Signal Processing Approach Research Articles

Machine learning based system for early heart disease detection and classification using audio signal processing approach

Cardiovascular diseases (CVDs) remain a leading cause of mortality globally, accounting for approximately 17.9 million deaths annually. Traditional diagnostic methods, though useful, have limitations such as invasiveness, high cost, and delays in detecting early-stage heart conditions. This study presents a novel machine learning-based system for early heart disease detection using audio signal processing, specifically leveraging phonocardiogram (PCG) data. Features were extracted using Mel-Frequency Cepstral Coefficients (MFCCs), Delta MFCCs, and Delta-Delta MFCCs, followed by dimensionality reduction via Principal Component Analysis (PCA). Support Vector Machine (SVM) and XGBoost classifiers were used to analyze the extracted features, and their performance was optimized through an ensemble model using the Moth Flame Optimization (MFO) algorithm. The model was rigorously evaluated using accuracy, precision, recall, and F1-score metrics. The ensemble model achieved an accuracy of 99.13%, precision of 98.94%, recall of 95.05%, and an F1-score of 97.46%. The application of SMOTE for data augmentation significantly improved classification performance, highlighting its effectiveness in addressing class imbalance. The proposed system provides a non-invasive, cost-effective solution for heart disease detection and holds potential for improving diagnostic access, particularly in resource-limited settings.

Faster extraction of matrimonial advertisements from digital archives using a signal processing pipeline: a case study on a 20th-Century Spanish newspaper

ABSTRACT With the exponential growth of digitized historical materials, historians and social scientists face the daunting task of navigating vast online collections. While online archives do provide search tools to query their materials, these usually do not meet the scholars’ need to trace and store all relevant materials from the online archive. This case study shows how computer vision methods, and more specifically a signal processing approach, can be used to identify, classify and extract relevant information items from a vast historical data collection. More specifically, this study reports the results of the construction of a data pipeline that extracts matrimonial advertisements from the digitized Catalan newspaper La Vanguardia. Matrimonial advertisements can provide genuine insights into the evolution of partner preferences over time, but they are hard to collect as they are scattered over millions of digitized historical newspapers and magazines. Moreover, to study variation in partner preferences by, for example, sex, social class, matrimonial status and time period, it is necessary to store the data into a database. The pipeline that we have constructed extracts matrimonial advertisements in a stepwise fashion, encompassing identification, through binarisation and segmentation, and classification based on Optical Character Recognition. By ways of a comprehensive evaluation, both qualitatively and quantitatively, the efficacy of the pipeline for the extraction of matrimonial advertisements is demonstrated. The findings not only underscore the viability of the signal processing approach but also underscore its potential for advancing research in historical demography, family history, as well as economic history, as similar pipelines can be set up to extract other relevant newspaper items, such as, marriage, birth, death and moving announcements, job vacancies or business announcements from digitized source collections.

Beyond traditional magnetic resonance processing with artificial intelligence

Smart signal processing approaches using Artificial Intelligence are gaining momentum in NMR applications. In this study, we demonstrate that AI offers new opportunities beyond tasks addressed by traditional techniques. We developed and trained artificial neural networks to solve three problems that until now were deemed “impossible”: quadrature detection using only Echo (or Anti-Echo) modulation from the traditional Echo/Anti-Echo scheme; accessing uncertainty of signal intensity at each point in a spectrum processed by any given method; and defining a reference-free score for quantitative access of NMR spectrum quality. Our findings highlight the potential of AI techniques to revolutionize NMR processing and analysis.

Application of Dual-Tree Complex Wavelet Transform in Islanding Detection for a Hybrid AC/DC Microgrid with Multiple Distributed Generators

