Motion states identification of underwater glider based on complex networks and graph convolutional networks.

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.

Characterizing gas-liquid two-phase flow behavior using complex network and deep learning.

Gas-liquid two-phase flow is polymorphic and unstable, and characterizing its flow behavior is a major challenge in the study of multiphase flow. We first conduct dynamic experiments on gas-liquid two-phase flow in a vertical tube and obtain multi-channel signals using a self-designed four-sector distributed conductivity sensor. In order to characterize the evolution of gas-liquid two-phase flow, we transform the obtained signals using the adaptive optimal kernel time-frequency representation and build a complex network based on the time-frequency energy distribution. As quantitative indicators, global clustering coefficients of the complex network at various sparsity levels are computed to analyze the dynamic behavior of various flow structures. The results demonstrate that the proposed approach enables effective analysis of multi-channel measurement information for revealing the evolutionary mechanisms of gas-liquid two-phase flow. Furthermore, for the purpose of flow structure recognition, we propose a temporal-spatio convolutional neural network and achieve a classification accuracy of 95.83%.

Interconnected ordinal pattern complex network for characterizing the spatial coupling behavior of gas-liquid two-phase flow.

The complex phase interactions of the two-phase flow are a key factor in understanding the flow pattern evolutional mechanisms, yet these complex flow behaviors have not been well understood. In this paper, we employ a series of gas-liquid two-phase flow multivariate fluctuation signals as observations and propose a novel interconnected ordinal pattern network to investigate the spatial coupling behaviors of the gas-liquid two-phase flow patterns. In addition, we use two network indices, which are the global subnetwork mutual information (I) and the global subnetwork clustering coefficient (C), to quantitatively measure the spatial coupling strength of different gas-liquid flow patterns. The gas-liquid two-phase flow pattern evolutionary behaviors are further characterized by calculating the two proposed coupling indices under different flow conditions. The proposed interconnected ordinal pattern network provides a novel tool for a deeper understanding of the evolutional mechanisms of the multi-phase flow system, and it can also be used to investigate the coupling behaviors of other complex systems with multiple observations.

Criticality in transient behavior of coupled oscillator system toward chimera and synchronization.

Chimera states in spatiotemporal dynamical systems have been investigated in physical, chemical, and biological systems, while how the system is steering toward different final destinies upon spatially localized perturbation is still unknown. Through a systematic numerical analysis of the evolution of the spatiotemporal patterns of multi-chimera states, we uncover a critical behavior of the system in transient time toward either chimera or synchronization as the final stable state. We measure the critical values and the transient time of chimeras with different numbers of clusters. Then, based on an adequate verification, we fit and analyze the distribution of the transient time, which obeys power-law variation process with the increase in perturbation strengths. Moreover, the comparison between different clusters exhibits an interesting phenomenon, thus we find that the critical value of odd and even clusters will alternatively converge into a certain value from two sides, respectively, implying that this critical behavior can be modeled and enabling the articulation of a phenomenological model.

Cross-subject emotion recognition using visibility graph and genetic algorithm-based convolution neural network.

An efficient emotion recognition model is an important research branch in electroencephalogram (EEG)-based brain-computer interfaces. However, the input of the emotion recognition model is often a whole set of EEG channels obtained by electrodes placed on subjects. The unnecessary information produced by redundant channels affects the recognition rate and depletes computing resources, thereby hindering the practical applications of emotion recognition. In this work, we aim to optimize the input of EEG channels using a visibility graph (VG) and genetic algorithm-based convolutional neural network (GA-CNN). First, we design an experiment to evoke three types of emotion states using movies and collect the multi-channel EEG signals of each subject under different emotion states. Then, we construct VGs for each EEG channel and derive nonlinear features representing each EEG channel. We employ the genetic algorithm (GA) to find the optimal subset of EEG channels for emotion recognition and use the recognition results of the CNN as fitness values. The experimental results show that the recognition performance of the proposed method using a subset of EEG channels is superior to that of the CNN using all channels for each subject. Last, based on the subset of EEG channels searched by the GA-CNN, we perform cross-subject emotion recognition tasks employing leave-one-subject-out cross-validation. These results demonstrate the effectiveness of the proposed method in recognizing emotion states using fewer EEG channels and further enrich the methods of EEG classification using nonlinear features.

