous methods. The ensemble method of the proposed deep learning model surpasses the performance of recent studies and is suitable for predicting and diagnosing heart-related diseases by classifying heart sounds through phonocardiogram (PCG) signals.

Noise suppression from the phonocardiogram (PCG) signal is important to improve the diagnostic efficiency. For the PCG signal, Discrete Wavelet Transform (DWT) based denoising method has been used extensively due to its good performance. However, the performance of this method depends on the threshold value and the way to apply it on the wavelet coefficients. Therefore, in this paper, an adaptive method is proposed to estimate the threshold value for the shrinking of the wavelet coefficients of the PCG signal. For this purpose, a new statistical parameter is obtained by incorporating medical domain knowledge about the PCG. The threshold value is estimated based on the statistical analysis of the wavelet coefficients and the present level of noise. Further, to overcome the issues related to existing threshold functions, soft and hard, new threshold functions, mid and non-linear mid are presented. The proposed method is applied to the PCG signal contaminated with simulated white Gaussian noise, red noise, and pink noise. The obtained results of the proposed method are compared with the results of state-of-the-art methods and they show the superiority of the proposed method.

Diagnosis of plasma processing equipment using neural network recognition of wavelet-filtered impedance matching

A new calibration model for plasma diagnosis was constructed by combining radio frequency impedance match data, wavelet, and neural network. A total of 30 fault symptoms were simulated with the variations in the four process parameters. Both discrete wavelet transformation (DWT) and continuous wavelet transformation (CWT) were utilized to filter the sensor information. Three types of diagnosis models (raw-, DWT-, and CWT-based models) were constructed. The comparisons revealed that the improvement in the prediction performance of DWT and CWT data models over the raw data model were about 42% and 30%, respectively.

In recent years, damage detection methods have been significantly increased in civil and mechanical structures. One of the most widely used and relatively new methods of signal processing is the method based on wavelet transform; with the help of this powerful tool, the damage in the structures can be detected in the early stages of damage formation, in order to prevent a larger damage event. In this paper, we have investigated the debonding damage of active surfaces in Concrete-Filled Tube (CFT) columns, which greatly reduces the effect of enclosure on concrete and decreases the bearing capacity of these tubes with the help of wavelet transformation (Discrete Wavelet Transform and Continuous Wavelet Transform). The debonding damage of the active surfaces was evaluated using wavelet types, and the occurrence and location of the damage were detected based on variations in frequency and mode shapes. The above studies have been done for the first six modes of the CFT column. The results of the analyzes indicate that the wavelet transform tool is very capable of detecting the occurrence and location of the damage and is able to detect high-level debonding damage in one side of the column that creates curvature and slight jump in the shape of the mode.

The phonocardiogram (PCG) signal is sometimes affected by added parameters that reflect the presence of a specific pathology. The intensity or the energy of the signal is one of the most reliable parameters when studying cardiac severity. Yet, in a pathological electrophysiological and audio signal, the severity information does not fully remain in the intensity or energy, but in other variables. In this paper, we will discuss the ability of a time-frequency parameter to discriminate, separate, and monitor the pathological cardiac severity levels. We studied 14 PCG signal from eight pathologies, six of them contain clicks (reduce murmurs), and eight murmur PCG signals with four different cardiac severity levels. We then calculated the entropy of approximation coefficients (EAC) from a discrete wavelet transform (DWT) analysis, to differentiate the PCG signals with clicks from those with murmurs and to assess the cardiac severity evolution. Since the entropy EAC is also related to the signal’s intensity (energy), we compared it to the energetic ratio (ER) evolution, a parameter widely used for PCG signals discrimination and classification, which revealed that the EAC provied better results for the paper' purposes.

In this paper, a three Degrees Of Freedom (DOF) model of a quarter vehicle suspension system is proposed including the seat driver mass. The modal parameters of this system, which indicate the comfort and the safety of the suspension, are identified using Wavelet analysis. Two applications of wavelet analysis are presented: signal denoising based on the Discrete Wavelet Transform (DWT) and modal identification based on the Continuous Wavelet Transform (CWT). It is shown that the CWT analysis of the system response, initially denoised using DWT, allows the estimation of the natural pulsations and the damping ratios. The usefulness of the DWT in denoising and the accuracy of the CWT in modal identification are tested and confirmed by applying them to the proposed model. The complete modeling and identification of a 3-DOF vehicle suspension system is developed and the simulation results verify these statements and are satisfactory.

