Classification Of Non-stationary Signals Research Articles

Retraction Note to: Feasibility of spectral domain techniques for the classification of non-stationary signals

Retraction Note to: Feasibility of spectral domain techniques for the classification of non-stationary signals

Detection of Non-Stationary GW Signals in High Noise From Cohen’s Class of Time–Frequency Representations Using Deep Learning

Analysis of non-stationary signals in a noisy environment is a challenging research topic in many fields often requiring simultaneous signal decomposition in the time and frequency domain. This paper proposes a method for the classification of noisy non-stationary time-series signals based on Cohen’s class of their time-frequency representations (TFRs) and deep learning algorithms. We demonstrated the proposed approach on the example of detecting gravitational-wave (GW) signals in intensive real-life, non-stationary, non-white, and non-Gaussian noise. For this purpose, we prepared a dataset based on the actual data from the Laser Interferometer Gravitational-Wave Observatory (LIGO) detector and the synthetic GW signals obtained by realistic simulations. Next, 12 different TFRs from Cohen’s class were calculated from the original noisy time-series data and used to train three state-of-the-art convolutional neural network (CNN) architectures: ResNet-101, Xception, and EfficientNet. The obtained classification results are compared to those achieved by the base model trained on the original time series. Analysis of the results suggests that the proposed approach combining deep CNN architectures with Cohen’s class TFRs yields high values of performance metrics and significantly improves the classification performance compared to the base model. The TFR-CNN models achieve the values of the classification accuracy of up to 97.10%, the area under the receiver operating characteristic curve (ROC AUC) of up to 0.9885, the recall of up to 95.87%, the precision of up to 99.51%, the F1 score of up to 97.03%, and the area under the precision-recall curve (PR AUC) of up to 0.9920. This classification performance is obtained on the dataset in which the signal-to-noise ratio (SNR) values of the raw, noisy time-series signals range from −123.46 to −2.27 dB. Therefore, this study suggests that using alternative TFRs of Cohen’s class can improve the deep learning-based detection of non-stationary GW signals in an intensive noise environment. Moreover, the proposed approach can also be a viable solution for deep learning-based analysis of numerous other noisy non-stationary signals in different practical applications.

Feasibility of Recurrent Neural Network for the Binary classification of Non stationary signals

Spectral domain techniques are best suited for the examination of signals which are non-stationary in nature. Features extracted from spectral decomposition can be represented with statistical parameters. These features are then fed to classifiers for classifying the non-stationary signals. In this work, Recurrent Neural Network is used as the classifier for labeling signals as normal or abnormal and also embedded. Bursts and saw tooth non-stationary signals are considered and the performance is studied. Also the significant parameters are identified based on sensitivity, specificity and accuracy. From the analysis, it is found that Discreet Framelet Transform (DFT) co-efficients are best suited for binary classification of burst signals while Discrete Wavelet Transform (DWT) is the best suited technique for saw tooth non-stationary signals. This methods can be used for the non-stationary signals like ECG, speech signals etc.

Solution of the Problem of Classification of Hydroacoustic Signals Based on Harmonious Wavelets and Machine Learning

Two types of real hydroacoustic signals of whales are classified based on the harmonic wavelet transform (HWT) coefficients (fast implementation), windowed Fourier transform (FT) (spectrogram), and conventional FT using the k-NN algorithm. The accuracy of the classification is estimated for various signal-to-noise ratios (SNRs). In order to reduce the dimension of the feature space during classification using the k-NN algorithm, the use of the modulo N reduction method is proposed. The efficiency of the use of harmonic wavelets in the classification of complex nonstationary signals is experimentally proved. The applicability of speech processing methods for the classification of underwater bioacoustic signals is confirmed. The discussed methods are initially developed taking into account the characteristics of human speech, but, nevertheless, showed good results even without being tuned to the characteristics of the classified signals. The problem of classifying two types of whales by the sounds they make using a neural network is solved.

