Search

Mesoscale eddies have attracted increased attention due to their central role in ocean energy and mass transport. The observations of their three-dimensional structure will facilitate the understanding of nonlinear eddy dynamics. In this paper, we propose a novel framework, the mesoscale eddy characterization from ordinal modalities recurrence networks method (MeC-OMRN), that utilizes a Petrel-II underwater glider for in situ observations and vertical structure characterization of a moving mesoscale eddy in the northern South China Sea. First, higher resolution continuous observation profile data collected throughout the traversal by the underwater glider are acquired and preprocessed. Subsequently, we analyze and compute these nonlinear data. To further amplify the hidden structural features of the mesoscale eddy, we construct ordinal modalities sequences rich in spatiotemporal characteristics based on the measured vertical density of the mesoscale eddy. Based on this, we employ ordinal modalities recurrence plots (OMRPs) to depict the vertical structure inside and outside the eddy, revealing significant differences in the OMRPs and the unevenness of density stratification within the eddy. To validate our intriguing findings from the perspective of complex network theory, we build the multivariate weighted ordinal modalities recurrence networks, through which network measures exhibit a more random distribution of vertical density stratification within the eddy, possibly due to more intense vertical convection and oscillations within the eddy's seawater micelles. These framework and intriguing findings are anticipated to be applied to more data-driven in situ observation tasks of oceanic phenomena. [ABSTRACT FROM AUTHOR]

Driving fatigue has been one of the major causes of traffic accident. Efficient and accurate detection of driving fatigue are a legitimate public concern. In this paper, we conduct the simulated driving experiments and an EEG-based driving fatigue detection framework integrating multilayer brain network and convolutional neural network (CNN) is developed. This lightweight attention-based multi-frequency topology learning (AMFTL) framework first captures the fatigue-related multi-frequency brain topological information and then feeds it into a CNN-based topology feature extraction (TFE) module to fully explore and integrate the critical topological features. The quantitative analysis results show that there are significant differences in brain topologies between the alert and fatigue states. And experimental results show that our proposed framework achieves an average detection accuracy of 94.71% for driving fatigue, which outperforms the current state-of-the-art methods. This proposed framework is expected to open new venues for EEG-based brain state analysis, and holds promising practical application potential. [ABSTRACT FROM AUTHOR]

Using electroencephalography (EEG) signals to drive a vehicle could help disabled people expand their range of motion and improve their independence. A brain-controlled vehicle (BCV) is a vehicle that is commanded by analyzing EEG signals. However, the analysis and transmission effect of EEG signals is not ideal, the driving performance of the BCV solely relying on EEG signals is relatively poor. In this paper, to solve this problem, we propose a dynamic shared control method based on adaptive network-based fuzzy inference system (ANFIS). First, an ANFIS intelligent controller is designed to automatically make decisions according to the state of the vehicle. Then, safety coefficient and intention coefficient are proposed to evaluate the safety and driving intention of the brain-controlled driver. Finally, a fuzzy controller with safety and intention coefficients as inputs and brain-controlled driver weights as outputs is designed. The controller is the embodiment of a human–machine interaction, which allows the driver to maintain maximum control authority over the BCV under safe conditions by dynamically balancing the control authority of the brain-controlled driver and the ANFIS controller on the BCV. To verify the effectiveness of the proposed method, a joint simulation platform of Carsim and Matlab is established, and several groups of comparative simulation experiments are carried out, through which, it is demonstrated that the proposed method can effectively avoid road deviation while well maintaining the control authority of the brain-controlled driver. [ABSTRACT FROM AUTHOR]

