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.

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.

Revolutionizing food science with mass spectrometry imaging: A comprehensive review of applications and challenges.

Food science encounters increasing complexity and challenges, necessitating more efficient, accurate, and sensitive analytical techniques. Mass spectrometry imaging (MSI) emerges as a revolutionary tool, offering more molecular-level insights. This review delves into MSI's applications and challenges in food science. It introduces MSI principles and instruments such as matrix-assisted laser desorption/ionization, desorption electrospray ionization, secondary ion mass spectrometry, and laser ablation inductively coupled plasma mass spectrometry, highlighting their application in chemical composition analysis, variety identification, authenticity assessment, endogenous substance, exogenous contaminant and residue analysis, quality control, and process monitoring in food processing and food storage. Despite its potential, MSI faces hurdles such as the complexity and cost of instrumentation, complexity in sample preparation, limited analytical capabilities, and lack of standardization of MSI for food samples. While MSI has a wide range of applications in food analysis and can provide more comprehensive and accurate analytical results, challenges persist, demanding further research and solutions. The future development directions include miniaturization of imaging devices, high-resolution and high-speed MSI, multiomics and multimodal data fusion, as well as the application of data analysis and artificial intelligence. These findings and conclusions provide valuable references and insights for the field of food science and offer theoretical and methodological support for further research and practice in food science.

Niobium Oxide Anode with Lattice Structure Self-Optimization for High-Power and Nearly Zero-Degeneration Battery Operation.

Li+ insertion-induced structure transformation in crystalline electrodes vitally influence the energy density and cycle life of secondary lithium-ion battery. However, the influence mechanism of structure transformation-induced Li+ migration on the electrochemical performance of micro-crystal materials is still unclear and the strategy to profit from such structure transformation remains exploited. Here, an interesting self-optimization of structure evolution during electrochemical cycling in Nb2 O5 micro-crystal with rich domain boundaries is demonstrated, which greatly improves the charge transfer property and mechanical strength. The lattice rearrangement activates the Li+ diffusion kinetics and hinders the particle crack, thus enabling a nearly zero-degeneration operation after 8000 cycles. Full cell paired with lithium cobalt oxides displays an exceptionally high capacity of 176 mA h g-1 at 8000 mA g-1 and excellent long-term durability at 6000 mA g-1 with 63% capacity retention over 2000 cycles. Interestingly, a unique fingerprint based on the intensity ratio of two X-ray diffraction peaks is successfully extracted as a measure of Nb2 O5 electrochemical performance. The structure self-optimization for fast charge transfer and high mechanical strength exemplifies a new battery electrode design concept and opens up a vast space of strategy to develop high-performance lithium-ion batteries with high energy density and ultra-long cycle life.

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.

Diagnostic and prognostic value of echocardiography in pulmonary hypertension: an umbrella review of systematic reviews and meta-analyses.

BACKGROUND: The role of echocardiography in the diagnostic and prognostic assessment of pulmonary hypertension (PH) has been widely studied recently. However, these findings have not undergone normative evaluation and may provide confusing evidence for clinicians. To evaluate and summarize existing evidence, we performed an umbrella review. METHODS: Systematic reviews and meta-analyses were searched in PubMed, Embase, Web of Science, and Cochrane Library from inception to September 4, 2022. The methodological quality of the included studies was assessed using Assessment of Multiple Systematic Reviews (AMSTAR), and the Grading of Recommendations Assessment, Development and Evaluation (GRADE) system was used to evaluate the quality of evidence. RESULTS: Thirteen meta-analyses (nine diagnostic and four prognostic studies) were included after searching four databases. The methodological quality of the included studies was rated as high (62%) or moderate (38%) by AMSTAR. The thirteen included meta-analyses involved a total of 28 outcome measures. The quality of evidence for these outcomes were high (7%), moderate (29%), low (39%), and very low (25%) using GRADE methodology. In the detection of PH, the sensitivity of systolic pulmonary arterial pressure is 0.85-0.88, and the sensitivity and specificity of right ventricular outflow tract acceleration time are 0.84. Pericardial effusion, right atrial area, and tricuspid annulus systolic displacement provide prognostic value in patients with pulmonary arterial hypertension with hazard ratios between 1.45 and 1.70. Meanwhile, right ventricular longitudinal strain has independent prognostic value in patients with PH, with a hazard ratio of 2.96-3.67. CONCLUSION: The umbrella review recommends echocardiography for PH detection and prognosis. Systolic pulmonary arterial pressure and right ventricular outflow tract acceleration time can be utilized for detection, while several factors including pericardial effusion, right atrial area, tricuspid annular systolic displacement, and right ventricular longitudinal strain have demonstrated prognostic significance. TRIAL REGISTRATION: PROSPERO (CRD42022356091), https://www.crd.york.ac.uk/prospero/ .