Convolutional neural network based on recurrence plot for EEG recognition.

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.

Howling Detection and Suppression Based on Segmented Notch Filtering.

The existing adaptive echo cancellation based howling (typically in hearing aids) removal methods have several drawbacks such as insufficient attenuation of the howling component, slow response and nonlinear distortion. To solve these problems, we propose a segmented notch filtering based scheme. Specifically, firstly, it is proved that the attenuation value can reach -330 dB at any detected howling frequency; secondly, the filter coefficients can be readily calculated by a closed-form formula, yielding a fast response to the sudden howling accident; thirdly, the closed-form formula of this filter is theoretically an even function, indicating that this filter possesses a linear transfer characteristic. In combination with proper segmentation and precisely removing these transient samples arising from FIR (Finite Impulsive Response) filtering, nonlinear distortion can be entirely avoided. Experimental results show that our proposed scheme can not only accurately estimate the howling frequency, but can also completely remove it, which yields a high-quality output waveform with a recovery SNR of about 22 dB. Therefore, the proposed segmented notching based scheme possesses vast potential for hearing aid development and other relevant applications.

A Multifrequency Brain Network-Based Deep Learning Framework for Motor Imagery Decoding.

Motor imagery (MI) is an important part of brain-computer interface (BCI) research, which could decode the subject's intention and help remodel the neural system of stroke patients. Therefore, accurate decoding of electroencephalography- (EEG-) based motion imagination has received a lot of attention, especially in the research of rehabilitation training. We propose a novel multifrequency brain network-based deep learning framework for motor imagery decoding. Firstly, a multifrequency brain network is constructed from the multichannel MI-related EEG signals, and each layer corresponds to a specific brain frequency band. The structure of the multifrequency brain network matches the activity profile of the brain properly, which combines the information of channel and multifrequency. The filter bank common spatial pattern (FBCSP) algorithm filters the MI-based EEG signals in the spatial domain to extract features. Further, a multilayer convolutional network model is designed to distinguish different MI tasks accurately, which allows extracting and exploiting the topology in the multifrequency brain network. We use the public BCI competition IV dataset 2a and the public BCI competition III dataset IIIa to evaluate our framework and get state-of-the-art results in the first dataset, i.e., the average accuracy is 83.83% and the value of kappa is 0.784 for the BCI competition IV dataset 2a, and the accuracy is 89.45% and the value of kappa is 0.859 for the BCI competition III dataset IIIa. All these results demonstrate that our framework can classify different MI tasks from multichannel EEG signals effectively and show great potential in the study of remodelling the neural system of stroke patients.

A recurrence network-based convolutional neural network for fatigue driving detection from EEG.

Driver fatigue is an important cause of traffic accidents, which has triggered great concern for detecting drivers' fatigue. Numerous methods have been proposed to fulfill this challenging task, including feature methods and machine learning methods. Recently, with the development of deep learning techniques, many studies achieved better results than traditional feature methods, and the combination of traditional methods and deep learning techniques gradually received attention. In this paper, we propose a recurrence network-based convolutional neural network (RN-CNN) method to detect fatigue driving. To be specific, we first conduct a simulated driving experiment to collect electroencephalogram (EEG) signals of subjects under alert state and fatigue state. Then, we construct the multiplex recurrence network (RN) from EEG signals to fuse information from the original time series. Finally, CNN is employed to extract and learn the features of a multiplex RN for realizing a classification task. The results indicate that the proposed RN-CNN method can achieve an average accuracy of 92.95%. To verify the effectiveness of our method, some existing competitive methods are compared with ours. The results show that our method outperforms the existing methods, which demonstrate the effect of the RN-CNN method.