Underwater glider (UG) plays an important role in ocean observation and exploration for a more efficient and deeper understanding of complex ocean environment. Timely identifying the motion states of UG is conducive for timely attitude adjustment and detection of potential anomalies, thereby improving the working reliability of UG. Combining limited penetrable visibility graph (LPVG) and graph convolutional networks (GCN) with self-attention mechanisms, we propose a novel method for motion states identification of UG, which is called as visibility graph and self-attention mechanism-based graph convolutional network (VGSA-GCN). Based on the actual sea trial data of UG, we chose the attitude angle signals of motion states related sensors collected by the control system of UG as the research object and constructed complex networks based on the LPVG method from pitch angle, roll angle, and heading angle data in diving and climbing states. Then, we build a self-attention mechanism-based GCN framework and classify the graphs under different motion states constructed by a complex network. Compared with support vector machines, convolutional neural network, and GCN without self-attention pooling layer, the proposed VGSA-GCN method can more accurately distinguish the diving and climbing states of UG. Subsequently, we analyze the variation of the transitivity coefficient corresponding to these two motion states. The results suggest that the coordination of the various sensors in the attitude adjustment unit during diving becomes closer and more efficient, which corresponds to the higher network measure of the diving state compared to the climbing state. [ABSTRACT FROM AUTHOR]

Constructing reliable and effective models to recognize human emotional states has become an important issue in recent years. In this article, we propose a double way deep residual neural network combined with brain network analysis, which enables the classification of multiple emotional states. To begin with, we transform the emotional EEG signals into five frequency bands by wavelet transform and construct brain networks by inter-channel correlation coefficients. These brain networks are then fed into a subsequent deep neural network block which contains several modules with residual connection and enhanced by channel attention mechanism and spatial attention mechanism. In the second way of the model, we feed the emotional EEG signals directly into another deep neural network block to extract temporal features. At the end of the two ways, the features are concatenated for classification. To verify the effectiveness of our proposed model, we carried out a series of experiments to collect emotional EEG from eight subjects. The average accuracy of the proposed model on our emotional dataset is 94.57%. In addition, the evaluation results on public databases SEED and SEED-IV are 94.55% and 78.91%, respectively, demonstrating the superiority of our model in emotion recognition tasks. [ABSTRACT FROM AUTHOR]

Human gesture-related electromyographic signal in intelligent recognition systems has attracted widespread attention. The EMG signal is the temporal and spatial superposition of motor unit neural potentials and it contains nonlinear and complex characteristics. Despite the previous efforts, recognizing more different actions and building an online recognition system remain challenging. To address these issues, we construct a multi-feature time-frequency neural network system and a dataset which contains twenty kinds of hand movements. In a multi-featured time-frequency neural network system, the multi-layer CNN structure is used to obtain faster recognition and better classification results. The experimental results demonstrate that equipment and algorithmic model can reach a 94.66% accuracy. Our approach focuses on processing multiple time and frequency domain features of sEMG using CNN. Importantly, we also perform real-time validation. The system can accurately recognize hand movements to control UAV motion in real-time, in which case system classification takes 0.05s. This demonstrates the practicality and effectiveness of the sEMG acquisition system based on the multifeatured time-frequency neural network. [ABSTRACT FROM AUTHOR]

Brain–computer interface (BCI) based on motor imagery electroencephalogram (EEG) has been widely used in various applications. Despite the previous efforts, the remained major challenges are effective feature extraction and the time-consuming calibration procedure. To address these issues, a novel multiattention adaptation network integrating the multiple attention mechanism and transfer learning is proposed to classify the EEG signals. First, the multiattention layer is introduced to automatically capture the dominant brain regions relevant to mental tasks without incorporating any prior knowledge about the physiology. Then, a multiattention convolutional neural network is employed to extract deep representation from raw EEG signals. Especially, a domain discriminator is applied to deep representation to reduce the differences between sessions for target subjects. The extensive experiments are conducted on three public EEG datasets (Dataset IIa and IIb of BCI Competition IV, and High Gamma dataset), achieving the competitive performance with average classification accuracy of 81.48%, 82.54%, and 93.97%, respectively. All the results outperform the state-of-the-art algorithms demonstrate the effectiveness and robustness of the proposed method. Importantly, we confirm that it is easier and more appropriate to transfer the information from local brain regions than from the whole brain. This enhances the transfer ability of deep features and, hence, it improves the performance of BCI systems. [ABSTRACT FROM AUTHOR]

