Search

Purpose of Review Pain presents a unique challenge due to the complexity of the biological pathways involved in the pain perception, the growing concern regarding the use of opioid analgesics, and the limited availability of optimal treatment options. The use of biomaterials and regenerative medicine in pain management is being actively explored and showing exciting progress in improving the efficacy of conventional pharmacotherapy and as novel non-pharmacological therapy for chronic pain caused by degenerative diseases. In this paper we review current clinical applications, and promising research in the use of biomaterials and regenerative medicine in pain management. Recent Findings Regenerative therapies have been developed to repair damaged tissues in back, joint, and shoulder that lead to chronic and inflammatory pain. Novel regenerative biomaterials have been designed to incorporate biochemical and physical pro-regenerative cues that augment the efficacy of regenerative therapies. New biomaterials improve target localization with improved tunability for controlled drug delivery, and injectable scaffolds enhance the efficacy of regenerative therapies through improving cellular migration. Advanced biomaterial carrier systems have been developed for sustained and targeted delivery of analgesic agents to specific tissues and organs, showing improved treatment efficacy, extended duration of action, and reduced dosage. Targeting endosomal receptors by nanoparticles has shown promising anti-nociception effects. Biomaterial scavengers are designed to remove proinflammatory reactive oxygen species that trigger nociceptors and cause pain hypersensitivity, providing a proactive approach for pain management. Summary Pharmacotherapy remains the method of choice for pain management; however, conventional analgesic agents are associated with adverse effects. The relatively short duration of action when applied as free drug limited their efficacy in postoperative and chronic pain treatment. The application of biomaterials in pain management is a promising strategy to improve the efficacy of current pharmacotherapy through sustained and targeted delivery of analgesic agents. Regenerative medicine strategies target the damaged tissue and provide non-pharmacological alternatives to manage chronic and inflammatory pain. In the future, the successful development of regenerative therapies that completely repair damaged tissues will provide a more optimal alternative for the treatment of chronic pain caused. Future studies will leverage on the increasing understanding of the molecular mechanisms governing pain perception and transmission, injury response and tissue regeneration, and the development of new biomaterials and tissue regenerative methods.

P2Y12 inhibitors, including aspirin, are key components of dual-antiplatelet therapy (DAPT), which is the optimal therapeutic strategy for preventing arterial thrombosis in patients with acute coronary syndromes (ACS) who underwent stent implantation. Ticagrelor is a cyclopentyl-triazole pyrimidine antiplatelet drug that was the first reversible oral P2Y12 receptor antagonist. Compared with clopidogrel, ticagrelor exerts a faster onset and offset of function by reversible and selective inhibition of platelet aggregation in ACS patients, including those with coronary artery blood revascularization. Despite improvement in stent materials, stent thrombosis (ST) due to high on-treatment platelet reactivity (HPR) to clopidogrel continues to occur. In addition to antiplatelet aggregation, ticagrelor displays pleiotropic cardioprotective effects, including improving coronary blood flow, reducing myocardial necrosis after an ischemic event, and anti-inflammatory effects. The benefits of ticagrelor over clopidogrel were consistent in the PLATO results, with lower incidence of the primary endpoint. Also, in 2020, the findings from the phase 3 THALES trial (NCT03354429) showed that aspirin combined with 90 mg of ticagrelor significantly reduced the rates of stroke and death compared with aspirin alone in patients with AIS or TIA. Here, we review recent research on the superiority of ticagrelor over clopidogrel, discuss the pharmacological mechanism, and present future perspectives. This review aims to present the roles of ticagrelor in the management of acute coronary syndrome, acute thrombotic disease, and other diseases.

