Multichannel Method Research Articles

Optical Frequency Comb Frequency-division Multiplexing Dispersive Interference Multichannel Distance Measurement

An optical frequency comb (OFC) frequency-division multiplexing dispersive interference multichannel distance measurement method is proposed. Based on the OFC dispersive interference, the wide OFC spectrum is divided into multiple channels using a wavelength-division multiplexer. Under the existing light source and spectrometer, a single interference system can realize six channels of the high-precision parallel absolute distance measurement. The influence of the spectrum width and shape on the performance of the distance measurement channel is analyzed. The ranging accuracy of six channels is higher than ± 4 μm under the optimization of a nonuniform discrete Fourier transform and Hanning window.

A multi-task and multi-channel convolutional neural network for semi-supervised neonatal artefact detection

Objective. Automated artefact detection in the neonatal electroencephalogram (EEG) is crucial for reliable automated EEG analysis, but limited availability of expert artefact annotations challenges the development of deep learning models for artefact detection. This paper proposes a semi-supervised deep learning approach for artefact detection in neonatal EEG that requires few labelled data by training a multi-task convolutional neural network (CNN). Approach. An unsupervised and a supervised objective were jointly optimised by combining an autoencoder and an artefact classifier in one multi-output model that processes multi-channel EEG inputs. The proposed semi-supervised multi-task training strategy was compared to a classical supervised strategy and other existing state-of-the-art models. The models were trained and tested separately on two different datasets, which contained partially annotated multi-channel neonatal EEG. Models were evaluated using the F1-statistic and the relevance of the method was investigated in the context of a functional brain age (FBA) prediction model. Main results. The proposed multi-task and multi-channel CNN methods outperformed state-of-the-art methods, reaching F1 scores of 86.2% and 95.7% on two separate datasets. The proposed semi-supervised multi-task training strategy was shown to be superior to a classical supervised training strategy when the amount of labels in the dataset was artificially reduced. Finally, we found that the error of a brain age prediction model correlated with the amount of automatically detected artefacts in the EEG segment. Significance. Our results show that the proposed semi-supervised multi-task training strategy can train CNNs successfully even when the amount of labels in the dataset is limited. Therefore, this method is a promising semi-supervised technique for developing deep learning models with scarcely labelled data. Moreover, a correlation between the error of FBA estimates and the amount of detected artefacts in the corresponding EEG segments indicates the relevance of artefact detection for robust automated EEG analysis.

A Multi-Channel Ensemble Method for Error-Related Potential Classification Using 2D EEG Images

An error-related potential (ErrP) occurs when people's expectations are not consistent with the actual outcome. Accurately detecting ErrP when a human interacts with a BCI is the key to improving these BCI systems. In this paper, we propose a multi-channel method for error-related potential detection using a 2D convolutional neural network. Multiple channel classifiers are integrated to make final decisions. Specifically, every 1D EEG signal from the anterior cingulate cortex (ACC) is transformed into a 2D waveform image; then, a model named attention-based convolutional neural network (AT-CNN) is proposed to classify it. In addition, we propose a multi-channel ensemble approach to effectively integrate the decisions of each channel classifier. Our proposed ensemble approach can learn the nonlinear relationship between each channel and the label, which obtains 5.27% higher accuracy than the majority voting ensemble approach. We conduct a new experiment and validate our proposed method on a Monitoring Error-Related Potential dataset and our dataset. With the method proposed in this paper, the accuracy, sensitivity and specificity were 86.46%, 72.46% and 90.17%, respectively. The result shows that the AT-CNNs-2D proposed in this paper can effectively improve the accuracy of ErrP classification, and provides new ideas for the study of classification of ErrP brain-computer interfaces.

