Uncertainty-Aware Denoising Network for Artifact Removal in EEG Signals.

The electroencephalogram (EEG) is extensively employed for detecting various brain electrical activities. Nonetheless, EEG recordings are susceptible to undesirable artifacts, resulting in misleading data analysis and even significantly impacting the interpretation of results. While previous efforts to mitigate or reduce the impact of artifacts have achieved commendable performance, several challenges in this domain still persist: 1) due to black-box skepticism, deep-learning-based automatic EEG artifact removal methods have been impeded from being applied in clinical environments. How to support reliable denoised EEG signals with high accuracy is important; and 2) effectively exploring valuable local and global information from contaminated contexts remains challenging. On the one hand, feature extraction and aggregation in prior works are often performed blindly and assumed to be accurate, which is not always the case. On the other hand, global contextual information is gradually modeled by local fixed single-scaled convolutional filters layer by layer, which is neither efficient nor effective. To address the above challenges, we propose an Uncertainty-aware Denoising Network (UDNet) with multi-scaled pooling attention for efficient context capturing. Specifically, we predict the aleatoric and epistemic uncertainty existing during the denoising process to assist in finding and reducing the uncertain feature representation. We further propose a simple yet effective architecture to capture local and global contexts at multiple scales. Our proposed method can serve as an effective metric for identifying low-confidence epochs that warrant deferral to human experts for further inspection and assessment. Experimental results on two public datasets show that the proposed model outperforms state-of-the-art baselines.

A homologous and heterogeneous multi-view inter-patient adaptive network for arrhythmia detection.

BACKGROUND AND OBJECTIVE: Electrocardiogram (ECG) is a widely used diagnostic tool for arrhythmia assessment in clinical practice. However, current arrhythmia detection algorithms rely heavily on signal-based data, while cardiologists often use image-based data. This discrepancy, combined with individual differences in physiological signals, poses challenges for accurate arrhythmia detection. To address these challenges and improve arrhythmia detection performance, we propose a homologous and heterogeneous multi-view inter-patient adaptive network. METHODS: We designed a multi-view representation learning module to capture dynamic and morphological characteristics from ECG signals and electrocardiographic images. Expert knowledge was also elicited to gain internally-invariant characteristics of each category. Finally, we designed a new loss function that aligns the embedding of the source and target domains in the feature space to minimize the negative effects of individual differences. RESULTS: Experiments on the MIT-BIH arrhythmia database demonstrate that our proposed method outperforms state-of-the-art baselines in terms of accuracy, positive predictive value, sensitivity and F1-score. These results indicate the effectiveness of our method in accurately detecting arrhythmias. CONCLUSIONS: Our homologous and heterogeneous multi-view inter-patient adaptive network successfully addresses the challenges of utilizing both ECG signal and electrocardiographic image data for arrhythmia detection and overcoming individual differences in physiological signals. Our proposed method has the potential to improve early diagnosis and treatment outcomes of arrhythmias in clinical practice.

Identity-Guided Spatial Attention for Vehicle Re-Identification.

In vehicle re-identification, identifying a specific vehicle from a large image dataset is challenging due to occlusion and complex backgrounds. Deep models struggle to identify vehicles accurately when critical details are occluded or the background is distracting. To mitigate the impact of these noisy factors, we propose Identity-guided Spatial Attention (ISA) to extract more beneficial details for vehicle re-identification. Our approach begins by visualizing the high activation regions of a strong baseline method and identifying noisy objects involved during training. ISA generates an attention map to mask most discriminative areas, without the need for manual annotation. Finally, the ISA map refines the embedding feature in an end-to-end manner to improve vehicle re-identification accuracy. Visualization experiments demonstrate ISA's ability to capture nearly all vehicle details, while results on three vehicle re-identification datasets show that our method outperforms state-of-the-art approaches.

TRR: Target-relation regulated network for sequential recommendation.

Item co-occurrence is an important pattern in recommendation. Due to the difference in correlation, the matching degrees between the target and historical items vary. The higher the matching degree, the greater probability they co-occur. Recently, the recommendation performance has been greatly improved by leveraging item relations. As an important bond imposed by relations, these connected items should have a strong correlation in the calculation of certain measures. This kind of correlation can be the biased knowledge that benefits parameter training. Specifically, we focus on tuples containing the target item and latest relational items that have relations such as complement or substitute with the target item in user's behavior sequence. Such close relations mean the matching degrees between relational items and historical items should be highly affected by that of the target item and historical items. For example, given a relational item having relation complement with the target item, if the target item has high matching degrees with some items in user's behavior sequence, this complementary item should behave similarly for the co-occurrence of complementary items. Under guidance of the above thought, in this work, we propose a target-relation regulated mechanism which converts the biased knowledge of high correlation of matching degrees into a regulation. It integrates the target item and relational items in history as a whole to characterize the matching score between the target item and historical items. Experiments conducted on three real-world datasets demonstrate that our model can significantly outperform a set of state-of-the-art models.