Remote sensing object detection is a difficult task because it often requires real-time feedback through numerous objects in complex environments. In object detection, Feature Pyramids Networks (FPN) have been widely used for better representations based on a multi-scale problem. However, the multiple level features cause detectors’ structures to be complex and makes redundant calculations that slow down the detector. This paper uses a single-layer feature to make the detection lightweight and accurate without relying on Feature Pyramid Structures. We proposed a method called the Cross Stage Partial Strengthen Matching Detector (StrMCsDet). The StrMCsDet generates a single-level feature map architecture in the backbone with a cross stage partial network. To provide an alternative way of replacing the traditional feature pyramid, a multi-scale encoder was designed to compensate the receptive field limitation. Additionally, a stronger matching strategy was proposed to make sure that various scale anchors may be equally matched. The StrMCsDet is different from the conventional full pyramid structure and fully exploits the feature map which deals with a multi-scale encoder. Methods achieved both comparable precision and speed for practical applications. Experiments conducted on the DIOR dataset and the NWPU-VHR-10 dataset achieved 65.6 and 73.5 mAP on 1080 Ti, respectively, which can match the performance of state-of-the-art works. Moreover, StrMCsDet requires less computation and achieved 38.5 FPS on the DIOR dataset.

Objective To investigate the preventive effect of hydration combined with reduced glutathione on contrast-induced nephropathy (CIN) after coronary intervention therapy in elderly Chinese patients with diabetes. Methods Patients with diabetes aged ≥65 years, who received percutaneous coronary intervention (PCI) between 1 August 2016 and 31 December 2018, were enrolled and randomized into two groups: patients treated with hydration combined with reduced glutathione (treatment group) and patients who received hydration alone (controls). Serum creatinine and creatinine clearance levels were measured in all patients before PCI and then daily for 3 days after PCI. Occurrence of CIN (the primary endpoint) was defined as serum creatinine value 25% or 44.2 mmol/l (0.5 mg/dl) above baseline at 72 h after an exposure to contrast medium. Results A total of 396 patients were included (treatment group, n = 204; and controls, n = 192). The CIN occurrence rate in the treatment and control group was 5.88% and 6.77%, respectively, with no statistically significant between-group difference. Conclusion In elderly patients with diabetes receiving PCI, the risk of CIN was not effectively lowered by hydration combined with reduced glutathione.

Data that correspond to real-world scenarios can often be organized in several different ways in a database or program. Appreciating the differences between them and choosing an organization that addresses a system's needs are valuable and necessary computing skills. Unfortunately, little of the computing-education literature seems to deal with this topic. In this paper we consider a technique for getting students to engage with this issue, grounded in theories of examples and differences. Instead of presenting a single organization, we present a pair of organizations and ask students to contrast them. Students then interact directly with the two organizations in a reflection step, which is followed by a further round of contrasting. Our data show that even novice college students can handle this task fairly well. They are able to find many crucial differences (especially in terms of access and update operations), but also miss some (especially performance and privacy). These data suggest that this is a useful technique to pursue further, and also point to areas where students may need more instructional support.

The aim of this paper is to model long-term evolution of an action video with temporal multi-scale representation. This task is tough due to huge intra-class variations in motion speed. Most of the existing methods consider evolution modeling and multi-scale feature fusion in two separated phases, which generates sub-optimal representation. To address this issue, this paper proposes a novel method to integrate the evolution modeling and multi-scale representation into a unified framework. The core idea is to introduce a temporal multi-scale smoothing vector, which is used to define how the representations at different temporal scales are combined together for frame smoothing. By formulating the smoothing vector learning, evolution modeling and classifier training jointly, our method can learn a discriminative and flexible representation of multi-scale rather than a single scale or a fixed multi-scale smoothing. Experimental results on three datasets demonstrate the effectiveness of our method.

Optimal reduct is one of the challenging problems in rough set theory, and most of the existing algorithms cannot achieve the optimal reduct on high dimensional data sets. To explore an efficient algorithm for the optimal reduct problem, this paper proposes its generalization problem, which is defined as the K -size partial reduct problem. For this type of problem, an inefficient enumeration algorithm is first proposed. Then we enhance the enumeration algorithm through three improvements with the local search algorithm, i.e., fast initial solution construction, generation rules of solution, and dynamic object weighting strategy. The fast initial solution construction dramatically reduces the number of iterations, the generation rules of solution define a reasonable neighborhood structure and an effective candidate solution transfer model, and the dynamic object weighting strategy adjusts the iterative process to guide the algorithm to jump out of the local optimal solution. On the basis of these three improvements, an efficient local search-based K -size partial reduct algorithm is raised. Finally, a K -size partial reduct-based attribute reduction algorithm is designed by using the relationship between optimal reduct and K -size partial reduct. To validate the effectiveness of our proposed algorithms, we implemented a broad range of experimental simulations. The results of the experiments show the superiorities and innovations of the proposed algorithms compared with state-of-the-art algorithms.

