SVD-AE: An asymmetric autoencoder with SVD regularization for multivariate time series anomaly detection.

Anomaly detection in multivariate time series is of critical importance in many real-world applications, such as system maintenance and Internet monitoring. In this article, we propose a novel unsupervised framework called SVD-AE to conduct anomaly detection in multivariate time series. The core idea is to fuse the strengths of both SVD and autoencoder to fully capture complex normal patterns in multivariate time series. An asymmetric autoencoder architecture is proposed, where two encoders are used to capture features in time and variable dimensions and a shared decoder is used to generate reconstructions based on latent representations from both dimensions. A new regularization based on singular value decomposition theory is designed to force each encoder to learn features in the corresponding axis with mathematical supports delivered. A specific loss component is further proposed to align Fourier coefficients of inputs and reconstructions. It can preserve details of original inputs, leading to enhanced feature learning capability of the model. Extensive experiments on three real world datasets demonstrate the proposed algorithm can achieve better performance on multivariate time series anomaly detection tasks under highly unbalanced scenarios compared with baseline algorithms.

IASA: An IoU-aware tracker with adaptive sample assignment.

Most of existing trackers develop tracking in a tracking head network, which is composed of classification branch and regression branch. However, they lack a meaningful exploration of how to define positive and negative samples during training, which can significantly affect tracking performance. Furthermore, they cannot provide a reliable ranking by using classification scores or a combination of classification and regression scores to obtain candidate locations. To address these issues, we propose an intersection over union (IoU) aware tracker with adaptive sample assignment (IASA). The IASA introduces an IoU-aware classification score to achieve a more accurate ranking for candidate tracking locations. We also propose a new loss function, IoU-focal loss, to train the anchor-free tracker IASA to predict the classification scores and introduce a star-shaped box feature representation to refine classification features. To explore the actual content of the training samples, we develop an adaptive sample assignment (ASA) strategy to divide the positive and negative samples according to the statistical characteristics of the sample IoUs. By combining these two proposed components, the IASA tracker treats the tracking task as a classification and a regression problem. It directly finds the candidate tracking location in the classification branch and then regresses the four distances from the location to the four sides of the tracking box. Experimental results show that the proposed IASA can achieve state-of-the-art performance on seven public datasets.

ExpGCN: Review-aware Graph Convolution Network for explainable recommendation.

Existing works in recommender system have widely explored extracting reviews as explanations beyond user-item interactions, and formulated the explanation generation as a ranking task to enhance item recommendation performance. To associate explanations with users and items, graph neural networks (GNN) are usually employed to learn node representations on the heterogeneous user-item-explanation interaction graph. However, modeling heterogeneous graph convolution poses limitations in both message passing styles and computational efficiency, resulting in sub-optimal recommendation performance. To address the limitations, we propose an Explanation-aware Graph Convolution Network (ExpGCN). In particular, the heterogeneous interaction graph is divided to subgraphs regard to the edge types in ExpGCN. By aggregating information from distinct subgraphs, ExpGCN is capable of generating node representations for explanation ranking task and item recommendation task respectively. Task-oriented graph convolution can not only reduce the complexity of heterogeneous node aggregation, but also alleviate the performance degeneration caused by the conflicts between task learning objectives, which has been neglected in current studies. Extensive experiments on four public datasets show that ExpGCN significantly outperforms state-of-the-art baselines with high efficiency, demonstrating the effectiveness of ExpGCN in explainable recommendations.

Modeling Self-Representation Label Correlations for Textual Aspects and Emojis Recommendation.

