Bispectral Analysis Research Articles

Heart sound classification algorithm based on bispectral feature extraction and convolutional neural networks

Cardiovascular disease (CVD) is one of the leading causes of death worldwide. Heart sound classification plays a key role in the early detection of CVD. The difference between normal and abnormal heart sounds is not obvious. In this paper, in order to improve the accuracy of the heart sound classification model, we propose a heart sound feature extraction method based on bispectral analysis and combine it with convolutional neural network (CNN) to classify heart sounds. The model can effectively suppress Gaussian noise by using bispectral analysis and can effectively extract the features of heart sound signals without relying on the accurate segmentation of heart sound signals. At the same time, the model combines with the strong classification performance of convolutional neural network and finally achieves the accurate classification of heart sound. According to the experimental results, the proposed algorithm achieves 0.910, 0.884 and 0.940 in terms of accuracy, sensitivity and specificity under the same data and experimental conditions, respectively. Compared with other heart sound classification algorithms, the proposed algorithm shows a significant improvement and strong robustness and generalization ability, so it is expected to be applied to the auxiliary detection of congenital heart disease.

Comparison of Electrocardiogram between Dilated Cardiomyopathy and Ischemic Cardiomyopathy Based on Empirical Mode Decomposition and Variational Mode Decomposition.

The clinical manifestations of ischemic cardiomyopathy (ICM) bear resemblance to dilated cardiomyopathy (DCM), yet their treatments and prognoses are quite different. Early differentiation between these conditions yields positive outcomes, but the gold standard (coronary angiography) is invasive. The potential use of ECG signals based on variational mode decomposition (VMD) as an alternative remains underexplored. An ECG dataset containing 87 subjects (44 DCM, 43 ICM) is pre-processed for denoising and heartbeat division. Firstly, the ECG signal is processed by empirical mode decomposition (EMD) and VMD. And then, five modes are determined by correlation analysis. Secondly, bispectral analysis is conducted on these modes, extracting corresponding bispectral and nonlinear features. Finally, the features are processed using five machine learning classification models, and a comparative assessment of their classification efficacy is facilitated. The results show that the technique proposed provides a better categorization for DCM and ICM using ECG signals compared to previous approaches, with a highest classification accuracy of 98.30%. Moreover, VMD consistently outperforms EMD under diverse conditions such as different modes, leads, and classifiers. The superiority of VMD on ECG analysis is verified.

Application of Bispectral Analysis to Assess the Effect of Drought on the Photosynthetic Activity of Lettuce Plants Lactuca sativa L.

Application of Bispectral Analysis to Assess the Effect of Drought on the Photosynthetic Activity of Lettuce Plants Lactuca sativa L.

Study of the Synchronization and Transmission of Intracellular Signaling Oscillations in Cells Using Bispectral Analysis.

The oscillation synchronization analysis in biological systems will expand our knowledge about the response of living systems to changes in environmental conditions. This knowledge can be used in medicine (diagnosis, therapy, monitoring) and agriculture (increasing productivity, resistance to adverse effects). Currently, the search is underway for an informative, accurate and sensitive method for analyzing the synchronization of oscillatory processes in cell biology. It is especially pronounced in analyzing the concentration oscillations of intracellular signaling molecules in electrically nonexcitable cells. The bispectral analysis method could be applied to assess the characteristics of synchronized oscillations of intracellular mediators. We chose endothelial cells from mouse microvessels as model cells. Concentrations of well-studied calcium and nitric oxide (NO) were selected for study in control conditions and well-described stress: heating to 40 °C and hyperglycemia. The bispectral analysis allows us to accurately evaluate the proportion of synchronized cells, their synchronization degree, and the amplitude and frequency of synchronized calcium and NO oscillations. Heating to 40 °C increased cell synchronization for calcium but decreased for NO oscillations. Hyperglycemia abolished this effect. Heating to 40 °C changed the frequencies and increased the amplitudes of synchronized oscillations of calcium concentration and the NO synthesis rate. The first part of this paper describes the principles of the bispectral analysis method and equations and modifications of the method we propose. In the second part of this paper, specific examples of the application of bispectral analysis to assess the synchronization of living cells in vitro are presented. The discussion compares the capabilities of bispectral analysis with other analytical methods in this field.