Attenuated and normalized item-item product network for sequential recommendation.

Sequential recommendation has become a research trending that exploits user's recent behaviors for recommendation. The user-item interactions contain a sequential dependency that we need to capture to better recommend. Item-item Product (IIP), which models item co-occurrence, has shown good potential by characterizing the pairwise item relationships. Generally, recent behaviors have a greater impact on the current than long-term historical behaviors. And the decaying rate of influence around infrequent behaviors is fast. However, IIP ignores such a phenomenon when considering item-item relevance and leads to suboptimal performance. In this paper, we propose an attenuated IIP mechanism which is position-aware and decays the influence of historical items at an exponential rate. Besides, In order to make up for scenarios where the influence is not in a monotonous decline trend, we add another normalized IIP mechanism to complement the attenuated IIP mechanism. It also strengthen the model's ability in discriminating favorite items under the sparse data condition by enlarging the gap of matching degree between items. Experiments conducted on five real-world datasets demonstrate that our proposed model achieves better performance than a set of state-of-the-art sequential recommendation models.

Multi-View Spatial-Temporal Graph Convolutional Networks With Domain Generalization for Sleep Stage Classification.

Sleep stage classification is essential for sleep assessment and disease diagnosis. Although previous attempts to classify sleep stages have achieved high classification performance, several challenges remain open: 1) How to effectively utilize time-varying spatial and temporal features from multi-channel brain signals remains challenging. Prior works have not been able to fully utilize the spatial topological information among brain regions. 2) Due to the many differences found in individual biological signals, how to overcome the differences of subjects and improve the generalization of deep neural networks is important. 3) Most deep learning methods ignore the interpretability of the model to the brain. To address the above challenges, we propose a multi-view spatial-temporal graph convolutional networks (MSTGCN) with domain generalization for sleep stage classification. Specifically, we construct two brain view graphs for MSTGCN based on the functional connectivity and physical distance proximity of the brain regions. The MSTGCN consists of graph convolutions for extracting spatial features and temporal convolutions for capturing the transition rules among sleep stages. In addition, attention mechanism is employed for capturing the most relevant spatial-temporal information for sleep stage classification. Finally, domain generalization and MSTGCN are integrated into a unified framework to extract subject-invariant sleep features. Experiments on two public datasets demonstrate that the proposed model outperforms the state-of-the-art baselines.

End-to-End Light Field Spatial Super-Resolution Network Using Multiple Epipolar Geometry.

Light Field (LF) cameras are considered to have many potential applications since angular and spatial information is captured simultaneously. However, the limited spatial resolution has brought lots of difficulties in developing related applications and becomes the main bottleneck of LF cameras. In this paper, an end-to-end learning-based method is proposed to simultaneously reconstruct all view images in LFs with higher spatial resolution. Based on the epipolar geometry, view images in one LF are first grouped into several image stacks and fed into different network branches to learn sub-pixel details for each view image. Since LFs have dense sampling in angular domain, sub-pixel details in multiple spatial directions are learned from corresponding angular directions in multiple branches, respectively. Then, sub-pixel details from different directions are further integrated to generate global high-frequency residual details. Combined with the spatially upsampled LF, the final LF with high spatial resolution is obtained. Experimental results on synthetic and real-world datasets demonstrate that the proposed method outperforms other state-of-the-art methods in both visual and numerical evaluations. We also implement the proposed method on LFs with different angular resolution and experiments show that the proposed method achieves superior results than others, especially for LFs with small angular resolution. Furthermore, since the epipolar geometry is fully considered, the proposed network shows good performances in preserving the inherent epipolar property in LF images.

Unsupervised Anomaly Detection with Distillated Teacher-Student Network Ensemble.

We address the problem of unsupervised anomaly detection for multivariate data. Traditional machine learning based anomaly detection algorithms rely on specific assumptions of normal patterns and fail to model complex feature interactions and relations. Recently, existing deep learning based methods are promising for extracting representations from complex features. These methods train an auxiliary task, e.g., reconstruction and prediction, on normal samples. They further assume that anomalies fail to perform well on the auxiliary task since they are never trained during the model optimization. However, the assumption does not always hold in practice. Deep models may also perform the auxiliary task well on anomalous samples, leading to the failure detection of anomalies. To effectively detect anomalies for multivariate data, this paper introduces a teacher-student distillation based framework Distillated Teacher-Student Network Ensemble (DTSNE). The paradigm of the teacher-student distillation is able to deal with high-dimensional complex features. In addition, an ensemble of student networks provides a better capability to avoid generalizing the auxiliary task performance on anomalous samples. To validate the effectiveness of our model, we conduct extensive experiments on real-world datasets. Experimental results show superior performance of DTSNE over competing methods. Analysis and discussion towards the behavior of our model are also provided in the experiment section.