The rapid development of Internet services and social platforms encourages users to share their opinions. To help users give valuable comments, content providers expect the recommender system to offer appropriate suggestions, including specific features of the item described in texts and emojis, which are all considered aspects of the user reviews. Hence, the review aspect recommendation task has become significant, where the key lies in handling personal preferences and semantic correlations between suggested items. This article proposes a correlation-aware review aspect recommender (CARAR) system model by constructing self-representation correlations between different views of review aspects, including textual aspects and emojis to make a personalized recommendation. The dependencies between different textual aspects and emojis can be identified and utilized to facilitate the factorization process to learn user and item latent factors. The cross-view correlation mapping between textual aspects and emojis can be built to enhance the recommendation performance. Moreover, the additional information in the real-world environment is also applied to our model to adjust the recommendation results. We constructed experiments on five self-collected and public datasets and compared with six existing models. The results show that our model can outperform the existing models on review aspects recommendation tasks, validating the effectiveness of our approach.

Von Hippel-Lindau syndrome with a rare complication of dilated cardiomyopathy: a case report.

BACKGROUND: Von Hippel-Lindau (VHL) syndrome is an autosomal dominant hereditary disease affecting multiple organs, with pheochromocytoma in 26% of cases. However, VHL syndrome with congestive heart failure and dilated cardiomyopathy as the primary clinical manifestations has been rarely reported. CASE PRESENTATION: A 35-year-old male patient was admitted to the hospital with dyspnea. The patient had a history of cerebellar hemangioblastoma that had been resected, and a one-year history of hypertension. Echocardiography and cardiac magnetic resonance imaging demonstrated a dilated left ventricle, decreased systolic function, and nonischemic myocardial changes. Contrast-enhanced abdominal computed tomography showed pheochromocytoma, neoplastic lesions, and multiple cysts in the kidneys and pancreas. Genetic analysis revealed a missense mutation of the VHL gene, c.269 A > T (p.Asn90Ile), which was identified as the cause of the disease. Dilated cardiomyopathy and VHL syndrome type 2 were diagnosed. The patient was administered a diuretic, α-blocker, ß-blocker, and an angiotensin receptor neprilysin inhibitor (ARNI), but refused pheochromocytoma resection. At the six-month follow-up, the patient was asymptomatic with improved cardiac function. CONCLUSION: Cardiac involvement is an atypical manifestation in VHL syndrome. Early diagnosis with genetic screening is essential for avoiding life-threatening complications associated with VHL. The management of this rare manifestation of VHL syndrome requires further investigation.

CLRNet: A Cross Locality Relation Network for Crowd Counting in Videos.

In this article, we propose a new cross locality relation network (CLRNet) to generate high-quality crowd density maps for crowd counting in videos. Specifically, a cross locality relation module (CLRM) is proposed to enhance feature representations by modeling local dependencies of pixels between adjacent frames with an adapted local self-attention mechanism. First, different from the existing methods which measure similarity between pixels by dot product, a new adaptive cosine similarity is advanced to measure the relationship between two positions. Second, the traditional self-attention modules usually integrate the reconstructed features with the same weights for all the positions. However, crowd movement and background changes in a video sequence are uneven in real-life applications. As a consequence, it is inappropriate to treat all the positions in reconstructed features equally. To address this issue, a scene consistency attention map (SCAM) is developed to make CLRM pay more attention to the positions with strong correlations in adjacent frames. Furthermore, CLRM is incorporated into the network in a coarse-to-fine way to further enhance the representational capability of features. Experimental results demonstrate the effectiveness of our proposed CLRNet in comparison to the state-of-the-art methods on four public video datasets. The codes are available at: https://github.com/Amelie01/CLRNet.

Joint clothes image detection and search via anchor free framework.

Clothes image search is an important learning task in fashion analysis to find the most relevant clothes in a database given a user-provided query. To address this problem, most existing methods employ a two-step approach, i.e., first detect the target clothes, and then crop it to feed the model for similarity learning. But the two-step approach is time-consuming and resource-intensive. On the other hand, one-step methods provide efficient solutions to integrate clothes detection and search in a unified framework. However, since one-step methods usually explore anchor-based detectors, they inevitably inherit limitations, such as high computational complexity caused by dense anchors, and high sensitivity to hyperparameters. To address the aforementioned issues, we propose an anchor-free framework for joint clothes detection and search. Specifically, we first choose an anchor-free detector as backbone. We then add a mask prediction branch and a Re-ID embedding branch to the framework. The mask prediction branch aims to predict the masks of clothes, while Re-ID embedding branch aims to extract the rich embedding features of clothes, in which we aggregate the feature of clothes via a mask pooling module by referencing the estimated target clothes masks. In this way, the extracted target clothes features can grasp more information in the area of the clothes mask; finally, we further introduce a match loss to fine-tune the embedding feature in Re-ID branch for improving the retrieval performance. Simulation results based on real datasets demonstrate the effectiveness of the proposed work.