Example of bispectral analysis of a transmission line pylon

Example of bispectral analysis of a transmission line pylon

Effects of gabapentin on slow-wave sleep period in critically ill adult patients: A randomized controlled trial.

Sleep deprivation is a prevalent problem in critically ill patients, which leads to delayed recovery and delirium. Slow-wave sleep (SWS) is essential to energy restoration, tissue repair, and immune system strengthening. This study aimed to investigate the effects of gabapentin on SWS in critically ill patients. We performed a prospective open-label randomized controlled study to compare SWS and the clinical outcomes of gabapentin versus a control intervention in critically ill adult patients admitted to the intensive care unit (ICU) within 24 h. The patients' characteristics and sleep-related outcomes were recorded. The sleep-related outcomes, namely, bispectral analysis (BIS), the Richards-Campbell Sleep Questionnaire (RCSQ), and insulin-like growth factor-1 (IGF-1) levels, were evaluated. Furthermore, clinical outcomes and safety were assessed. Sixty patients from 348 cases were eligible for randomization. On day 3 of the study, patients in the gabapentin group had significantly increased SWS (66.79 vs. 0.00 min; p < 0.001), total sleep time (TST) (331.39 vs. 46.16 min; p = 0.001), RCSQ score (55.05 ± 20.18 vs. 32.80 ± 15.31; p < 0.001), and IGF-1 concentrations (84.33 ± 12.40 vs. 44.00 ± 10.20 ng/mL, p < 0.001) compared with the control group. Improvements in clinical outcomes, such as delirium, ICU-free days, and mechanical ventilator-free days, were observed; however, these differences did not reach statistically significant. Gabapentin at bedtime increased SWS, TST, and IGF-1 concentrations in critically ill patients. This regimen might be beneficial to critically ill patients for improving their sleep quality.

Machine learning Based Bearing Fault Classification Using Higher Order Spectral Analysis

In the defense sector, where mission success often hinges on the reliability of complex mechanical systems, the health of bearings within aircraft, naval vessels, ground vehicles, missile systems, drones, and robotic platforms is paramount. Different signal processing techniques along with Higher Order Spectral Analysis (HOSA) have been used in literature for the fault diagnosis of bearings. Bispectral analysis offers a valuable means of finding higher-order statistical associations within signals, thus proving to detect the nonlinearities among Gaussian and non-Gaussian data. Their resilience to noise and capacity to unveil concealed information render them advantageous across a range of applications. Therefore, this research proposesa novel approach of utilizing the features extracted directly from the Bispectrum for classifying the bearing faults, departing from the common practice in other literature where the Bispectrum is treated as an image for fault classification. In this work vibration signalsare used to detect the bearing faults. The features from the non-redundant region and diagonal slice of the Bispectrum are used to capture the statistical and higher-order spectral characteristics of the vibration signal. A set of sixteen machine learning models, viz., Decision Trees, K-Nearest Neighbors, Naive Bayes, and Support Vector Machine, is employed to classify the bearing faults. The evaluation process involves a robust 10-fold cross-validation technique. The results reveal that the Decision Tree algorithm outperformed all others, achieving a remarkable accuracy rate of 100 %. The naive Bayes algorithm also demonstrated the least performance, with an accuracy score of 99.68 %. The results obtained from these algorithms have been compared with those achieved using Convolutional Neural Network (CNN), revealing that the training time of these algorithms is significantly shorter in comparison to CNN.

A bicoherence approach to analyze multi-dimensional cross-frequency coupling in EEG/MEG data

We introduce a blockwise generalisation of the Antisymmetric Cross-Bicoherence (ACB), a statistical method based on bispectral analysis. The Multi-dimensional ACB (MACB) is an approach that aims at detecting quadratic lagged phase-interactions between vector time series in the frequency domain. Such a coupling can be empirically observed in functional neuroimaging data, e.g., in electro/magnetoencephalographic signals. MACB is invariant under orthogonal trasformations of the data, which makes it independent, e.g., on the choice of the physical coordinate system in the neuro-electromagnetic inverse procedure. In extensive synthetic experiments, we prove that MACB performance is significantly better than that obtained by ACB. Specifically, the shorter the data length, or the higher the dimension of the single data space, the larger the difference between the two methods.