Characterization of SSMVEP-based EEG signals using multiplex limited penetrable horizontal visibility graph.

The steady state motion visual evoked potential (SSMVEP)-based brain computer interface (BCI), which incorporates the motion perception capabilities of the human visual system to alleviate the negative effects caused by strong visual stimulation from steady-state VEP, has attracted a great deal of attention. In this paper, we design a SSMVEP-based experiment by Newton's ring paradigm. Then, we use the canonical correlation analysis and Support Vector Machines to classify SSMVEP signals for the SSMVEP-based electroencephalography (EEG) signal detection. We find that the classification accuracy of different subjects under fatigue state is much lower than that in the normal state. To probe into this, we develop a multiplex limited penetrable horizontal visibility graph method, which enables to infer a brain network from 62-channel EEG signals. Subsequently, we analyze the variation of the average weighted clustering coefficient and the weighted global efficiency corresponding to these two brain states and find that both network measures are lower under fatigue state. The results suggest that the associations and information transfer efficiency among different brain regions become weaker when the brain state changes from normal to fatigue, which provide new insights into the explanations for the reduced classification accuracy. The promising classification results and the findings render the proposed methods particularly useful for analyzing EEG recordings from SSMVEP-based BCI system.

Multivariate weighted recurrence network analysis of EEG signals from ERP-based smart home system.

Smart home has been widely used to improve the living quality of people. Recently, the brain-computer interface (BCI) contributes greatly to the smart home system. We design a BCI-based smart home system, in which the event-related potentials (ERP) are induced by the image interface based on the oddball paradigm. Then, we investigate the influence of mental fatigue on the ERP classification by the Fisher linear discriminant analysis. The results indicate that the classification accuracy of ERP decreases as the brain evolves from the normal stage to the mental fatigue stage. In order to probe into the difference of the brain, cognitive process between mental fatigue and normal states, we construct multivariate weighted recurrence networks and analyze the variation of the weighted clustering coefficient and weighted global efficiency corresponding to these two brain states. The findings suggest that these two network metrics allow distinguishing normal and mental fatigue states and yield novel insights into the brain fatigue behavior resulting from a long use of the ERP-based smart home system. These properties render the multivariate recurrence network, particularly useful for analyzing electroencephalographic recordings from the ERP-based smart home system.

A recurrence quantification analysis-based channel-frequency convolutional neural network for emotion recognition from EEG.

Constructing a reliable and stable emotion recognition system is a critical but challenging issue for realizing an intelligent human-machine interaction. In this study, we contribute a novel channel-frequency convolutional neural network (CFCNN), combined with recurrence quantification analysis (RQA), for the robust recognition of electroencephalogram (EEG) signals collected from different emotion states. We employ movie clips as the stimuli to induce happiness, sadness, and fear emotions and simultaneously measure the corresponding EEG signals. Then the entropy measures, obtained from the RQA operation on EEG signals of different frequency bands, are fed into the novel CFCNN. The results indicate that our system can provide a high emotion recognition accuracy of 92.24% and a relatively excellent stability as well as a satisfactory Kappa value of 0.884, rendering our system particularly useful for the emotion recognition task. Meanwhile, we compare the performance of the entropy measures, extracted from each frequency band, in distinguishing the three emotion states. We mainly find that emotional features extracted from the gamma band present a considerably higher classification accuracy of 90.51% and a Kappa value of 0.858, proving the high relation between emotional process and gamma frequency band.

Multiplex multivariate recurrence network from multi-channel signals for revealing oil-water spatial flow behavior.