Anti-hypoxic pharmacological effects of betelnut polyphenols. / æ§Ÿæ¦”å¤šé šçš„æŠ—ç¼ºæ°§è¯ç†ä½œç”¨.

Areca catechu L. medicinal materials and their preparations are widely used in clinical practice. Betelnut polyphenol is one of the main chemical components with antioxidant, anti-inflammatory, and antibacterial effects. With continuous increase of high altitude activities, tissue oxidative damage caused by high altitude hypoxia seriously affects the ability to work, and the studies on anti-hypoxia drugs are particularly important. Recent studies have shown that betelnut polyphenols have protective effects on oxidative stress injury caused by hypoxia via improving blood gas index of hypoxic organism, increasing superoxide dismutase glutathione catalase activity, and scavenging excessive free radicals. The effects of betelnut polyphenols against hypoxia and oxidative damage protection suggest that betelnut polyphenols can be used as potential anti-hypoxia drugs and posses clinical prospects.

Topic-Based Instance and Feature Selection in Multilabel Classification.

Multilabel learning has been extensively studied in the past years, as it has many applications in different domains. It aims at annotating the labels for unseen data according to training data, which are often high dimensional in both instance and feature levels. The training data often have noisy and redundant information on these two levels. As an effective data preprocessing step, instance and feature selection should both be performed to find relevant training instances for each testing instance and relevant features for each label, respectively. However, most of the existing methods overlook the input-output correlation in each kind of selection. It will lead to the performance degradation. This article presents a formulation for multilabel learning from a topic view that exploits the dependence between features and labels in a topic space. We can perform effective instance and feature selection in the latent topic space, as the relationship between the input and output spaces is well captured in this space. The results from intensive experiments on various benchmarks demonstrate the effectiveness of the proposed framework.

Semantic-Gap-Oriented Feature Selection and Classifier Construction in Multilabel Learning.

Multilabel learning focuses on assigning instances with different labels. In essence, the multilabel learning aims at learning a predictive function from feature space to a label space. The predictive function learning procedure can be regarded as a feature selection procedure and as a classifier construction procedure. For feature selection, we extract features for each label based on the learned positive and negative feature-label correlations. The positive and negative relationships can illustrate which labels can and cannot be well presented by the corresponding features, respectively, due to the semantic gap. For classifier construction, we perform sample-specific and label-specific classifications. The interlabel and interinstance correlations are combined in these two kinds of classifications. These two correlations are learned from both input features and output labels when the output labels are too sparse to reveal the informative correlation. However, there exists the semantic gap when combining input and output spaces to mine the labelwise relationship. The semantic gap can be bridged by the learned feature-label correlation. Finally, extensive experimental results on several benchmarks under four domains are presented to show the effectiveness of the proposed framework.

Multilabel Classification With Group-Based Mapping: A Framework With Local Feature Selection and Local Label Correlation.

Multilabel learning, which handles instances associated with multiple labels, has attracted much attention in recent years. Many extant multilabel feature selection methods target global feature selection, which means feature selection weights for each label are shared by all instances. Also, many extant multilabel classification methods exploit global label selection, which means labels correlations are shared by all instances. In real-world objects, however, different subsets of instances may share different feature selection weights and different label correlations. In this article, we propose a novel framework with local feature selection and local label correlation, where we assume instances can be clustered into different groups, and the feature selection weights and label correlations can only be shared by instances in the same group. The proposed framework includes a group-specific feature selection process and a label-specific group selection process. The former process projects instances into different groups by extracting the instance-group correlation. The latter process selects labels for each instance based on its related groups by extracting the group-label correlation. In addition, we also exploit the intergroup correlation. These three kinds of group-based correlations are combined to perform effective multilabel classification. The experimental results on various datasets validate the effectiveness of our approach.

