Time-domain Network Research Articles

Ship-Radiated Noise Separation in Underwater Acoustic Environments Using a Deep Time-Domain Network

Ship-radiated noise separation is critical in both military and economic domains. However, due to the complex underwater environments with multiple noise sources and reverberation, separating ship-radiated noise poses a significant challenge. Traditionally, underwater acoustic signal separation has employed blind source separation methods based on independent component analysis. Recently, the separation of underwater acoustic signals has been approached as a deep learning problem. This involves learning the features of ship-radiated noise from training data. This paper introduces a deep time-domain network for ship-radiated noise separation by leveraging the power of parallel dilated convolution and group convolution. The separation layer employs parallel dilated convolution operations with varying expansion factors to better extract low-frequency features from the signal envelope while preserving detailed information. Additionally, we use group convolution to reduce the expansion of network size caused by parallel convolution operations, enabling the network to maintain a smaller size and computational complexity while achieving good separation performance. The proposed approach is demonstrated to be superior to the other common networks in the DeepShip dataset through comprehensive comparisons.

CSF-GTNet: A Novel Multi-Dimensional Feature Fusion Network Based on Convnext-GeLU- BiLSTM for EEG-Signals-Enabled Fatigue Driving Detection.

Electroencephalography (EEG) signal has been recognized as an effective fatigue detection method, which can intuitively reflect the drivers' mental state. However, the research on multi-dimensional features in existing work could be much better. The instability and complexity of EEG signals will increase the difficulty of extracting data features. More importantly, most current work only treats deep learning models as classifiers. They ignored the features of different subjects learned by the model. Aiming at the above problems, this paper proposes a novel multi-dimensional feature fusion network, CSF-GTNet, based on time and space-frequency domains for fatigue detection. Specifically, it comprises Gaussian Time Domain Network (GTNet) and Pure Convolutional Spatial Frequency Domain Network (CSFNet). The experimental results show that the proposed method effectively distinguishes between alert and fatigue states. The accuracy rates are 85.16% and 81.48% on the self-made and SEED-VIG datasets, respectively, which are higher than the state-of-the-art methods. Moreover, we analyze the contribution of each brain region for fatigue detection through the brain topology map. In addition, we explore the changing trend of each frequency band and the significance between different subjects in the alert state and fatigue state through the heat map. Our research can provide new ideas in brain fatigue research and play a specific role in promoting the development of this field.

CompNet: Complementary network for single-channel speech enhancement

Recent multi-domain processing methods have demonstrated promising performance for monaural speech enhancement tasks. However, few of them explain why they behave better over single-domain approaches. As an attempt to fill this gap, this paper presents a complementary single-channel speech enhancement network (CompNet) that demonstrates promising denoising capabilities and provides a unique perspective to understand the improvements introduced by multi-domain processing. Specifically, the noisy speech is initially enhanced through a time-domain network. However, despite the waveform can be feasibly recovered, the distribution of the time–frequency bins may still be partly different from the target spectrum when we reconsider the problem in the frequency domain. To solve this problem, we design a dedicated dual-path network as a post-processing module to independently filter the magnitude and refine the phase. This further drives the estimated spectrum to closely approximate the target spectrum in the time–frequency domain. We conduct extensive experiments with the WSJ0-SI84 and VoiceBank + Demand datasets. Objective test results show that the performance of the proposed system is highly competitive with existing systems.

Multi-center atrial fibrillation electrocardiogram (ECG) classification using Fourier space convolutional neural networks (FD-CNN) and transfer learning

There has been a proliferation of machine learning (ML) electrocardiogram (ECG) classification algorithms reaching >85% accuracy for various cardiac pathologies. Despite the high accuracy at individual institutions, challenges remain when it comes to multi-center deployment. Transfer learning (TL) is a technique in which a model trained for a specific task is repurposed for another related task, in this case ECG ML model trained at one institution is fine-tuned to be utilized to classify ECGs at another institution. Models trained at one institution, however, might not be generalizable for accurate classification when deployed broadly due to differences in type, time, and sampling rate of traditional ECG acquisition. In this study, we evaluate the performance of time domain (TD) and frequency domain (FD) convolutional neural network (CNN) classification models in an inter-institutional scenario leveraging three different publicly available datasets. The larger PTB-XL ECG dataset was used to initially train TD and FD CNN models for atrial fibrillation (AFIB) classification. The models were then tested on two different data sets, Lobachevsky University Electrocardiography Database (LUDB) and Korea University Medical Center database (KURIAS). The FD model was able to retain most of its performance (>0.81 F1-score), whereas TD was highly affected (<0.53 F1-score) by the dataset variations, even with TL applied. The FD CNN showed superior robustness to cross-institutional variability and has potential for widespread application with no compromise to ECG classification performance.