Enhancing Li-Ion Transport in Solid Electrolytes by Confined Water.

Developing new oxide solid electrolytes with fast Li-ion transport and high stability is an important step to realize high-performance solid-state Li-ion batteries. Hydrate materials containing confined water widely exist in nature or can be easily synthesized. However, they have seldom been explored as Li-ion solid electrolytes due to the stereotype that the presence of water limits the electrochemical stability window of a solid electrolyte. In this work, it is demonstrated that confined water can enhance Li-ion transport while not compromising the stability window of solid electrolytes using Li-H-Ti-O quaternary compounds as an example system. Three Li-H-Ti-O quaternary compounds containing different amounts of confined water are synthesized, and their ionic conductivity and electrochemical stability are compared. The compound containing structural pseudo-water is demonstrated to have an ionic conductivity that is 2-3 order of magnitude higher than the water-free Li4 Ti5 O12 and similar stability window. A solid-state battery is made with this new compound as the solid electrolyte, and good rate and cycling performance are achieved, which demonstrates the promise of using such confined-water-containing compounds as Li-ion solid electrolytes. The knowledge and insights gained in this work open a new direction for designing solid electrolytes for future solid-state Li-ion batteries. Broadly, by confining water into solid crystal structures, new design freedoms for tailing the properties of ceramic materials are introduced, which creates new opportunities in designing novel materials to address critical problems in various engineering fields.

SSC-EKE: Semi-Supervised Classification with Extensive Knowledge Exploitation.

We introduce a new, semi-supervised classification method that extensively exploits knowledge. The method has three steps. First, the manifold regularization mechanism, adapted from the Laplacian support vector machine (LapSVM), is adopted to mine the manifold structure embedded in all training data, especially in numerous label-unknown data. Meanwhile, by converting the labels into pairwise constraints, the pairwise constraint regularization formula (PCRF) is designed to compensate for the few but valuable labelled data. Second, by further combining the PCRF with the manifold regularization, the precise manifold and pairwise constraint jointly regularized formula (MPCJRF) is achieved. Third, by incorporating the MPCJRF into the framework of the conventional SVM, our approach, referred to as semi-supervised classification with extensive knowledge exploitation (SSC-EKE), is developed. The significance of our research is fourfold: 1) The MPCJRF is an underlying adjustment, with respect to the pairwise constraints, to the graph Laplacian enlisted for approximating the potential data manifold. This type of adjustment plays the correction role, as an unbiased estimation of the data manifold is difficult to obtain, whereas the pairwise constraints, converted from the given labels, have an overall high confidence level. 2) By transforming the values of the two terms in the MPCJRF such that they have the same range, with a trade-off factor varying within the invariant interval [0, 1), the appropriate impact of the pairwise constraints to the graph Laplacian can be self-adaptively determined. 3) The implication regarding extensive knowledge exploitation is embodied in SSC-EKE. That is, the labelled examples are used not only to control the empirical risk but also to constitute the MPCJRF. Moreover, all data, both labelled and unlabelled, are recruited for the model smoothness and manifold regularization. 4) The complete framework of SSC-EKE organically incorporates multiple theories, such as joint manifold and pairwise constraint-based regularization, smoothness in the reproducing kernel Hilbert space, empirical risk minimization, and spectral methods, which facilitates the preferable classification accuracy as well as the generalizability of SSC-EKE.