Multimodal Image Classification by Multiview Latent Pattern Extraction, Selection, and Correlation.

The large amount of data available in the modern big data era opens new opportunities to expand our knowledge by integrating information from heterogeneous sources. Multiview learning has recently achieved tremendous success in deriving complementary information from multiple data modalities. This article proposes a framework called multiview latent space projection (MVLSP) to integrate features extracted from multiple sources in a discriminative way to facilitate binary and multiclass classifications. Our approach is associated with three innovations. First, most existing multiview learning algorithms promote pairwise consistency between two views and do not have a natural extension to applications with more than two views. MVLSP finds optimum mappings from a common latent space to match the feature space in each of the views. As the matching is performed on a view-by-view basis, the framework can be readily extended to multiview applications. Second, feature selection in the common latent space can be readily achieved by adding a class view, which matches the latent space representations of training samples with their corresponding labels. Then, high-order view correlations are extracted by considering feature-label correlations. Third, a technique is proposed to optimize the integration of different latent patterns based on their correlations. The experimental results on the prostate image dataset demonstrate the effectiveness of the proposed method.

Protective effect of salidroside on lung tissue in rats exposed rapidly to high altitude.

OBJECTIVE: To study the protective effect and mechanism of salidroside on lung tissue of rats exposed rapidly to high altitude. METHODS: Thirty-six Wistar male rats were randomly divided into blank control group, model control group, Rhodiola rosea capsule (137 mg/kg) group, salidroside low-dose (14 mg/kg), medium-dose (28 mg/kg) and high-dose (56 mg/kg) groups, with 6 rats in each group. After 5 continuous days of drug administration in the plain lab, rats were rapidly moved to 4010 m plateau field lab. After exposure to hypoxia condition for 3 days the blood gas indexes were detected; the serum levels of inflammatory factors were measured by enzyme linked immunosorbent assay (ELISA); the oxidative stress index of lung tissue was measured; the pathological changes of lung tissue were observed by microscopy with hematoxylin and eosin (HE) staining; and the expression of occludin in lung tissues was determined by western blotting. RESULTS: Compared with blank control group, arterial oxygen saturation (SaO 2), arterial oxygen partial pressure (PaO 2), blood pH, standard bicarbonate (SBC) and actual bicarbonate levels in model control group were significantly decreased, and hemoglobin level was significantly increased (all P<0.05). In the model control group, the contents of mast cell protease (MCP) 1, interleukin (IL)-6 and IL-1ß were significantly increased, while the contents of interferon-γ were significantly decreased (all P<0.01). The contents of glutathione and total superoxide dismutase in the lung tissues of model control group were significantly decreased, while the content of malondialdehyde was significantly increased (all P<0.01). After Rhodiola rosea and salidroside were given, SaO 2, pH, hemoglobin, SBC and actual bicarbonate were improved compared with the model control group. Compared with the model control group, the Rhodiola rosea group and salidroside groups had different degrees of improvement in the contents of the above inflammatory factors and oxidative stress indexes, and the salidroside groups had better improvement in MCP-1 and IL-6 than the Rhodiola rosea group. HE staining showed that, after the administration of Rhodiola rosea capsules and salidroside at low, medium and high doses, the hypoxic injury was significantly improved, the cell wall gradually became thinner, and the alveolar wall gradually became complete. The expression of occludin in the model control group was lower than that in the blank control group ( P<0.05), while the expression of occludin in the salidroside high-dose group was significantly higher than that in the model control group ( P<0.01). CONCLUSION: Salidroside can improve the abnormality of blood gas index, hypoxia symptoms and acid-base balance disorder, dysregulation of inflammatory factors caused by hypoxia in rats, and improve lung tissue injury and oxidative stress injury, which has a protective effect on lung tissue injury of rats exposed rapidly to the high-altitude plateau, and the effect is better than Rhodiola rosea capsule on the whole.