Essential thrombocythemia (ET) can cause arterial embolism. Patients with arterial thrombosis usually have additional risk factors, such as smoking and hypertension. We report a 70-year-old woman with ET who had no risk factors, except for age. Cranial magnetic resonance imaging showed fresh lacunar infarction in several lobes. Electrocardiography showed ST-segment elevation in leads II, III, and aVF. Coronary angioplasty and stenting were successfully performed. We checked the bone marrow and performed genetic testing. The Janus kinase 2 (JAK2) V617F gene mutation was found. This case was a rare initial presentation of previously undiagnosed ET with embolism of cardiovascular and cerebral vessels. Anti-platelet drugs and hydroxyurea were used to prevent further thrombosis in the coronary and cerebral arteries.

We present a 26-year-old woman with ST-segment elevation myocardial infarction in the 14th week of pregnancy. Coronary angiography revealed no abnormalities in the coronary arteries. She had no history of coronary risk factors such as smoking, diabetes mellitus, hypertension, or dyslipidemia. Although we do not have direct evidence of coronary spasm in this patient, several factors suggest that coronary spasm is the most likely cause of myocardial infarction. We suspect that hyperthyroidism may have played an important role in coronary spasm in this patient. Early use of coronary angiography is helpful to identify the types of coronary artery lesions.

Aims The purpose of this study was to reveal the therapeutic efficacy and underlying mechanism of cannabinoid type 2 receptor agonist (AM1241) on myocardial ischemia-reperfusion injury (MIRI) in rats. Main methods We established a rat myocardial ischemia/reperfusion (I/R) model and H9c2 hypoxia/reoxygenation (H/R) model. ELISA was used to determine the concentrations of cardiac troponin I (cTnI), creatine kinase-MB (CK-MB), aspartate aminotransferase (AST) and lactate dehydrogenase (LDH) in plasma. EB/TTC staining was performed to observe the myocardial infarct size. Besides, the pathological changes of myocardial tissue were identified via H&E staining and Masson's trichrome staining. TUNEL assay was performed to examine myocardial apoptosis. Then, the protein expression of Pink1, Parkin and autophagy-related markers (Beclin-1, P62 and LC3) were detected by Western blot, and autophagy was evaluated by Mitotracker staining. Key findings The results of EB/TTC staining, H&E staining, Masson's trichrome staining and cardiac enzymes measuring showed that AM1241 treatment significantly diminished infarct size, the structural abnormalities and the activities of cardiac enzymes (cTnI, CK-MB, AST and LDH). AM1241 also significantly reduced the number of TUNEL-positive cells induced by I/R in a dose-dependent manner. Furthermore, AM1241 activated Pink1/Parkin signaling pathway and upregulated autophagy level. Significance AM1241 exerts a protective effect against MIRI in rats by inducing autophagy through the activation of Pink1/Parkin pathway.

