Frequency Domain Channel-Wise Attack to CNN Classifiers in Motor Imagery Brain-Computer Interfaces

OBJECTIVE

Convolutional neural network (CNN), a classical structure in deep learning, has been commonly deployed in the motor imagery brain-computer interface (MIBCI). Many methods have been proposed to evaluate the vulnerability of such CNN models, primarily by attacking them using direct temporal perturbations. In this work, we propose a novel attacking approach based on perturbations in the frequency domain instead.

METHODS

For a given natural MI trial in the frequency domain, the proposed approach, called frequency domain channel-wise attack (FDCA), generates perturbations at each channel one after another to fool the CNN classifiers. The advances of this strategy are two-fold. First, instead of focusing on the temporal domain, perturbations are generated in the frequency domain where discriminative patterns can be extracted for motor imagery (MI) classification tasks. Second, the perturbing optimization is performed based on differential evolution algorithm in a black-box scenario where detailed model knowledge is not required.

RESULTS

Experimental results demonstrate the effectiveness of the proposed FDCA which achieves a significantly higher success rate than the baselines and existing methods in attacking three major CNN classifiers on four public MI benchmarks.

CONCLUSION

Perturbations generated in the frequency domain yield highly competitive results in attacking MIBCI deployed by CNN models even in a black-box setting, where the model information is well-protected.

SIGNIFICANCE

To our best knowledge, existing MIBCI attack approaches are all gradient-based methods and require details about the victim model, e.g., the parameters and objective function. We provide a more flexible strategy that does not require model details but still produces an effective attack outcome.

MINDG: a drug-target interaction prediction method based on an integrated learning algorithm

MOTIVATION

Drug-target interaction (DTI) prediction refers to the prediction of whether a given drug molecule will bind to a specific target and thus exert a targeted therapeutic effect. Although intelligent computational approaches for drug target prediction have received much attention and made many advances, they are still a challenging task that requires further research. The main challenges are manifested as follows: (i) most graph neural network-based methods only consider the information of the first-order neighboring nodes (drug and target) in the graph, without learning deeper and richer structural features from the higher-order neighboring nodes. (ii) Existing methods do not consider both the sequence and structural features of drugs and targets, and each method is independent of each other, and cannot combine the advantages of sequence and structural features to improve the interactive learning effect.

RESULTS

To address the above challenges, a Multi-view Integrated learning Network that integrates Deep learning and Graph Learning (MINDG) is proposed in this study, which consists of the following parts: (i) a mixed deep network is used to extract sequence features of drugs and targets, (ii) a higher-order graph attention convolutional network is proposed to better extract and capture structural features, and (iii) a multi-view adaptive integrated decision module is used to improve and complement the initial prediction results of the above two networks to enhance the prediction performance. We evaluate MINDG on two dataset and show it improved DTI prediction performance compared to state-of-the-art baselines.

AVAILABILITY AND IMPLEMENTATION

https://github.com/jnuaipr/MINDG.

Cell classification with worse-case boosting for intelligent cervical cancer screening

Cell classification underpins intelligent cervical cancer screening, a cytology examination that effectively decreases both the morbidity and mortality of cervical cancer. This task, however, is rather challenging, mainly due to the difficulty of collecting a training dataset representative sufficiently of the unseen test data, as there are wide variations of cells' appearance and shape at different cancerous statuses. This difficulty makes the classifier, though trained properly, often classify wrongly for cells that are underrepresented by the training dataset, eventually leading to a wrong screening result. To address it, we propose a new learning algorithm, called worse-case boosting, for classifiers effectively learning from under-representative datasets in cervical cell classification. The key idea is to learn more from worse-case data for which the classifier has a larger gradient norm compared to other training data, so these data are more likely to correspond to underrepresented data, by dynamically assigning them more training iterations and larger loss weights for boosting the generalizability of the classifier on underrepresented data. We achieve this idea by sampling worse-case data per the gradient norm information and then enhancing their loss values to update the classifier. We demonstrate the effectiveness of this new learning algorithm on two publicly available cervical cell classification datasets (the two largest ones to the best of our knowledge), and positive results (4% accuracy improvement) yield in the extensive experiments. The source codes are available at: https://github.com/YouyiSong/Worse-Case-Boosting.

MVDINET: A Novel Multi-Level Enzyme Function Predictor With Multi-View Deep Interactive Learning

As a class of extremely significant of biocatalysts, enzymes play an important role in the process of biological reproduction and metabolism. Therefore, the prediction of enzyme function is of great significance in biomedicine fields. Recently, computational methods for predicting enzyme function have been proposed, and they effectively reduce the cost of enzyme function prediction. However, there are still deficiencies for effectively mining the discriminant information for enzyme function recognition in existing methods. In this study, we present MVDINET, a novel method for multi-level enzyme function prediction. First, the initial multi-view feature data is extracted by the enzyme sequence. Then, the above initial views are fed into various deep specific network modules to learn the depth-specificity information. Further, a deep view interaction network is designed to extract the interaction information. Finally, the specificity information and interaction information are fed into a multi-view adaptively weighted classification. We compressively evaluate MVDINET on benchmark datasets and demonstrate that MVDINET is superior to existing methods.

Correntropy-Based Low-Rank Matrix Factorization With Constraint Graph Learning for Image Clustering

This article proposes a novel low-rank matrix factorization model for semisupervised image clustering. In order to alleviate the negative effect of outliers, the maximum correntropy criterion (MCC) is incorporated as a metric to build the model. To utilize the label information to improve the clustering results, a constraint graph learning framework is proposed to adaptively learn the local structure of the data by considering the label information. Furthermore, an iterative algorithm based on Fenchel conjugate (FC) and block coordinate update (BCU) is proposed to solve the model. The convergence properties of the proposed algorithm are analyzed, which shows that the algorithm exhibits both objective sequential convergence and iterate sequential convergence. Experiments are conducted on six real-world image datasets, and the proposed algorithm is compared with eight state-of-the-art methods. The results show that the proposed method can achieve better performance in most situations in terms of clustering accuracy and mutual information.