Isotope effects on transport characteristics of edge and core plasmas heated by neutral beam injection (NBI) in an inward shifted configuration at the Large Helical Device

Isotope effects have been investigated in Neutral Beam Injection (NBI) heated plasmas on the Large Helical Device with similar operational parameters between Hydrogen (H) and Deuterium (D) plasmas. Experimental results show that the global energy confinement has no significant dependence on the isotope mass under similar discharge conditions with nearly the same heating power, line-averaged density ( nˉe ) and magnetic field. For both electron and ion energy transport, the transport coefficients, which are obtained based on local power balance analysis, have analogous profiles between H and D dominant plasmas. For neoclassical χe and χi values, they are almost equal between H and D dominant plasmas in low nˉe discharges, whereas in high nˉe cases they are lower in H plasmas than those in D ones. At low nˉe , the electron and ion thermal transport in both H and D plasmas are dominated by neoclassical transport at a certain zone ( ρ≈0.6−0.85 ), while the anomalous transport process has primary effects in the remaining area, and the density fluctuations exhibit ion temperature gradient mode nature. With increase of nˉe , the anomalous transport becomes prevailing and the density fluctuations propagate along electron diamagnetic drift direction. Bispectral analysis reveals that the H plasma has stronger nonlinear coupling in edge density fluctuations in both low and high density discharges, which is probably due to that the D plasma has stronger damping rate for the nonlinear interaction of turbulence. For a comparative study, the present results have been compared with those observed in the ECRH discharges (Tanaka et al 2019 Nucl. Fusion 59 126040). The reasons for the similarities and dissimilarities between these two different heating manners are not clear yet. To unravel the underlying physics, essential inputs from theories and simulations are required.

Experimental study of the effects of isolated roughness elements on the stability and transition of a hypersonic boundary layer on a flat plate

Surface roughness elements on hypersonic vehicles can cause early boundary layer transition, increasing wall skin friction and heat flux and affecting aircraft range and thermal protection systems. Accurate prediction of the transition caused by these roughness elements is crucial for the design of hypersonic vehicles. In this work, wind tunnel experiments on isolated roughness-induced boundary layer transition at Ma = 6 are conducted. Infrared thermography and high-frequency pressure sensors are utilized to investigate the effects of different roughness element configurations (cylindrical, diamond, ramp) on the hypersonic boundary layer instability and transition. The experimental results show that all three roughness elements can effectively enhance the generation of second mode waves and promote boundary layer transition. Compared to smooth surfaces, they exhibit similar frequency band range, faster growth, and earlier saturation. Among them, the ramp roughness element most effectively triggers the boundary layer transition, with a relatively small heat flux increase. Furthermore, bispectral analysis illustrates that all three roughness elements undergo self-interactions that lead to spectral broadening, ultimately resulting in boundary layer transitions.

Assessment of scale interactions associated with wake meandering using bispectral analysis methodologies

Large atmospheric boundary layer fluctuations and smaller turbine-scale vorticity dynamics are separately hypothesized to initiate the wind turbine wake meandering phenomenon, a coherent, dynamic, turbine-scale oscillation of the far wake. Triadic interactions, the mechanism of energy transfers between scales, manifest as triples of wavenumbers or frequencies and can be characterized through bispectral analyses. The bispectrum, which correlates the two frequencies to their sum, is calculated by two recently developed multi-dimensional modal decomposition methods: scale-specific energy transfer method and bispectral mode decomposition. Large-eddy simulation of a utility-scale wind turbine in an atmospheric boundary layer with a broad range of large length-scales is used to acquire instantaneous velocity snapshots. The bispectrum from both methods identifies prominent upwind and wake meandering interactions that create a broad range of energy scales including the wake meandering scale. The coherent kinetic energy associated with the interactions shows strong correlation between upwind scales and wake meandering.