Multilabel Classification With Label-Specific Features and Classifiers: A Coarse- and Fine-Tuned Framework.

Multilabel classification deals with instances assigned with multiple labels simultaneously. It focuses on learning a mapping from feature space to label a space for out-of-sample extrapolation. The mapping can be seen as a feature selection process in the feature domain or as a classifier training process in the classifier domain. The existing methods do not effectively learn the mapping when combining these two domains together. In this article, we derive a mechanism to extract label-specific features in local and global levels. We also derive a mechanism to train label-specific classifiers in individual and joint levels. Extracting features globally and training classifiers jointly can be seen as a dual process of learning the mapping function on two domains in a coarse-tuned way, while extracting features locally and training classifiers individually can be seen as a dual process of learning the mapping function on two domains in a fine-tuned way. The two-level feature selection and the two-level classifier training are derived to make the entire mapping learning process robust. Finally, extensive experimental results on several benchmarks under four domains are presented to demonstrate the effectiveness of the proposed approach.

Label-specific feature selection and two-level label recovery for multi-label classification with missing labels.

In multi-label learning, each instance is assigned by several nonexclusive labels. However, these labels are often incomplete, resulting in unsatisfactory performance in label related applications. We design a two-level label recovery mechanism to perform label imputation in training sets. An instance-wise semantic relational graph and a label-wise semantic relational graph are used in this mechanism to recover the label matrix. These two graphs exhibit a capability of capturing reliable two-level semantic correlations. We also design a label-specific feature selection mechanism to perform label prediction in testing sets. The local and global feature-label connection are both exploited in this mechanism to learn an inductive classifier. By updating the matrix that represents the relevance between features and the predicted labels, the label-specific feature selection mechanism is robust to missing labels. At last, intensive experimental results on nine datasets under different domains are presented to demonstrate the effectiveness of the proposed approach.

Topic-Based Algorithm for Multilabel Learning With Missing Labels.

In multilabel learning (MLL), each instance can be assigned by several concepts simultaneously from a class dictionary. Usually, labels in the class dictionary have semantic correlations and semantic hierarchy. Instances can be categorized into different topics. Each topic has its own label candidates, and some topics have overlapped label candidates. In this paper, we propose a novel MLL method to deal with missing labels. The proposed algorithm can recover the label matrix according to local, topic-wise, and global semantic properties. Specifically, in the global level, label consistency, label-wise semantic correlations, and semantic hierarchy are exploited; in the local level, label importance and instance-wise semantic correlations in each topic are extracted; and in the topic level, label importance similarities and instance-wise semantic similarities between topics are mined. The experimental results on five image data sets in different applications demonstrate the effectiveness of the proposed approach.

Meta-analysis of interleukin 6, 8, and 10 between off-pump and on-pump coronary artery bypass groups.

This study aimed to evaluate the role of off-pump coronary artery bypass (CAB) surgery on the decrease of postoperative inflammatory responses in patients. We systematically searched databases of PubMed and Embase to select the related studies. Interleukin (IL) 6, 8, and 10 were used as outcomes and pooled analysis was performed using R 3.12 software. Standardized mean differences (SMDs) and their 95% confidence intervals (95% CIs) were considered as effect estimates. A total of 27 studies, including 1340 participants, were recruited in this meta-analysis. The pooled analyses showed that postoperative concentration of IL-10 at 12 hours was significantly lower in off-pump CAB group compared to on-pump CAB group (SMD = -1.3640, 95% CI = -2.0086--0.7193). However, no significant differences were found in pre and postoperative concentrations of IL-6 and 8 between off-pump and on-pump CAB groups. These results suggest that there is no advantage of off-pump CAB surgery in the reduction of inflammation compared to on-pump CAB surgery.

Parathyroid hormone and risk of heart failure in the general population: A meta-analysis of prospective studies.