Domain-Generalized EEG Classification With Category-Oriented Feature Decorrelation and Cross-View Consistency Learning

Generalizing the electroencephalogram (EEG) decoding methods to unseen subjects is an important research direction for realizing practical application of brain-computer interfaces (BCIs). Since distribution shifts across subjects, the performance of most current deep neural networks for decoding EEG signals degrades when dealing with unseen subjects. Domain generalization (DG) aims to tackle this issue by learning invariant representations across subjects. To this end, we propose a novel domain-generalized EEG classification framework, named FDCL, to generalize EEG decoding through category-relevant and -irrelevant Feature Decorrelation and Cross-view invariant feature Learning. Specifically, we first devise data augmented regularization through mixing the segments of same-category features from multiple subjects, which increases the diversity of EEG data by spanning the space of subjects. Furthermore, we introduce feature decorrelation regularization to learn the weights of the augmented EEG trials to remove the dependencies between their features, so that the true mapping relationship between relevant features and corresponding labels can be better established. To further distill subject-invariant EEG feature representations, cross-view consistency learning regularization is introduced to encourage consistent predictions of category-relevant features induced from different augmented EEG views. We seamlessly integrate three complementary regularizations into a unified DG framework to jointly improve the generalizability and robustness of the model on unseen subjects. Experimental results on motor imagery (MI) based EEG datasets validate that the proposed FDCL outperforms the available state-of-the-art methods.

MLNGCF: circRNA-disease associations prediction with multilayer attention neural graph-based collaborative filtering

MOTIVATION

CircRNAs play a critical regulatory role in physiological processes, and the abnormal expression of circRNAs can mediate the processes of diseases. Therefore, exploring circRNAs-disease associations is gradually becoming an important area of research. Due to the high cost of validating circRNA-disease associations using traditional wet-lab experiments, novel computational methods based on machine learning are gaining more and more attention in this field. However, current computational methods suffer to insufficient consideration of latent features in circRNA-disease interactions.

RESULTS

In this study, a multilayer attention neural graph-based collaborative filtering (MLNGCF) is proposed. MLNGCF first enhances multiple biological information with autoencoder as the initial features of circRNAs and diseases. Then, by constructing a central network of different diseases and circRNAs, a multilayer cooperative attention-based message propagation is performed on the central network to obtain the high-order features of circRNAs and diseases. A neural network-based collaborative filtering is constructed to predict the unknown circRNA-disease associations and update the model parameters. Experiments on the benchmark datasets demonstrate that MLNGCF outperforms state-of-the-art methods, and the prediction results are supported by the literature in the case studies.

AVAILABILITY AND IMPLEMENTATION

The source codes and benchmark datasets of MLNGCF are available at https://github.com/ABard0/MLNGCF.

Domain-adaptive message passing graph neural network

Cross-network node classification (CNNC), which aims to classify nodes in a label-deficient target network by transferring the knowledge from a source network with abundant labels, draws increasing attention recently. To address CNNC, we propose a domain-adaptive message passing graph neural network (DM-GNN), which integrates graph neural network (GNN) with conditional adversarial domain adaptation. DM-GNN is capable of learning informative representations for node classification that are also transferrable across networks. Firstly, a GNN encoder is constructed by dual feature extractors to separate ego-embedding learning from neighbor-embedding learning so as to jointly capture commonality and discrimination between connected nodes. Secondly, a label propagation node classifier is proposed to refine each node's label prediction by combining its own prediction and its neighbors' prediction. In addition, a label-aware propagation scheme is devised for the labeled source network to promote intra-class propagation while avoiding inter-class propagation, thus yielding label-discriminative source embeddings. Thirdly, conditional adversarial domain adaptation is performed to take the neighborhood-refined class-label information into account during adversarial domain adaptation, so that the class-conditional distributions across networks can be better matched. Comparisons with eleven state-of-the-art methods demonstrate the effectiveness of the proposed DM-GNN.

Predicting Dementia Risk for Elderly Community Dwellers in Primary Care Services Using Subgroup-specific Prediction Models

Early detection of individuals with a high risk of dementia is crucial for prompt intervention and clinical care. This study aims to identify high-risk groups for developing dementia by predicting the outcome of the Mini-Mental State Examination (MMSE), using historical data collected from community-based primary care services. To mitigate the effect of inter-individual variability and enhance the accuracy of the prediction, we implemented a multi-stage method powered by supervised and unsupervised machine learning methods. Firstly, we preprocessed the original data by imputing missing values and using a wrapper-based feature selection algorithm to pick significant features, resulting in ten variables out of 567 being selected for further modeling. Secondly, we optimized hierarchical clustering to partition the unlabeled data into groups by their similarities, and then applied supervised machine learning models to build subgroup-specific prediction models for the identified groups. The results demonstrate that the proposed subgroup-specific prediction models generated from the multi-stage method achieved satisfactory performance in predicting the outcome classes of dementia risk. This study highlights the potential of incorporating unsupervised and supervised learning models to predict high-risk cases of dementia early and facilitate better clinical decision-making.

MMSMAPlus: a multi-view multi-scale multi-attention embedding model for protein function prediction

Protein is the most important component in organisms and plays an indispensable role in life activities. In recent years, a large number of intelligent methods have been proposed to predict protein function. These methods obtain different types of protein information, including sequence, structure and interaction network. Among them, protein sequences have gained significant attention where methods are investigated to extract the information from different views of features. However, how to fully exploit the views for effective protein sequence analysis remains a challenge. In this regard, we propose a multi-view, multi-scale and multi-attention deep neural model (MMSMA) for protein function prediction. First, MMSMA extracts multi-view features from protein sequences, including one-hot encoding features, evolutionary information features, deep semantic features and overlapping property features based on physiochemistry. Second, a specific multi-scale multi-attention deep network model (MSMA) is built for each view to realize the deep feature learning and preliminary classification. In MSMA, both multi-scale local patterns and long-range dependence from protein sequences can be captured. Third, a multi-view adaptive decision mechanism is developed to make a comprehensive decision based on the classification results of all the views. To further improve the prediction performance, an extended version of MMSMA, MMSMAPlus, is proposed to integrate homology-based protein prediction under the framework of multi-view deep neural model. Experimental results show that the MMSMAPlus has promising performance and is significantly superior to the state-of-the-art methods. The source code can be found at https://github.com/wzy-2020/MMSMAPlus.

One-Step Multiview Fuzzy Clustering With Collaborative Learning Between Common and Specific Hidden Space Information

Multiview data are widespread in real-world applications, and multiview clustering is a commonly used technique to effectively mine the data. Most of the existing algorithms perform multiview clustering by mining the commonly hidden space between views. Although this strategy is effective, there are two challenges that still need to be addressed to further improve the performance. First, how to design an efficient hidden space learning method so that the learned hidden spaces contain both shared and specific information of multiview data. Second, how to design an efficient mechanism to make the learned hidden space more suitable for the clustering task. In this study, a novel one-step multiview fuzzy clustering (OMFC-CS) method is proposed to address the two challenges by collaborative learning between the common and specific space information. To tackle the first challenge, we propose a mechanism to extract the common and specific information simultaneously based on matrix factorization. For the second challenge, we design a one-step learning framework to integrate the learning of common and specific spaces and the learning of fuzzy partitions. The integration is achieved in the framework by performing the two learning processes alternately and thereby yielding mutual benefit. Furthermore, the Shannon entropy strategy is introduced to obtain the optimal views weight assignment during clustering. The experimental results based on benchmark multiview datasets demonstrate that the proposed OMFC-CS outperforms many existing methods.