Localization of an acoustic autonomous underwater vehicle using multi-channel back-propagation methods

Autonomous underwater vehicles (AUVs) are extremely useful tools for studying the acoustics of complex ocean environments due to their ability to detect environmental changes with greater spatial resolution than fixed moorings. During the New England Shelf Break Acoustics (NESBA) experiments in May 2021, an AUV system was deployed to collect acoustic data for investigating the local biological, physical, and geological oceanography. This acoustic AUV system was comprised of a modified REMUS 600 vehicle, a hull-mounted 3.5 kHz transducer, and a towed multi-channel hydrophone array. Along mission profiles where the AUV is fully submerged but too shallow for bottom-lock navigation, one challenge is accurate localization of the AUV. Localization was performed in post-processing using multi-channel back-propagation methods applied to AUV source signals received at mooring hydrophones in the NESBA network as well as ship-towed sound source signals received at the AUV-towed array. Uncertainty in the localization estimates due to spatiotemporal sound speed changes was investigated, and hydrophone mooring tilt angle was determined by minimizing the localization uncertainty. Following localization, this AUV acoustic data was used to investigate local seafloor sub-bottom properties and the acoustic effects of biological scattering layers and varying physical oceanography. [Work supported by the Office of Naval Research.]

Imbalanced Text Sentiment Classification Based on Multi-Channel BLTCN-BLSTM Self-Attention.

With the continuous expansion of the field of natural language processing, researchers have found that there is a phenomenon of imbalanced data distribution in some practical problems, and the excellent performance of most methods is based on the assumption that the samples in the dataset are data balanced. Therefore, the imbalanced data classification problem has gradually become a problem that needs to be studied. Aiming at the sentiment information mining of an imbalanced short text review dataset, this paper proposed a fusion multi-channel BLTCN-BLSTM self-attention sentiment classification method. By building a multi-channel BLTCN-BLSTM self-attention network model, the sample after word embedding processing is used as the input of the multi-channel, and after fully extracting features, the self-attention mechanism is fused to strengthen the sentiment to further fully extract text features. At the same time, focus loss rebalancing and classifier enhancement are combined to realize text sentiment predictions. The experimental results show that the optimal F1 value is up to 0.893 on the Chnsenticorp-HPL-10,000 corpus. The comparison and ablation of experimental results, including accuracy, recall, and F1-measure, show that the proposed model can fully integrate the weight of emotional feature words. It effectively improves the sentiment classification performance of imbalanced short-text review data.

Fast pre-stack multi-channel inversion constrained by seismic reflection features

Classical multi-channel technology can significantly reduce the pre-stack seismic inversion uncertainty, especially for complex geology such as high dipping structures. However, due to the consideration of complex structure or reflection features, the existing multi-channel inversion methods have to adopt the highly time-consuming strategy of arranging seismic data trace-by-trace, limiting its wide application in pre-stack inversion. A fast pre-stack multi-channel inversion constrained by seismic reflection features has been proposed to address this issue. The key to our method is to re-characterize the reflection features to directly constrain the pre-stack inversion through a Hadamard product operator without rearranging the seismic data. The seismic reflection features can reflect the distribution of the stratum reflection interface, and we obtained them from the post-stack profile by searching the shortest local Euclidean distance between adjacent seismic traces. Instead of directly constructing a large-size reflection features constraint operator advocated by the conventional methods, through decomposing the reflection features along the vertical and horizontal direction at a particular sampling point, we have constructed a computationally well-behaved constraint operator represented by the vertical and horizontal partial derivatives. Based on the Alternating Direction Method of Multipliers (ADMM) optimization, we have derived a fast algorithm for solving the objective function, including Hadamard product operators. Compared with the conventional reflection features constrained inversion, the proposed method is more efficient and accurate, proved on the Overthrust model and a field data set.