Multi-task diagnosis for autism spectrum disorders using multi-modality features: A multi-center study.

Autism spectrum disorder (ASD) is a neurodevelopment disease characterized by impairment of social interaction, language, behavior, and cognitive functions. Up to now, many imaging-based methods for ASD diagnosis have been developed. For example, one may extract abundant features from multi-modality images and then derive a discriminant function to map the selected features toward the disease label. A lot of recent works, however, are limited to single imaging centers. To this end, we propose a novel multi-modality multi-center classification (M3CC) method for ASD diagnosis. We treat the classification of each imaging center as one task. By introducing the task-task and modality-modality regularizations, we solve the classification for all imaging centers simultaneously. Meanwhile, the optimal feature selection and the modeling of the discriminant functions can be jointly conducted for highly accurate diagnosis. Besides, we also present an efficient iterative optimization solution to our formulated problem and further investigate its convergence. Our comprehensive experiments on the ABIDE database show that our proposed method can significantly improve the performance of ASD diagnosis, compared to the existing methods. Hum Brain Mapp 38:3081-3097, 2017. © 2017 Wiley Periodicals, Inc.

Knowledge-leveraged transfer fuzzy C-Means for texture image segmentation with self-adaptive cluster prototype matching.

We study a novel fuzzy clustering method to improve the segmentation performance on the target texture image by leveraging the knowledge from a prior texture image. Two knowledge transfer mechanisms, i.e. knowledge-leveraged prototype transfer (KL-PT) and knowledge-leveraged prototype matching (KL-PM) are first introduced as the bases. Applying them, the knowledge-leveraged transfer fuzzy C-means (KL-TFCM) method and its three-stage-interlinked framework, including knowledge extraction, knowledge matching, and knowledge utilization, are developed. There are two specific versions: KL-TFCM-c and KL-TFCM-f, i.e. the so-called crisp and flexible forms, which use the strategies of maximum matching degree and weighted sum, respectively. The significance of our work is fourfold: 1) Owing to the adjustability of referable degree between the source and target domains, KL-PT is capable of appropriately learning the insightful knowledge, i.e. the cluster prototypes, from the source domain; 2) KL-PM is able to self-adaptively determine the reasonable pairwise relationships of cluster prototypes between the source and target domains, even if the numbers of clusters differ in the two domains; 3) The joint action of KL-PM and KL-PT can effectively resolve the data inconsistency and heterogeneity between the source and target domains, e.g. the data distribution diversity and cluster number difference. Thus, using the three-stage-based knowledge transfer, the beneficial knowledge from the source domain can be extensively, self-adaptively leveraged in the target domain. As evidence of this, both KL-TFCM-c and KL-TFCM-f surpass many existing clustering methods in texture image segmentation; and 4) In the case of different cluster numbers between the source and target domains, KL-TFCM-f proves higher clustering effectiveness and segmentation performance than does KL-TFCM-c.

Cross-domain, soft-partition clustering with diversity measure and knowledge reference.