T-A-MFFNet: Multi-feature fusion network for EEG analysis and driving fatigue detection based on time domain network and attention network

Driving fatigue detection based on EEG signals is a research hotspot in applying brain-computer interfaces. EEG signal is complex, unstable, and nonlinear. Most existing methods rarely analyze the data characteristics from multiple dimensions, so it takes work to analyze the data comprehensively. To analyze EEG signals more comprehensively, this paper evaluates a feature extraction strategy of EEG data based on differential entropy (DE). This method combines the characteristics of different frequency bands, extracts the frequency domain characteristics of EEG, and retains the spatial information between channels. This paper proposes a multi-feature fusion network (T-A-MFFNet) based on the time domain and attention network. The model is composed of a time domain network (TNet), channel attention network (CANet), spatial attention network (SANet), and multi-feature fusion network(MFFNet) based on a squeeze network. T-A-MFFNet aims to learn more valuable features from the input data to achieve good classification results. Specifically, the TNet network extracts high-level time series information from EEG data. CANet and SANet are used to fuse channel and spatial features. They use MFFNet to merge multi-dimensional features and realize classification. The validity of the model is verified on the SEED-VIG dataset. The experimental results show that the accuracy of the proposed method reaches 85.65 %, which is superior to the current popular model. The proposed method can learn more valuable information from EEG signals to improve the ability to identify fatigue status and promote the development of the research field of driving fatigue detection based on EEG signals.

Intelligent fault detection algorithm based on Hi/H∞ optimization and a cascaded neural networks

Autonomous surface ships (ASSs) have attracted attention owing to their ability to perform various tasks in complex and challenging aquatic environments without relying on a crew. However, they require reliable sensors to ensure navigational safety. In this study, a robust and intelligent fault detection algorithm was designed for the integrated navigation system of an ASS. First, a residual observer-based fault detection algorithm using Hi/H∞ optimization is proposed to deal with process disturbances and measurement noise. Such noise can be modeled under the condition of a bounded l2-norm to account for the sensitivity and robustness of the residual observer against random noise with unknown properties. However, this fault detection algorithm is insensitive to soft faults, which manifest as noise characterized by a small amplitude and slow variation. Conventional strategies for evaluating the fault detection threshold rely on human experience, which is insufficiently sophisticated for fault detection. Therefore, a cascaded neural network is proposed for optimizing the fault detection algorithm when the amount of training data is limited. The cascaded neural network consists of a multi-feature time domain network, a frequency-domain fault detection network as well as a decision-level fusion network. The proposed algorithm was verified in simulations as well as on historical data collected from real ship sensors. The results demonstrated that the proposed algorithm offers intelligent fault detection, including soft faults, with a low false alarm rate for integrated navigation systems.

Towards Unified All-Neural Beamforming for Time and Frequency Domain Speech Separation

Recently, frequency domain all-neural beamforming methods have achieved remarkable progress for multichannel speech separation. In parallel, the integration of time domain network structure and beamforming also gains significant attention. This study proposes a novel all-neural beamforming method in time domain and makes an attempt to unify the all-neural beamforming pipelines for time domain and frequency domain multichannel speech separation. The proposed model consists of two modules: separation and beamforming. Both modules perform temporal-spectral-spatial modeling and are trained from end-to-end using a joint loss function. The novelty of this study lies in two folds. Firstly, a time domain directional feature conditioned on the direction of the target speaker is proposed, which can be jointly optimized within the time domain architecture to enhance target signal estimation. Secondly, an all-neural beamforming network in time domain is designed to refine the pre-separated results. This module features with parametric time-variant beamforming coefficient estimation, without explicitly following the derivation of optimal filters that may lead to an upper bound. The proposed method is evaluated on simulated reverberant overlapped speech data derived from the AISHELL-1 corpus. Experimental results demonstrate significant performance improvements over frequency domain state-of-the-arts, ideal magnitude masks and existing time domain neural beamforming methods.

Exploration of effective electroencephalography features for the recognition of different valence emotions.