A Multi-Channel Contrastive Learning Network Based Intrusion Detection Method

Network intrusion data are characterized by high feature dimensionality, extreme category imbalance, and complex nonlinear relationships between features and categories. The actual detection accuracy of existing supervised intrusion-detection models performs poorly. To address this problem, this paper proposes a multi-channel contrastive learning network-based intrusion-detection method (MCLDM), which combines feature learning in the multi-channel supervised contrastive learning stage and feature extraction in the multi-channel unsupervised contrastive learning stage to train an effective intrusion-detection model. The objective is to research whether feature enrichment and the use of contrastive learning for specific classes of network intrusion data can improve the accuracy of the model. The model is based on an autoencoder to achieve feature reconstruction with supervised contrastive learning and for implementing multi-channel data reconstruction. In the next stage of unsupervised contrastive learning, the extraction of features is implemented using triplet convolutional neural networks (TCNN) to achieve the classification of intrusion data. Through experimental analysis, the multichannel contrastive learning network-based intrusion-detection method achieves 98.43% accuracy in dataset CICIDS17 and 93.94% accuracy in dataset KDDCUP99.

Structure-adapted Multichannel Matching Pursuit for Seismic Trace Decomposition

While the single-channel matching pursuit decomposes a seismic trace into a series of wavelets, the multichannel matching pursuit examines the lateral coherence of the seismic traces as a constraint to improve the lateral continuity of the decomposition. However, the presence of structures in the subsurface negatively affects the performance of the multichannel matching pursuit. We proposed a structure-adapted matching pursuit method that combines with a dynamic time-warping (DTW) algorithm to estimate the similarity between adjacent seismic traces and extract an optimal wavelet along the dip plane. This structure-adapted implementation would significantly speed up the convergence of the decomposition process. We modified the DTW algorithm by combining the Euclidean distance of the seismic trace and the first-order temporal derivative of the seismic trace. We also updated the amplitudes of all extracted wavelets simultaneously based on the least-squares principle. This DTW-based, structure-adapted, least-squares, multichannel matching pursuit method would improve the robustness and accuracy of seismic trace decomposition.

Evaluation of multi-channel phase reconstruction methods for quantitative susceptibility mapping on postmortem human brain

Quantitative Susceptibility Mapping (QSM) is an established Magnetic Resonance Imaging (MRI) technique with high potential in brain iron studies associated to several neurodegenerative diseases. Unlike other MRI techniques, QSM relies on phase images to estimate tissue's relative susceptibility, therefore requiring a reliable phase data. Phase images from a multi-channel acquisition should be reconstructed in a proper way. On this work it was compared the performance of combination of phase matching algorithms (MCPC3D-S and VRC) and phase combination methods based on a complex weighted sum of phases, considering the magnitude at different powers (k = 0 to 4) as the weighting factor. These reconstruction methods were applied in two datasets: a simulated brain dataset for a 4-coil array and data of 22 postmortem subjects acquired at a 7T scanner using a 32 channels coil. For the simulated dataset, differences between the ground truth and the Root Mean Squared Error (RMSE) were evaluated. For both simulated and postmortem data, the mean (MS) and standard deviation (SD) of susceptibility values of five deep gray matter regions were calculated. For the postmortem subjects, MS and SD were statistically compared across all subjects. A qualitative analysis indicated no differences between methods, except for the Adaptive approach on postmortem data, which showed intense artifacts. In the 20% noise level case, the simulated data showed increased noise in central regions. Quantitative analysis showed that both MS and SD were not statistically different when comparing k=1 and k=2 on postmortem brain images, however visual inspection showed some boundaries artifacts on k=2. Furthermore, the RMSE decreased (on regions near the coils) and increased (on central regions and on overall QSM) with increasing k. In conclusion, for reconstruction of phase images from multiple coils with no reference available, alternative methods are needed. In this study it was found that overall, the phase combination with k=1 is preferred over other powers of k.

Modelling A Multichannel Signature Diagnostics Method in Multimedia Terminal Devices

The issues of analytical and simulation-based evaluation of reliability of controlling the multi-channel signature diagnostic method are described in this paper. The stages of the life cycle of technical means of data transmission systems and the ways of increasing their reliability characteristics are covered. Developed multi-channel signature method modelling algorithms and software to automate the identification of reference signatures for multi-output diagnostic devices. The analysis of modern microprocessor devices of data transmission systems as an object of control and diagnostics necessary for the selection of characteristics of methods of signature analysis is considered.