Conventional, soft-partition clustering approaches, such as fuzzy c-means (FCM), maximum entropy clustering (MEC) and fuzzy clustering by quadratic regularization (FC-QR), are usually incompetent in those situations where the data are quite insufficient or much polluted by underlying noise or outliers. In order to address this challenge, the quadratic weights and Gini-Simpson diversity based fuzzy clustering model (QWGSD-FC), is first proposed as a basis of our work. Based on QWGSD-FC and inspired by transfer learning, two types of cross-domain, soft-partition clustering frameworks and their corresponding algorithms, referred to as type-I/type-II knowledge-transfer-oriented c-means (TI-KT-CM and TII-KT-CM), are subsequently presented, respectively. The primary contributions of our work are four-fold: (1) The delicate QWGSD-FC model inherits the most merits of FCM, MEC and FC-QR. With the weight factors in the form of quadratic memberships, similar to FCM, it can more effectively calculate the total intra-cluster deviation than the linear form recruited in MEC and FC-QR. Meanwhile, via Gini-Simpson diversity index, like Shannon entropy in MEC, and equivalent to the quadratic regularization in FC-QR, QWGSD-FC is prone to achieving the unbiased probability assignments, (2) owing to the reference knowledge from the source domain, both TI-KT-CM and TII-KT-CM demonstrate high clustering effectiveness as well as strong parameter robustness in the target domain, (3) TI-KT-CM refers merely to the historical cluster centroids, whereas TII-KT-CM simultaneously uses the historical cluster centroids and their associated fuzzy memberships as the reference. This indicates that TII-KT-CM features more comprehensive knowledge learning capability than TI-KT-CM and TII-KT-CM consequently exhibits more perfect cross-domain clustering performance and (4) neither the historical cluster centroids nor the historical cluster centroid based fuzzy memberships involved in TI-KT-CM or TII-KT-CM can be inversely mapped into the raw data. This means that both TI-KT-CM and TII-KT-CM can work without disclosing the original data in the source domain, i.e. they are of good privacy protection for the source domain. In addition, the convergence analyses regarding both TI-KT-CM and TII-KT-CM are conducted in our research. The experimental studies thoroughly evaluated and demonstrated our contributions on both synthetic and real-life data scenarios.

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.

Developing a detection strategy for ten paralytic shellfish poisonings in urine, combining high-throughput DESI-MS screening and accurate UPLC-QqQ/MS quantification.

Paralytic shellfish poisoning (PSP) is the most widespread and harmful form of shellfish poisoning with high mortality rate. In this study, a combined desorption electrospray ionization mass spectrometry (DESI-MS) and ultra-performance liquid chromatography triple quadrupole mass spectrometry (UPLC-QqQ/MS) method was established for the detection of PSPs in urine. The method was optimized using a spray solution of methanol and water (1:1, v/v) containing 0.1 % FA, at a flow rate of 2.5 µL·min-1 and an applied voltage of 3 kV. The limit of detection (LOD) for PSPs detection by DESI-MS was in the range of 87-265 µg·L-1, which basically meets the requirements for the rapid screening of PSPs. The LOD for UPLC-QqQ/MS was in the range of 2.2-14.9 µg·L-1, with a limit of quantification (LOQ) of 7.3-49.7 µg·L-1, thus fulfilling the quantitative demand for PSPs in urine. Finally, after spiking the urine samples of six volunteers with PSPs to a concentration of 100 µg·L-1, DESI-MS successfully and efficiently detected the positive samples. Subsequently, UPLC-QqQ/MS was employed for precise quantification, yielding results in the range of 84.6-95.1 µg·L-1. The experimental findings demonstrated that the combination of DESI-MS and UPLC-QqQ/MS enables high-throughput, rapid screening of samples and accurate quantification of positive samples, providing assurance for food safety and human health.

Empagliflozin alleviates neuroinflammation by inhibiting astrocyte activation in the brain and regulating gut microbiota of high-fat diet mice.