When facing high dimensional data, dimension reduction is necessary before classification. Among dimension reduction methods, linear discriminant analysis (LDA) is a popular one that has been widely used. LDA aims to maximize the ratio of the between-class scatter and total data scatter in projected space, and the label of each data is necessary. However, in real applications, the labeled data are scarce and unlabeled data are in large quantity, so LDA is hard to be used under such case. In this paper, we propose a novel method named semi-supervised linear discriminant analysis (SLDA), which can use limited number of labeled data and a quantity of the unlabeled ones for training so that LDA can accommodate to the situation of a few labeled data available. Assuming that F represents the calculated class indicator matrix of the training data and Y denotes the true label of the labeled data, the objective function contains two parts: one is the criterion of LDA (which is a function of projection W, and a class indicator matrix F), the other is the difference between the true data label and calculated label of these labeled data. As far as we know, there is no closed-form solution to the objective function. To solve such problem, we develop an iterative algorithm which calculates the class indicator matrix and the projection alternatively. The convergence of the proposed iterative algorithm is proved and confirmed by experiments. The experimental results on eight datasets show that the performance of SLDA is superior to that of traditional LDA and some state-of-the-art semi-supervised algorithms. HighlightsA semi-supervised variant of LDA named semi-supervised LDA is proposed.Our method can use limited number of labeled data and a quantity of the unlabeled ones for training.We develop an iterative algorithm which calculates the class indicator matrix and the projection alternatively.

The therapeutic benefits of bone marrow mononuclear cells (BM-MNCs) in many diseases have been well established. To advance BM-MNC-based cell therapy into the clinic for peripheral nerve repair, in this study we developed a new design of tissue-engineered nerve grafts (TENGs), which consist of a chitosan/fibroin-based nerve scaffold and BM-MNCs serving as support cells. These TENGs were used for interpositional nerve grafting to bridge a 10-mm-long sciatic nerve defect in rats. Histological and functional assessments after nerve grafting showed that regenerative outcomes achieved by our developed TENGs were better than those achieved by chitosan/silk fibroin scaffolds and were close to those achieved by autologous nerve grafts. In addition, we used green fluorescent protein-labeled BM-MNCs to track the cell location within the chitosan/fibroin-based nerve scaffold and trace the cell fate at an early stage of sciatic nerve regeneration. The result suggested that BM-MNCs could survive at least 2 weeks after nerve grafting, thus helping to gain a preliminary mechanistic insight into the favorable effects of BM-MNCs on axonal regrowth.

The tetracycline regulatory system has been widely used to control the transgene expression. With this powerful tool, it might be possible to effectively control the functional activity of chimeric antigen receptor (CAR) T cells and manage the severe side effects after infusion. In this study, we developed novel inducible CD19CAR (iCAR19) T cells by incorporating a one-vector Tet-on system into the CD19CAR construct. The iCAR19 T cells showed dox-dependent cell proliferation, cytokine production, CAR expression, and strong CD19-specific cytotoxicity. After 48 h of dox induction, the relative CAR expression of induced cells was five times greater than that of uninduced cells. Twenty-four hours after dox removal, CAR expression significantly decreased by more than 60%. In cytotoxicity assays, dox-treated cells induced significantly higher specific lysis against target cells. These results suggested that the activity of iCAR19 T cells was successfully controlled by our Tet-on system, offering an enhanced safety profile while maintaining a robust anti-tumor effect. Besides, all manufacture processes of the lentiviral vectors and the T cells were conducted according to the Good Manufacturing Practice (GMP) standards for subsequent clinical translation.

The purpose of this study was to determine whether retinol palmitate could protect against myocardial ischemia/reperfusion (I/R) injury and explore the underlying mechanism. Retinol palmitate reduced the level of reactive oxygen species and prevented cellular apoptosis. In vivo, retinol palmitate increased superoxide dismutase (SOD) activity and reduced the level of malondialdehyde in I/R mice. Retinol palmitate also decreased myocardial infarct size and reduced cellular apoptosis by suppressing the expression of proapoptotic-related proteins and increasing that of SOD-related proteins. Our results suggest that retinol palmitate pretreatment has a protective effect against myocardial I/R injury by maintaining the balance between intracellular oxidants and antioxidants.