RETRACTED ARTICLE: Feasibility of spectral domain techniques for the classification of non-stationary signals

Extensive research is carried out in the analysis of non stationary signals. Most of the real time signals are non-stationary in nature. In most cases, these non stationary signals are of types viz defect / non defect, normal / abnormal etc. Hence analysis refers to categorising the signals. Developing a signal processing algorithm for performing the above task is a major challenge. In Machine learning, features are extracted and classifiers are used for categorizing the signals. Feature extraction can be done in time domain, frequency domain and spectral domain. In this paper, feasibility of Singular Value Decomposition (SVD), Framelet Transforms, Discrete Wavelet Transform (DWT) and Discrete Cosine Transform (DCT) for feature extraction is studied. These features are aggregated using statistical parameters, namely mean, skewness and kurtosis. These aggregated features are then fed to Back Propagation Network (BPN). Performance of Back Propagation Network is measured in terms of sensitivity, specificity and accuracy.

Classification of Hydroacoustic Signals Based on Harmonic Wavelets and a Deep Learning Artificial Intelligence System

This paper considers two approaches to hydroacoustic signal classification, taking the sounds made by whales as an example: a method based on harmonic wavelets and a technique involving deep learning neural networks. The study deals with the classification of hydroacoustic signals using coefficients of the harmonic wavelet transform (fast computation), short-time Fourier transform (spectrogram) and Fourier transform using a kNN-algorithm. Classification quality metrics (precision, recall and accuracy) are given for different signal-to-noise ratios. ROC curves were also obtained. The use of the deep neural network for classification of whales’ sounds is considered. The effectiveness of using harmonic wavelets for the classification of complex non-stationary signals is proved. A technique to reduce the feature space dimension using a ‘modulo N reduction’ method is proposed. A classification of 26 individual whales from the Whale FM Project dataset is presented. It is shown that the deep-learning-based approach provides the best result for the Whale FM Project dataset both for whale types and individuals.

An optimized design of seizure detection system using joint feature extraction of multichannel EEG signals.

The detection of seizure onset and events using electroencephalogram (EEG) signals are important tasks in epilepsy research. The literature available on seizure detection has discussed the implementation of advanced signal processing algorithms using tools accessed over the cloud. However, seizure monitoring application needs near sensor processing due to privacy and latency issues. In this paper, a real time seizure detection system has been implemented using an embedded system. The proposed system is based on ensemble empirical mode decomposition (EEMD) and tunable-Q wavelet transform (TQWT) algorithms. The analysis and classification of non-stationary EEG signals require the wavelet transform with high Q-factor. However, direct use of TQWT increases the computational complexity of feature extraction from multivariate EEG signals. In this paper, the first step is to process the signal by using EEMD to obtain 8 intrinsic mode functions (IMFs). The Kraskov (KraEn), sample (SampEn), and permutation (PermEn) entropy features of IMFs are extracted and based on optimum values, and 4 IMFs are decomposed using TQWT. Secondly, centered correntropy (CenCorrEn) features of the 1st and 16th sub-band of TQWT have been used as classifier inputs. The performance of multilayer perceptron neural networks (MLPNN), least squares support vector machine (LSSVM), and random forest (RF) classifiers has been tested on the multichannel EEG data recorded from a local hospital. The RF classifier has produced the highest accuracy of 96.2% in classifying the signals. The proposed scheme has been employed in developing an embedded seizure detection system to assist neurologists in making seizure diagnostic decisions.

Detection and Classification of Nonstationary Signals: Application to Uterine EMG for Prognostication of Premature Delivery

In recent literature, several techniques have been adopted to reject noise from EMG recordings, which is important for using EMG techniques in clinics and research work. In this paper, the least mean square (LMS) and recursive least square (RLS) adaptive algorithms have been proposed to denoise uterine EMG signals taken from the open-source database TPEHG. Simulations were performed in the MATLAB Simulink environment. The obtained results were then compared with the wavelet transform and 0.34–1.0 Hz bandpass filter using signal-to-noise ratio measures. The results showed that the RLS-based algorithm performs the best among the other tested algorithms; the possible use of uterine EMG signals for prognostication of premature vs. term delivery has been taken into consideration.