This paper presents the design and validation of a novel adaptive islanding detection method (AIDM) for a hybrid AC/DC microgrid network using a combination of Artificial Intelligence (AI) and Signal Processing (SP) approaches. The proposed AIDM is aimed to detect and discriminate between the different fault/disturbance conditions that result in islanding and/or non-islanding conditions in a hybrid microgrid. For the islanding and non-islanding conditions detection by the AIDM, firstly, fault/disturbance signals are obtained from a test microgrid. Secondly, these signals are decomposed using Dual-Tree Complex Wavelet Transform. Thirdly, a Synthetic Minority Oversampling Technique (SMOTE) is applied for data preprocessing to increase the accuracy of the classifier. Finally, an artificial neural network (ANN) is used as the classifier for training and testing the proposed AIDM for different microgrid configurations and event scenarios. The proposed method is tested with different data categories from three different microgrid test systems with different scenarios. All modeling and simulations are executed in MATLAB Simulink Version 2023a. Results indicate that the proposed scheme could detect and discriminate between islanding and non-islanding conditions accurately in terms of dependability, precision, and accuracy. An average accuracy of 99–100% could be achieved when tested and validated with microgrid networks adapted from IEEE 13-bus systems.

Adaptive nonlinear filtering algorithms for removal of non-stationary noise in electronystagmographic signals

Non-stationary physiological noise poses significant difficulties due to its time-varying and previously unknown characteristics. When processing electronystagmographic signals, linear filtering can distort diagnostically significant rapid changes caused by saccadic eye movements. In such cases, nonlinear filters based on robust estimators are more appropriate, whereas linear filtering effectively reduces white noise in parts of a signal with linear behaviour. Therefore, an adaptive signal processing approach that varies in nonlinearity from highly nonlinear robust estimation to linear averaging and combines their benefits appears promising. We have proposed a low-complexity adaptive method for switching filter sets and relevant filter parameter settings based on the estimated noise level and local signal behaviour. This method does not require time for filter parameter modification and does not need prior information on the signal model and noise variance. Based on this method, we have designed adaptive nonlinear filtering algorithms to exploit the advantages of both the nonlinear robust and linear averaging estimators. We have evaluated the filtering quality statistically using the minimum mean square error criteria and the maximum signal-to-noise ratio for a model signal with different levels of additive Gaussian noise. The proposed real-time adaptive filtering algorithms demonstrate a significant efficiency improvement compared to the commonly used filters. The proposed adaptive myriad algorithm achieves the highest efficiency by adjusting a sample myriad linearity parameter depending on the local estimate of a signal scale and changing the sliding window length and the coefficient affecting the linearity parameter.

Experimental analysis of wheel and bogie frame transfer functions for on-board measurements of rail roughness

Acceleration measurements on in-service rail vehicles give many valuable insights into track condition. These measurements are favourable in terms of measurement frequency, no need for additional track possession for measurements, operator safety, etc. The collected acceleration data however needs to be further processed to extract more detailed information on rail surface defects. To derive rail roughness from bogie frame acceleration, a complex signal processing approach is required, as well as determining the dynamic parameters of the track, vehicle, and operational conditions. In this paper, a method to evaluate the influence of resilient wheel and bogie frame on the acceleration data received from bogie frame-mounted accelerometers is described. The method is based on a standstill measurement of frequency response functions on wheel and bogie frame positions using an impact hammer and accelerometers. Following the preliminary results of bogie acceleration measurements, in-situ wheel receptance measurements were carried out on the same tramway vehicle in a standstill position, to determine the transfer function between the wheel-rail contact point and the position of the accelerometer mounted on the wheel frame. After the experimental study, a discussion of their potential application in the method for deriving rail roughness from vibration data is presented.

Wavelet-based arcing signal source localization algorithm using a compact multi-square microstrip antenna

Ensuring power system safety involves effective arc fault detection and localization. Existing devices struggle to differentiate between normal and abnormal conditions, especially in confined spaces, posing precision challenges. Strategically placing antennas around the arc helps detect electromagnetic radiation, even in limited areas, enabling valuable data collection for real-time monitoring. To address these challenges, this paper proposes integrating experimental work using a compact multi-square microstrip antenna and signal processing techniques. The study compares the effectiveness of two signal processing approaches: Discrete Wavelet Transform (DWT), and Continuous Wavelet Transform (CWT). These techniques separate genuine arc signals from background noise by identifying unique characteristics and isolating the dominant frequency. The Time of Arrival (ToA) is measured and used in Least Square and Gauss-Jordan Elimination methods to calculate the arc source location. The outcomes illustrate the precision of the proposed model in detecting and pinpointing arc source signals, with error margins ranging from 0.0615 to 0.0713 m for the CWT technique, 0.0688 to 0.0789 m for the DWT technique, and 0.0799 to 0.0844 m from the actual signal captured. These results hold promise for enhancing the integration of experimental approaches in assessing arcing conditions, thereby addressing challenges in insulation systems.

