Time-frequency Representation Images Research Articles

Radar-Based Elderly Fall Detection Using Smoothed Pseudo Wigner Ville Distribution and XGBoost Learning.

Falls among the elderly population pose significant health risks, often leading to morbidity and decreased quality of life. Traditional fall detection methods, namely wearable devices and cameras, have limitations such as lighting conditions and privacy concerns. Radar-based fall detection has emerged as a promising alternative, offering unobtrusive technique. In this study, an attempt has been made to classify fall detection using smoothed pseudo wigner-ville distribution (SPWVD) images and XGBoost learning. For this, online publicly available radar database (N=15) is considered. Radar signals is employed to SPWVD for time-frequency representation images. Ten features are extracted and applied to XGBoost learning. Experiments are performed and performance is evaluated using 10-fold cross validation. The proposed approach is able to discriminate elderly fall. Using XGBoost learning, the approach yields a maximum average classification accuracy, f1-score, precision, sensitivity, specificity, and kappa scores of 87.47%, 87.38%, 88.12%, 86.81%, 88.31% and 74.94% respectively. The combination of conventional features with concentration measures and median frequency obtained the second best performance. Thus, the proposed framework could be utilized for accurate and efficient detection of falls among the elderly population in their private spaces.

Modulation recognition of optical and electromagnetic waves based on transfer learning

Light is a type of electromagnetic wave. Research on the modulation recognition of communication signals, which are also electromagnetic waves, can be applied to the field of modulation and demodulation of optical waves. The limited signal data and varying data distribution have an impact on the automatic modulation recognition of signals. To address this, we proposed a method to enhance the characteristic information of modulation patterns carried by signal data. We used the Wigner–Ville distribution and short-time Fourier transform to convert the original I/Q multi-channel modulated communication signal into time–frequency representation images (TFRIs). Additionally, we adopted a transfer learning approach, the domain adaptation network (DAN), to identify modulation modes of signals under different SNRs. The combination of signal conversion and transfer learning significantly improved the identification of modulation recognition. Our experiments demonstrated that our proposed method outperformed existing state-of-the-art methods in terms of classification accuracy at both high and low signal-to-noise ratios (SNRs). Specifically, our method achieved a 10% increase in Top1-accuracy under high SNR, and overall improved the classification accuracy under low SNR compared to the adversarial transfer learning architecture (ATLA). This is attributed to the use of a more diverse and accurate dataset that provides a better representation of real-world communication signals. We also compared our experimental results with those of other papers, and the results show that our method achieved the best performance among the current state-of-the-art methods, considering the classification accuracy at different SNRs.

An image-based feature extraction method for fault diagnosis of variable-speed rotating machinery

This paper proposes a new feature extraction method using time–frequency image data for fault diagnosis of variable-speed rotating machinery. Time-frequency representation (TFR) is widely used to analyze time-varying behaviors of rotating machinery. Recently, methods have been developed to extract fault-related features from TFR image data. However, these methods can be only applied to in-phase TFR image data, or have limited sensitivity because they cannot utilize the characteristics of faults in rotating machinery. Therefore, the research outlined in this paper proposes a new fault feature for rotating machinery under variable-speed conditions. The proposed feature enhances sensitivity by exploiting faulty behaviors in the TFR image data. Two experimental case studies are presented to demonstrate the performance of the proposed method: a planetary gearbox and a spur gearbox. From the results, we conclude that the proposed method shows higher fault sensitivity than the previous image-based features, while showing consistent behavior under different phases of TFR image data.

FBDM based time-frequency representation for sleep stages classification using EEG signals