Recent studies have shown that the recognition and monitoring of different valence emotions can effectively avoid the occurrence of human errors due to the decline in cognitive ability. The quality of features directly affects emotion recognition results, so this manuscript explores the effective electroencephalography (EEG) features for the recognition of different valence emotions. First, 110 EEG features were extracted from the time domain, frequency domain, time-frequency domain, spatial domain, and brain network, including all the current mainly used features. Then, the classification performance, computing time, and important electrodes of each feature were systematically compared and analyzed on the self-built dataset involving 40 subjects and the public dataset DEAP. The experimental results show that the first-order difference, second-order difference, high-frequency power, and high-frequency differential entropy features perform better in the recognition of different valence emotions. Also, the time-domain features, especially the first-order difference features and second-order difference features, have less computing time, so they are suitable for real-time emotion recognition applications. Besides, the features extracted from the frontal, temporal, and occipital lobes are more effective than others for the recognition of different valence emotions. Especially, when the number of electrodes is reduced by 3/4, the classification accuracy of using features from 16 electrodes located in these brain regions is 91.8%, which is only about 2% lower than that of using all electrodes. The study results can provide an important reference for feature extraction and selection in emotion recognition based on EEG.

Pulse Signal Analysis Based on Deep Learning Network.

Pulse signal is one of the most important physiological features of human body, which is caused by the cyclical contraction and diastole. It has great research value and broad application prospect in the detection of physiological parameters, the development of medical equipment, and the study of cardiovascular diseases and pulse diagnosis objective. In recent years, with the development of the sensor, measuring and saving of pulse signal has become very convenient. Now the pulse signal feature analysis is a hotspot and difficulty in the signal processing field. Therefore, to realize pulse signal automatic analysis and recognition is vital significance in the aspects of the noninvasive diagnosis and remote monitoring, etc. In this article, we combined the pulse signal feature extraction in time and frequency domain and convolution neural network to analyze the pulse signal. Firstly, a theory of wavelet transform and the ensemble empirical mode decomposition (EEMD) which is gradually developed in recent years have been used to remove the noises in the pulse signal. Moreover, a method of feature point detection based on differential threshold method is proposed which realized the accurate positioning and extraction time-domain values. Finally, a deep learning method based on one-dimensional CNN has been utilized to make the classification of multiple pulse signals in the article. In conclusion, a deep learning method is proposed for the pulse signal classification combined with the feature extraction in time and frequency domain in this article.

Single-channel blind separation of co-frequency signals based on convolutional network

Single-channel blind separation (SCBS) of co-frequency signals has been a challenging task in the blind signal processing field. Most effective approaches were still formulated in signal space, triggering complicated signal processing and high computational cost. To reduce the complexity and improve the separation accuracy of SCBS, in this paper, we propose a new waveform separation-demodulation scheme. As the first quintessential step, we design a convolutional time-domain network with squeeze-and-excitation blocks (CNSE) to carry out waveform separation in latent feature space, then the separated results are demodulated by the low-complexity per-survivor processing (LC-PSP) method. Our network adopts the backbone structure of encoder, separator, and decoder. And, it is worth noting that we deepen the encoder/decoder of the network to emphasize the low-level features and further weigh these features by means of the channel attention module. The encoder-decoder structure helps to eliminate the influence of noise during the stage of signal feature extraction and signal reconstruction. In our experiment, CNSE surpasses long short-term memory network and convolutional time-domain audio separation network as evaluated by signal-to-distortion ratio, signal-to-interferences ratio, and symbol error rate. Additionally, to reduce the influence of the truncation effect in separation, we also propose a data pre-processing method called redundancy protection (RP), and our trials reveal that RP can compensate for the performance of CNSE in the whole signal-to-noise ratio range. It is also verified that, compared with the traditional PSP algorithm, our method has better noise robustness and higher separation efficiency, especially when processing more complex mixtures.

Single-channel speech separation method based on attention mechanism

In order to improve the efficiency of speech interaction so that both humans and machines can hear it clearly, to solve the problem of single channel speech separation, a singlechannel speech separation method combined with attention mechanism is proposed. Based on the time-domain speech separation network, the method uses Encoder-separator-decoder framework and improves the Separator structure of the framework. First, the encoder transforms the input mixed speech signal into the latent space and extracts the feature of the speech signal to obtain the deep representation of the speech. Then, the deep attention features of speech were extracted by the splitter combined with the attention mechanism, and the mask was estimated for each independent sound source. Finally, the decoder inversely transforms the separated source signals back to the time domain. Experiments on WSJ0 speech separation data set show that the proposed method can effectively improve the SI-SNR of mixed speech separation, which is 0.31dB higher than the original time-domain network, and 0.94dB higher for the mixed case of boys and girls.