Graph signal processing and graph learning approaches to Schizophrenia pattern identification in brain Electroencephalogram

The detection of Schizophrenia (SZ) directly from brain Electroencephalogram (EEG) signals has recently gained importance. Traditionally, EEG-based SZ detection is done by either manually extracting features from each EEG channel and using Machine Learning classifiers or by Deep Learning-based automated detection. These methods neglect the functional interactions between spatially distributed brain regions. This study proposes a graph signal processing and graph learning framework to detect SZ. Here, the individual channels’ features and the global interactions are combined into a unified graph signal (GS) representation. The proposed representation consists of the GS values and the underlying connectivity network. An SZ-specific feature, namely, the permutation entropies of each electrode’s signal, is considered as the GS values. The graph learning method learns the underlying network from a collection of GS observations. The learned network serves as the Fourier basis for the graph Fourier and wavelet transform. Utilizing these transforms, the graph spectral features are extracted from GSs. Lastly, the extracted features are classified using a set of Machine Learning models. The proposed graph signal processing and graph learning method is an effective approach to decode Schizophrenia patterns in brain EEG signals and outperform the existing approaches.

Optimal prototype filter design in GFDM systems for self-interference elimination: A novel signal processing approach

We present an innovative conceptual framework and a comprehensive mathematical model to advance the understanding and mitigation of self-interference phenomena within generalized frequency division multiplexing (GFDM). By introducing a novel analytical perspective, we decompose the self-interference effects inherent to GFDM into two orthogonal constituents through a vectorized representation. Our elucidation of the self-interference components in terms of prototype filter parameters in the frequency domain is of particular significance. This theoretical characterization allows us to derive explicit analytical expressions, thereby paving the way for the proposition of an optimal filter design strategy that effectively mitigates self-interference distortions within GFDM systems. Our investigation reveals a noteworthy linkage between the required bandwidth allocation for individual subcarriers and the sub-symbol configuration within the proposed optimal prototype filter. This relationship underscores the filter’s adeptness in optimizing spectrum utilization across the system. Through an analytical examination of the bit error rate (BER) performance within the GFDM framework, we establish the superior efficacy of our proposed optimal filter design relative to contemporary approaches documented in extant literature. Validation of our analytical findings is conducted via meticulous computer simulations, where a strong concurrence between the analytical predictions and the observed simulation outcomes is manifest.

LS-based multipath channel measurement method using software defined radio platform

Multipath channel measurement is the foundation of multipath channel modeling and analysis. Recently, the software defined radio (SDR) has provided new ideas for the design of multipath channel measurement systems due to universality and reconfigurability. Therefore, this paper introduces a multipath channel measurement method applicable to various SDR platforms. At first, to enhance the resolution of multipath measurements, a signal processing approach combining the least squares (LS) estimation algorithm within the SDR framework is proposed. Furthermore, to mitigate LS estimation errors stemming from high correlation among baseband signals, a scrambled measurement signal is introduced and its effectiveness is demonstrated through eigenvalue decomposition. Next, the systematic errors of In-phase and Quadrature(IQ) imbalance and bandwidth limitation are further analyzed and addressed within the SDR framework. Finally, the proposed measurement method is implemented based on a practical universal software radio peripheral (USRP) device and validated under simulated and real channels. The proposed measurement method mainly focuses on the baseband signal processing within the software component of SDR, making it applicable to most general USRP devices. The experiment results demonstrate that multipath channel measurement results with high accuracy can be obtained.

Time domain characterization of nonstationary low-Mach number aeroacoustic sources using principal component analysis.