Multivariate complex modulation model decomposition and its application to gear fault diagnosis

The single-channel vibration signal of gears contains limited information, and it is easily affected by the transmission path. Therefore, multi-channel signals should be used for fault diagnosis because multi-channel gear signals usually contain richer and more comprehensive information about the equipment status. But the existing single-channel signal processing methods are not applicable to multi-channel signals, and each of the existing multi-channel signal processing methods has its own limitations. Therefore, this study proposes a new multi-channel signal processing method called multivariate complex modulation model decomposition (MCMMD), by which multi-channel signals can be decomposed accurately and adaptively at the same time. The core of the method is to iteratively update the model parameters by combining all channel signals to acquire the pattern alignment property. The decomposition performance is analyzed first. Then MCMMD is applied to simulation and experimental multi-channel gear fault signals. For comparison, ensemble empirical mode decomposition (EEMD), multivariate empirical mode decomposition (MEMD), multivariate variational mode decomposition (MVMD), multivariate local characteristic-scale decomposition (MLCD), and completely adaptive projection MLCD (CAPMLCD) are presented as well. The results show that the decomposition accuracy and robustness of MCMMD are better than those of the other methods compared. Therefore, MCMMD is an accurate and effective multi-channel signal processing method.

Time delay estimation via average magnitude differences among multiple microphone signals

Time delay estimation (TDE) plays a significant role in hands-free speech communication systems for localizing and tracking speakers. To boost the robustness of time delay estimators in room acoustic environments, a novel TDE approach is proposed in this paper. This method first exploits the reciprocals of average magnitude difference functions of sound signals captured at a microphone array, instead of cross correlation coefficients, to construct the entries of the parameterized correlation coefficient matrix in the multichannel cross-correlation coefficient algorithm. A multichannel average magnitude difference coefficient is then defined to establish the time delay estimator. Simulation results demonstrate that the proposed TDE strategy can yield better performance as compared to the multichannel cross-correlation coefficient method in noisy and reverberant environment.

Breast Tumor Classification in Ultrasound Images by Fusion of Deep Convolutional Neural Network and Shallow LBP Feature.

Breast cancer is one of the most dangerous and common cancers in women which leads to a major research topic in medical science. To assist physicians in pre-screening for breast cancer to reduce unnecessary biopsies, breast ultrasound and computer-aided diagnosis (CAD) have been used to distinguish between benign and malignant tumors. In this study, we proposed a CAD system for tumor diagnosis using a multi-channel fusion method and feature extraction structure based on multi-feature fusion on breast ultrasound (BUS) images. In the pre-processing stage, the multi-channel fusion method completed the color conversion of the BUS image to make it contain richer information. In the feature extraction stage, the pre-trained ResNet50 network was selected as the basic network, and three levels of features were combined based on adaptive spatial feature fusion (ASFF), and finally, the shallow local binary pattern (LBP) texture features were fused. Support vector machine (SVM) was used for comparative analysis. A retrospective analysis was carried out, and 1615 breast tumor images (572 benign and 1043 malignant) confirmed by pathological examinations were collected. After data processing and augmentation, for an independent test set consisting of 874 breast ultrasound images (457 benign and 417 malignant), the accuracy, precision, recall, specificity, F1 score, and AUC of our method were 96.91%, 98.75%, 94.72%, 98.91%, 0.97, and 0.991, respectively. The results show that the integration of shallow LBP texture features and multi-level depth features can more effectively improve the comprehensive performance of breast tumor diagnosis, and has strong clinical application value. Compared with the past methods, our proposed method is expected to realize the automatic diagnosis of breast tumors and provide an auxiliary tool for radiologists to accurately diagnose breast diseases.