Multi-View Temporal Ensemble for Classification of Non-Stationary Signals

In the classification of non-stationary time series data such as sounds, it is often tedious and expensive to get a training set that is representative of the target concept. To alleviate this problem, the proposed method treats the outputs of a number of deep learning sub-models as the views of the same target concept that can be linearly combined according to their complementarity. It is proposed that the view's complementarity be the contribution of the view to the global view, chosen in this paper to be the Laplacian eigenmap of the combined data. Complementarity is computed by alternate optimization, a process that involves the cost function of the Laplacian eigenmap and the weights of the linear combination. By blending the views in this way, a more complete view of the underlying phenomenon can be made available to the final classifier. Better generalization is obtained, as the consensus between the views reduces the variance while the increase in the discriminatory information reduces the bias. The data experiment with artificial views of environment sounds formed by deep learning structures of different configurations shows that the proposed method can improve the classification performance.

Time‐frequency analysis and classification of power signals using adaptive cuckoo search algorithm

AbstractA new approach to Hilbert energy spectrum and pattern recognition of nonstationary power signals is presented in this paper. In the proposed work, visual localization, detection, and classification of nonstationary power signals are achieved using Hilbert transform (HT)–based adaptive local iterative filter (ALIF). The HT is applied on all the intrinsic mode functions that are obtained from both empirical mode decomposition (EMD) and ALIF to extract instantaneous amplitude and frequency components. The instantaneous Hilbert energy spectrum results in clear visual detection, localization, and classification of the different power signal disturbances. The visual energy spectrum by Hilbert‐Huang Transform (HHT) on ALIF showing a better result than HHT applied on EMD. The feature vectors are extracted from the Hilbert energy spectrum for automatic pattern recognition of various nonstationary signals using a traditional fuzzy C‐means algorithm (FCMA). Finally, the center of the cluster is further optimized using fuzzy C‐means–based adaptive cuckoo search algorithm. The average classification accuracy of the disturbances is 91.25% and 99.25% using fuzzy C‐means and adaptive cuckoo search–based FCMA, respectively.

A new feature for the classification of non-stationary signals based on the direction of signal energy in the time–frequency domain

The detection of seizure activity in electroencephalogram (EEG) segments is very important for the classification and localization of epileptic seizures. The evolution of a seizure in an EEG usually appears as a train of non-uniformly spaced spikes and/or as piecewise linear frequency modulated signals. If a seizure is present, then the energy of the EEG is concentrated along the time axis and the frequency axis in the time–frequency plane. However, in the absence of a seizure, the energy of the EEG signal is uniformly distributed along all directions in the time–frequency plane. Based on this observation, we propose a new approach for the detection of a seizure. In this paper, we develop a new feature that exploits the direction of the energy of the signal in the time–frequency domain to distinguish between seizures and non-seizures in an EEG. Our experimental results indicate the superiority of the proposed approach over other conventional time–frequency approaches; for example, the proposed feature set achieves a classification accuracy of 98.25% by only using five features.

Designing high-resolution time–frequency and time–scale distributions for the analysis and classification of non-stationary signals: a tutorial review with a comparison of features performance

This paper deals with the problem of extracting information from non-stationary signals in the form of features that can be used for effective decision-making in both data analysis and machine learning for automatic classification systems. Suitable time–frequency (TF) and time–scale (TS) representations of such signals are reviewed for these purposes, and, the relationships between such TF and TS signal transformations is discussed. Both linear (atomic) decompositions and quadratic distributions are considered as well as other related methods such as fractional Fourier transform, polynomial Wigner–Ville distributions and time-varying order spectra. Current state-of-the-art methods are reviewed, and new results are presented including extensions of existing methods.Machine learning methodologies using TF/TS features can result in the design of systems that improve the classification of non-stationary signals. Using selected TF distributions (TFDs) and TS distributions (TSDs), the extraction of such TF/TS features is demonstrated on multi-channel recordings using channel fusion or feature fusion approaches. Extending the findings of previous studies, a TF/TS feature set is formed by including two complementary categories: signal related features and image features. The design of high-resolution TF/TS algorithms is then refined to account for issues of accuracy and robustness. Then, the desired TF/TS features are selected using different feature selection algorithms and compared with respect to the classification performance. Finally, other features from related methods are added, and comparisons performed. Improvements of up to 5% are obtained when using the chosen feature set after wrapper feature selection with channel feature fusion.