This paper presents the use of principal component analysis (PCA) for time domain microphone array denoising to characterize an impulsive aeroacoustic source, which is illustrated with the aeroacoustic emission caused by a vortex ring/edge interaction. Prior studies have used signal processing approaches that required assumptions about the source directivity or user intervention at low signal-to-noise ratio (SNR) conditions. In this context, PCA, a matrix decomposition tool which identifies the most common features across an ensemble of observations, provides a data-driven (hands-off) approach to signal processing. For microphone array time series, particular attention is paid to the temporal alignment of the signals to facilitate PCA. A time domain approach is necessary when sources are impulsive and nonstationary. Two such signal arrangements are discussed in this work. Results from this method are in good agreement with theory, validated by prior results using an ensemble averaging approach requiring user support. Furthermore, the results of this method are improved when compared to the ensemble averaging approach without user intervention. A SNR limit is identified where PCA becomes less effective for the vortex/edge interaction problem. This SNR limit is intended to aid in the design of similar future experiments.

Identification of Power Quality Disturbances in Electrical Distribution System using Fast Fourier Transforms and Super Learner Ensembles

Currently, the use of non-linear loads and equipment, as well as renewable energy sources injected into the power system, tends to increase. As a result, the waveform of the electrical signal changes, and distortion occurs in the distribution system, which affects the quality and reliability of the electrical system. Importantly, sometimes this leads to malfunctions in protection equipment. This paper presents the algorithm for power quality disturbance (PQD) identification in electrical distribution systems, which involves three main steps: (1) Generating simulated waveforms using a signal processing approach; (2) extracting features using the Fast Fourier Transforms (FFT) technique; and (3) identifying the type of PQD using Super Learner Ensembles (SLE), which employs cross-validation to assess the performance of multiple machine learning models. Subsequently, the model’s efficiency is verified and tested using data from electronic energy meters installed in the distribution system of the Provincial Electricity Authority (PEA). The accuracy resulting from synthetic and experimental data sets is 99.90% and 99.69%, respectively. The results indicate that the model performs well in identifying power quality disturbances and achieves high accuracy.

Real-time motion artifact suppression using convolution neural networks with penalty in fNIRS.

Removing motion artifacts (MAs) from functional near-infrared spectroscopy (fNIRS) signals is crucial in practical applications, but a standard procedure is not available yet. Artificial neural networks have found applications in diverse domains, such as voice and image processing, while their utility in signal processing remains limited. In this work, we introduce an innovative neural network-based approach for online fNIRS signals processing, tailored to individual subjects and requiring minimal prior experimental data. Specifically, this approach employs one-dimensional convolutional neural networks with a penalty network (1DCNNwP), incorporating a moving window and an input data augmentation procedure. In the training process, the neural network is fed with simulated data derived from the balloon model for simulation validation and semi-simulated data for experimental validation, respectively. Visual validation underscores 1DCNNwP's capacity to effectively suppress MAs. Quantitative analysis reveals a remarkable improvement in signal-to-noise ratio by over 11.08 dB, surpassing the existing methods, including the spline-interpolation, wavelet-based, temporal derivative distribution repair with a 1 s moving window, and spline Savitzky-Goaly methods. Contrast-to-noise ratio (CNR) analysis further demonstrated 1DCNNwP's ability to restore or enhance CNRs for motionless signals. In the experiments of eight subjects, our method significantly outperformed the other approaches (except offline TDDR, t < -3.82, p < 0.01). With an average signal processing time of 0.53 ms per sample, 1DCNNwP exhibited strong potential for real-time fNIRS data processing. This novel univariate approach for fNIRS signal processing presents a promising avenue that requires minimal prior experimental data and adapts seamlessly to varying experimental paradigms.

EDA-Graph: Graph Signal Processing of Electrodermal Activity for Emotional States Detection.