With the increasing development of internet, the security of personal information becomes more and more important. Thus, variety of personal recognition methods have been introduced to ensure persons' information security. Traditional recognition methods such as Personal Identification Number (PIN), or Identification tag (ID) are vulnerable to hackers. Then the biometric technology, which uses the unique physiological characteristics of human body to identify user information has been proposed. But the biometrics widely used at present such as human face, fingerprint, iris, and voice can also be forged and falsified. The biometric with living body features such as electromyography (EMG) signal is a good method to achieve aliveness detection and prevent the spoofing attacks. However, there are few studies on personal recognition based on EMG signal. According to the application context, personal recognition system may operate either in identification mode or verification mode. In the personal identification mode, the system recognizes an individual by searching the templates of all the users in the database for a match. While in the personal verification mode, the system validates a person's identity by comparing the captured features with her or his own template(s) stored in the system database. In this paper, both EMG-based personal identification method and EMG-based personal verification method are investigated. First, the Myo armband is placed on the right forearm (specifically, the height of the radiohumeral joint) of 21 subjects to collect the surface EMG signal under hand-open gesture. Then, two different methods are proposed for EMG-based personal identification, i.e., personal identification method based on Discrete Wavelet Transform (DWT) and ExtraTreesClassifier, and personal identification method based on Continuous Wavelet Transform (CWT) and Convolutional Neural Networks (CNN). Experiments with 21 subjects show that the identification accuracy of this two methods can achieve 99.206% and 99.203% respectively. Then based on the identification method using CWT and CNN, transfer learning algorithm is adopted to solve the model update problem when new data is added. Finally, an EMG-based personal verification method using CWT and siamese networks is proposed. Experiments show that the verification accuracy of this method can achieve 99.285%.

By viewing a gene expression profile as a pseud-time signal, we apply wavelet transformation (WT) to analyze gene expression data in a time-frequency manner. As a result, two pattern extraction approaches, continuous wavelet transformation (CWT)-based one and discrete wavelet transformation (DWT)-based one, are proposed to extract hidden expression patterns for cancer classification and are compared. Gene expression data are highly redundant and highly noisy, and hidden gene correlation patterns play more important roles to cancer classification than any single gene or simple combinations of genes. The CWT can more efficiently detect the consistent correlation signature than the DWT due to the availability of more detail information. Testing results on two publicly available gene expression datasets show the effectiveness and efficiency of the CWT-based approach.

In wind energy systems, doubly-fed induction generators (DFIGs) are widely used because they can produce electricity efficiently and operate over a wide range of wind speeds. However, like all electromechanical systems, DFIGs are prone to failures, one of which is open phase failure. The main objective of this paper is to present new results in the DFIG diagnostic approach for identifying stator and rotor open-phase failures. The approach is based on steady-state stator current analysis, using Fast Fourier Transform (FFT) and wavelets transforms (Continuous Wavelet Transform (CWT) and Discrete Wavelet Transform (DWT)) analysis with 2-D and 3-D approaches respectively. The effectiveness of the wavelet transform is confirmed by exposing simulation results, which demonstrate its ability to effectively analyze signals across various scales and resolutions. These results highlight how the wavelet transform can overcome traditional limitations associated with other signal processing techniques, such as the inability to provide localized information in both time and frequency domains. This capability is particularly evident in the 3-D time-frequency plot, where the wavelet transform offers a detailed and intuitive representation of the current signal. By capturing transient features and variations in the signal, the wavelet transform allows for a more comprehensive understanding of its underlying characteristics. Consequently, this method proves invaluable in applications such as audio processing, image analysis, and biomedical signal interpretation, where precise localization of features is crucial for accurate analysis and interpretation.