Osthole, the main active constituents in traditional Chinese medicine fructus cnidii, has anti-inflammatory and anti-oxidant activities. Apoptosis of vascular endothelial cells is an important cause of cardiovascular disease. Inflammation and oxidative stress are two key factors in injury of endotheliocyte. In this study, we investigated the effect of osthole on Ang II-induced apoptosis of rat aortic endothelial cells (RAECs) and explored the underlying mechanisms. In the present study, the protective effects of osthole on RAECs induced by Ang II in vitro were tested. Additionally, molecular docking and molecular dynamics (MD) simulations were utilized to investigate the potential binding mode of osthole to NF-κB and Keap1. Our results showed osthole remarkably attenuates Ang II-induced apoptosis of RAECs via alleviating inflammation and oxidative stress. Molecular docking and MD simulations revealed the potential interaction of osthole bind to the P65 subunit of NF-κB and the Keap1 protein, an adaptor for the degradation of Nrf2. We further found that osthole decreased Ang II-induced inflammation and oxidative stress through respectively modulating NF-κB and Nrf2 pathways in RAECs. These studies provide evidence that osthole may represent a potential therapeutic agent for the treatment of vascular injury.

Our method considers the correlation of two views, and exploits the local geometric structure of data.The correlation of two views is measured by the angle between their principle components.We introduce manifold regularization to maintain the local geometric. Canonical correlation analysis (CCA) is a popular method that has been widely used in information fusion. However, CCA requires that the data from two views must be paired, which is hard to satisfy in the real applications, moreover, it only considers the correlated information of the paired data. Thus, it cannot be used when there are only a little paired data or no paired data. In this paper, we propose a novel method named Canonical Principal Angles Correlation Analysis (CPACA) which does not need paired data during training stage. It makes classic CCA escape from the limitation of paired information. Its objective function can be constructed as follows: First, the correlation of two views is represented by the similarity between two subspace spanned by the principal components, which makes CPACA favorably compare with CCA in the case of limited paired data; Second, in order to increase the discriminative information of CPACA, we utilize manifold regularization to exploit the geometry of the marginal distribution. To optimize the objective function, we propose a new method to calculate the projected vectors. The experimental results show that the performance of CPACA is superior to that of traditional CCA and its variants.

Canonical correlation analysis (CCA) has been widely applied to information fusion. However, it only considers the correlated information between the paired data and ignores the correlated information between the samples in the same class. Furthermore, class information is helpful for CCA to extract the discriminant feature, but there is no class information available in application of clustering. Thus, it is difficult to utilize the correlated information between the samples in the same class. In order to utilize this correlated information, we propose a method named Unsupervised Discriminant Canonical Correlation Analysis based on Spectral Clustering (UDCCASC). Class membership of the samples is calculated using the normalized spectral clustering, while the mappings for feature fusion are computed by using the generalized eigenvalue method. These two algorithms are executed alternately before the desired result is obtained. Two extensions of UDCCASC are proposed also to deal with multi-view data and nonlinear data. The experimental results on MFD dataset, ORL dataset, MSRC-v1 dataset show that our methods outperform traditional CCA and part of state-of-art methods for feature fusion.

Slow Feature Discriminant Analysis (SFDA) is a supervised feature extraction method for classification inspired by biological mechanism. However, SFDA only considers the local geometrical structure information of data and ignores the global geometrical structure information. Furthermore, previous works have demonstrated that uncorrelated features of minimum redundancy are effective for classification. In this paper, a novel method called uncorrelated slow feature discriminant analysis using globality preserving projections (USFDA-GP) is proposed for feature extraction and recognition. In USFDA-GP, two kinds of global information are imposed to the objective function of conventional SFDA for respecting some more global geometric structures. We also provide an analytical solution by simple eigenvalue decomposition to the optimal model instead of previous iterative method. Experimental results on Extended YaleB, CMU PIE and LFW-a face databases demonstrate the effectiveness of our proposed method.

Accurate rapidly developing convection (RDC) detection is an essential part of a severe weather warning. A novel algorithm called object track and identification (OTI) is proposed for detecting RDC using infrared image sequences from geostationary meteorology satellite. Convective cells are computed using extended maxima transform-based region growing algorithm. Firstly, a novel area overlap-based object tracking method is proposed to track convective cells in successive images. Secondly, the lowest 25% of overall brightness temperature of the same convective cloud is averaged in order to preserve the extremum information of evolution of cloud. Thirdly, a new identification criterion, which contains three subcriteria, is developed to detect RDC. Contingency table approach applied to various case studies over China shows that the OTI algorithm is efficient and accurate.