Intra-Patient Lung CT Registration through Large Deformation Decomposition and Attention-Guided Refinement

Deformable lung CT image registration is an essential task for computer-assisted interventions and other clinical applications, especially when organ motion is involved. While deep-learning-based image registration methods have recently achieved promising results by inferring deformation fields in an end-to-end manner, large and irregular deformations caused by organ motion still pose a significant challenge. In this paper, we present a method for registering lung CT images that is tailored to the specific patient being imaged. To address the challenge of large deformations between the source and target images, we break the deformation down into multiple continuous intermediate fields. These fields are then combined to create a spatio-temporal motion field. We further refine this field using a self-attention layer that aggregates information along motion trajectories. By leveraging temporal information from a respiratory cycle, our proposed methods can generate intermediate images that facilitate image-guided tumor tracking. We evaluated our approach extensively on a public dataset, and our numerical and visual results demonstrate the effectiveness of the proposed method.

Data Discernment for Affordable Training in Medical Image Segmentation

Collecting sufficient high-quality training data for deep neural networks is often expensive or even unaffordable in medical image segmentation tasks. We thus propose to train the network by using external data that can be collected in a cheaper way, e.g., crowd-sourcing. We show that by data discernment, the network is able to mine valuable knowledge from external data, even though the data distribution is very different from that of the original (internal) data. We discern the external data by learning an importance weight for each of them, with the goal to enhance the contribution of informative external data to network updating, while suppressing the data that are 'useless' or even 'harmful'. An iterative algorithm that alternatively estimates the importance weight and updates the network is developed by formulating the data discernment as a constrained nonlinear programming problem. It estimates the importance weight according to the distribution discrepancy between the external data and the internal dataset, and imposes a constraint to drive the network to learn more effectively, compared with the network without using the external data. We evaluate the proposed algorithm on two tasks: abdominal CT image and cervical smear image segmentation, using totally 6 publicly available datasets. The effectiveness of the algorithm is demonstrated by extensive experiments. Source codes are available at: https://github.com/YouyiSong/Data-Discernment.

Dynamic Loss Weighting for Multiorgan Segmentation in Medical Images

Deep neural networks often suffer from performance inconsistency for multiorgan segmentation in medical images; some organs are segmented far worse than others. The main reason might be organs with different levels of learning difficulty for segmentation mapping, due to variations such as size, texture complexity, shape irregularity, and imaging quality. In this article, we propose a principled class-reweighting algorithm, termed dynamic loss weighting, which dynamically assigns a larger loss weight to organs if they are discriminated as more difficult to learn according to the data and network's status, for forcing the network to learn from them more to maximally promote the performance consistency. This new algorithm uses an extra autoencoder to measure the discrepancy between the segmentation network's output and the ground truth and dynamically estimates the loss weight of organs per the contribution of the organ to the new updated discrepancy. It can capture the variation in organs' learning difficult during training, and it is neither sensitive to data's property nor dependent on human priors. We evaluate this algorithm in two multiorgan segmentation tasks: abdominal organs and head-neck structures, on publicly available datasets, with positive results obtained from extensive experiments which confirm the validity and effectiveness. Source codes are available at: https://github.com/YouyiSong/Dynamic-Loss-Weighting.

Center transfer for supervised domain adaptation

Domain adaptation (DA) is a popular strategy for pattern recognition and classification tasks. It leverages a large amount of data from the source domain to help train the model applied in the target domain. Supervised domain adaptation (SDA) approaches are desirable when only few labeled samples from the target domain are available. They can be easily adopted in many real-world applications where data collection is expensive. In this study, we propose a new supervision signal, namely center transfer loss (CTL), to efficiently align features under the SDA setting in the deep learning (DL) field. Unlike most previous SDA methods that rely on pairing up training samples, the proposed loss is trainable only using one-stream input based on the mini-batch strategy. The CTL exhibits two main functionalities in training to increase the performance of DL models, i.e., domain alignment and increasing the feature's discriminative power. The hyper-parameter to balance these two functionalities is waived in CTL, which is the second improvement from the previous approaches. Extensive experiments completed on well-known public datasets show that the proposed method performs better than recent state-of-the-art approaches.

Maximum likelihood-based extended Kalman filter for soft tissue modelling

Realistic modelling of human soft tissue is very important in medical applications. This paper proposes a novel method by dynamically incorporating soft tissue characterisation in the process of soft tissue modelling to increase the modelling fidelity. This method defines nonlinear tissue deformation with unknown mechanical properties as a problem of nonlinear filtering identification to dynamically identify mechanical properties and further estimate nonlinear deformation behaviour of soft tissue. It combines maximum likelihood theory, nonlinear filtering and nonlinear finite element method (NFEM) for modelling of nonlinear tissue deformation behaviour based on dynamic identification of homogeneous tissue properties. On the basis of hyperelasticity, a nonlinear state-space equation is established by discretizing tissue deformation through NFEM for dynamic filtering. A maximum likelihood algorithm is also established to dynamically identify tissue mechanical properties during the deformation process. Upon above, a maximum likelihood-based extended Kalman filter is further developed for dynamically estimating tissue nonlinear deformation based on dynamic identification of tissue mechanical properties. Simulation and experimental analyses reveal that the proposed method not only overcomes the NFEM limitation of expensive computations, but also absorbs the NFEM merit of high accuracy for modelling of homogeneous tissue deformation. Further, the proposed method also effectively identifies tissue mechanical properties during the deformation modelling process.

Using knowledge of, attitude toward, and daily preventive practices for COVID-19 to predict the level of post-traumatic stress and vaccine acceptance among adults in Hong Kong

Introduction

COVID-19 has been perceived as an event triggering a new type of post-traumatic stress (PTSD) that can live during and after the pandemic itself. However, it remains unclear whether such PTSD is partly related to people's knowledge of, attitude toward and daily behavioral practices (KAP) for COVID-19.

Methods

Through a telephone survey, we collected responses from 3,011 adult Hong Kong residents. Then using the Catboost machine learning method, we examined whether KAP predicted the participant's PTSD level, vaccine acceptance and participation in voluntary testing.