Objective. Heart sounds can reflect detrimental changes in cardiac mechanical activity that are common pathological characteristics of chronic heart failure (CHF). The ACC/AHA heart failure (HF) stage classification is essential for clinical decision-making and the management of CHF. Herein, a machine learning model that makes use of multi-scale and multi-domain heart sound features was proposed to provide an objective aid for ACC/AHA HF stage classification. Approach. A dataset containing phonocardiogram (PCG) signals from 275 subjects was obtained from two medical institutions and used in this study. Complementary ensemble empirical mode decomposition and tunable-Q wavelet transform were used to construct self-adaptive sub-sequences and multi-level sub-band signals for PCG signals. Time-domain, frequency-domain and nonlinear feature extraction were then applied to the original PCG signal, heart sound sub-sequences and sub-band signals to construct multi-scale and multi-domain heart sound features. The features selected via the least absolute shrinkage and selection operator were fed into a machine learning classifier for ACC/AHA HF stage classification. Finally, mainstream machine learning classifiers, including least-squares support vector machine (LS-SVM), deep belief network (DBN) and random forest (RF), were compared to determine the optimal model. Main results. The results showed that the LS-SVM, which utilized a combination of multi-scale and multi-domain features, achieved better classification performance than the DBN and RF using multi-scale or/and multi-domain features alone or together, with average sensitivity, specificity, and accuracy of 0.821, 0.955 and 0.820 on the testing set, respectively. Significance. PCG signal analysis provides efficient measurement information regarding CHF severity and is a promising noninvasive method for ACC/AHA HF stage classification.

Artificial intelligence (AI) has shown potential in analyzing electromyography (EMG) signals, but clinical applicability remains limited by studies based on small, curated datasets, and variable accuracy. This study evaluated AI performance in classifying needle electromyography (EMG) signals as muscle activity versus background/noise/artifact, and then in distinguishing three clinical categories: amyotrophic lateral sclerosis (ALS), myopathy, and non-disease controls. Data from the Cleveland Clinic Foundation EMG Database (CCFDB), a large clinically acquired EMG dataset was utilized for this study. A two-step classification approach was used: a convolutional neural network (CNN) to separate muscle activity from background/noise/artifact, followed by a random forest algorithm and CNNs for clinical category classification. Feature extraction techniques included Short-Time Fourier Transform (STFT), Discrete Wavelet Transform (DWT), Continuous Wavelet Transform (CWT), and Wavelet Packet Decomposition (WPD). EMG data from 608 participants (266 ALS, 89 myopathy, 253 non-disease controls), totaling 11,456 muscle recordings, and 15,613 segments of muscle activity were included. The muscle activity detection model achieved 85.4% accuracy. For clinical category classification, CWT with a two-layer CNN performed best on the CCFDB (62% accuracy). Deeper CNN architectures did not consistently improve performance. On the publicly available curated EMGlab dataset, the best accuracy using the same AI models was higher (91%). AI can assist in EMG analysis, but the performance gap between curated and clinically-acquired datasets underscores the need for robust models capable of handling signal variability and complexity in authentic clinical contexts. Future efforts should focus on clinically-oriented AI development to improve translational applicability.

Analysis of PCG signals using quality assessment and homomorphic filters for localization and classification of heart sounds

In this paper, fractal theory and wavelet transform are combined to detect and classify self-extinguishing and fugitive scenarios of power quality disturbances (PQDs). After deciding whether the disturbance is simple or complex, the additional voltage is denoised through Discrete Wavelet Transform (DWT); the denoising process is adapted according to whether the distorted voltage contains oscillatory transients or not. At the detection stage, the grille fractal dimension of the DWT decomposition detail is computed. Then, a threshold is deduced to detect the start and end moments of the disturbance. The results reveal that the proposed detection scheme yields accurate location of PQDs even in the presence of high oscillatory transients. An algorithm based on geometric and statistical approaches is developed at the classification stage to recognize PQDs automatically. The geometric classification is based on Continuous Wavelet Transform (CWT), whereas the statistical classification is based on Multifractal Detrended Fluctuations Analysis (MFDFA) and an energy metric. The results prove that the combination of geometric and statistical classification can serve as an effective discrimination tool for PQDs. The major strength of the proposed approach is its ability to interpret the impact of each disturbance on the multifractal behavior of the nominal voltage, thus giving the possibility to draw the necessary generalizations for real-time applications.