Bispectral analysis and simulation modeling of quadratic nonlinear system with specific turbulent-fluctuation-excitation-response types

There exists a kind of quadratic nonlinear system with specific type of turbulent fluctuation excitation in nature, which belongs to a special non-Gaussian input signal system. Its characteristic is that the input signal spectrum is generated by turbulent fluctuations, and the power spectrum distribution of this turbulence fluctuation signal is close to Gaussian distribution. Starting with the work of Choi et al. (&lt;ext-link ext-link-type="uri" xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="https://doi.org/10.1016/0022-460X(85)90370-0"&gt;1985 &lt;i&gt;J. Sound Vib&lt;/i&gt;&lt;i&gt;.&lt;/i&gt; &lt;b&gt;99&lt;/b&gt; 309&lt;/ext-link&gt;) and Kim et al. [&lt;ext-link ext-link-type="uri" xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="https://ieeexplore.ieee.org/document/1145286"&gt;1987 &lt;i&gt;IEEE J. Ocean. Eng.&lt;/i&gt; &lt;b&gt;OE-12&lt;/b&gt; 568&lt;/ext-link&gt;), we extend the simulation of a specific turbulent fluctuation excited response-type quadratic nonlinear system represented by the wave excited mooring ship response, and fully develop the internal development of turbulence based on bispectral analysis technology. We also extend the simulation system and conduct systematic modeling analysis. The complete iterative method [&lt;ext-link ext-link-type="uri" xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="https://doi.org/10.1088/1402-4896/ab725f"&gt;2020 &lt;i&gt;Phys. Scr.&lt;/i&gt; &lt;b&gt;95&lt;/b&gt; 055202&lt;/ext-link&gt;] is used to solve the model, and calculate the linear transfer function and quadratic nonlinear transfer function. The comparison of simulation and modeling results with the real systems and their models confirms the correctness of the results from system simulation, system modeling, and model solving. The results obtained are all in line with expectations. The coherence analysis shows that the quadratic coherence of the random wave-ship swaying system is much greater than the linear coherence, but the linear coherence of the fully developed turbulence is greater for the near Gaussian input type. The reverse computation verification or comparison with real systems indicates that the turbulence simulation and system modeling method in this work have good accuracy and high efficiency in solving algorithms, and the research results can be effectively applied to the model description and system analysis of the quadratic nonlinear systems related to specific turbulent fluctuation excitation response.

Measurement and analysis of crossflow instability modes on a 7-degree yawed cone at Mach 6

In this work, the crossflow instability modes on a 7° half-angle cone with 6° angle of attack at Mach 6 have been experimentally studied. To begin with, the complete laminar-to-turbulence transition process is acquired by infrared thermography, and the heat flux streaks caused by the stationary crossflow vortices are distinct over the areas of leeward side. Further wavelet analysis reveals a dominant wavenumber of the stationary crossflow vortices, which is centered at about k = 50. Subsequently, the spatial distribution characteristics of the traveling crossflow instability (f = 20–50 kHz) and high-frequency instabilities (f = 100–500 kHz) are acquired between the azimuthal angle Φ = 90°–150° (windside to leeside) through wall mounted pressure sensors. The results of spectral and wavelet analysis indicate that the two types of instability are the traveling crossflow instability and its secondary instability, respectively. Further bispectral analysis is used to show that these high-frequency waves undergo several quadratic phase-coupled interactions with themselves to produce harmonics, as well interact with low-frequency waves that results in spectral broadening.

A comprehensive framework for advanced protein classification and function prediction using synergistic approaches: Integrating bispectral analysis, machine learning, and deep learning

Proteins are fundamental components of diverse cellular systems and play crucial roles in a variety of disease processes. Consequently, it is crucial to comprehend their structure, function, and intricate interconnections. Classifying proteins into families or groups with comparable structural and functional characteristics is a crucial aspect of this comprehension. This classification is crucial for evolutionary research, predicting protein function, and identifying potential therapeutic targets. Sequence alignment and structure-based alignment are frequently ineffective techniques for identifying protein families.This study addresses the need for a more efficient and accurate technique for feature extraction and protein classification. The research proposes a novel method that integrates bispectrum characteristics, deep learning techniques, and machine learning algorithms to overcome the limitations of conventional methods. The proposed method uses numbers to represent protein sequences, utilizes bispectrum analysis, uses different topologies for convolutional neural networks to pull out features, and chooses robust features to classify protein families. The goal is to outperform existing methods for identifying protein families, thereby enhancing classification metrics. The materials consist of numerous protein datasets, whereas the methods incorporate bispectrum characteristics and deep learning strategies. The results of this study demonstrate that the proposed method for identifying protein families is superior to conventional approaches. Significantly enhanced quality metrics demonstrated the efficacy of the combined bispectrum and deep learning approaches. These findings have the potential to advance the field of protein biology and facilitate pharmaceutical innovation. In conclusion, this study presents a novel method that employs bispectrum characteristics and deep learning techniques to improve the precision and efficiency of protein family identification. The demonstrated advancements in classification metrics demonstrate this method’s applicability to numerous scientific disciplines. This furthers our understanding of protein function and its implications for disease and treatment.