Auditory performance of reproduced sound field in aircraft cabin mock-up by feedback controlled multichannel least-square equalization method

The cost of experimental evaluation on the acoustic environment in an aircraft during the flight is enormous. Building a cabin mock-up on the ground and reproducing the acoustic environment based on the method of sound field reproduction is of great significance for subsequent noise reduction and sound quality research. In this paper, feedback control was combined with general multichannel least-square equalization method, and the target sound field recording from a real flight was reproduced in an aircraft cabin mock-up. The frequency error was controlled within 3 dB in all frequency bands. In addition, the reproduction errors of psychoacoustics parameters, such as loudness and sharpness, were obviously reduced, indicating that the auditory perception of reproduced sound field was in consistent with target sound.

S-wave velocity characteristics and mineralization of the southern tibet detachment system-yalaxiangbo dome

A series of extensional structures, including the southern Tibet detachment system (STDS), the north-south trending rifts (NSTR), and the northern Himalayan gneiss dome (NHGD), developed from the collision and compression between the Indian and Eurasian plates. These tectonic movements were accompanied by magmatism and polymetallic mineralization. Cuona Rift (CR) is located on the STDS next to the Yalaxiangbo Dome (YD) and passes through the Zhegucuo-longzi fault (ZLF), the Lhozhag fault (LZF), the Rongbu-Gudui fault (RGF), the Cuonadong dome (CD), and the YD. The study area contains numerous metal deposits, such as rare metal ore, lead zinc ore, gold deposits, and two geothermal fields, i.e., the Cuona geothermal field (CGF) and the Gudui geothermal field (GGF). Current research on the geological structures from the STDS to the YD is mainly based on magnetotelluric and natural seismic imaging. These surveys have a low resolution, making it impossible to image the shallow crust in detail. This study obtained about a 112 km S-wave velocity profile from the STDS to the YD using the multichannel surface wave imaging method. The profile results indicated that the average thickness of the sedimentary layer from the STDS to the YD is 400–500 m, while it is more than 800 m at certain fault zones. The CD is connected to the high-velocity body below the Zhaxikang ore concentration area (ZOCA) and may have the same provenance. The thermal conductivity reveals that the CGF, the GGF, and the ZOCA have high values and a more intense thermal radiation capacity. This drives the migration and circulation of the thermal fluids in the CGF and the GGF, causing them to continuously transmit heat to the shallow surface along the fault system. The migration of the thermal fluids extracts useful elements from the geological bodies through which it flows. When these elements mix with the atmospheric infiltration water, it precipitates to form the Zhaxikang hydrothermal superimposed transformation type lead-zinc polymetallic deposit.

Electron scattering by formamide: Elastic and electronically inelastic cross sections up to 179 energetically open states

The Schwinger multichannel method with pseudopotentials was employed to obtain elastic and electronically inelastic cross sections for the scattering of electrons by formamide up to impact energies of 50 eV. The scattering calculations were carried out according to the minimal orbital basis for the single-configuration-interaction strategy and considered up to 179 open target states in the composition of the space of coupled channels for the description of the multichannel coupling. To include polarization effects, we consider only the excitations related to the hole-particle pairs used in the active space of the minimal orbital basis for the single-configuration-interaction approach. The elastic and electronically inelastic cross sections for the excitation from the ground state to the first four low-lying electronically excited states of formamide are presented, and these results are compared to previous calculations available in the literature. The partial and total ionization cross sections calculated with the binary-encounter-Bethe model and the total cross section calculated as the sum of the elastic, total electronically inelastic, and total ionization cross sections are also reported.