In this paper, we have proposed a new method of time-frequency representation (TFR) which is based on the Fourier-Bessel decomposition method (FBDM). This proposed method is an advanced version of the existing Fourier decomposition method (FDM). The proposed method decomposes the non-stationary signal into a finite number of Fourier-Bessel intrinsic band functions (FBIBFs). The FBIBFs are the real parts of analytic FBIBFs (AFBIBFs) which are obtained from an analytic signal during frequency scanning (FS) operations. The Hilbert transform (HT) is used to generate an analytic signal from the Fourier-Bessel series (FBS) expansion of an arbitrary signal. In addition to FBDM, we have also proposed zero-phase filter-bank based FBDM in order to get fix number of FBIBFs in this work. The performance of the proposed FBDM has been evaluated with the help of Poverall measure and TFR analysis of synthesized signals. The experimental results and performance measures show that the proposed FBDM is more capable for analysis of non-stationary multi-component signals such as linear frequency modulated and nonlinear frequency modulated signals as compared to the existing methods. The developed FBDM has also been used for the classification of six different sleep stages using electroencephalogram (EEG) signals. The convolutional neural network (CNN) classifier has been utilized for the classification of TFR images, which were obtained with the application of FBDM on a publicly available sleep EEG signals database. The developed classification system has achieved 91.90% classification accuracy for the classification of six different sleep stages using EEG signals.

Automatic modulation recognition of compound signals using a deep multi-label classifier: A case study with radar jamming signals

The modern battlefield is getting more complicated due to the increasing number of different radiation sources as well as their fierce contention (interference) and confrontations (jamming) in the frequency spectrum. A radar, or a communication system usually has to struggle with multiple overlapped signals injected into its receiver to ensure desired system performance. Thus, the requirement for recognition of the modulation type of each constituent signal in a compound signal has emerged as a multiuser automatic modulation classification (mAMC) task in a signal processing field. This paper proposes a deep multi-label based mAMC framework (MLAMC) for compound signals which includes three serial steps, the time-frequency representation image (TFRI) extraction for signal preprocessing, multi-label convolutional neural network (MLCNN) construction for multi-label classification, and multi-decision thresholds optimization for output label decision. By applying the proposed MLAMC method on the compound radar jamming signals as a case study, the effectiveness and superiority of our proposed method are validated in four aspects of a smaller model size, better total performance, good extensibility for unseen signal combinations, and fine-grained analysis for recognition results.

Ventricular Fibrillation and Tachycardia detection from surface ECG using time-frequency representation images as input dataset for machine learning

Background and objectiveTo safely select the proper therapy for Ventricullar Fibrillation (VF) is essential to distinct it correctly from Ventricular Tachycardia (VT) and other rhythms. Provided that the required therapy would not be the same, an erroneous detection might lead to serious injuries to the patient or even cause Ventricular Fibrillation (VF). The main novelty of this paper is the use of time-frequency (t-f) representation images as the direct input to the classifier. We hypothesize that this method allow to improve classification results as it allows to eliminate the typical feature selection and extraction stage, and its corresponding loss of information. MethodsThe standard AHA and MIT-BIH databases were used for evaluation and comparison with other authors. Previous to t-f Pseudo Wigner-Ville (PWV) calculation, only a basic preprocessing for denoising and signal alignment is necessary. In order to check the validity of the method independently of the classifier, four different classifiers are used: Logistic Regression with L2 Regularization (L2 RLR), Adaptive Neural Network Classifier (ANNC), Support Vector Machine (SSVM), and Bagging classifier (BAGG). ResultsThe main classification results for VF detection (including flutter episodes) are 95.56% sensitivity and 98.8% specificity, 88.80% sensitivity and 99.5% specificity for ventricular tachycardia (VT), 98.98% sensitivity and 97.7% specificity for normal sinus, and 96.87% sensitivity and 99.55% specificity for other rhythms. ConclusionResults shows that using t-f data representations to feed classifiers provide superior performance values than the feature selection strategies used in previous works. It opens the door to be used in any other detection applications.

Ultra-wideband synthetic aperture radar time-frequency representation image formation

In ultra-wideband synthetic aperture radar (UWB SAR) imaging, scatterers often perform the frequency- and aspect angle-dependent reflectivity characteristic, which is usually neglected in traditional imaging processing. A novel UWB SAR time-frequency representation image formation (TFRIF) is proposed to retrieve the frequency- and aspect angle-dependent information, which is valuable in target detection. Based on the TFRIF, two fusion schemes are studied: pixel level fusion (PLF) and decision level fusion (DLF). Based on the analytical expressions, it is concluded that TFRIF can extract the reflectivity pattern information with high precision and little sacrifice of the spatial resolutions. Quantitative analyses of spatial resolutions and detectability improvement of the proposed fusion schemes are tested on airborne UWB SAR data. The real data results validate the proposed TFRIF and its associated PLF and DLF schemes.