Multiclassification for heart sound signals under multiple networks and multi-view feature

Heart sound signals play a crucial role in assessing cardiovascular health. Building upon this, we have designed five networks to effectively classify these signals. Initially, it is essential to standardize them. Subsequently, we generate four types of two-dimensional (2D) heart sound feature images, namely Spectrogram, Mel-spectrogram, Bispectral analysis, and Phonocardiogram (PCG). To enhance performance, we refine the block in ConvNext and compare two one-dimensional (1D) ConvNext networks. After obtaining a superior network, we merge it with a pre-trained 2D ConvNext network on ImageNet. Then, we introduce the Encoder block from the Transformer network and combine it with the improved 1D ConvNext network. Among them, the Conv-Encoder1 network achieved classification accuracies of 98.7%, 91.9%, and 97.9% on the three datasets, respectively. Furthermore, by observing all the test results, it can be concluded that utilizing 1D heart sound signals for automatic classification offers significant advantages compared to using 2D feature images.

Anomalous cross-field transport in a Hall thruster inferred from direct measurement of instability growth rates.

The contribution of the electron drift instability to anomalous electron transport is experimentally assessed in a Hall effect discharge. The transport is represented by an anomalous collision frequency, which is related through quasilinear theory to the energy and growth rate of the instability. The wave energy is measured directly with ion saturation probes, while estimates of the growth rate are employed based on both linearized theory and direct measurement. The latter measurement is performed with a bispectral analysis method. The wave-driven collision frequency is compared to measurements of the actual collision frequency inferred from a method based on laser-induced fluorescence. It is found that estimates for transport using linearized theory for the growth differ by over an order of magnitude from the actual anomalous collision frequency in the plasma. The wave-driven anomalous collision frequency with measured growth, however, is shown to agree with the electron collision frequency in magnitude and capture aspects of the trends in spatial variation. This result demonstrates experimentally that wave-driven effects ultimately can explain the observed cross-field transport in these devices. The implications of this finding are discussed in the context of the key lengthscales that drive the transport as well as the implications identifying reduced fidelity models that could be used to predict anomalous collision frequency.

Mechanical seal friction condition monitoring based on bispectral characteristics

PurposeThe purpose of this paper is to investigate the monitoring of the friction condition of mechanical seals.Design/methodology/approachAcoustic emission signals from the friction of the seal end face were obtained, and their bispectral characteristics were extracted. The variation of non-Gaussian information with the degree of friction was investigated, and by combining bispectral characteristics with information entropy, a bispectral entropy index was established to represent the friction level of the seal end face.FindingsIn the start-up stage, the characteristic frequency amplitude of the micro-convex body contact is obvious, the friction of the end face is abnormal, the complexity of the system increases in a short time and the bispectral entropy rises continuously in a short time. In the stable operation stage, the characteristic frequency amplitude of the micro-convex body contact varies with the intensity of the seal face friction, the seal face friction is stable and the bispectral entropy fluctuates up and down for a period of time.Originality/valueThe bispectral analysis method is applied to the seal friction monitoring, the seal frequency domain characteristics are extracted, the micro-convex body contact characteristic frequency is defined and the bispectral entropy characteristic index is proposed, which provides a certain theoretical basis for the mechanical seal friction monitoring.Peer reviewThe peer review history for this article is available at: https://publons.com/publon/10.1108/ILT-07-2023-0242/

Brain-to-brain communication during musical improvisation: a performance case study