Representation based on ordinal patterns for seizure detection in EEG signals.

EEG signals carry rich information about brain activity and play an important role in the diagnosis and recognition of epilepsy. Numerous algorithms using EEG signals to detect seizures have been developed in recent decades. However, most of them require well-designed features that highly depend on domain-specific knowledge and algorithm expertise. In this study, we introduce the unigram ordinal pattern (UniOP) and bigram ordinal pattern (BiOP) representations to capture the different underlying dynamics of time series, which only assumes that time series derived from different dynamics can be characterized by repeated ordinal patterns. Specifically, we first transform each subsequence in a time series into the corresponding ordinal pattern in terms of the ranking of values and consider the distribution of ordinal patterns of all subsequences as the UniOP representation. Furthermore, we consider the distribution of the cooccurrence of ordinal patterns as the BiOP representation to characterize the contextual information for each ordinal pattern. We then combine the proposed representations with the nearest neighbor algorithm to evaluate its effectiveness on three publicly available seizure datasets. The results on the Bonn EEG dataset demonstrate that this method provides more than 90% accuracy, sensitivity, and specificity in most cases and outperforms several state-of-the-art methods, which proves its ability to capture the key information of the underlying dynamics of EEG time series at healthy, seizure-free, and seizure states. The results on the second dataset are comparable with the state-of-the-art method, showing the good generalization ability of the proposed method. All performance metrics on the third dataset are approximately 89%, which demonstrates that the proposed representations are suitable for large-scale datasets.

Refined nonuniform embedding for coupling detection in multivariate time series.

State-space reconstruction is essential to analyze the dynamics and internal interactions of complex systems. However, it is difficult to estimate high-dimensional conditional mutual information and select the optimal time delays in most existing nonuniform state-space reconstruction methods. Therefore, we propose a nonuniform embedding method framed in information theory for state-space reconstruction. We use a low-dimensional approximation of conditional mutual information criterion for time delay selection, which is effectively solved by the particle swarm optimization algorithm. The obtained embedded vector has relatively strong independence and low redundancy, which better characterizes multivariable complex systems and detects coupling within complex systems. In addition, the proposed nonuniform embedding method exhibits good performance in coupling detection of linear stochastic, nonlinear stochastic, chaotic systems. In the actual application, the importance of small airports that cause delay propagation has been demonstrated by constructing the delay propagation network.

A RR interval based automated apnea detection approach using residual network.

BACKGROUND AND OBJECTIVE: Apnea is one of the most common conditions that causes sleep-disorder breathing. With growing number of patients worldwide, more and more patients suffer from complications of apnea. But most of them stay untreated due to the complex and time-consuming polysomnography (PSG) diagnosis method. Effective and precise diagnosis support system using electrocardiograph (ECG) is required. In this paper, we propose an approach using residual network to detect apnea based on RR intervals (intervals between R-peaks of ECG signal). METHODS: In our model, we apply residual network to represent information carried by RR intervals. Moreover, we proposed a novel perspective, called dynamic autoregressive representation, to provide interpretation of representing the RR intervals by convolutional layers. RESULTS: This approach is tested for per-segment apnea detection using publicly available dataset on Physionet. 30 overnight recordings are used for training and 5 for testing. We achieve a good result of 94.4% accuracy, 93.0% sensitivity and 94.9% specificity. This result outperform other prevalent methods based on RR intervals. This model also shows its good adaptivity while using ECG-derived respiration signal (EDR) in experiments. Its extensiveness is evaluated and compared in experiments. The proposed model is also compared with deep neural networks using original ECG signals for apnea detection, and it achieves better result using fewer input samples. CONCLUSIONS: We develop a deep residual network to detect apnea on low-sample-rate RR intervals. The result suggests a possibility of representing RR intervals by neural network. The model showed strong adaptivity when using EDR input.

A new exhaustive method and strategy for finding motifs in ChIP-enriched regions.

ChIP-seq, which combines chromatin immunoprecipitation (ChIP) with next-generation parallel sequencing, allows for the genome-wide identification of protein-DNA interactions. This technology poses new challenges for the development of novel motif-finding algorithms and methods for determining exact protein-DNA binding sites from ChIP-enriched sequencing data. State-of-the-art heuristic, exhaustive search algorithms have limited application for the identification of short (l, d) motifs (l ≤ 10, d ≤ 2) contained in ChIP-enriched regions. In this work we have developed a more powerful exhaustive method (FMotif) for finding long (l, d) motifs in DNA sequences. In conjunction with our method, we have adopted a simple ChIP-enriched sampling strategy for finding these motifs in large-scale ChIP-enriched regions. Empirical studies on synthetic samples and applications using several ChIP data sets including 16 TF (transcription factor) ChIP-seq data sets and five TF ChIP-exo data sets have demonstrated that our proposed method is capable of finding these motifs with high efficiency and accuracy. The source code for FMotif is available at http://211.71.76.45/FMotif/.