A speech separation algorithm based on the comb-filter effect

In the field of speech separation, the traditional single-channel and multi-channel speech separation methods have made great progress. However, the accuracy of separation and automatic speech recognition(ASR) rate are not yet satisfactory. With the development of neural networks, some scholars began to use deep learning to achieve speech separation. Although this kind of method improves the accuracy of speech separation, it also leads to the need for pre-training the model, higher computational complexity and reduced separation performance when the model does not match the mixed signal. This paper has conducted an in-depth study on the scene of multi-speaker separation, and proposed a new dual-channel speech separation algorithm based on the Comb-Filter Effect (CFE). The CFE is an effect that occurs when a signal passes through a first-order differential microphone(FDM) array. And this effect is discovered and exploited for the first time. By using this effect, this paper designed a new signal spectrum estimation method that can realize accurate estimation of speech signal, and combined this method with traditional spectral subtraction to achieve the purpose of speech separation. Finally, this paper compared the proposed algorithm with the traditional FastICA-based algorithm and the fully-convolutional time-domain audio separation network(Conv-TasNet)-based algorithm. The results of simulation and comparison experiments show that the algorithm can effectively separate two-way speech signals while greatly reducing the computational complexity and has excellent robustness. In various situations, the proposed algorithm can obtain the Scale-Invariant Source-to-Noise Ratio improvement (SI-SNRi) of 9.19 dB on average. In addition, the Short-Time Objective Intelligibility (STOI) and Perceptual Evaluation of Speech Quality (PESQ) of the speech signal can be improved by an average of 33% and 70% or more respectively.

FDA-MIMO Radar Target Recognition Based on SVM Classification with Multi-channel Feature Extraction

FDA-MIMO radar has good anti-active interference performance and has received extensive attention due to its distance dependence. However, there is still a lack of target and interference recognition methods for FDA-MIMO radar in complex environments. Therefore, in this paper, we propose a multi-channel feature extraction classification method based on the support vector machine (SVM), which realizes the classification of four active interferences and targets. In short, we classify the fine signal characteristics of different interference signals by extracting effective features and selecting efficient classifiers. Simulation results show that when the interference to noise ratio (INR) is greater than -15 dB, the recognition accuracy is greater than 0.95. It also shows that the proposed method can distinguish target and interference well in a variety of complex environments.

Emotion Recognition of Subjects With Hearing Impairment Based on Fusion of Facial Expression and EEG Topographic Map.

Emotion analysis has been employed in many fields such as human-computer interaction, rehabilitation, and neuroscience. But most emotion analysis methods mainly focus on healthy controls or depression patients. This paper aims to classify the emotional expressions in individuals with hearing impairment based on EEG signals and facial expressions. Two kinds of signals were collected simultaneously when the subjects watched affective video clips, and we labeled the video clips with discrete emotional states (fear, happiness, calmness, and sadness). We extracted the differential entropy (DE) features based on EEG signals and converted DE features into EEG topographic maps (ETM). Next, the ETM and facial expressions were fused by the multichannel fusion method. Finally, a deep learning classifier CBAM_ResNet34 combined Residual Network (ResNet) and Convolutional Block Attention Module (CBAM) was used for subject-dependent emotion classification. The results show that the average classification accuracy of four emotions recognition after multimodal fusion achieves 78.32%, which is higher than 67.90% for facial expressions and 69.43% for EEG signals. Moreover, visualization by the Gradient-weighted Class Activation Mapping (Grad-CAM) of ETM showed that the prefrontal, temporal and occipital lobes were the brain regions closely related to emotional changes in individuals with hearing impairment.

Joint Separation and Localization of Moving Sound Sources Based on Neural Full-Rank Spatial Covariance Analysis

This paper presents an unsupervised multichannel method that can separate moving sound sources based on an amortized variational inference (AVI) of joint separation and localization. A recently proposed blind source separation (BSS) method called neural full-rank spatial covariance analysis (FCA) trains a neural separation model based on a nonlinear generative model of multichannel mixtures and can precisely separate unseen mixture signals. This method, however, assumes that the sound sources hardly move, and thus its performance is easily degraded by the source movements. In this paper, we solve this problem by introducing time-varying spatial covariance matrices and directions of arrival of sources into the nonlinear generative model of the neural FCA. This generative model is used for training a neural network to jointly separate and localize moving sources by using only multichannel mixture signals and array geometries. The training objective is derived as a lower bound on the log-marginal posterior probability in the framework of AVI. Experimental results obtained with mixture signals of moving sources show that our method outperformed an existing joint separation and localization method and standard BSS methods.