A high-fat diet can modify the composition of gut microbiota, resulting in dysbiosis. Changes in gut microbiota composition can lead to increased permeability of the gut barrier, allowing bacterial products like lipopolysaccharides (LPS) to enter circulation. This process can initiate systemic inflammation and contribute to neuroinflammation. Empagliflozin (EF), an SGLT2 inhibitor-type hypoglycemic drug, has been reported to treat neuroinflammation. However, there is a lack of evidence showing that EF regulates the gut microbiota axis to control neuroinflammation in HFD models. In this study, we explored whether EF could improve neuroinflammation caused by an HFD via regulation of the gut microbiota and the mechanism underlying this phenomenon. Our data revealed that EF alleviates pathological brain injury, reduces the reactive proliferation of astrocytes, and increases the expression of synaptophysin. In addition, the levels of inflammatory factors in hippocampal tissue were significantly decreased after EF intervention. Subsequently, the results of 16S rRNA gene sequencing showed that EF could change the microbial community structure of mice, indicating that the abundance of Lactococcus, Ligilactobacillus and other microbial populations decreased dramatically. Therefore, EF alleviates neuroinflammation by inhibiting gut microbiota-mediated astrocyte activation in the brains of high-fat diet-fed mice. Our study focused on the gut-brain axis, and broader research on neuroinflammation can provide a more holistic understanding of the mechanisms driving neurodegenerative diseases and inform the development of effective strategies to mitigate their impact on brain health. The results provide strong evidence supporting the larger clinical application of EF.

Lactate enhances NMNAT1 lactylation to sustain nuclear NAD+ salvage pathway and promote survival of pancreatic adenocarcinoma cells under glucose-deprived conditions.

The aim of this study was to investigate the underlying molecular mechanism behind the promotion of cell survival under conditions of glucose deprivation by l-lactate. To accomplish this, we performed tissue microarray and immunohistochemistry staining to analyze the correlation between the abundance of pan-Lysine lactylation and prognosis. In vivo evaluations of tumor growth were conducted using the KPC and nude mice xenograft tumor model. For mechanistic studies, multi-omics analysis, RNA interference, and site-directed mutagenesis techniques were utilized. Our findings robustly confirmed that l-lactate promotes cell survival under glucose deprivation conditions, primarily by relying on GLS1-mediated glutaminolysis to support mitochondrial respiration. Mechanistically, we discovered that l-lactate enhances the NMNAT1-mediated NAD+ salvage pathway while concurrently inactivating p-38 MAPK signaling and suppressing DDIT3 transcription. Notably, Pan-Kla abundance was significantly upregulated in patients with Pancreatic adenocarcinoma (PAAD) and associated with poor prognosis. We identified the 128th Lysine residue of NMNAT1 as a critical site for lactylation and revealed EP300 as a key lactyltransferase responsible for catalyzing lactylation. Importantly, we elucidated that lactylation of NMNAT1 enhances its nuclear localization and maintains enzymatic activity, thereby supporting the nuclear NAD+ salvage pathway and facilitating cancer growth. Finally, we demonstrated that the NMNAT1-dependent NAD+ salvage pathway promotes cell survival under glucose deprivation conditions and is reliant on the activity of Sirt1. Collectively, our study has unraveled a novel molecular mechanism by which l-lactate promotes cell survival under glucose deprivation conditions, presenting a promising strategy for targeting lactate and NAD+ metabolism in the treatment of PAAD.

Dark-field microscopic image stitching method for surface defects evaluation of large fine optics.

One of the challenges in surface defects evaluation of large fine optics is to detect defects of microns on surfaces of tens or hundreds of millimeters. Sub-aperture scanning and stitching is considered to be a practical and efficient method. But since there are usually few defects on the large aperture fine optics, resulting in no defects or only one run-through line feature in many sub-aperture images, traditional stitching methods encounter with mismatch problem. In this paper, a feature-based multi-cycle image stitching algorithm is proposed to solve the problem. The overlapping areas of sub-apertures are categorized based on the features they contain. Different types of overlapping areas are then stitched in different cycles with different methods. The stitching trace is changed to follow the one that determined by the features. The whole stitching procedure is a region-growing like process. Sub-aperture blocks grow bigger after each cycle and finally the full aperture image is obtained. Comparison experiment shows that the proposed method is very suitable to stitch sub-apertures that very few feature information exists in the overlapping areas and can stitch the dark-field microscopic sub-aperture images very well.

Fast AUC Maximization Learning Machine With Simultaneous Outlier Detection.