Results

Results suggested that having good preventative practices for, poor knowledge of, and negative attitude toward COVID-19 were associated with greater susceptibility to PTSD. Having a positive attitude and good compliance with preventative practices significantly predicted willingness to get vaccinated and participate in voluntary testing. Good knowledge of COVID-19 predicted engagement in testing but showed little association with vaccine acceptance.

Discussion

To maintain good mental health and ongoing vaccine acceptance, it is important to foster people's sense of trust and belief in health professionals' and government's ability to control COVID-19, in addition to strengthening people's knowledge of and compliance with preventative measures.

Adaptive Multimodel Knowledge Transfer Matrix Machine for EEG Classification

The emerging matrix learning methods have achieved promising performances in electroencephalogram (EEG) classification by exploiting the structural information between the columns or rows of feature matrices. Due to the intersubject variability of EEG data, these methods generally need to collect a large amount of labeled individual EEG data, which would cause fatigue and inconvenience to the subjects. Insufficient subject-specific EEG data will weaken the generalization capability of the matrix learning methods in neural pattern decoding. To overcome this dilemma, we propose an adaptive multimodel knowledge transfer matrix machine (AMK-TMM), which can selectively leverage model knowledge from multiple source subjects and capture the structural information of the corresponding EEG feature matrices. Specifically, by incorporating least-squares (LS) loss with spectral elastic net regularization, we first present an LS support matrix machine (LS-SMM) to model the EEG feature matrices. To boost the generalization capability of LS-SMM in scenarios with limited EEG data, we then propose a multimodel adaption method, which can adaptively choose multiple correlated source model knowledge with a leave-one-out cross-validation strategy on the available target training data. We extensively evaluate our method on three independent EEG datasets. Experimental results demonstrate that our method achieves promising performances on EEG classification.

Transductive Multiview Modeling With Interpretable Rules, Matrix Factorization, and Cooperative Learning

Multiview fuzzy systems aim to deal with fuzzy modeling in multiview scenarios effectively and to obtain the interpretable model through multiview learning. However, current studies of multiview fuzzy systems still face several challenges, one of which is how to achieve efficient collaboration between multiple views when there are few labeled data. To address this challenge, this article explores a novel transductive multiview fuzzy modeling method. The dependency on labeled data is reduced by integrating transductive learning into the fuzzy model to simultaneously learn both the model and the labels using a novel learning criterion. Matrix factorization is incorporated to further improve the performance of the fuzzy model. In addition, collaborative learning between multiple views is used to enhance the robustness of the model. The experimental results indicate that the proposed method is highly competitive with other multiview learning methods.

MDGF-MCEC: a multi-view dual attention embedding model with cooperative ensemble learning for CircRNA-disease association prediction

Circular RNA (circRNA) is closely involved in physiological and pathological processes of many diseases. Discovering the associations between circRNAs and diseases is of great significance. Due to the high-cost to verify the circRNA-disease associations by wet-lab experiments, computational approaches for predicting the associations become a promising research direction. In this paper, we propose a method, MDGF-MCEC, based on multi-view dual attention graph convolution network (GCN) with cooperative ensemble learning to predict circRNA-disease associations. First, MDGF-MCEC constructs two disease relation graphs and two circRNA relation graphs based on different similarities. Then, the relation graphs are fed into a multi-view GCN for representation learning. In order to learn high discriminative features, a dual-attention mechanism is introduced to adjust the contribution weights, at both channel level and spatial level, of different features. Based on the learned embedding features of diseases and circRNAs, nine different feature combinations between diseases and circRNAs are treated as new multi-view data. Finally, we construct a multi-view cooperative ensemble classifier to predict the associations between circRNAs and diseases. Experiments conducted on the CircR2Disease database demonstrate that the proposed MDGF-MCEC model achieves a high area under curve of 0.9744 and outperforms the state-of-the-art methods. Promising results are also obtained from experiments on the circ2Disease and circRNADisease databases. Furthermore, the predicted associated circRNAs for hepatocellular carcinoma and gastric cancer are supported by the literature. The code and dataset of this study are available at https://github.com/ABard0/MDGF-MCEC.

EEG-based vibrotactile evoked brain-computer interfaces system: A systematic review

Recently, a novel electroencephalogram-based brain-computer interface (EVE-BCI) using the vibrotactile stimulus shows great potential for an alternative to other typical motor imagery and visual-based ones. (i) Objective: in this review, crucial aspects of EVE-BCI are extracted from the literature to summarize its key factors, investigate the synthetic evidence of feasibility, and generate recommendations for further studies. (ii) Method: five major databases were searched for relevant publications. Multiple key concepts of EVE-BCI, including data collection, stimulation paradigm, vibrotactile control, EEG signal processing, and reported performance, were derived from each eligible article. We then analyzed these concepts to reach our objective. (iii) Results: (a) seventy-nine studies are eligible for inclusion; (b) EEG data are mostly collected among healthy people with an embodiment of EEG cap in EVE-BCI development; (c) P300 and Steady-State Somatosensory Evoked Potential are the two most popular paradigms; (d) only locations of vibration are heavily explored by previous researchers, while other vibrating factors draw little interest. (e) temporal features of EEG signal are usually extracted and used as the input to linear predictive models for EVE-BCI setup; (f) subject-dependent and offline evaluations remain popular assessments of EVE-BCI performance; (g) accuracies of EVE-BCI are significantly higher than chance levels among different populations. (iv) Significance: we summarize trends and gaps in the current EVE-BCI by identifying influential factors. A comprehensive overview of EVE-BCI can be quickly gained by reading this review. We also provide recommendations for the EVE-BCI design and formulate a checklist for a clear presentation of the research work. They are useful references for researchers to develop a more sophisticated and practical EVE-BCI in future studies.

Deep Cross-Output Knowledge Transfer Using Stacked-Structure Least-Squares Support Vector Machines

This article presents a new deep cross-output knowledge transfer approach based on least-squares support vector machines, called DCOT-LS-SVMs. Its aim is to improve the generalizability of least-squares support vector machines (LS-SVMs) while avoiding the complicated parameter tuning process that occurs in many kernel machines. The proposed approach has two significant characteristics: 1) DCOT-LS-SVMs is inspired by a stacked hierarchical architecture that combines several layer-by-layer LS-SVMs modules. The module that forms the higher layer has additional input features that consider the predictions from all previous modules and 2) cross-output knowledge transfer is used to leverage knowledge from the predictions of the previous module to improve the learning process in the current module. With this approach, the model's parameters, such as a tradeoff parameter C and a kernel width δ , can be randomly assigned to each module in order to greatly simplify the learning process. Moreover, DCOT-LS-SVMs is able to autonomously and quickly decide the extent of the cross-output knowledge transfer between adjacent modules through a fast leave-one-out cross-validation strategy. In addition, we present an imbalanced version of DCOT-LS-SVMs, called IDCOT-LS-SVMs, given that imbalanced datasets are common in real-world scenarios. The effectiveness of the proposed approaches is demonstrated through a comparison with five comparative methods on UCI datasets and with a case study on the diagnosis of prostate cancer.