Slow feature discriminant analysis (SFDA) is an attractive biologically inspired learning method to extract discriminant features for classification. However, SFDA heavily relies on the constructed time series. For discriminant analysis, SFDA cannot make full use of discriminant power for classification, because the type of data distribution is unknown. To address those problems, we propose a new feature extraction method called adaptive slow feature discriminant analysis (ASFDA) in this paper. First, we design a new adaptive criterion to generate within-class time series. The time series have two properties: (1) a pair of time series lies on the same sub-manifold, (2) the sub-manifold of a pair of time series is smooth. Second, ASFDA seeks projections to minimize within-class temporal variation and maximize between-class temporal variation simultaneously based on maximum margin criterion. ASFDA provides an adaptive parameter to balance between-class temporal variation and within-class temporal variation to obtain an optimal discriminant subspace. Experimental results on three benchmark face databases demonstrate that our proposed ASFDA is superior to some state-of-the-art methods.

Knee osteoarthritis (KOA) is the most common progressive joint disorder associated with disability in the world. As a chronic disease, KOA has multifactorial etiology. However, the poor self-healing ability of the articular cartilage due to its intrinsic tissue hypovascularity and hypocellularity seems to be directly incriminated in the physio-pathological mechanism of KOA. While conventional therapies result in unfavorable clinical outcomes, regenerative cell therapies have shown great promise in articular cartilage regeneration. Adipose-derived stem cells (ASCs) appear to be an ideal alternative to bone-marrow derived stem cells (BMSCs) and autologous chondrocytes, due to their lower immunogenicity, richer source and easier acquisition. Since the first case report in 2011, ASCs have demonstrated safety and efficacy for articular cartilage regeneration in several phase I/II clinical trials. However, different levels of abnormality were found in the regenerated cartilage for most of the patients. A large portion of recent publications investigated different optimization strategies to improve the therapeutic function of ASCs, including cell source selection, preconditioning and co-delivery. Herein, we give an update on the latest research progress on ASCs, with a focus on the most promising optimization strategies for ASC-based therapy.

Convective cell detection is a critical step for tracking and forecasting of Mesoscale Convective Systems from geostationary satellite infrared (IR) data. Conventional threshold methods for identifying convective cell depend on the choice of threshold. Adjacent convective cells cannot be well distinguished because of the influence of anvil cloud. To address this problem, a new algorithm called extended maxima transform–based region growing (EMTRG) is proposed. First, EMTRG algorithm uses extended maxima transform to generate seed points of convective cell, and applies neighbourhood criterion to cluster adjacent seed points. Second, the merger and split times of pair-wise seed clusters are counted, and a merger criterion is utilized to decide whether pair-wise seed clusters should be merged. The algorithm is applied to various case studies over China. Experimental results on geostationary satellite IR images show that the proposed algorithm distinguishes adjacent convective cells region efficiently.