The continuous detection of emotional states has many applications in mental health, marketing, human-computer interaction, and assistive robotics. Electrodermal activity (EDA), a signal modulated by sympathetic nervous system activity, provides continuous insight into emotional states. However, EDA possesses intricate nonstationary and nonlinear characteristics, making the extraction of emotion-relevant information challenging. We propose a novel graph signal processing (GSP) approach to model EDA signals as graphical networks, termed EDA-graph. The GSP leverages graph theory concepts to capture complex relationships in time-series data. To test the usefulness of EDA-graphs to detect emotions, we processed EDA recordings from the CASE emotion dataset using GSP by quantizing and linking values based on the Euclidean distance between the nearest neighbors. From these EDA-graphs, we computed the features of graph analysis, including total load centrality (TLC), total harmonic centrality (THC), number of cliques (GNC), diameter, and graph radius, and compared those features with features obtained using traditional EDA processing techniques. EDA-graph features encompassing TLC, THC, GNC, diameter, and radius demonstrated significant differences (p < 0.05) between five emotional states (Neutral, Amused, Bored, Relaxed, and Scared). Using machine learning models for classifying emotional states evaluated using leave-one-subject-out cross-validation, we achieved a five-class F1 score of up to 0.68.

Применение машинного обучения и интеллектуального анализа данных в автоматизированной системе неразрушающего вихретокового контроля поверхностного слоя деталей подшипников

Changing the properties of the material during physical and mechanical processing can significantly reduce the working life of the manufactured product, therefore it is important to control the quality of the surface layer of the parts. To solve this problem, non-destructive testing techniques such as etching, visual, capillary, magnetic powder, ultrasonic, vibration, eddy current methods are used at bearing enterprises. The article discusses the physical foundations of the presented techniques and provides their comparative analysis. Machine vision and digital signal processing approaches can be used to automate the processing of the results of non-destructive testing of the surface layer of bearing parts within the framework of the Industry 4.0 concept. From the point of view of productivity and the possibility of integration into the production system, the eddy current method is the most promising, the result of surface control in this way is an array of digital values. The development of modern methods of information analysis makes it possible to efficiently process a large amount of data, and machine learning makes it possible to solve problems of classification, regression, etc. This article provides methodological support for the development and application of an automated eddy current control system using machine learning and data mining methods. The works of scientists devoted to the processing of the results of the shock control of various objects, including bearing parts, are considered, it is noted that previously attention had not been paid to the issue of a reasonable choice of a machine learning model for recognizing defects on the surface of parts. The possibility of using the median polishing method to transform the eddy current signal is shown. The development and implementation of a bearing defect recognition system based on the methodological support presented in this paper can significantly improve the efficiency of product quality control and optimize the technological process.

Motion artifacts in capacitive ECG monitoring systems: a review of existing models and reduction techniques.

Current research focuses on improving electrocardiogram (ECG) monitoring systems to enable real-time and long-term usage, with a specific focus on facilitating remote monitoring of ECG data. This advancement is crucial for improving cardiovascular health by facilitating early detection and management of cardiovascular disease (CVD). To efficiently meet these demands, user-friendly and comfortable ECG sensors that surpass wet electrodes are essential. This has led to increased interest in ECG capacitive electrodes, which facilitate signal detection without requiring gel preparation or direct conductive contact with the body. This feature makes them suitable for wearables or integrated measurement devices. However, ongoing research is essential as the signals they measure often lack sufficient clinical accuracy due to susceptibility to interferences, particularly Motion Artifacts (MAs). While our primary focus is on studying MAs, we also address other limitations crucial for designing a high Signal-to-Noise Ratio (SNR) circuit and effectively mitigating MAs. The literature on the origins and models of MAs in capacitive electrodes is insufficient, which we aim to address alongside discussing mitigation methods. We bring attention to digital signal processing approaches, especially those using reference signals like Electrode-Tissue Impedance (ETI), as highly promising. Finally, we discuss its challenges, proposed solutions, and offer insights into future research directions.

Remote sensing object detection with feature-associated convolutional neural networks

Neural networks have become integral to remote sensing data processing. Among neural networks, convolutional neural networks (CNNs) in deep learning offer numerous advanced algorithms for object detection in remote sensing imagery, which is pivotal in military and civilian contexts. CNNs excel in extracting features from training samples. However, traditional CNN models often lack specific signal assumptions tailored to remote sensing data at the feature level. In this paper, we propose a novel approach aimed at effectively representing and correlating information within CNNs for remote sensing object detection. We introduce object tokens and incorporate global information features in embedding layers, facilitating the comprehensive utilization of features across multiple hierarchical levels. Consideration of feature maps from images as two-dimensional signals, matrix image signal processing is employed to correlate features for diverse representations within the CNN framework. Moreover, hierarchical feature signals are effectively represented and associated during end-to-end network training. Experiments on various datasets demonstrate that the CNN model incorporating feature representation and association outperforms CNN models lacking these elements in object detection from remote sensing images. Additionally, integrating image signal processing enhances efficiency in end-to-end network training. Various signal processing approaches increase the process ability of the network, and the methodology could be transferred to other specific and well-defined task.

