Signal Classification Method Research Articles

ECG signal classification based on DWT denoising and XGBoost

Electrocardiogram signal (ECG) can directly reflect the health status of the heart, and is an important basis for prevention and treatment of heart disease. In order to realize ECG signal classification effectively, an ECG signal classification method based on discrete wavelet transform and Xgboost is proposed in this paper, which improves the accuracy of ECG signal classification. Specifically, we first divide, select and downsample the heart beat of the data, and then use the discrete wavelet transform to reduce the noise of the data set to improve the signal to noise ratio. Finally, we use Xgboost algorithm as the classifier to classify the data, and get 98.7% accuracy rate on the test set. In each module, we carried out comparative experiments to verify the correctness and rigor of our method. In addition, in order to make up for the lack of interpretability of traditional machine learning methods, we defined the importance of each feature according to the information gain generated by different features to the model during the training of XGBoost, and then got the key bands that should be paid attention to when distinguishing heart beats, which improved the interpretability of the model. It also provides a scientific basis for the classification of ECG signals and practical medical work.

Landmine Detection Using Electromagnetic Time Reversal‐Based Methods: 2. Performance Analysis of TR‐MUSIC

AbstractIn this paper, a series of numerical simulations are conducted for various 2D and 3D configurations to demonstrate the performance of the Time Reversal MUltiple SIgnal Classification (TR‐MUSIC) method. The results reveal the excellent performance of TR‐MUSIC, taking into account the effects of noise, soil types (both homogeneous and layered), and their electrical parameters, as well as different types of targets (varying in number, size, shape, and location). Additionally, unlike other electromagnetic TR‐based techniques, TR‐MUSIC offers very high resolution (on the order of /10 or higher) with a reasonable number of sensors, enabling the detection of multiple closely spaced targets. In TR‐based methods, reflections from the object(s) or landmine(s) are crucial and are determined by the difference between the constitutive parameters (e.g., permittivity, permeability, and conductivity) of the landmine(s) and their surrounding medium. Therefore, TR‐based approaches, similar to conventional GPR‐based approaches, are suitable for detecting objects or landmines with significant differences in constitutive parameters compared to their immersion medium. This research primarily focuses on metallic objects or landmines.

End-to-End Signal Classification in Signed Cumulative Distribution Transform Space.

This paper presents a new end-to-end signal classification method using the signed cumulative distribution transform (SCDT). We adopt a transport generative model to define the classification problem. We then make use of mathematical properties of the SCDT to render the problem easier in transform domain, and solve for the class of an unknown sample using a nearest local subspace (NLS) search algorithm in SCDT domain. Experiments show that the proposed method provides high accuracy classification results while being computationally cheap, data efficient, and robust to out-of-distribution samples with respect to the existing end-to-end classification methods. The implementation of the proposed method in Python language is integrated as a part of the software package PyTransKit [1].

Non-Intrusive System for Honeybee Recognition Based on Audio Signals and Maximum Likelihood Classification by Autoencoder.

Artificial intelligence and Internet of Things are playing an increasingly important role in monitoring beehives. In this paper, we propose a method for automatic recognition of honeybee type by analyzing the sound generated by worker bees and drone bees during their flight close to an entrance to a beehive. We conducted a wide comparative study to determine the most effective preprocessing of audio signals for the detection problem. We compared the results for several different methods for signal representation in the frequency domain, including mel-frequency cepstral coefficients (MFCCs), gammatone cepstral coefficients (GTCCs), the multiple signal classification method (MUSIC) and parametric estimation of power spectral density (PSD) by the Burg algorithm. The coefficients serve as inputs for an autoencoder neural network to discriminate drone bees from worker bees. The classification is based on the reconstruction error of the signal representations produced by the autoencoder. We propose a novel approach to class separation by the autoencoder neural network with various thresholds between decision areas, including the maximum likelihood threshold for the reconstruction error. By classifying real-life signals, we demonstrated that it is possible to differentiate drone bees and worker bees based solely on audio signals. The attained level of detection accuracy enables the creation of an efficient automatic system for beekeepers.

DOA Estimation on One-Bit Quantization Observations through Noise-Boosted Multiple Signal Classification.