Performance evaluation of time-frequency image feature sets for improved classification and analysis of non-stationary signals: Application to newborn EEG seizure detection

This study demonstrates that a time-frequency (TF) image pattern recognition approach offers significant advantages over standard signal classification methods that use t-domain only or f-domain only features. Two approaches are considered and compared. The paper describes the significance of the standard TF approach for non-stationary signals; TF signal (TFS) features are defined by extending t-domain or f-domain features to a joint (t, f) domain resulting in e.g. TF flatness and TF flux. The performance of the extended TFS features is comparatively assessed using Receiver Operating Characteristic (ROC) analysis Area Under the Curve (AUC) measure. Experimental results confirm that the extended TFS features generally yield improved performance (up to 19%) when compared to the corresponding t-domain and f-domain features.The study also explores a second approach based on novel TF image (TFI) features that further improves TF-based classification of non-stationary signals. New TFI features are defined and extracted from the (t, f) domain; they include TF Hu invariant moments, TF Haralick features, and TF Local Binary Patterns (LBP). Using a state-of-the-art classifier, different metrics based on confusion matrix performance are compared for all extended TFS features and TFI features. Experimental results show the improved performance of TFI features over both TFS features and t-domain only or f-domain only features, for all TF representations and for all the considered performance metrics. The experiment is validated by comparing this new proposed methodology with a recent study, utilizing the same large and complex data set of EEG signals, and the same experimental setup. The resulting classification results confirm the superior performance of the proposed TFI features with accuracy improvement up to 5.52%.

Classification of EEG Physiological Signal for the Detection of Epileptic Seizure by Using DWT Feature Extraction and Neural Network

EEG (Electroencephalogram) is a technique for identifying neurological disorders. There are various neurological disorders like Epilepsy, brain cancer, etc. Feature extraction and classification of electroencephalogram (EEGs) signals for (normal and epileptic) is a challenge for engineers and scientists. Various signal processing techniques have already been proposed for classification of non-linear and non stationary signals like EEG. In this work, neural network analysis (NNA) based classifier was employed to detect epileptic seizure activity from background electro encephalographs (EEGs). Two types of EEG signals (healthy subject with eye open condition, epileptic) were selected for the analysis. Signals were reprocessed, decomposed by using discrete wavelet transform DWT till 5th level of decomposition tree. Various features like mean. Standard deviation, median, entropy, kurtosis and skewness were computed and consequently used for classification of signals. The range of these features in non-epileptic and epileptic group of 80 subjects each from data set is analyzed for data available at the Department of Epileptology, University of Bonn, and the parameters with distinct non-overlapping zone are identified. The results show the promising classification accuracy of nearly 100% in detection of abnormal from normal EEG signals. The main purpose of this new approach is that the computation time of NNA classifier is less to provide better accuracy. This proposed classifier can be used to design expert system for epilepsy diagnosis purpose in various hospitals.

An information rich subspace separation for non-stationary signal classification

This paper proposes a novel automated approach for the classification of highly non-stationary signals based on a non-principal component analysis (non-PCA) methodology. This method generates an eigen analysis based pseudospectrum to emulate the spectral characteristic variations of the non-stationary signals to be classified. Then, the estimated pseudo-spectrum is used to implement a comb like subspace filter structure, which captures the variations of all significant spectral components throughout the whole observation period. It is shown that this filter implementation method yields better results than the existing dimensionality reduction methods, which only utilise the principal k components of the eigen space. Finally, a novel probabilistic approach which creates a signature vector representing each class of signals in the training phase is proposed for the classification process. It is also shown that the proposed method can be effectively used not only for classification but also for the extraction of hidden stationary signature features from a non-stationary signal. Further, it is also proven that the proposed subspace filtering scheme can be used as a dynamic spectral estimation technique, which can eliminate the time frequency resolution tradeoff that exists in techniques such as short-time fourier transform (STFT).

