Nuclei segmentation and classification in Hematoxylin and Eosin (H&E) stained histology images play a vital role in cancer diagnosis, treatment planning, and research. However, accurate segmentation can be hindered by factors like irregular cell shapes, unclear boundaries, and class imbalance. To address these challenges, we propose the Adaptive Gated Attention Fusion Network (AGAFNet), which integrates three innovative attention-based blocks into a U-shaped architecture complemented by dedicated decoders for both segmentation and classification tasks. These blocks comprise the Channel-wise and Spatial Attention Integration Block (CSAIB) for enhanced feature representation and selective focus on informative regions; the Adaptive Gated Convolutional Block (AGCB) for robust feature selection throughout the network; and the Fusion Attention Refinement Block (FARB) for effective information fusion. AGAFNet leverages these elements to provide a robust solution for precise nuclei segmentation and classification in H&E stained histology images. We evaluate the performance of AGAFNet on three large-scale multi-tissue datasets: PanNuke, CoNSeP, and Lizard. The experimental results demonstrate our proposed AGAFNet achieves comparable performance to state-of-the-art methods.

Brain-computer interfaces (BCIs) based on motor imagery electroencephalogram (MI-EEG) signals have been extensively applied in various neural rehabilitation scenarios. However, existing methods primarily focus on designing complex architectures to extract spatio-temporal features from MI-EEG signals, often neglecting the brain dynamics information embedded within them. This oversight leads to the extraction of redundant information, ultimately reducing decoding performance. To address these challenges, we design a multi-level topology-guidance network (ML-TGNet) that leverages topological brain synchronization information to more effectively extract features related to MI tasks. ML-TGNet specifically comprises a multi-level topology guidance module, a feature pool module, and a multi-branch decoding module. To evaluate its performance, extensive experiments are conducted on three publicly available MI datasets: the BCI Competition IV-2a dataset, the High Gamma dataset, and the OpenBMI dataset. ML-TGNet achieves classification accuracies of 82.33%, 96.42%, and 85.26% on these three datasets, respectively, outperforming current state-of-the-art models. These findings confirm the efficacy of using brain synchronization information to guide MI decoding, thereby opening a novel approach for EEG-based brain state decoding by integrating brain dynamics into deep learning.

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${\%}$).

Robust decoding performance is essential for the practical deployment of brain-computer interface (BCI) systems. Existing EEG decoding models often rely on large amounts of annotated data collected through specific experimental setups, which fail to address the heterogeneity of data distributions across different domains. This limitation hinders BCI systems from effectively managing the complexity and variability of real-world data. To overcome these challenges, we propose Synchronized Self-Training Domain Adaptation (SSTDA) for cross-domain motor imagery classification. Specifically, SSTDA leverages labeled signals from a source domain and applies self-training to unlabeled signals from a target domain, enabling the simultaneous training of a more robust classifier. The raw EEG signals are mapped into a latent space by a feature extractor for discriminative representation learning. A domain-shared latent space is then learned by optimizing the feature extractor with both source and target samples, using an easy-tohard self-training process. We validate the method with extensive experiments on two public motor imagery datasets: Dataset IIa of BCI Competition IV and the High Gamma dataset. In the inter-subject task, our method achieves classification accuracies of 64.43% and 80.40%, respectively. It also outperforms existing methods in the inter-session task. Moreover, we develope a new six-class motor imagery dataset and achieve test accuracies of 77.09% and 80.18% across different datasets. All experimental results demonstrate that our SSTDA outperforms existing algorithms in inter-session, inter-subject, and inter-dataset validation protocols, highlighting its capability to learn discriminative, domain-invariant representations that enhance EEG decoding performance.

A robust decoding model that can efficiently deal with the subject and period variation is urgently needed to apply the brain-computer interface (BCI) system. The performance of most electroencephalogram (EEG) decoding models depends on the characteristics of specific subjects and periods, which require calibration and training with annotated data prior to application. However, this situation will become unacceptable as it would be difficult for subjects to collect data for an extended period, especially in the rehabilitation process of disability based on motor imagery (MI). To address this issue, we propose an unsupervised domain adaptation framework called iterative self-training multisubject domain adaptation (ISMDA) that focuses on the offline MI task. First, the feature extractor is purposefully designed to map the EEG to a latent space of discriminative representations. Second, the attention module based on dynamic transfer matches the source domain and target domain samples with a higher coincidence degree in latent space. Then, an independent classifier oriented to the target domain is employed in the first stage of the iterative training process to cluster the samples of the target domain through similarity. Finally, a pseudolabel algorithm based on certainty and confidence is employed in the second stage of the iterative training process to adequately calibrate the error between prediction and empirical probabilities. To evaluate the effectiveness of the model, extensive testing has been performed on three publicly available MI datasets, the BCI IV IIa, the High gamma dataset, and Kwon et al. datasets. The proposed method achieved 69.51%, 82.38%, and 90.98% cross-subject classification accuracy on the three datasets, which outperforms the current state-of-the-art offline algorithms. Meanwhile, all results demonstrated that the proposed method could address the main challenges of the offline MI paradigm.