Electroencephalography-based Brain Computer Interfaces (BCIs) invariably have a degenerate performance due to the considerable individual variability. To address this problem, we develop a novel domain adaptation method with optimal transport and frequency mixup for cross-subject transfer learning in motor imagery BCIs. Specifically, the preprocessed EEG signals from source and target domain are mapped into latent space with an embedding module, where the representation distributions and label distributions across domains have a large discrepancy. We assume that there exists a non-linear coupling matrix between both domains, which can be utilized to estimate the distance of joint distributions for different domains. Depending on the optimal transport, the Wasserstein distance between source and target domains is minimized, yielding the alignment of joint distributions. Moreover, a new mixup strategy is also introduced to generalize the model, where the inputs trials are mixed in frequency domain rather than in raw space. The extensive experiments on three evaluation benchmarks are conducted to validate the proposed framework. All the results demonstrate that our method achieves a superior performance than previous state-of-the-art domain adaptation approaches. [ABSTRACT FROM AUTHOR]

Visual evoked potential (VEP)-related EEG signals have attracted widespread attention in the construction of brain-computer interface (BCI) systems. However, long-term use of the BCI system is prone to fatigue. Effectively coping with fatigue is the key to expanding BCI application scenarios. In this brief, we conduct two VEP experiments and propose a novel, concise and practical convolutional neural network (CNN) model to study and solve this problem. In detail, firstly, in terms of the stimulus frequencies in VEP experiments, we intercept the spectrum sequences of the fundamental waves and two harmonics. All these spectrum sequences are then paralleled input into the proposed multi-harmonic linkage CNN (MHLCNN) model, through three branches. Finally, the linkage characteristics of multiple harmonics are combined for VEP signal classification. The experimental results demonstrate that the proposed model shows good scalability, and can respectively improve the average classification accuracy by 23.17% and 15.85% when applied to steady-state VEP (SSVEP) signals in fatigue state and steady-state motion VEP (SSMVEP) signals, compared with the benchmark methods. All these provide a feasible and high-quality solution for reducing the impact of fatigue on the performance of VEP-based BCI systems. [ABSTRACT FROM AUTHOR]

Epilepsy makes the patients suffer great pain and has a very bad impact on daily life. In this paper, a novel method is proposed to implement electroencephalogram (EEG)-based epilepsy detection, in which multi-frequency multilayer brain network and deep learning are jointly utilized. Firstly, based on the multi-frequency characteristics of brain, we construct a multilayer brain network from the multi-channel EEG signals. The time, frequency and channel-related information from EEG signals are all mapped into the multilayer network topology, making it an effective feature for epilepsy detection. Subsequently, with multilayer brain network as input, a multilayer deep convolutional neural network (MDCNN) model is designed. MDCNN model has two blocks and uses a parallel multi-branch design in the first block, which exactly matches the multilayer structure of the proposed brain network. The experimental results on publicly available CHB-MIT datasets show that the proposed method can accurately detect epilepsy, with a high average accuracy of 99.56%, sensitivity of 99.29%, and specificity of 99.84%. All these provide an efficient solution for characterizing the complex brain states using multi-channel EEG signals. [ABSTRACT FROM AUTHOR]

Electroencephalogram (EEG) is a typical physiological signal. The classification of EEG signals is of great significance to human beings. Combining recurrence plot and convolutional neural network (CNN), we develop a novel method for classifying EEG signals. We select two typical EEG signals, namely, epileptic EEG and fatigue driving EEG, to verify the effectiveness of our method. We construct recurrence plots from EEG signals. Then, we build a CNN framework to classify the EEG signals under different brain states. For the classification of epileptic EEG signals, we design three different experiments to evaluate the performance of our method. The results suggest that the proposed framework can accurately distinguish the normal state and the seizure state of epilepsy. Similarly, for the classification of fatigue driving EEG signals, the method also has a good classification accuracy. In addition, we compare with the existing methods, and the results show that our method can significantly improve the detection results. [ABSTRACT FROM AUTHOR]