Due to the low-complexity implementation, direction-of-arrival (DOA) estimation-based one-bit quantized data are of interest, but also, signal processing struggles to obtain the demanded estimation accuracy. In this study, we injected a number of noise components into the receiving data before the uniform linear array (ULA) composed of one-bit quantizers. Then, based on this designed noise-boosted quantizer unit (NBQU), we propose an efficient one-bit multiple signal classification (MUSIC) method for estimating the DOA. Benefiting from the injected noise, the numerical results show that the proposed NBQU-based MUSIC method outperforms existing one-bit MUSIC methods in terms of estimation accuracy and resolution. Furthermore, with the optimal root mean square (RMS) of the injected noise, the estimation accuracy of the proposed method for estimating DOA can approach that of the MUSIC method based on the complete analog data.

GW-MUSIC focusing algorithm with high accuracy for composite damage diagnosis

The Guided Wave (GW)-based Multiple Signal Classification (MUSIC) method for damage imaging in composite structures offers high-resolution and flexible sensor array placement, demonstrating considerable potential for precise damage localization. However, the application to real aircraft composite structures, characterized by complex structural features, presents substantial challenges. These include complex boundary reflections, pronounced anisotropy, and diminished scattered signals from damage sites. This paper presents a novel single-peak anisotropy-compensated MUSIC method for damage imaging of complex composites. This method, designed for improved localization accuracy, combines a self-excited calibration strategy to mitigate anisotropy with single wave peak focusing to amplify signals and reduce boundary reflections. Experimental validation on a complex composite wing structure demonstrated significant enhancements in localization precision, affirming the method's efficacy.

Spatial Spectrum Estimation of Weak Scattering Wave Signal in Range-Doppler Domain

How to enhance the desired signal with low signal-to-noise ratio (SNR) is a difficult problem in the estimation process of the direction-of-arrival (DOA) of the target scattering wave signal. In this paper, the feasibility of spatial spectrum estimation in the Range-Doppler (RD) domain is analyzed in principle, and the SNR gain expression of weak scattering wave signal is derived when constructing multi-snapshots virtual array data. On this basis, the mutual eigenvector singular value decomposition (MESVD) method based on RD domain mode excitation is proposed, which can robustly and effectively estimate the direction of the coherent weak signals. Simulation experiments verify that the RD domain spectral estimation method has the ability to simultaneously obtain the direction of multiple weak target scattering waves, and the direction-finding accuracy can reach the Cramer–Rao bound (CRB) of conventional spectral estimation method. The results of Monte Carlo experiments show that the root-mean-square-error (RMSE) of azimuth estimation of RD domain spatial spectrum estimation method is 5.76° lower than that of a conventional multiple signal classification (MUSIC) method. In addition, the practicability of the proposed method is demonstrated by comparing the DOA estimation results of a set of real data with Automatic Dependent Surveillance-Broadcast (ADS-B) data.

Deep Learning-based Thigh Muscle Investigation Using MRI For Prosthetic Development for Patients Undergoing Total Knee Replacement (TKR).

A prosthetic device is designed based on the quantitative analysis of muscle MRI which will improve the muscle control achieved with functional electrical stimulation/ guided robotic exoskeletons. Electromyography (EMG) provides muscle functionality information while MRI provides the physiological and functionality of muscles. The sensor feedbacks were used for the bionic prosthesis, but the length of muscle using image processing was not correlated. To investigate and perform qualitative and quantitative assessment of thigh muscle using MRI. The objective of the work is to improve the existing VAG signal classification method to diagnose abnormality using MRI for patients undergoing Total knee replacement (TKR). A deep learning method for qualitative and quantitative assessment of thigh muscle is done using MRI. In existing prosthetic devices, electrical measurements of a person's muscles are obtained using surface or implantable electrodes. Several methods were used for the classification and diagnostic processes. The existing methods have drawbacks in feature extraction and require experts to design the system. This work combines medical image processing and orthopaedic prosthetics to develop a therapeutic method. This design provides much more precise control of prosthetic limbs using the image processing technique. The hybrid CNN swarm-based method measures the muscle structure and functions. Along with the sensor readings, these details are combined for prosthetic control. The implementation was carried out in MATLAB, Sketchuppro, and Arduino IDE. A combined swarm intelligence and deep learning method were proposed for qualitative and quantitative assessment of thigh muscle. The prosthetic device choice was done from the scanned MRI image like Humerus-T prosthetics, segmental prosthesis and arthrodesis prosthesis. The investigation was done for the Total knee replacement (TKR) approach.