Brain-computer interface (BCI) establishes an interactive platform by translating brain activity patterns into commands of external devices. BCIs, especially motor imagery (MI)-based BCIs, have injected new vitality into the development of rehabilitation medicine and many other fields. In this work, one convolutional neural network, named as Flashlight-Net model, is proposed for multiclass MI classification. Flashlight-Net model adopts modular design, in which channel fusion module and time domain module ensure the directions of feature extraction, while feature pool module reduces the loss of effective information. Given the multi-frequency nature of the brain, we combine three frequency bands and construct an ensemble Flashlight-Net model. During the model training, by means of transfer learning, pretraining and fine-tuning processes are designed to integrate training samples from multiple subjects. The experimental results on publicly available BCI Competition IV-2a dataset show that the proposed model can achieve good results on all nine subjects, with an average classification accuracy of 81.23% for four classes. All these demonstrate that the proposed Flashlight-Net model can effectively decode multi-channel and multiclass MI signals.

Brain tumor segmentation is a key step in brain cancer diagnosis. Segmentation of brain tumor sub-regions, including necrotic, enhancing, and edematous regions, can provide more detailed guidance for clinical diagnosis. Weakly supervised brain tumor segmentation methods have received much attention because they do not require time-consuming pixel-level annotations. However, existing weakly supervised methods focus on the segmentation of the entire tumor region while ignoring the challenging task of multi-label segmentation for the tumor sub-regions. In this article, we propose a weakly supervised approach to solve the multi-label brain tumor segmentation problem. To the best of our knowledge, it's the first end-to-end multi-label weakly supervised segmentation model applied to brain tumor segmentation. With well-designed loss functions and a contrastive learning pre-training process, our proposed Transformer-based segmentation method (WS-MTST) has the ability to perform segmentation of brain tumor sub-regions. We conduct comprehensive experiments and demonstrate that our method reaches the state-of-the-art on the popular brain tumor dataset BraTS (from 2018 to 2020).

We consider the decentralized control problem of a class of continuous-time nonlinear systems with mismatched interconnections. Initially, with the discounted cost functions being introduced to auxiliary subsystems, we have the decentralized control problem converted into a set of optimal control problems. To derive solutions to these optimal control problems, we first present the related Hamilton-Jacobi-Bellman equations (HJBEs). Then, we develop a novel critic learning method to solve these HJBEs. To implement the newly developed critic learning approach, we only use critic neural networks (NNs) and tune their weight vectors via the combination of a modified gradient descent method and concurrent learning. By using the present critic learning method, we not only remove the restriction of initial admissible control but also relax the persistence-of-excitation condition. After that, we employ Lyapunov's direct method to demonstrate that the critic NNs' weight estimation error and the states of closed-loop auxiliary systems are stable in the sense of uniform ultimate boundedness. Finally, we separately provide a nonlinear-interconnected plant and an unstable interconnected power system to validate the present critic learning approach.

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.

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.

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.

Fatigue driving has attracted a great deal of attention for its huge influence on automobile accidents. Recognizing driving fatigue provides a primary but significant way for addressing this problem. In this paper, we first conduct the simulated driving experiments to acquire the EEG signals in alert and fatigue states. Then, for multi-channel EEG signals without pre-processing, a novel rhythm-dependent multilayer brain network (RDMB network) is developed and analyzed for driving fatigue detection. We find that there exists a significant difference between alert and fatigue states from the view of network science. Further, key sub-RDMB network based on closeness centrality are extracted. We calculate six network measures from the key sub-RDMB network and construct feature vectors to classify the alert and fatigue states. The results show that our method can respectively achieve the average accuracy of 95.28% (with sample length of 5 s), 90.25% (2 s), and 87.69% (1 s), significantly higher than compared methods. All these validate the effectiveness of RDMB network for reliable driving fatigue detection via EEG.

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.

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.

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.

Electroencephalogram (EEG), obtained by wearable devices, can realize effective human health monitoring. Traditional methods based on artificially designed features have achieved valid results in EEG-based recognition, and numerous studies start to apply deep learning techniques in this area. In this article, we propose a coincidence-filtering-based method to build a connection between artificial-features-based methods and convolutional neural networks (CNNs), and design CNNs through simulating the information extraction pattern of artificial-features-based methods. Based on this method, we propose a novel, simple, and effective CNNs structure for EEG-based classification. We implement two experiments to obtain EEG data, and perform experiments based on the two health monitoring tasks. The results illustrate that the proposed network can achieve a prominent average accuracy on the emotion recognition and fatigue driving detection task. Due to its generality, the proposed framework design of CNNs is expected to be useful for broader applications in health monitoring areas.