ConvTasNet-based anomalous noise separation for intelligent noise monitoring

Noise pollution has become a growing concern in public health. The availability of low-cost wireless acoustic sensor networks permits continuous monitoring of noise. However, real acoustic scenes are composed of irrelevant sources (anomalous noise) that overlap with monitored noise, causing biased evaluation and controversy. One classical scene is selected in our study. For road traffic noise assessment, other possible non-traffic noise (e.g., speech, thunder) should be excluded to obtain a reliable evaluation. Because anomalous noise is diverse, occasional, and unpredictable in real-life scenes, removing it from the mixture is a challenge. We explore a fully convolutional time-domain audio separation network (ConvTasNet) for arbitrary sound separation. ConvTasNet is trained by a large dataset, including environmental sounds, speech, and music over 150 hours. After training, the scale-invariant signal-to-distortion ratio (SI-SDR) is improved by 11.40 dB on average for an independent test dataset. ConvTasNet is next applied to anomalous noise separation of traffic noise scenes. We mix traffic noise and anomalous noise at random SNR between -10 dB to 0 dB. Separation is especially effective for salient and long-term anomalous noise, which smooth the overall sound pressure level curve over time. Results emphasize the importance of anomalous noise separation for reliable evaluation.

MFFNet: Multi-dimensional Feature Fusion Network based on attention mechanism for sEMG analysis to detect muscle fatigue

Muscle fatigue detection based on surface Electromyography (sEMG) is one of the essential goals of human–computer interaction. The main challenge is that the sEMG signal is unstable and complex. Meanwhile, the individual’s difference in fatigue tolerance will increase the detection difficulty. In order to reduce the impact of the above challenges, in this article, we use the sEMG signal to detect muscle fatigue based on the Multi-dimensional Feature Fusion Network (MFFNet), which is composed of Attention Frequency domain Network (AFNet) and Attention Time domain Network (ATNet). Precisely, AFNet consists of the convolutional neural network, channel attention network and spatial attention network. ATNet is composed of a two-way long and short-term memory network and time attention network. Furthermore, through the filter and Gaussian short-time Fourier transform, we can analyze the feature of the time domain and frequency domain of sEMG. Subsequently, fuse features of different dimensions are used to predict fatigue detection in many muscle fatigue detection experiments based on sEMG. The proposed method has better performance and interpretability. Experimental results prove that the proposed method can promote the development of sEMG in the field of muscle fatigue detection.

Experimental Analysis of Concentrated versus Distributed Massive MIMO in an Indoor Cell at 3.5 GHz

This paper presents a measurement-based comparison between distributed and concentrated massive multiple-input multiple-output (MIMO) systems, which are called D-mMIMO and C-mMIMO systems, in an indoor environment considering a 400 MHz bandwidth centered at 3.5 GHz. In both cases, we have considered an array of 64 antennas in the base station and eight simultaneously active users. The work focuses on the characterization of both schemes in the up-link, considering the analysis of the sum capacity, the total spectral efficiency (SE) achievable by using the zero forcing (ZF) combining method, as well as the user fairness. The effect of the power imbalance between the different transmitters or user terminal (UT) locations, and thus, the benefits of performing an adequate power control are also investigated. The differences between the C-mMIMO and D-mMIMO channel performances are explained through the observation of the structure of their respective measured channel matrices through parameters such as the condition number or the power imbalance between the channels established by each UT. The channel measurements have been performed in the frequency domain, emulating a massive MIMO system in the framework of a time-domain duplex orthogonal frequency multiple access network (TDD-OFDM-MIMO). The characterization of the MIMO channel is based on the virtual array technique for both C-mMIMO and D-mMIMO systems. The deployment of the C-mMIMO and D-MIMO systems, as well as the distribution of users in the measurement environment, has been arranged as realistically as possible, avoiding the movement of people or machines.

Robust Structure Identification of Industrial Cyber-Physical System From Sparse Data: A Network Science Perspective

Industrial cyber-physical systems (ICPSs) are deployed in many high-value facilities recently, and the monitoring of ICPS is more and more important. However, the prerequisite of ICPS monitoring is how to obtain an accurate network structure. In addition, the structure of ICPS may change over time and the observations data are limited and noisy. These situations make the ICPS network structure identification more difficult. In this article, we proposed the algorithm of temporal network identification from sparse data (ATNISD) to address these two issues simultaneously. First, we established the temporal network analysis model from the aspect of state equation and observation equation. Then, we analyze the characteristics of temporal networks in both time domain and space domain and propose a general framework of temporal networks structure identification, which is a combinatorial optimization problem. To improve the accuracy and alleviate the computational complexity, we decompose the combinatorial problem into small independent simple problems, which can be solved efficiently. The performance of the proposed algorithm is verified on synthetic evolutionary game dynamics on both homogeneous and heterogeneous temporal networks. The experimental results show that the proposed method can efficiently solve the problem of temporal networks structure identification from sparse data. Note to Practitioners—This article addresses the importance of network structure identification in industrial cyber-physical systems (ICPSs). The proposed method can effectively cope with the task of ICPS network structure identification in time-varying environments by exploiting the spatial and temporal features of networks in both time domain and space domain. The proposed algorithm can be implemented in typical slowing changing ICPS with or without observation noise, and it can decompose the combinatorial problem into small independent simple problems to improve the accuracy and release the computational complexity. Extensive simulation experiments demonstrate the accuracy and robustness of the proposed method for solving the structure identification task of temporal networks.