Диагностика сигналов ЭКГ на основе цифровой обработки и оптимизированной модели трансформера

Heartbeat disorders are considered one of the main maladies that cause mortality. Therefore, their precocious diagnosis via ECG signal is critical for introducing prompt therapy. The advanced automatic classification of ECG signals has the potential to save cardiologists a tremendous amount of time while simultaneously decreasing the chance of misdiagnosis. The dilemma of massive parameters is troubling the current methods of ECG signal classification. Most recent methods exhibit inadequate performance for diagnosing ECG signals in the inter-patient mode. In an attempt to deal with the above limitations, this study offers an innovative, efficient, and end-to-end model. The suggested model uses the optimized transformer framework to classify the heartbeats according to the "Association for the Advancement of Medical Instrumentation, AAMI," and obeys the inter-patient setting. We constructed an efficient architecture called the optimized network to substitute the Self Attention Unit (SAU) in the encoder part of the transformer model. The suggested model, which includes an optimized network, outperforms the SAU-based transformer model and requires fewer computations. A robust embedding architecture based on a Convolutional Neural Network (CNN) with a Squeeze and Excitation (SE) network-based attention scheme that has been used for weighting the Local Heartbeat Shape Pattern (LHSP) features is presented. The introduced model exceeds the state-of-the-art. An extensive test has been done to compare the achievements of the suggested model with those of the cardiologists. The results proved the closeness of their performances.

C-Slot Circular Polarized Antenna for Hybrid Energy Harvesting and Wireless Sensing

This paper presents a new hybrid energy harvesting on electromagnetic solar for wireless energy harvesting of ambient from sensors of low-power devices. The axial ratio (AR) requirements produce Left-Hand Circular Polarization (LHCP) and Right-Hand Circular Polarization (RHCP) and simultaneously produce a 90-degree phase difference during energy harvesting, adopting a new design in designing a dual-feed broadband circular polarized (CP) antenna. To get the frequency band 2.3–2.4 GHz, we propose a C-Slot antenna with a circular patch dual feed. To estimate the diversity of the phase and magnitude output of the feed configuration under AR value, we used a 50 Ohm feed network output of the characteristic analysis for a dual feed CP antenna. An Axial ratio frequency range of less than 3 dB is achieved using polarization analysis with different branch channel couplers. To produce a DC output voltage, a high-frequency rectifier circuit embedded with a thin-film solar cell on the antenna is then connected to two T-junction power divider rectifiers, resulting in a high-efficiency design. A complete system-level analysis will include multiple signal classification methods of powered ambient RF energy using a wireless energy harvesting array that proposes a compact structure and demonstrates optimal configuration. Reliable operation in typical indoor environments indicates a self-contained sensor Node. Therefore, it has significant implications for powering small electronics and wireless sensor applications independently of the IoT Network or real implementation telecommunications industry.

Gradient Boosting for Predicting the Relation Between Bio-medical Signals and Seizures Using LGBM and XGBoost

Background and aim: In recent years, research in the fields of brain-computer interfacing techniques and related areas are developing at a very rapid rate with the help of exploding of Artificial Intelligence, Machine Learning and Deep Learning. A new concept of Gradient Boosting has become popular research area among the researchers related to the field of automatic classification of Electroencephalograph (EEG) signals for predication of mental health issues like seizures. Methods: However effective feature extraction from EEG and accurately classify them with efficient classifiers is still an important task and attracted wide attention in this area. Therefore in this paper, we presented the detailed mathematical analysis of these methods and ensemble learnings based EEG signals classification method for seizures classification in EEG using Extreme Gradient Boosting Model such as Light Gradient Boosting Machine Learning (LGBM) and XGBoost. Results: Time-frequency domain based non-linear features are selected from preprocessed EEG Dataset, and PCA (Principal Component Analysis) is used for dimensionality reduction for features engineering, then optimized feature based training and testing is done for two class classification in ensemble learning method i.e. LGBM and XGBoost. Finally, both models are tested with dataset of University of Bonn, Germany to classify the signals. Conclusions: In addition this paper highlights the Correlation Analysis Methodology to Identify Strong Predictor and Attributes Correlation-based Attribute Ranking for the Feature Engineering which has proved to be more efficient in EEG signals Classification and provide comparative analysis with other existing models for performance evaluation in terms of accuracy which is 87.34 and 92.31 for LBGM and XGBoost, sensitivity of 85.21 and 90.18 and specificity of 83.0 and 90.04 for LBGM and XGBoost.