In this paper, an approximately optimal control strategy is developed for the tracking control of a class of continuous-time nonlinear systems with unmatched uncertainties. By transforming the unmatched uncertain term, the auxiliary system associated with the uncertain nonlinear system is established. The auxiliary system is divided into steady and transient parts, and the related controllers are separately solved, meanwhile the transient tracking error system is also obtained by introducing the reference system. A neural network-based adaptive dynamic programming method is used to get the approximately optimal tracking control law of uncertain nonlinear systems with a predefined cost function. Furthermore, the ultimately uniform boundedness of neural network weights and the stability of tracking error systems are both proved through Lyapunov theory. Two cases of nonlinear systems with unmatched uncertainties are investigated to illustrate the effectiveness of the proposed robust tracking control strategy.

Driver fatigue is an important contributor to road accidents, and driver fatigue detection has attracted a great deal of attention on account of its significant importance. Numerous methods have been proposed to fulfill this challenging task, though, the characterization of the fatigue mechanism still, to a large extent, remains to be investigated. To address this problem, we, in this work, develop a novel Multiplex Limited Penetrable Horizontal Visibility Graph (Multiplex LPHVG) method, which allows in not only detecting fatigue driving but also probing into the brain fatigue behavior. Importantly, we use the method to construct brain networks from EEG signals recorded from different subjects performing simulated driving tasks under alert and fatigue driving states. We then employ clustering coefficient, global efficiency and characteristic path length to characterize the topological structure of the networks generated from different brain states. In addition, we combine average edge overlap with the network measures to distinguish alert and mental fatigue states. The high-accurate classification results clearly demonstrate and validate the efficacy of our multiplex LPHVG method for the fatigue detection from EEG signals. Furthermore, our findings show a significant increase of the clustering coefficient as the brain evolves from alert state to mental fatigue state, which yields novel insights into the brain behavior associated with fatigue driving.

Due to the inherent disturbances associated with flow structures, measurement of the complicated flow parameters in multiphase flows remains a challenging problem of significant importance. The flow dynamical behaviors are still elusive. In this paper, a multichannel complex impedance measurement system is designed to cope with this difficult issue. First, the geometry of the distributed multielectrode impedance sensor is optimized and a matched hardware measurement system is developed. After performance evaluation, a convolutional neural network and long short-term memory based measurement model is formulated for measuring flow parameters with high accuracy. The mean absolute error is only 0.36% for water cut and 0.77% for total flow velocity. Further, from the perspective of Lempel-Ziv complexity and mutual information, the relationship between the diverse flow structures and spatial flow behaviors is explored, leading to a deeper understanding of oil-water flows. All the experimental and analytical results demonstrate that the combination of deep learning and the designed impedance sensor measurement system allows measuring the complicated flow parameters, thereby characterizing the flow structures and behaviors. This opens up a new venue for exploring industrial multiphase flows and serving for an efficient oilfield exploitation as well.

Driver fatigue evaluation is of great importance for traffic safety and many intricate factors would exacerbate the difficulty. In this paper, based on the spatial-temporal structure of multichannel electroencephalogram (EEG) signals, we develop a novel EEG-based spatial-temporal convolutional neural network (ESTCNN) to detect driver fatigue. First, we introduce the core block to extract temporal dependencies from EEG signals. Then, we employ dense layers to fuse spatial features and realize classification. The developed network could automatically learn valid features from EEG signals, which outperforms the classical two-step machine learning algorithms. Importantly, we carry out fatigue driving experiments to collect EEG signals from eight subjects being alert and fatigue states. Using 2800 samples under within-subject splitting, we compare the effectiveness of ESTCNN with eight competitive methods. The results indicate that ESTCNN fulfills a better classification accuracy of 97.37% than these compared methods. Furthermore, the spatial-temporal structure of this framework advantages in computational efficiency and reference time, which allows further implementations in the brain-computer interface online systems.

Increasingly advanced technology allows the monitoring of complex systems from a wide variety of perspectives. But the exploration of such systems from a multichannel sensor information viewpoint remains a complicated challenge of ongoing interest. In this paper, first, based on a well-designed double-layer distributed-sector conductance (DLDSC) sensor, systematic oil-water and gas-liquid two-phase flow experiments are carried out to capture abundant spatiotemporal flow information. Second, well flow parameter measurement performance of the DLDSC sensor is effectively validated from the perspective of normalized conductance. Third, a novel multiplex network-based model is presented to implement data mining and characterize the evolution of flow dynamics. The results demonstrate that the model is powerful for the exploration of the spatial flow behaviors from heterogeneity to randomness in the studied two-phase flows.

Detecting epileptic seizure from EEG signals constitutes a challenging problem of significant importance. Combining adaptive optimal kernel time-frequency representation and visibility graph, we develop a novel method for detecting epileptic seizure from EEG signals. We construct complex networks from EEG signals recorded from healthy subjects and epilepsy patients. Then we employ clustering coefficient, clustering coefficient entropy and average degree to characterize the topological structure of the networks generated from different brain states. In addition, we combine energy deviation and network measures to recognize healthy subjects and epilepsy patients, and further distinguish brain states during seizure free interval and epileptic seizures. Three different experiments are designed to evaluate the performance of our method. The results suggest that our method allows a high-accurate classification of epileptiform EEG signals.