The exploration of the spatial dynamical flow behaviors of oil-water flows has attracted increasing interests on account of its challenging complexity and great significance. We first technically design a double-layer distributed-sector conductance sensor and systematically carry out oil-water flow experiments to capture the spatial flow information. Based on the well-established recurrence network theory, we develop a novel multiplex multivariate recurrence network (MMRN) to fully and comprehensively fuse our double-layer multi-channel signals. Then we derive the projection networks from the inferred MMRNs and exploit the average clustering coefficient and the spectral radius to quantitatively characterize the nonlinear recurrent behaviors related to the distinct flow patterns. We find that these two network measures are very sensitive to the change of flow states and the distributions of network measures enable to uncover the spatial dynamical flow behaviors underlying different oil-water flow patterns. Our method paves the way for efficiently analyzing multi-channel signals from multi-layer sensor measurement system.

Directed weighted network structure analysis of complex impedance measurements for characterizing oil-in-water bubbly flow.

Characterizing the flow structure underlying the evolution of oil-in-water bubbly flow remains a contemporary challenge of great interests and complexity. In particular, the oil droplets dispersing in a water continuum with diverse size make the study of oil-in-water bubbly flow really difficult. To study this issue, we first design a novel complex impedance sensor and systematically conduct vertical oil-water flow experiments. Based on the multivariate complex impedance measurements, we define modalities associated with the spatial transient flow structures and construct modality transition-based network for each flow condition to study the evolution of flow structures. In order to reveal the unique flow structures underlying the oil-in-water bubbly flow, we filter the inferred modality transition-based network by removing the edges with small weight and resulting isolated nodes. Then, the weighted clustering coefficient entropy and weighted average path length are employed for quantitatively assessing the original network and filtered network. The differences in network measures enable to efficiently characterize the evolution of the oil-in-water bubbly flow structures.

Multivariate weighted recurrence network inference for uncovering oil-water transitional flow behavior in a vertical pipe.

Exploring the dynamical behaviors of high water cut and low velocity oil-water flows remains a contemporary and challenging problem of significant importance. This challenge stimulates us to design a high-speed cycle motivation conductance sensor to capture spatial local flow information. We systematically carry out experiments and acquire the multi-channel measurements from different oil-water flow patterns. Then we develop a novel multivariate weighted recurrence network for uncovering the flow behaviors from multi-channel measurements. In particular, we exploit graph energy and weighted clustering coefficient in combination with multivariate time-frequency analysis to characterize the derived complex networks. The results indicate that the network measures are very sensitive to the flow transitions and allow uncovering local dynamical behaviors associated with water cut and flow velocity. These properties render our method particularly useful for quantitatively characterizing dynamical behaviors governing the transition and evolution of different oil-water flow patterns.

Masked autoencoders with handcrafted feature predictions: Transformer for weakly supervised esophageal cancer classification.

BACKGROUND AND OBJECTIVE: Esophageal cancer is a serious disease with a high prevalence in Eastern Asia. Histopathology tissue analysis stands as the gold standard in diagnosing esophageal cancer. In recent years, there has been a shift towards digitizing histopathological images into whole slide images (WSIs), progressively integrating them into cancer diagnostics. However, the gigapixel sizes of WSIs present significant storage and processing challenges, and they often lack localized annotations. To address this issue, multi-instance learning (MIL) has been introduced for WSI classification, utilizing weakly supervised learning for diagnosis analysis. By applying the principles of MIL to WSI analysis, it is possible to reduce the workload of pathologists by facilitating the generation of localized annotations. Nevertheless, the approach's effectiveness is hindered by the traditional simple aggregation operation and the domain shift resulting from the prevalent use of convolutional feature extractors pretrained on ImageNet. METHODS: We propose a MIL-based framework for WSI analysis and cancer classification. Concurrently, we introduce employing self-supervised learning, which obviates the need for manual annotation and demonstrates versatility in various tasks, to pretrain feature extractors. This method enhances the extraction of representative features from esophageal WSI for MIL, ensuring more robust and accurate performance. RESULTS: We build a comprehensive dataset of whole esophageal slide images and conduct extensive experiments utilizing this dataset. The performance on our dataset demonstrates the efficiency of our proposed MIL framework and the pretraining process, with our framework outperforming existing methods, achieving an accuracy of 93.07% and AUC (area under the curve) of 95.31%. CONCLUSION: This work proposes an effective MIL method to classify WSI of esophageal cancer. The promising results indicate that our cancer classification framework holds great potential in promoting the automatic whole esophageal slide image analysis.