Improved empirical mode decomposition bagging RCSP combined with Fisher discriminant method for EEG feature extraction and classification

BackgroundTraditional Common Spatial Pattern (CSP) algorithms for Electroencephalogram (EEG) signal classification are sensitive to noise and can produce low accuracy in small sample datasets. New methodTo solve the problem, an improved Empirical Mode Decomposition (EMD) Bagging Regularized CSP (RCSP) algorithm is proposed. It filters EEG signals through improved EMD, inhibits high-frequency noise, retains effective information in the characteristic frequency band, and uses Bagging algorithm for data reconstruction. Feature extraction is performed with regularization of spatial patterns and Fisher linear discriminant analysis for feature classification. T-test is used for classification. ResultsThe improved EMD Bagging RCSP algorithm has improved accuracy and robustness compared to CSP and its derivatives. The average classification rate is increased by about 6%, demonstrating the effectiveness and correctness of the proposed algorithm.Comparison with existing methods: The proposed algorithm outperforms CSP and its derivatives by retaining effective information and inhibiting high-frequency noise in small sample EEG datasets. ConclusionsThe proposed EMD Bagging RCSP algorithm provides a reliable and effective method for EEG signal classification and can be used in various applications, including brain-computer interfaces and clinical EEG diagnosis.

Intelligent non-cooperative optical networks: Leveraging scattering neural networks with small training data

Artificial intelligence (AI) is enabling intelligent communications where learning based signal classification simplifies optical network signal allocation and shifts signal processing pressure to each network edge. This work proposes a non-orthogonal signal waveform framework that leverages its unique spectral compression characteristic as a user address for efficiently forwarding messages to target users. The primary focus of this work lies in the physical layer intelligent receiver design, which can automatically identify different received signal formats without preamble notification in a non-cooperative communication approach. Traditional signal classification methods, such as convolutional neural network (CNN), rely on extensive training, resulting in a heavy dependency on large training datasets. To overcome this limitation, this work designs a specific two-layer scattering neural network that can accurately separate signals even when the training data is limited, leading to reduced training complexity. Its performance remains robust in diverse transmission conditions. Furthermore, the scattering neural network is interpretable because features are extracted based on deterministic wavelet filters rather than training based filters.

A Heart Sound Signal Classification Method Based on the Mixed Characteristics of Mel Cepstrum Coefficient and Second-Order Spectrum

A Heart Sound Signal Classification Method Based on the Mixed Characteristics of Mel Cepstrum Coefficient and Second-Order Spectrum

A Review on the Classification of Partial Discharges in Medium-Voltage Cables: Detection, Feature Extraction, Artificial Intelligence-Based Classification, and Optimization Techniques

Medium-voltage (MV) cables often experience a shortened lifespan attributed to insulation breakdown resulting from accelerated aging and anomalous operational and environmental stresses. While partial discharge (PD) measurements serve as valuable tools for assessing the insulation state, complexity arises from the presence of diverse discharge sources, making the evaluation of PD data challenging. The reliability of diagnostics for MV cables hinges on the precise interpretation of PD activity. To streamline the repair and maintenance of cables, it becomes crucial to discern and categorize PD types accurately. This paper presents a comprehensive review encompassing the realms of detection, feature extraction, artificial intelligence, and optimization techniques employed in the classification of PD signals/sources. Its exploration encompasses a variety of sensors utilized for PD detection, data processing methodologies for efficient feature extraction, optimization techniques dedicated to selecting optimal features, and artificial intelligence-based approaches for the classification of PD sources. This synthesized review not only serves as a valuable reference for researchers engaged in the application of methods for PD signal classification but also sheds light on potential avenues for future developments of techniques within the context of MV cables.