Application of signal processing techniques for the spectroscopic analysis of dolutegravir and lamivudine: a comparative assessment and greenness appraisal

HIV treatment has greatly improved over the years, with the introduction of antiretroviral drugs that target the virus and suppress its replication. Dolutegravir and lamivudine are two such antiretroviral drugs that are commonly used in HIV treatment regimens. Herein, three spectrophotometric methods manipulating ratio spectra were developed for the simultaneous analysis of dolutegravir and lamivudine in their binary mixtures. These methods include mathematical processing stages like ratio difference method or signal processing approaches such as the first derivative of the ratio spectra, and continuous wavelet transform. The developed spectrophotometric methods exploit the characteristic spectral differences between dolutegravir and lamivudine in order to quantify them simultaneously. These methods have shown promising results in terms of sensitivity and selectivity as validated per the ICH guidelines. Moreover, these methods offer a straightforward and economical alternative to more intricate analytical methodologies like high-performance liquid chromatography. By incorporating the analytical eco-scale and AGREE for greenness evaluation of the proposed methods, we can further ensure that these techniques are effective and environmentally friendly, aligning with the principles of green chemistry. This evaluation will provide a comprehensive understanding of the environmental friendliness of these spectrophotometric methods in pharmaceutical analysis.

Terahertz nondestructive layer thickness measurement and delamination characterization of GFRP laminates

Three-dimensional nondestructive location of defects, such as delaminations, in glass fiber-reinforced polymer (GFRP) laminates remains a challenge. Terahertz techniques have shown promise, but their success relies on advanced signal-processing techniques applied to the raw data. The current work presents an advance in the quantitative three-dimensional nondestructive location of delaminations in GFRP laminates. Namely, terahertz time-of-flight tomography, together with adaptive sparse deconvolution based on a two-step iterative shrinkage-thresholding algorithm, as well as the Canny edge-detection operator, are employed in nondestructive measurement of layer thicknesses and to extract the edges of delaminations in GFRP laminates. Compared with the commonly used frequency wavelet-domain deconvolution method or previous implementations of sparse deconvolution, the adaptive sparse deconvolution approach provides a clearer and rapid stratigraphic reconstruction of GFRP laminates while yielding accurate thickness information for each resin layer and low sensitivity to noise. In addition, the proposed edge-detection algorithm presents better performance in estimating the transverse size of delaminations, compared to the common −6 dB drop approach. Finally, our experiments verify the effectiveness of the proposed signal and image processing approaches for three-dimensional localization of delamination defects in GFRP laminates and the quantitative characterization of layer thickness.

Tensor low-rank and sparse decomposition and its application in bearing fault information separation

Abstract Properly separating fault information from noisy measured signals is crucial for effective bearing health sensing. However, conventional fault information separation methods face challenges such as predefined model parameters and poor noise robustness. Additionally, with the advent of Industry Big Data, multichannel monitoring signals present significant challenges for traditional single decomposition approaches. To address these challenges and fully extract potential fault information, this paper introduces a tensor low-rank and sparse decomposition (tensor LRSD) approach for multichannel signal processing. Inspired by matrix LRSD, we construct a tensor LRSD model that adaptively decomposes the signal into a tensor sparse term containing fault information and a low-rank term representing the intrinsic signal pattern. To further enhance the decomposition performance, a maximum correlation-based selection strategy is designed. This strategy evaluates the correlation between each tensor slice and selects appropriate tensor sparse terms for fault information extraction. Simulation analysis and two experimental studies involving typical bearing failures are implemented to verify the capability and superiority of the presented tensor LRSD approach. The consequences demonstrate that the presented method outperforms conventional techniques, showcasing its capability to effectively separate fault information from noisy signals.