Inconsistent findings have been reported on the association between the parathyroid hormone (PTH) level and risk of heart failure. We aimed to systematically evaluate the association between circulating level of PTH and risk of heart failure in the general population by conducting a meta-analysis. We made a comprehensive literature search in PubMed, Embase, VIP, CNKI, and Wanfang databases published until January 2016. Only prospective observational studies reporting the association between circulating level of PTH and risk of heart failure in the general population were selected. Pooled adjusted hazard ratio (HR) and corresponding 95% confidence intervals (CIs) were calculated for the highest versus lowest PTH category. Six studies with 25,207 participants identified. Higher circulating level of PTH was associated with an increased risk of heart failure (HR: 1.38; 95% CI 1.09-1.74) in a random effect model. Subgroup analyses revealed that the risk of heart failure was more pronounced among men (HR: 1.75; 95% CI 1.38-2.22) than in both genders. However, the risk increment was not statistically significant (HR: 1.12; 95% CI 0.76-1.66) in the middle-aged population. Higher PTH level is independently associated with an exacerbated risk of heart failure in the general population.

Obstructive sleep apnea syndrome is a risk factor of hypertension.

INTRODUCTION: Some studies investigated the association between obstructive sleep apnea syndrome (OSAS) and hypertension risk. However, the results remained inconclusive. Thus, we performed a meta-analysis to clarify the association of OSAS and hypertension risk. EVIDENCE ACQUISITION: Online electronic databases (PubMed and EMBASE) was searched. The strength of association between the OSAS and hypertension risk was assessed by calculating OR with 95% CI. EVIDENCE SYNTHESIS: A total of 6 articles with 20,637 patients on OSAS and hypertension risk met the study inclusion criteria, and were included in the meta-analysis. OSAS was associated with a significantly increased risk of hypertension (OR=1.41; 95%CI, 1.29-1.8855 I2=20%). In the race subgroup analysis, Caucasians with OSAS had increased hypertension risk (OR=1.43; 95%CI, 1.29-1.59; I2=20%). In the subgroup analysis according to gender, male OSAS patients were significantly associated with risk of hypertension (OR=1.59; 95%CI, 1.16-2.17; I2=0%), while female OSAS patients were not significantly associated with risk of hypertension (OR=1.18; 95%CI, 0.80-1.73; I2=0%). All of the different severities of OSAS patients had an increased hypertension risk (mild: OR=1.26; 95%CI, 1.17-1.35; I2=45%; moderate: OR=1.50; 95%CI, 1.27-1.76; I2=46%; severe: OR=1.47; 95%CI, 1.33-1.64; I2=63%). CONCLUSIONS: In conclusion, this meta-analysis suggested that OSAS may be associated with hypertension risk.

An inhibitor binding pocket distinct from the catalytic active site on human beta-APP cleaving enzyme.

Beta-APP cleaving enzyme (BACE) is responsible for the first of two proteolytic cleavages of the APP protein that together lead to the generation of the Alzheimer's disease-associated Abeta peptide. It is widely believed that halting the production of Abeta peptide, by inhibition of BACE, is an attractive therapeutic modality for the treatment of Alzheimer's disease. BACE is an aspartyl protease, and there is significant effort in the pharmaceutical community to apply traditional design methods to the development of active site-directed inhibitors of this enzyme. We report here the discovery of a ligand binding pocket within the catalytic domain of BACE that is distinct from the enzymatic active site (i.e., an exosite). Peptides, initially identified from combinatorial phage peptide libraries, contain the sequence YPYF(I/L)P(L/I) and bind specifically to this exosite, even in the presence of saturating concentrations of active site-directed inhibitors. Binding of peptides to the BACE exosite leads to a concentration-dependent inhibition of proteolysis for APP-related, protein-based substrates of BACE. The discovery of this exosite opens new opportunities for the identification and development of novel and potentially selective small molecule inhibitors of BACE that act through exosite, rather than active site, binding interactions.