A Deep-Ensemble-Level-Based Interpretable Takagi-Sugeno-Kang Fuzzy Classifier for Imbalanced Data

Existing research reveals that the misclassification rate for imbalanced data depends heavily on the problematic areas due to the existence of small disjoints, class overlap, borderline, and rare data samples. In this study, by stacking zero-order Takagi-Sugeno-Kang (TSK) fuzzy subclassifiers on the minority class and its problematic areas in the deep ensemble, a novel deep-ensemble-level-based TSK fuzzy classifier (IDE-TSK-FC) for imbalanced data classification tasks is presented to achieve both promising classification performance and high interpretability of zero-order TSK fuzzy classifiers. Simultaneously, according to the stacked generalization principle, the proposed classifier lifts up oversampling from the data level to the deep ensemble level with a guarantee of enhanced generalization capability for class imbalance learning. In the structure of IDE-TSK-FC, the first interpretable zero-order TSK fuzzy subclassifier is built on the original training dataset. After that, several successive zero-order TSK fuzzy subclassifiers are stacked layer by layer on the newly identified problematic areas from the original training dataset plus the corresponding interpretable predictions obtained by the averaging strategy on all previous layers. IDE-TSK-FC simply takes the classical K -nearest neighboring algorithm at each layer to identify its problematic area that consists of the minority samples and its surrounding K majority neighbors. After randomly neglecting certain input features and randomly selecting the five Gaussian membership functions for all the chosen input features and the augmented feature in the premise of each fuzzy rule, each subclassifier can be quickly obtained by using the least learning machine to determine the consequent part of each fuzzy rule. The experimental results on both the public datasets and a real-world healthcare dataset demonstrate IDE-TSK-FC's superiority in class imbalanced learning.

Relation Learning Using Temporal Episodes for Motor Imagery Brain-Computer Interfaces

For practical motor imagery (MI) brain-computer interface (BCI) applications, generating a reliable model for a target subject with few MI trials is important since the data collection process is labour-intensive and expensive. In this paper, we address this issue by proposing a few-shot learning method called temporal episode relation learning (TERL). TERL models MI with only limited trials from the target subject by the ability to compare MI trials through episode-based training. It can be directly applied to a new user without being re-trained, which is vital to improve user experience and realize real-world MIBCI applications. We develop a new and effective approach where, unlike the original episode learning, the temporal pattern between trials in each episode is encoded during the learning to boost the classification performance. We also perform an online evaluation simulation, in addition to the offline analysis that the previous studies only conduct, to better understand the performance of different approaches in real-world scenario. Extensive experiments are completed on four publicly available MIBCI datasets to evaluate the proposed TERL. Results show that TERL outperforms baseline and recent state-of-the-art methods, demonstrating competitive performance for subject-specific MIBCI where few trials are available from a target subject and a considerable number of trials from other source subjects.

Development of a Healthcare Information System for Community Care of Older Adults and Evaluation of Its Acceptance and Usability

Objective

The need for health and social care for community-dwelling elderly is on the rise as the population ages. Through the provision of comprehensive services by multiple professionals in local communities, elderly people can receive continual care in a non-medical setting, which is favorable for early detection and intervention of potential problems. However, the lack of digitalization in primary care affects the effectiveness of the services and precludes full exploitation of the data. This study proposed an information system dedicated to caring for community-dwelling elderly people and investigated its acceptance and usability.

Methods

An information system was designed for elderly care centers in the community, where data generated during care delivery, involving socio-demographic data, bio-measurements and health assessments and questionnaires, were digitized and stored for information management and exchange. A study was conducted to evaluate the acceptance and usability of the system after routine use of 6 months. The users of the system at an elderly care center were recruited to respond to a technology acceptance questionnaire and a system usability questionnaire.

Results

The mean scores of the acceptance and usability questionnaires reached 5.1 out of the highest possible score of 7. The constructs of the acceptance questionnaire had good reliability. The social influence and facilitating conditions constructs had a significant correlation with the behavioral intention construct.

Conclusions

The proposed information system demonstrated good acceptance and usability, which supported the feasibility of implementing it in community care centers for older adults. Further research will be conducted to address the limitation of sample size by extending the system to other elderly care centers, forming a large user base for a more in-depth and comprehensive performance evaluation.

A Generalizable and Discriminative Learning Method for Deep EEG-Based Motor Imagery Classification

Convolutional neural networks (CNNs) have been widely applied to the motor imagery (MI) classification field, significantly improving the state-of-the-art (SoA) performance in terms of classification accuracy. Although innovative model structures are thoroughly explored, little attention was drawn toward the objective function. In most of the available CNNs in the MI area, the standard cross-entropy loss is usually performed as the objective function, which only ensures deep feature separability. Corresponding to the limitation of current objective functions, a new loss function with a combination of smoothed cross-entropy (with label smoothing) and center loss is proposed as the supervision signal for the model in the MI recognition task. Specifically, the smoothed cross-entropy is calculated by the entropy between the predicted labels and the one-hot hard labels regularized by a noise of uniform distribution. The center loss learns a deep feature center for each class and minimizes the distance between deep features and their corresponding centers. The proposed loss tries to optimize the model in two learning objectives, preventing overconfident predictions and increasing deep feature discriminative capacity (interclass separability and intraclass invariant), which guarantee the effectiveness of MI recognition models. We conduct extensive experiments on two well-known benchmarks (BCI competition IV-2a and IV-2b) to evaluate our method. The result indicates that the proposed approach achieves better performance than other SoA models on both datasets. The proposed learning scheme offers a more robust optimization for the CNN model in the MI classification task, simultaneously decreasing the risk of overfitting and increasing the discriminative power of deeply learned features.

circRNA-binding protein site prediction based on multi-view deep learning, subspace learning and multi-view classifier