Understanding and predicting others' actions in ecological settings is an important research goal in social neuroscience. Here, we deployed a mobile brain-body imaging (MoBI) methodology to analyze inter-brain communication between professional musicians during a live jazz performance. Specifically, bispectral analysis was conducted to assess the synchronization of scalp electroencephalographic (EEG) signals from three expert musicians during a three-part 45 minute jazz performance, during which a new musician joined every five minutes. The bispectrum was estimated for all musician dyads, electrode combinations, and five frequency bands. The results showed higher bispectrum in the beta and gamma frequency bands (13-50 Hz) when more musicians performed together, and when they played a musical phrase synchronously. Positive bispectrum amplitude changes were found approximately three seconds prior to the identified synchronized performance events suggesting preparatory cortical activity predictive of concerted behavioral action. Moreover, a higher amount of synchronized EEG activity, across electrode regions, was observed as more musicians performed, with inter-brain synchronization between the temporal, parietal, and occipital regions the most frequent. Increased synchrony between the musicians' brain activity reflects shared multi-sensory processing and movement intention in a musical improvisation task.

Bispectral analysis and information fusion technique for bearing fault classification

The feasibility and effectiveness of data fusion for the fault classification of bearing faults have been very well iterated in the literature. However, all previous endeavors have been limited to time, frequency, and time-frequency domain techniques. The use of higher-order spectral analysis (HOSA), especially Bispectrum and Trispectrum, for fault detection is gaining importance in recent studies due to the many advantages of HOSA. Bispectral features provide a valuable tool for capturing higher-order statistical relationships in signals, making them particularly effective in detecting nonlinearities and distinguishing between Gaussian and non-Gaussian data. Their robustness to noise and ability to reveal hidden information make them advantageous in applications such as vibration analysis, speech recognition, and image processing, where complex signal interactions and nonlinearity play a significant role in data interpretation and pattern recognition. This paper proposes a methodology for the fusion of the data from the vibration and the acoustic sensors for the fault detection of roller element bearings using bispectral features. Higher-order spectral characteristics are derived from vibration and acoustic sensor data, and they are fused using artificial neural networks and various other machine learning algorithms like support vector machine, K nearest neighbor, Naïve Bayes algorithm, and decision tree. This work primarily aims to evaluate the performance of each classifier when applied to the fused data, in contrast to the performance when using individual sensor data alone. The outcomes revealed that, even though the accuracy of the acoustic sensor data was lower in comparison to the vibration sensor data, which exhibited the highest performance of 100% accuracy with nearly all the classifiers, the fused data achieved remarkable results of 100% accuracy with artificial neural networks and decision trees. However, the Naïve Bayes algorithm yielded the lowest accuracy when applied to the fused data. The primary objective of this paper is to demonstrate the application of bispectrum analysis for data fusion and to enhance confidence in fault detection. It achieves this by maintaining the capability to accurately and dependably detect faults, even when a single sensor encounters issues or falls short of anticipated performance standards.

Comparison of chlorin-e6 detection efficiency by video systems with excitation wavelengths of 405nm and 635nm

BackgroundFluorescence diagnostics with two different wide field-of-view imaging systems with fluorescence excitation at 405 nm and 635 nm, respectively, were compared. Both systems include fluorescence quantification and experimental geometry normalization algorithms. MethodsA newly developed system with an excitation wavelength of 405 nm was tested on intralipid fluorescent tumor phantoms with chlorin-e6. Both, this new system and a second existing system with an excitation wavelength of 635 nm, were used for fluorescent diagnosis in six patients with basal cell carcinoma and cancer of the oral mucosa. For PDT, a red diode laser with a wavelength of 660 nm was used for all 6 patients. One patient received an additional irradiation using the red LED source of the new system ResultsThe boundaries of the lesions and the fluorescence intensity were successfully determined by both video systems. ConclusionsBoth fluorescence imaging approaches showed comparable contrast between diseased and healthy tissues. For oral mucosal cancer, a system with violet fluorescence excitation, bispectral frame analysis, and time-resolved background suppression showed better contrast between the tumor and normal tissue and effective elimination of autofluorescence. Moreover, both systems provided efficient quantification of fluorescence and gave fluorescence indices that were weakly dependent on the distance between the device and the tissue.