Transformer-Based Weakly Supervised Learning for Whole Slide Lung Cancer Image Classification.

Image analysis can play an important role in supporting histopathological diagnoses of lung cancer, with deep learning methods already achieving remarkable results. However, due to the large scale of whole-slide images (WSIs), creating manual pixel-wise annotations from expert pathologists is expensive and time-consuming. In addition, the heterogeneity of tumors and similarities in the morphological phenotype of tumor subtypes have caused inter-observer variability in annotations, which limits optimal performance. Effective use of weak labels could potentially alleviate these issues. In this paper, we propose a two-stage transformer-based weakly supervised learning framework called Simple Shuffle-Remix Vision Transformer (SSRViT). Firstly, we introduce a Shuffle-Remix Vision Transformer (SRViT) to retrieve discriminative local tokens and extract effective representative features. Then, the token features are selected and aggregated to generate sparse representations of WSIs, which are fed into a simple transformer-based classifier (SViT) for slide-level prediction. Experimental results demonstrate that the performance of our proposed SSRViT is significantly improved compared with other state-of-the-art methods in discriminating between adenocarcinoma, pulmonary sclerosing pneumocytoma and normal lung tissue (accuracy of 96.9% and AUC of 99.6%).

Self-supervised contrastive learning for EEG-based cross-subject motor imagery recognition.

Objective. The extensive application of electroencephalography (EEG) in brain-computer interfaces (BCIs) can be attributed to its non-invasive nature and capability to offer high-resolution data. The acquisition of EEG signals is a straightforward process, but the datasets associated with these signals frequently exhibit data scarcity and require substantial resources for proper labeling. Furthermore, there is a significant limitation in the generalization performance of EEG models due to the substantial inter-individual variability observed in EEG signals.Approach. To address these issues, we propose a novel self-supervised contrastive learning framework for decoding motor imagery (MI) signals in cross-subject scenarios. Specifically, we design an encoder combining convolutional neural network and attention mechanism. In the contrastive learning training stage, the network undergoes training with the pretext task of data augmentation to minimize the distance between pairs of homologous transformations while simultaneously maximizing the distance between pairs of heterologous transformations. It enhances the amount of data utilized for training and improves the network's ability to extract deep features from original signals without relying on the true labels of the data.Main results. To evaluate our framework's efficacy, we conduct extensive experiments on three public MI datasets: BCI IV IIa, BCI IV IIb, and HGD datasets. The proposed method achieves cross-subject classification accuracies of 67.32%, 82.34%, and 81.13%on the three datasets, demonstrating superior performance compared to existing methods.Significance. Therefore, this method has great promise for improving the performance of cross-subject transfer learning in MI-based BCI systems.

Reinforcement learning for robust stabilization of nonlinear systems with asymmetric saturating actuators.

We study the robust stabilization problem of a class of nonlinear systems with asymmetric saturating actuators and mismatched disturbances. Initially, we convert such a robust stabilization problem into a nonlinear-constrained optimal control problem by constructing a discounted cost function for the auxiliary system. Then, for the purpose of solving the nonlinear-constrained optimal control problem, we develop a simultaneous policy iteration (PI) in the reinforcement learning framework. The implementation of the simultaneous PI relies on an actor-critic architecture, which employs actor and critic neural networks (NNs) to separately approximate the control policy and the value function. To determine the actor and critic NNs' weights, we use the approach of weighted residuals together with the typical Monte-Carlo integration technique. Finally, we perform simulations of two nonlinear plants to validate the established theoretical claims.