Circular RNAs (circRNAs) generally bind to RNA-binding proteins (RBPs) to play an important role in the regulation of autoimmune diseases. Thus, it is crucial to study the binding sites of RBPs on circRNAs. Although many methods, including traditional machine learning and deep learning, have been developed to predict the interactions between RNAs and RBPs, and most of them are focused on linear RNAs. At present, few studies have been done on the binding relationships between circRNAs and RBPs. Thus, in-depth research is urgently needed. In the existing circRNA-RBP binding site prediction methods, circRNA sequences are the main research subjects, but the relevant characteristics of circRNAs have not been fully exploited, such as the structure and composition information of circRNA sequences. Some methods have extracted different views to construct recognition models, but how to efficiently use the multi-view data to construct recognition models is still not well studied. Considering the above problems, this paper proposes a multi-view classification method called DMSK based on multi-view deep learning, subspace learning and multi-view classifier for the identification of circRNA-RBP interaction sites. In the DMSK method, first, we converted circRNA sequences into pseudo-amino acid sequences and pseudo-dipeptide components for extracting high-dimensional sequence features and component features of circRNAs, respectively. Then, the structure prediction method RNAfold was used to predict the secondary structure of the RNA sequences, and the sequence embedding model was used to extract the context-dependent features. Next, we fed the above four views' raw features to a hybrid network, which is composed of a convolutional neural network and a long short-term memory network, to obtain the deep features of circRNAs. Furthermore, we used view-weighted generalized canonical correlation analysis to extract four views' common features by subspace learning. Finally, the learned subspace common features and multi-view deep features were fed to train the downstream multi-view TSK fuzzy system to construct a fuzzy rule and fuzzy inference-based multi-view classifier. The trained classifier was used to predict the specific positions of the RBP binding sites on the circRNAs. The experiments show that the prediction performance of the proposed method DMSK has been improved compared with the existing methods. The code and dataset of this study are available at https://github.com/Rebecca3150/DMSK.

Extended Kalman filter based on stochastic epidemiological model for COVID-19 modelling

This paper presents a new stochastic-based method for modelling and analysis of COVID-19 spread. A new deterministic Susceptible, Exposed, Infectious, Recovered (Re-infected) and Deceased-based Social Distancing model, named SEIR(R)D-SD, is proposed by introducing the re-infection rate and social distancing factor into the traditional SEIRD (Susceptible, Exposed, Infectious, Recovered and Deceased) model to account for the effects of re-infection and social distancing on COVID-19 spread. The deterministic SEIRD(R)D-SD model is further converted into the stochastic form to account for uncertainties involved in COVID-19 spread. Based on this, an extended Kalman filter (EKF) is developed based on the stochastic SEIR(R)D-SD model to simultaneously estimate both model parameters and transmission state of COVID-19 spread. Simulation results and comparison analyses demonstrate that the proposed method can effectively account for the re-infection and social distancing as well as uncertain effects on COVID-19 spread, leading to improved accuracy for prediction of COVID-19 spread.

Network Together: Node Classification via Cross-Network Deep Network Embedding

Network embedding is a highly effective method to learn low-dimensional node vector representations with original network structures being well preserved. However, existing network embedding algorithms are mostly developed for a single network, which fails to learn generalized feature representations across different networks. In this article, we study a cross-network node classification problem, which aims at leveraging the abundant labeled information from a source network to help classify the unlabeled nodes in a target network. To succeed in such a task, transferable features should be learned for nodes across different networks. To this end, a novel cross-network deep network embedding (CDNE) model is proposed to incorporate domain adaptation into deep network embedding in order to learn label-discriminative and network-invariant node vector representations. On the one hand, CDNE leverages network structures to capture the proximities between nodes within a network, by mapping more strongly connected nodes to have more similar latent vector representations. On the other hand, node attributes and labels are leveraged to capture the proximities between nodes across different networks by making the same labeled nodes across networks have aligned latent vector representations. Extensive experiments have been conducted, demonstrating that the proposed CDNE model significantly outperforms the state-of-the-art network embedding algorithms in cross-network node classification.

Maximum likelihood-based extended Kalman filter for COVID-19 prediction

Prediction of COVID-19 spread plays a significant role in the epidemiology study and government battles against the epidemic. However, the existing studies on COVID-19 prediction are dominated by constant model parameters, unable to reflect the actual situation of COVID-19 spread. This paper presents a new method for dynamic prediction of COVID-19 spread by considering time-dependent model parameters. This method discretises the susceptible-exposed-infected-recovered-dead (SEIRD) epidemiological model in time domain to construct the nonlinear state-space equation for dynamic estimation of COVID-19 spread. A maximum likelihood estimation theory is established to online estimate time-dependent model parameters. Subsequently, an extended Kalman filter is developed to estimate dynamic COVID-19 spread based on the online estimated model parameters. The proposed method is applied to simulate and analyse the COVID-19 pandemics in China and the United States based on daily reported cases, demonstrating its efficacy in modelling and prediction of COVID-19 spread.

Extended Kalman Filter Nonlinear Finite Element Method for Nonlinear Soft Tissue Deformation

BACKGROUND AND OBJECTIVE

Soft tissue modelling is crucial to surgery simulation. This paper introduces an innovative approach to realistic simulation of nonlinear deformation behaviours of biological soft tissues in real time.

METHODS

This approach combines the traditional nonlinear finite-element method (NFEM) and nonlinear Kalman filtering to address both physical fidelity and real-time performance for soft tissue modelling. It defines tissue mechanical deformation as a nonlinear filtering process for dynamic estimation of nonlinear deformation behaviours of biological tissues. Tissue mechanical deformation is discretized in space using NFEM in accordance with nonlinear elastic theory and in time using the central difference scheme to establish the nonlinear state-space models for dynamic filtering.

RESULTS

An extended Kalman filter is established to dynamically estimate nonlinear mechanical deformation of biological tissues. Interactive deformation of biological soft tissues with haptic feedback is accomplished as well for surgery simulation.

CONCLUSIONS

The proposed approach conquers the NFEM limitation of step computation but without trading off the modelling accuracy. It not only has a similar level of accuracy as NFEM, but also meets the real-time requirement for soft tissue modelling.

A Novel Transfer Support Matrix Machine for Motor Imagery-Based Brain Computer Interface

In recent years, emerging matrix learning methods have shown promising performance in motor imagery (MI)-based brain-computer interfaces (BCIs). Nonetheless, the electroencephalography (EEG) pattern variations among different subjects necessitates collecting a large amount of labeled individual data for model training, which prolongs the calibration session. From the perspective of transfer learning, the model knowledge inherent in reference subjects incorporating few target EEG data have the potential to solve the above issue. Thus, a novel knowledge-leverage-based support matrix machine (KL-SMM) was developed to improve the classification performance when only a few labeled EEG data in the target domain (target subject) were available. The proposed KL-SMM possesses the powerful capability of a matrix learning machine, which allows it to directly learn the structural information from matrix-form EEG data. In addition, the KL-SMM can not only fully leverage few labeled EEG data from the target domain during the learning procedure but can also leverage the existing model knowledge from the source domain (source subject). Therefore, the KL-SMM can enhance the generalization performance of the target classifier while guaranteeing privacy protection to a certain extent. Finally, the objective function of the KL-SMM can be easily optimized using the alternating direction method of multipliers method. Extensive experiments were conducted to evaluate the effectiveness of the KL-SMM on publicly available MI-based EEG datasets. Experimental results demonstrated that the KL-SMM outperformed the comparable methods when the EEG data were insufficient.