Brain–computer interface (BCI) systems based on electroencephalography (EEG) signals have been extensively used in medical practice. To enhance the BCI performance, improving the classification accuracy of EEG signals is the key, which has always been the focus of research and development. In this article, a novel method integrating complex network and broad learning system (BLS) is proposed for visual evoked potential (VEP)-based BCI research. First, systematic VEP-based brain experiments are conducted for obtaining EEG signals, including steady-state VEP (SSVEP) and steady-state motion VEP (SSMVEP). Then, limited penetrable visibility graph (LPVG) and its degree sequence are employed to implement the preliminary feature extraction. All these features are finally fed into a BLS to study and classify the SSVEP and SSMVEP signals, respectively. The classification results show that our LPVG-based BLS can effectively classify VEP-based EEG signals, with average classification accuracy 96.22% for SSVEP and 74.54% for SSMVEP. These results are significantly better than other comparison methods as well as traditional CCA-based methods. All these open up new venues for studying EEG-based BCI systems via the fusion of network science and BLS. [ABSTRACT FROM AUTHOR]

Early screening of COVID-19 is essential for pandemic control, and thus to relieve stress on the health care system. Lung segmentation from chest X-ray (CXR) is a promising method for early diagnoses of pulmonary diseases. Recently, deep learning has achieved great success in supervised lung segmentation. However, how to effectively utilize the lung region in screening COVID-19 still remains a challenge due to domain shift and lack of manual pixel-level annotations. We hereby propose a multi-appearance COVID-19 screening framework by using lung region priors derived from CXR images. Firstly, we propose a multi-scale adversarial domain adaptation network (MS-AdaNet) to boost the cross-domain lung segmentation task as the prior knowledge to the classification network. Then, we construct a multi-appearance network (MA-Net), which is composed of three sub-networks to realize multi-appearance feature extraction and fusion using lung region priors. At last, we can obtain prediction results from normal, viral pneumonia, and COVID-19 using the proposed MA-Net. We extend the proposed MS-AdaNet for lung segmentation task on three different public CXR datasets. The results suggest that the MS-AdaNet outperforms contrastive methods in cross-domain lung segmentation. Moreover, experiments reveal that the proposed MA-Net achieves accuracy of 98.83 $\%$ and F1-score of 98.71 $\%$ on COVID-19 screening. The results indicate that the proposed MA-Net can obtain significant performance on COVID-19 screening. [ABSTRACT FROM AUTHOR]

Driver fatigue detection is of great significance for guaranteeing traffic safety and further reducing economic as well as societal loss. In this article, a novel complex network (CN) based broad learning system (CNBLS) is proposed to realize an electroencephalogram (EEG)-based fatigue detection. First, a simulated driving experiment was conducted to obtain EEG recordings in alert and fatigue state. Then, the CN theory is applied to facilitate the broad learning system (BLS) for realizing an EEG-based fatigue detection. The results demonstrate that the proposed CNBLS can accurately differentiate the fatigue state from an alert state with high stability. In addition, the performances of the four existing methods are compared with the results of the proposed method. The results indicate that the proposed method outperforms these existing methods. In comparison to directly using EEG signals as the input of BLS, CNBLS can sharply improve the detection results. These results demonstrate that it is feasible to apply BLS in classifying EEG signals by means of CN theory. Also, the proposed method enriches the EEG analysis methods. [ABSTRACT FROM AUTHOR]