Robust feature representation for classification of bird song syllables

A novel feature set for low-dimensional signal representation, designed for classification or clustering of non-stationary signals with complex variation in time and frequency, is presented. The feature representation of a signal is given by the first left and right singular vectors of its ambiguity spectrum matrix. If the ambiguity matrix is of low rank, most signal information in time direction is captured by the first right singular vector while the signal’s key frequency information is encoded by the first left singular vector. The resemblance of two signals is investigated by means of a suitable similarity assessment of the signals’ respective singular vector pair. Application of multitapers for the calculation of the ambiguity spectrum gives an increased robustness to jitter and background noise and a consequent improvement in performance, as compared to estimation based on the ordinary single Hanning window spectrogram. The suggested feature-based signal compression is applied to a syllable-based analysis of a song from the bird species Great Reed Warbler and evaluated by comparison to manual auditive and/or visual signal classification. The results show that the proposed approach outperforms well-known approaches based on mel-frequency cepstral coefficients and spectrogram cross-correlation.

Noise robustness analysis of sparse representation based classification method for non-stationary EEG signal classification

Abstract In the electroencephalogram (EEG)-based brain–computer interface (BCI) systems, classification is an important signal processing step to control external devices using brain activity. However, scalp-recorded EEG signals have inherent non-stationary characteristics; thus, the classification performance is deteriorated by changing the background activity of the EEG during the BCI experiment. Recently, the sparse representation based classification (SRC) method has shown a robust classification performance in many pattern recognition fields including BCI. In this study, we aim to analyze noise robustness of the SRC method to evaluate the capability of the SRC for non-stationary EEG signal classification. For this purpose, we generate noisy test signals by adding a noise source such as random Gaussian and scalp-recorded background noise into the original motor imagery based EEG signals. Using the noisy test signals and real online-experimental dataset, we compare the classification performance of the SRC and support vector machine (SVM). Furthermore, we analyze the unique classification mechanism of the SRC. We observed that the SRC method provided better classification accuracy and noise robustness compared with the SVM method. In addition, the SRC has an inherent adaptive classification mechanism that makes it suitable for time-varying EEG signal classification for online BCI systems.

Detection and Classification of Nonstationary Transient Signals Using Sparse Approximations and Bayesian Networks

This paper considers sequential detection and classification of multiple transient signals from vector observations corrupted with additive noise and multiple types of structured interference. Sparse approximations of observations are found to facilitate computation of the likelihood of each signal model without relying on restrictive assumptions concerning the distribution of observations. Robustness to interference may be incorporated by virtue of the inherent separation capabilities of sparse coding. Each signal model is characterized by a Bayesian Network, which captures the temporal dependency structure among coefficients in successive sparse approximations under the associated hypothesis. Generalized likelihood ratios tests may then be used to perform signal detection and classification during quiescent periods, and quiescent detection whenever a signal is present. The results of applying the proposed method to a national park soundscape analysis problem demonstrate its practical utility for detecting and classifying real acoustical sources present in complex sonic environments.

Nonstationary power signal time series data classification using LVQ classifier

A new approach to time–frequency analysis and pattern recognition of non-stationary power signals is proposed in this paper. In this manuscript, visual localization, detection and classification of non-stationary power signals are achieved using wavelet packet decomposition and automatic pattern recognition is carried out through learning vector quantization neural network. The wavelet packet decomposition (WPD) of the non-stationary power signals is carried out to extract the coefficients at multiple level of decomposition. The relevant features for pattern classification are derived from the time-scale information obtained by WPD. The extracted features are used to classify different power quality disturbances by using learning vector quantization neural net. Various non-stationary power signal waveforms are considered to verify the applicability of the proposed technique.

Embedded Grey Relation Theory in Hopfield Neural Network

In this study, grey-based Hopfield neural network (GHNN), is proposed for the unsupervised analysis of motor imagery (MI) electroencephalogram (EEG) data. Combined with segment selection and feature extraction, GHNN is used for the recognition of left and right MI data. A Gaussian-like filter is proposed to reduce noise, to further enhance performance of active segment selection. Features are extracted by coherence from wavelet data, and then discriminated by GHNN, which is an unsupervised approach suitable for the online classification of nonstationary biomedical signals. Compared to EEG data without segment selection, several usual features, and classifiers, the proposed system is potentially an analytic approach in brain-computer interface (BCI) applications.