[Integrating Artificial Intelligence Into Healthcare Research]

The rapid development of artificial intelligence (AI) technologies in recent decades has led to innovation and new development opportunities in many industries. The application of AI technologies in the medical and healthcare sector offers significant potential benefit. In this paper, the integration of AI into healthcare research is introduced to encourage more medical and healthcare experts to research this promising cross-disciplinary area. After introducing the basic concepts that underlie AI, the two major schools of machine learning approaches, namely 'supervised learning' and 'unsupervised learning', are discussed. Next, two commonly used algorithms (artificial neural networks and decision trees) are discussed. The paper then focuses on three healthcare applications of AI technologies, including predicting postoperative mortality, quality of life in older adults, and risk of dementia. Finally, the challenges to integrating AI into healthcare research such as class imbalance, missing data, and data scarcity are discussed along with feasible approaches to resolving these challenges.

Deep stacked support matrix machine based representation learning for motor imagery EEG classification

BACKGROUND AND OBJECTIVE

Electroencephalograph (EEG) classification is an important technology that can establish a mapping relationship between EEG features and cognitive tasks. Emerging matrix classifiers have been successfully applied to motor imagery (MI) EEG classification, but they belong to shallow classifiers, making powerful stacked generalization principle not exploited for automatically learning deep EEG features. To learn the high-level representation and abstraction, we proposed a novel deep stacked support matrix machine (DSSMM) to improve the performance of existing shallow matrix classifiers in EEG classification.

METHODS

The main idea of our framework is founded on the stacked generalization principle, where support matrix machine (SMM) is introduced as the basic building block of deep stacked network. The weak predictions of all previous layers obtained via SMM are randomly projected to help move apart the manifold of the original input EEG feature, and then the newly generated features are fed into the next layer of DSSMM. The framework only involves an efficient feed-forward rather than parameter fine-tuning with backpropagation, each layer of which is a convex optimization problem, thus simplifying the objective function solving process.

RESULTS

Extensive experiments on three public EEG datasets and a self-collected EEG dataset are conducted. Experimental results demonstrate that our DSSMM outperforms the available state-of-the-art methods.

CONCLUSION

The proposed DSSMM inherits the characteristic of matrix classifiers that can learn the structural information of data as well as the powerful capability of deep representation learning, which makes it adapted to classify complex matrix-form EEG data.

Using Dual Neural Network Architecture to Detect the Risk of Dementia With Community Health Data: Algorithm Development and Validation Study

Background

Recent studies have revealed lifestyle behavioral risk factors that can be modified to reduce the risk of dementia. As modification of lifestyle takes time, early identification of people with high dementia risk is important for timely intervention and support. As cognitive impairment is a diagnostic criterion of dementia, cognitive assessment tools are used in primary care to screen for clinically unevaluated cases. Among them, Mini-Mental State Examination (MMSE) is a very common instrument. However, MMSE is a questionnaire that is administered when symptoms of memory decline have occurred. Early administration at the asymptomatic stage and repeated measurements would lead to a practice effect that degrades the effectiveness of MMSE when it is used at later stages.

Objective

The aim of this study was to exploit machine learning techniques to assist health care professionals in detecting high-risk individuals by predicting the results of MMSE using elderly health data collected from community-based primary care services.

Methods

A health data set of 2299 samples was adopted in the study. The input data were divided into two groups of different characteristics (ie, client profile data and health assessment data). The predictive output was the result of two-class classification of the normal and high-risk cases that were defined based on MMSE. A dual neural network (DNN) model was proposed to obtain the latent representations of the two groups of input data separately, which were then concatenated for the two-class classification. Mean and k-nearest neighbor were used separately to tackle missing data, whereas a cost-sensitive learning (CSL) algorithm was proposed to deal with class imbalance. The performance of the DNN was evaluated by comparing it with that of conventional machine learning methods.

Results

A total of 16 predictive models were built using the elderly health data set. Among them, the proposed DNN with CSL outperformed in the detection of high-risk cases. The area under the receiver operating characteristic curve, average precision, sensitivity, and specificity reached 0.84, 0.88, 0.73, and 0.80, respectively.

Conclusions

The proposed method has the potential to serve as a tool to screen for elderly people with cognitive impairment and predict high-risk cases of dementia at the asymptomatic stage, providing health care professionals with early signals that can prompt suggestions for a follow-up or a detailed diagnosis.

RNA-binding protein recognition based on multi-view deep feature and multi-label learning

RNA-binding protein (RBP) is a class of proteins that bind to and accompany RNAs in regulating biological processes. An RBP may have multiple target RNAs, and its aberrant expression can cause multiple diseases. Methods have been designed to predict whether a specific RBP can bind to an RNA and the position of the binding site using binary classification model. However, most of the existing methods do not take into account the binding similarity and correlation between different RBPs. While methods employing multiple labels and Long Short Term Memory Network (LSTM) are proposed to consider binding similarity between different RBPs, the accuracy remains low due to insufficient feature learning and multi-label learning on RNA sequences. In response to this challenge, the concept of RNA-RBP Binding Network (RRBN) is proposed in this paper to provide theoretical support for multi-label learning to identify RBPs that can bind to RNAs. It is experimentally shown that the RRBN information can significantly improve the prediction of unknown RNA-RBP interactions. To further improve the prediction accuracy, we present the novel computational method iDeepMV which integrates multi-view deep learning technology under the multi-label learning framework. iDeepMV first extracts data from the views of amino acid sequence and dipeptide component based on the RNA sequences as the original view. Deep neural network models are then designed for the respective views to perform deep feature learning. The extracted deep features are fed into multi-label classifiers which are trained with the RNA-RBP interaction information for the three views. Finally, a voting mechanism is designed to make comprehensive decision on the results of the multi-label classifiers. Our experimental results show that the prediction performance of iDeepMV, which combines multi-view deep feature learning models with RNA-RBP interaction information, is significantly better than that of the state-of-the-art methods. iDeepMV is freely available at http://www.csbio.sjtu.edu.cn/bioinf/iDeepMV for academic use. The code is freely available at http://github.com/uchihayht/iDeepMV.