Gas–liquid two-phase flow is of great importance in various industrial processes. How to accurately measure the flow parameters in the gas–liquid two-phase flow remains a challenging problem. In this article, we develop a novel deep learning based soft measure technique to predict the gas void fraction, which is one key parameter in a gas–liquid two-phase flow. We conduct the vertical upward gas–liquid two-phase flow experiments to measure the flow signals by using the four-sector distributed conductance sensor. Then, we design a novel multitask-based temporal-channelwise convolutional neural network (MTCCNN) to predict the gas void fraction. In MTCCNN, we first utilize the decomposed convolutional block to extract temporal dependence and channel connection from fluid data. After further fusion by the dense layer, we apply multitask learning to make full use of the extracted features through both classification branch and gas void fraction prediction branch. We compare our MTCCNN with its variations to demonstrate the proposed improvements. We also present other competitive methods for comparisons, which shows that our MTCCNN presents a better performance in gas void fraction prediction. [ABSTRACT FROM AUTHOR]

Gas-liquid two-phase flow is attracting increasing attention in industrial areas. Precise measurement of total rate and void fraction, key parameters in two-phase flows, can significantly improve the industrial efficiency, which is still a challenging issue due to their complex characteristics. To cope with this problem, we design a Stage-wise Densely Connected Network (SDCN) to simultaneously measure the total rate and void fraction. First, we conduct series of vertical upward gas-liquid two-phase flow experiments to collect signals from the four-sector conductance sensor. Then, we combine the stage-wise strategy, dense connections and decomposed convolution kernels to construct the SDCN. Using the stage-wise strategy, we introduce the flow structures to improve the accuracy of the measurement. During this process, dense connections between blocks and decomposed convolution kernels are conducted to better extract the features. Finally, we compare the SDCN and its variations to demonstrate the importance of these improvements. We also show some other competitive methods for parameter measurement. The results suggest that our proposed SDCN could accurately measure both the total rate and void fraction of gas-liquid two-phase flow, which provides a new solution in parameter measurement of two-phase flows. [ABSTRACT FROM AUTHOR]

Electroencephalography (EEG) decoding is an important part of Visual Evoked Potentials-based Brain-Computer Interfaces (BCIs), which directly determines the performance of BCIs. However, long-time attention to repetitive visual stimuli could cause physical and psychological fatigue, resulting in weaker reliable response and stronger noise interference, which exacerbates the difficulty of Visual Evoked Potentials EEG decoding. In this state, subjects’ attention could not be concentrated enough and the frequency response of their brains becomes less reliable. To solve these problems, we propose an attention-based parallel multiscale convolutional neural network (AMS-CNN). Specifically, the AMS-CNN first extract robust temporal representations via two parallel convolutional layers with small and large temporal filters respectively. Then, we employ two sequential convolution blocks for spatial fusion and temporal fusion to extract advanced feature representations. Further, we use attention mechanism to weight the features at different moments according to the output-related interest. Finally, we employ a full connected layer with softmax activation function for classification. Two fatigue datasets collected from our lab are implemented to validate the superior classification performance of the proposed method compared to the state-of-the-art methods. Analysis reveals the competitiveness of multiscale convolution and attention mechanism. These results suggest that the proposed framework is a promising solution to improving the decoding performance of Visual Evoked Potential BCIs. [ABSTRACT FROM AUTHOR]

In this article, we propose a method for emotion classification based on multilayer convolutional neural network (MCNN) and combining differential entropy (DE) and brain network. First, we use continuous wavelet transform (CWT) to get the time–frequency representation (TFR) of electroencephalogram (EEG) signals on each channel and extract rich information from different frequency bands for subsequent analysis. Brain networks are then constructed in multiple bands to characterize the spatial connections hidden in the multichannel EEG signals. Based on brain networks, we further develop core brain networks through a set of key nodes determined by DE. These core brain networks are associated with brain activities and differ markedly between different emotional states. The final designed MCNN model takes DE features and core brain networks as inputs for emotion recognition. We evaluate our method on the SJTU emotion EEG dataset, and the average accuracy of 15 subjects achieves 91.45%. Utilizing the complementary features of DE and brain network, the proposed method provides an efficient framework for accurate emotion recognition from EEG signals. [ABSTRACT FROM AUTHOR]