A new approach to eliminate impacts of high-resistance faults by compensation of traditional distance relays’ input signals

Ground impedance measuring elements of digital distance relays, responsible for line to ground faults, are highly prone to underreach in case of high-resistance faults. To tackle this problem for the distance protection of parallel transmission lines, this paper presents an effective approach by compensating the input signals to the existent traditional distance relays. For this objective, the fault distance is estimated innovatively within a short duration by analyzing the line sequence networks in time domain. The fault distance is employed to generate the signals compensating the under-operation distance relays’ instantaneous input signals measured by instrument transformers, in a way as to eliminate the high fault resistance-caused underreach. The proposed approach would not threaten the relay security in normal operating conditions, irrelevant-circuit and external faults. Further, it would not interfere with the relay phase elements. Performance of the proposed approach is examined through comprehensive simulation studies conducted in PSCAD/ EMTDC for a variety of influencing situations and the results would reveal that the proposed approach is able to fully prevent underreach incidents arising from high-resistance faults, without having a significant impact on the relay response time.

Comparative Analysis of State-Space and Companion-Circuit Methodologies for the Periodic Steady-State Solution in Time-Domain of Nonlinear Electric Networks

This contribution reports a comparative analysis of two methodologies for the periodic steady-state solution of linear and nonlinear electric networks in time-domain (TD), based on the state-space model (SSM) and companion-circuit analysis (CCA), respectively. Newton methods based on a conventional Numerical Differentiation (ND) and Enhanced Numerical Differentiation (END) process, respectively, are used. The application of the SSM and CCA methods is done using a brute force (BF) procedure and the application of advanced numerical techniques (ANT) through the forward Euler (FE) and Trapezoidal Rule (TR) numerical integration, respectively. Related analysis show comparisons of each case study in terms of efficiency, speed, computer effort and accuracy between the combination of SSM, CCA and Newton methods, e.g. SSM-ND, SSM-END, CCA-ND and CCA-END, respectively. In particular, the analysis is shown in terms of time-steps per period, CPU processing time and a computer platform used are shown. The results obtained from the reported case studies are validated against the Power Systems Computer Aided Design/Electromagnetic Transients Program including Direct Current (PSCAD/EMTDC®) response, widely accepted by the power industry.

Propagation Loss Measurement of Wireless Body Area Network at 2.4 GHz and 3.35 GHz Bands

The main purpose of this work is to measure and analyze the propagation loss of the Wireless Body Area Network (WBAN) in frequency and time domain at two frequency bands, namely 2.4 GHz band with 80 MHz bandwidth and 3.35 GHz band with 500 MHz bandwidth. Four different scenarios (front to front, front to back, front to off-body node and back to off-body node) using many antenna´s locations on the body are used to investigate the channel response (path loss) of WBAN. It is found that the front to front channels and the front to off-body node channels have a low fading. The front to back channels and the back to off-body node channels have a high fading that can be approximated by the Distorted Rayleigh fading. Thus the WBAN range for the front to off-body node scenario is more than the range of the back to off-body node scenario.

An Improved Algorithm based on Time Domain Network Evolution

An Improved Algorithm based on Time Domain Network Evolution

Breakdown of Thalamo-Cortical Connectivity Precedes Spike Generation in Focal Epilepsies.

Electroencephalography (EEG) spikes and focal epileptic seizures are generated in circumscribed cerebral networks that have been insufficiently described. For precise time and spatial domain network characterization, we applied in patients with focal epilepsy dense array 256-channel EEG recordings with causal connectivity estimation by using time-resolved partial directed coherence and 3T-magnetic resonance imaging-derived cortical and thalamus integrity reconstruction. Before spike generation, significant theta and alpha bands driven information flows alterations were noted from both temporal and frontal lobes to the thalamus and from the thalamus to the frontal lobe. Medial dorsal and ventral anterior nuclei of the thalamus were delimited as possible pacemakers. Markedly reduced thalamic volumes and impaired cortical integrity in widespread areas predicted the altered information flows. Our data reveal distinct patterns of connectivity involving the thalamus and frontal cortex that are both directly and causally involved in spike generation. These structures might play an essential role in epileptogenesis and could be targeted in future therapeutic approaches.