96 Background: Stereotactic brachytherapy for extensive local tumors offers a very effective treatment option locally without significant complications in medically impaired patients. In this context, we have recently developed a new potential anticancer agent from Poly-L-Lysins dendrimer as a delivery nano system loaded with diffusible Imidazolic probes complexed with 188-Rhenium for targeting in particular hypoxic tumors resistant to conventional cancer treatments. The aim of the study is assessment the safety profile and therapeutic efficacy of anticancer agent derived from [188Re]rhenium-ligand as radioactive ligand loaded 5th generation poly-L-lysine dendrimer in patients with unresectable Lung Malignancies. Methods: The experiment agent “ 188Re-ImDendrim” is consisting of 5th generation poly-L-lysine dendrimer (20 nM) mixed with nitro-imidazole-methyl-1,2,3-triazol-methyl-di-(2-pycolyl) amine at GMP grade and labelled with [188Re]-rhenium. The study was approved by Shanghai East Hospital ethics committee. 5 patients received “188Re-ImDendrim” directly into lung tumors under CT-guidance, at an activity level of 162 MBq/cc of tumor (range 2 to 7 cm; mean diameter, 4 cm) . For voluminous tumors ( > 65 cc) the dose is given in divided injection spaced 2 weeks apart (Tumor of 115cc: 2 administrations, Tumor of 180 cc: 3 administrations). At H0.5, H 4, H24, H36 , H72 post-administration, the patient get a SPECT control. The response to treatment is evaluated thanks to PET/CT Standardized Uptake Values (SUVs). Results: Stereotactic administrations of “188-Rhenium-ImDendrim” were successfully carried out in all patients under local anesthesia. The radioactive product diffuses homogeneously in the tumor volume and remains 72 hours post-administration with no significant diffusion out site of injection. The One of the 5 patients reported discrete transitive hemoptysis as adverse events. All targeted tumors were responding at 12 weeks, with two complete responses. Conclusions: Percutaneous single and iterative administrations of this novel 188-Rhenium-Imdendrim brachytherapy device into lung cancers are safe and well tolerated. The initial data on therapeutic response are promising. Clinical trial information: EC.D (BG) 016.03.1.

Slow feature analysis (SFA) is motivated by biological model to extracts slowly varying feature from a quickly varying input signal. However, traditional slow feature analysis is an unsupervised method to extract slow or invariant feature and cannot be directly applied on the data set without an obvious temporal structure, i.e. face databases. In this paper, we propose a supervised slow feature analysis to do dimensionality reduction for face recognition. First, a new criterion is developed to construct a Pseudo-time series for data sets without an obvious temporal structure. Then, the first-order derivative at each point in the Pseudo-time series is computed in form of vectors. At last we construct the objective function of SSFA that ensures the secondary moment of first-order derivative as small as possible in the embedding space. SSFA is able to extract the invariant feature for each class and preserve the local structure in embedding space simultaneously. Experimental results on the Yale, ORL, AR, and FERET face databases show the effectiveness of the proposed algorithm.

Canonical correlation analysis (CCA) has been widely applied to information fusion. It only considers the correlated information of the paired data, but ignores the correlated information between the samples in the same class. Furthermore, class information is useful for CCA, but there is little class information in the scenarios of real applications. Thus, it is difficult to utilize the correlated information between the samples in the same class. To utilize the correlated information between the samples, we propose a method named Unsupervised Discriminant Canonical Correlation Analysis (UDCCA). In UDCCA, the class membership and mapping are iteratively computed by using the normalized spectral clustering and generalized Eigen value methods alternatively. The experimental results on the MFD dataset and ORL dataset show that UDCCA outperforms traditional CCA and its variants in most situations.

Slow feature analysis (SFA) is a new method based on the slowness principle and extracts slowly varying signals out of the input data. However, traditional SFA cannot be directly performed on those dataset without an obvious temporal structure. In this paper, a novel supervised slow feature analysis (SSFA) is proposed, which constructs pseudo-time series by taking advantage of the consensus information. Extensive experiments on AR and PIE face databases demonstrate superiority of our proposed method.

Slow feature analysis (SFA) extracts slowly varying features out of the input data and has been successfully applied on pattern recognition. However, SFA heavily relies on the constructed time series when SFA is applied on databases that neither have obvious temporal structure nor have label information. Traditional SFA constructs time series based on k-nearest neighborhood (k-NN) criterion. Specifically, the time series set constructed by k-NN criterion is likely to include noisy time series or lose suitable time series because the parameter k is difficult to determine. To overcome these problems, a method called adaptive unsupervised slow feature analysis (AUSFA) is proposed. First, AUSFA designs an adaptive criterion to generate time series for characterizing submanifold. The constructed time series have two properties: (1) two points of time series lie on the same submanifold and (2) the submanifold of the time series is smooth. Second, AUSFA seeks projections that simultaneously minimize the slowness scatter and maximize the fastness scatter to extract slow discriminant features. Extensive experimental results on three benchmark face databases demonstrate the effectiveness of our proposed method.