Comparative study of time-frequency transformation methods for ECG signal classification

In this study, we highlighted the growing need for automated electrocardiogram (ECG) signal classification using deep learning to overcome the limitations of traditional ECG interpretation algorithms that can lead to misdiagnosis and inefficiency. Convolutional neural networks (CNN) application to ECG signals is gaining significant attention owing to their exceptional image-classification capabilities. However, we addressed the lack of standardized methods for converting 1D ECG signals into 2D-CNN-compatible input images by using time-frequency methods and selecting hyperparameters associated with these methods, particularly the choice of function. Furthermore, we investigated the effects of fine-tuned training, a technique where pre-trained weights are adapted to a specific dataset, on 2D-CNNs for ECG classification. We conducted the experiments using the MIT-BIH Arrhythmia Database, focusing on classifying premature ventricular contractions (PVCs) and abnormal heartbeats originating from ventricles. We employed several CNN architectures pre-trained on ImageNet and fine-tuned using the proposed ECG datasets. We found that using the Ricker Wavelet function outperformed other feature extraction methods with an accuracy of 96.17%. We provided crucial insights into CNNs for ECG classification, underscoring the significance of fine-tuning and hyperparameter selection in image transformation methods. The findings provide valuable guidance for researchers and practitioners, improving the accuracy and efficiency of ECG analysis using 2D-CNNs. Future research avenues may include advanced visualization techniques and extending CNNs to multiclass classification, expanding their utility in medical diagnosis.

Model of an experimental bench for detecting defects in pipelines

Any technological system consists of devices interconnected by pipelines. Often, the length of pipelines is quite large. Checking their integrity is relevant and very costly in terms of time and human resources. It is not possible to create a real emergency situation at an existing production facility. It is possible to obtain information about the presence of a defect at an industrial facility only by simulating such a situation. For this, an experimental stand has been developed that allows monitoring the functioning of a closed air duct system of a simulated object. Situations are modeled under various external influences: when the dynamic characteristics of the working environment change; when various types of defects appear, etc. Functionally, the experimental stand was created as close as possible to real conditions. The developed stand opens up opportunities for practical experiments and direct obtaining of experimental data to identify defects in the air duct. To detect damage to the air circuit, integration of technical developments with the method of multiple signal classification (MUSIC) was performed.

Ensemble Feature Selection Method for Single Pulse Classification

Affected by a large number of radio frequency interference signals, it has become an important task for astronomical data processing to quickly and accurately identify single pulse signals from massive observation data. Designing and extracting effective data features is the key issue for efficient identification of single pulse signals using machine learning. This paper proposes an ensemble feature selection method for single pulse signal classification. The method first mixed three types of features, including the parametric features, statistical features, and abstract features of single pulse signals, and then used five individual feature selection methods to select the corresponding optimal feature set, respectively. At last, the features selected by the five individual methods are mixed, and the greedy strategy was used to select the optimal ensemble feature set. The experimental results show that the ensemble feature set can improve F1-score by a value of 1.8% at most, and can obtain higher accuracy than the features selected by individual methods. Under the background of high-speed and large-scale sky survey, the ensemble feature selection method plays an important role in reducing the number of features, improving classification performance, and speeding up data processing.

Coherent signals direction estimation using high-order quantities in the acoustic field

To meet the demands of underwater remote detection technology, the receiving array must be extended to low frequencies by increasing the array aperture required for detection. Furthermore, the base array aperture must be increased owing to the loss of effective array aperture in coherent targets detection using most decoherent algorithms; however, this prevents its use on small platforms, such as autonomous underwater platforms. Thus, reducing the array aperture while ensuring high resolution is required. In this article, high-order quantities in the acoustic field are utilized to construct a full rank covariance matrix to Multiple Signal Classification Method (MUSIC), which achieves high-resolution results for small aperture arrays with small incident angular intervals in low-frequency coherent targets. The correlated noise of each sensor is considered in the small aperture arrays and the gain of each element in the new matrix is derived. The theoretical analysis, numerical simulations, and experimental verifications show the validity of the method.

Evaluation of the Influence of the Spatial Smoothing Procedure of the Correlation Matrix on the Efficiency of the 2D-MUSIC Method

The occurrence of correlations between radio signals arriving at the antenna array of the base station reduces the effectiveness of subspace methods for positioning user devices in wireless communication networks. For the purpose of radiation sources decorrelation, a spatial smoothing algorithm can be applied dividing the base station antenna array into sub-arrays and then averaging the signal correlation matrices obtained for these sub-arrays. In this paper, we investigate the impact of various ways of dividing a flat equidistant antenna array into subarrays on the performance of the 2D-MUSIC multiple signal classification method in the scenario of ultra-dense networks operating in the FR2 band.