While AUC maximizing support vector machine (AUCSVM) has been developed to solve imbalanced classification tasks, its huge computational burden will make AUCSVM become impracticable and even computationally forbidden for medium or large-scale imbalanced data. In addition, minority class sometimes means extremely important information for users or is corrupted by noises and/or outliers in practical application scenarios such as medical diagnosis, which actually inspires us to generalize the AUC concept to reflect such importance or upper bound of noises or outliers. In order to address these issues, by means of both the generalized AUC metric and the core vector machine (CVM) technique, a fast AUC maximizing learning machine, called ρ -AUCCVM, with simultaneous outlier detection is proposed in this study. ρ -AUCCVM has its notorious merits: 1) it indeed shares the CVM's advantage, that is, asymptotically linear time complexity with respect to the total number of sample pairs, together with space complexity independent on the total number of sample pairs and 2) it can automatically determine the importance of the minority class (assuming no noise) or the upper bound of noises or outliers. Extensive experimental results about benchmarking imbalanced datasets verify the above advantages of ρ -AUCCVM.

Residual Sketch Learning for a Feature-Importance-Based and Linguistically Interpretable Ensemble Classifier.

Motivated by both the commonly used "from wholly coarse to locally fine" cognitive behavior and the recent finding that simple yet interpretable linear regression model should be a basic component of a classifier, a novel hybrid ensemble classifier called hybrid Takagi-Sugeno-Kang fuzzy classifier (H-TSK-FC) and its residual sketch learning (RSL) method are proposed. H-TSK-FC essentially shares the virtues of both deep and wide interpretable fuzzy classifiers and simultaneously has both feature-importance-based and linguistic-based interpretabilities. RSL method is featured as follows: 1) a global linear regression subclassifier on all original features of all training samples is generated quickly by the sparse representation-based linear regression subclassifier training procedure to identify/understand the importance of each feature and partition the output residuals of the incorrectly classified training samples into several residual sketches; 2) by using both the enhanced soft subspace clustering method (ESSC) for the linguistically interpretable antecedents of fuzzy rules and the least learning machine (LLM) for the consequents of fuzzy rules on residual sketches, several interpretable Takagi-Sugeno-Kang (TSK) fuzzy subclassifiers are stacked in parallel through residual sketches and accordingly generated to achieve local refinements; and 3) the final predictions are made to further enhance H-TSK-FC's generalization capability and decide which interpretable prediction route should be used by taking the minimal-distance-based priority for all the constructed subclassifiers. In contrast to existing deep or wide interpretable TSK fuzzy classifiers, benefiting from the use of feature-importance-based interpretability, H-TSK-FC has been experimentally witnessed to have faster running speed and better linguistic interpretability (i.e., fewer rules and/or TSK fuzzy subclassifiers and smaller model complexities) yet keep at least comparable generalization capability.

Global Plus Local Jointly Regularized Support Vector Data Description for Novelty Detection.

In many practice application, the cost for acquiring abnormal data is quite expensive, thus the one-class classification (OCC) problem attracts great attention. As one of the solutions, support vector data description (SVDD) gains a continuous focus in outlier detection since it is based on the data description. For the sphere obtained by SVDD, both the center and the volume (or radius) strongly depend on the support vectors, while the support vectors are sensitive to the tradeoff parameter C . Hence, how to select this parameter is a rather challenging problem. In order to address this problem, we define several distance metrics relative to the image region in Gaussian kernel space. With the distance metrics, two probability densities relative to the global region and the local region are designed, respectively. Then, the information quantity and the information entropy are developed for regularizing the tradeoff parameter. This novel SVDD is called global plus local jointly regularized support vector data description (GL-SVDD), in which both the global region information and the local image region information jointly penalize the images as possible outliers. Finally, we use the UCI dataset and the hyperspectral data of cherry fruit to evaluate the performance of several OCC approaches. Experimental results show that GL-SVDD is encouraging.

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.