Gas–liquid two-phase flow widely exists in petroleum, natural gas, and other industries. Recognition of flow structure is an important issue in the study of two-phase flow, and it is of great significance for the optimization of industrial processes. Therefore, how to recognize complex flow structures effectively represents a challenge. To cope with this problem, we develop a novel deep learning network to recognize flow structures under different flow conditions. In particular, we conduct vertical upward gas–liquid two-phase flow experiments to obtain the flow structure data set on the basis of images collected by a high-speed camera. Then, we design a branch-aggregation network (BAN), where the branch structure is utilized to increase the width of the network, and multilevel aggregation structure is used to fuse features of different levels. In recognition of flow structure, the proposed network achieves an accuracy of 99.60% with a fast convergence speed and shows the advantages in antinoise ability, which is significant for online recognition in industrial processes. The results indicate that BAN can be a feasible method to recognize complex flow structures. [ABSTRACT FROM AUTHOR]

Electroencephalogram (EEG) has been widely used in brain computer interface (BCI) due to its convenience and reliability. The EEG-based BCI applications are majorly limited by the time-consuming calibration procedure for discriminative feature representation and classification. Existing EEG classification methods either heavily depend on the handcrafted features or require adequate annotated samples at each session for calibration. To address these issues, we propose a novel dynamic joint domain adaptation network based on adversarial learning strategy to learn domain-invariant feature representation, and thus improve EEG classification performance in the target domain by leveraging useful information from the source session. Specifically, we explore the global discriminator to align the marginal distribution across domains, and the local discriminator to reduce the conditional distribution discrepancy between sub-domains via conditioning on deep representation as well as the predicted labels from the classifier. In addition, we further investigate a dynamic adversarial factor to adaptively estimate the relative importance of alignment between the marginal and conditional distributions. To evaluate the efficacy of our method, extensive experiments are conducted on two public EEG datasets, namely, Datasets IIa and IIb of BCI Competition IV. The experimental results demonstrate that the proposed method achieves superior performance compared with the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Electroencephalogram (EEG) signals acquired from brain can provide an effective representation of the human's physiological and pathological states. Up to now, much work has been conducted to study and analyze the EEG signals, aiming at spying the current states or the evolution characteristics of the complex brain system. Considering the complex interactions between different structural and functional brain regions, brain network has received a lot of attention and has made great progress in brain mechanism research. In addition, characterized by autonomous, multi-layer and diversified feature extraction, deep learning has provided an effective and feasible solution for solving complex classification problems in many fields, including brain state research. Both of them show strong ability in EEG signal analysis, but the combination of these two theories to solve the difficult classification problems based on EEG signals is still in its infancy. We here review the application of these two theories in EEG signal research, mainly involving brain–computer interface, neurological disorders and cognitive analysis. Furthermore, we also develop a framework combining recurrence plots and convolutional neural network to achieve fatigue driving recognition. The results demonstrate that complex networks and deep learning can effectively implement functional complementarity for better feature extraction and classification, especially in EEG signal analysis. [ABSTRACT FROM AUTHOR]

According to statistics from the World Health Organization, China has always been among the countries with high incidence of traffic accidents, and the main reason is fatigue driving. In recent years, regression analysis of electroencephalogram (EEG) signals has already been a topic of interest within the field of fatigue driving research, yet, it has not been effectively resolved. In this paper, we designed a platform for the collection of EEG signals for fatigue driving that monitors the brain's fatigue state through multiple sensors. Based on the collected EEG data, a framework of fatigue driving regression based on EEG has been proposed. In order to determine the driver's fatigue level, we produced the data set label, which calculates the fatigue index of EEG signals to characterize the level of fatigue. In order to better cope with individual differences, the fatigue index curve was fitted by least squares. At the same time, we proposed an Ensemble Learning driver fatigue index regression analysis method based on the Bayesian model combination, with the support vector regression algorithm as a base learner. By increasing the diversity and difference of the base learners, the performance of the regression analysis method during the process of driver fatigue index regression analysis has been improved. The experimental results showed that the proposed regression analysis method was reliable and could accurately and reliably characterize the driver's fatigue index. [ABSTRACT FROM AUTHOR]