Effects of an mHealth Brisk Walking Intervention on Increasing Physical Activity in Older People With Cognitive Frailty: Pilot Randomized Controlled Trial

BACKGROUND

Cognitive frailty is the coexistence of physical frailty and cognitive impairment and is an at-risk state for many adverse health outcomes. Moderate-to-vigorous physical activity (MVPA) is protective against the progression of cognitive frailty. Physical inactivity is common in older people, and brisk walking is a feasible form of physical activity that can enhance their MVPA. Mobile health (mHealth) employing persuasive technology has been successful in increasing the levels of physical activity in older people. However, its feasibility and effects on older people with cognitive frailty are unclear.

OBJECTIVE

We aimed to identify the issues related to the feasibility of an mHealth intervention and the trial (ie, recruitment, retention, participation, and compliance) and to examine the effects of the intervention on cognitive function, physical frailty, walking time, and MVPA.

METHODS

An open-label, parallel design, randomized controlled trial (RCT) was employed. The eligibility criteria for the participants were age ≥60 years, having cognitive frailty, and having physical inactivity. In the intervention group, participants received both conventional behavior change intervention and mHealth (ie, smartphone-assisted program using Samsung Health and WhatsApp) interventions. In the control group, participants received conventional behavior change intervention only. The outcomes included cognitive function, frailty, walking time, and MVPA. Permuted block randomization in 1:1 ratio was used. The feasibility issue was described in terms of participant recruitment, retention, participation, and compliance. Wilcoxon signed-rank test was used to test the within-group effects in both groups separately.

RESULTS

We recruited 99 participants; 33 eligible participants were randomized into either the intervention group (n=16) or the control (n=17) group. The median age was 71.0 years (IQR 9.0) and the majority of them were females (28/33, 85%). The recruitment rate was 33% (33/99), the participant retention rate was 91% (30/33), and the attendance rate of all the face-to-face sessions was 100% (33/33). The majority of the smartphone messages were read by the participants within 30 minutes (91/216, 42.1%). ActiGraph (58/66 days, 88%) and smartphone (54/56 days, 97%) wearing compliances were good. After the interventions, cognitive function improvement was significant in both the intervention (P=.003) and the control (P=.009) groups. The increase in frailty reduction (P=.005), walking time (P=.03), step count (P=.02), brisk walking time (P=.009), peak cadence (P=.003), and MVPA time (P=.02) were significant only in the intervention group.

CONCLUSIONS

Our mHealth intervention is feasible for implementation in older people with cognitive impairment and is effective at enhancing compliance with the brisk walking training program delivered by the conventional behavior change interventions. We provide preliminary evidence that this mHealth intervention can increase MVPA time to an extent sufficient to yield clinical benefits (ie, reduction in cognitive frailty). A full-powered and assessor-blinded RCT should be employed in the future to warrant these effects.

TRIAL REGISTRATION

HKU Clinical Trials Registry HKUCTR-2283; http://www.hkuctr.com/Study/Show/31df4708944944bd99e730d839db4756.

A Transfer-Based Additive LS-SVM Classifier for Handling Missing Data

The performance of a classifier might greatly deteriorate due to missing data. Many different techniques to handle this problem have been developed. In this paper, we solve the problem of missing data using a novel transfer learning perspective and show that when an additive least squares support vector machine (LS-SVM) is adopted, model transfer learning can be used to enhance the classification performance on incomplete training datasets. A novel transfer-based additive LS-SVM classifier is accordingly proposed. This method also simultaneously determines the influence of classification errors caused by each incomplete sample using a fast leave-one-out cross validation strategy, as an alternative way to clean the training data to further improve the data quality. The proposed method has been applied to seven public datasets. The experimental results indicate that the proposed method achieves at least comparable, if not better, performance than case deletion, mean imputation, and k -nearest neighbor imputation methods, followed by the standard LS-SVM and support vector machine classifiers. Moreover, a case study on a community healthcare dataset using the proposed method is presented in detail, which particularly highlights the contributions and benefits of the proposed method to this real-world application.

Segmentation of Overlapping Cytoplasm in Cervical Smear Images via Adaptive Shape Priors Extracted From Contour Fragments

We present a novel approach for segmenting overlapping cytoplasm of cells in cervical smear images by leveraging the adaptive shape priors extracted from cytoplasm's contour fragments and shape statistics. The main challenge of this task is that many occluded boundaries in cytoplasm clumps are extremely difficult to be identified and, sometimes, even visually indistinguishable. Given a clump where multiple cytoplasms overlap, our method starts by cutting its contour into a set of contour fragments. We then locate the corresponding contour fragments of each cytoplasm by a grouping process. For each cytoplasm, according to the grouped fragments and a set of known shape references, we construct its shape and, then, connect the fragments to form a closed contour as the segmentation result, which is explicitly constrained by the constructed shape. We further integrate the intensity and curvature information, which is complementary to the shape priors extracted from contour fragments, into our framework to improve the segmentation accuracy. We propose to iteratively conduct fragments grouping, shape constructing, and fragments connecting for progressively refining the shape priors and improving the segmentation results. We extensively evaluate the effectiveness of our method on two typical cervical smear datasets. The experimental results demonstrate that our approach is highly effective and consistently outperforms the state-of-the-art approaches. The proposed method is general enough to be applied to other similar microscopic image segmentation tasks, where heavily overlapped objects exist.

Deep Multi-View Feature Learning for EEG-Based Epileptic Seizure Detection

Epilepsy is a neurological illness caused by abnormal discharge of brain neurons, where epileptic seizure can lead to life-threatening emergencies. By analyzing the encephalogram (EEG) signals of patients with epilepsy, their conditions can be monitored and seizure can be detected and intervened in time. As the identification of effective features in EEG signals is important for accurate seizure detection, this paper proposes a multi-view deep feature extraction method in attempt to achieve this goal. The method first uses fast Fourier transform (FFT) and wavelet packet decomposition (WPD) to construct the initial multi-view features. Convolutional neural network (CNN) is then used to automatically learn deep features from the initial multi-view features, which reduces the dimensionality and obtain the features with better seizure identification ability. Furthermore, the multi-view Takagi-Sugeno-Kang fuzzy system (MV-TSK-FS), an interpretable rule-based classifier, is used to construct a classification model with strong generalizability based on the deep multi-view features obtained. Experimental studies show that the classification accuracy of the proposed multi-view deep feature extraction method is at least 1% higher than that of common feature extraction methods such as principal component analysis (PCA), FFT and WPD. The classification accuracy is also at least 4% higher than the average accuracy achieved with single-view deep features.