Search

The milk fat globule membrane (MFGM) is a complex structure with numerous functions, and its composition is affected by many factors. There have been few systematic investigations on goat MFGM proteome profiling during lactation. Individual milk samples from 15 healthy dairy goats were obtained at six lactation time points for investigation of the MFGM proteome using both data-independent acquisition (DIA) and data-dependent acquisition (DDA) proteomics techniques combined with multivariate statistical analysis. Using the DIA method, 890 variably abundant MFGM proteins were discovered throughout the lactation cycle. From 1 to 240 d, butyrophilin subfamily 1 member A1, lipoprotein lipase, perilipin-2, and adipose triglyceride lipase were upregulated, while APOE, complement C3, clusterin, and IgG were downregulated. Furthermore, from 1 to 90 d, annexin A1, annexin A2, and antithrombin-III were downregulated, then upregulated by d 240. Albumin had a high degree of connectedness, indicating that it was a key protein, according to protein–protein interaction research. Overall, our findings gave new insights into the biological features of MFGM protein in goat milk throughout lactation, which may aid in the creation of specialized MFGM products and infant formula.

Abstract Cluster of differentiation 24 (CD24), a mucin-like highly glycosylated molecule has been extensively studied as a cancer stem cell marker in a variety of solid cancers. The functional role of CD24 is either fulfilled by combining with ligands or participating in signal transduction, which mediate the initiation and progression of neoplasms. Recently, CD24 was also described as an innate immune checkpoint with apparent significance in several types of solid cancers. Herein, we review the current understanding of the molecular fundamentals of CD24, the role of CD24 in tumorigenesis and cancer progression, the possibility as a promising therapeutic target and summarized different therapeutic agents or strategies targeting CD24 in solid cancers. Video Abstract

The hot deformation behavior and microstructure evolution of AlCrFe2Ni2(MoNb)0.2 eutectic high entropy alloy at deformation temperatures of 900 °C–1100 °C and strain rates of 0.001 s−1∼1 s−1 were systematically investigated by hot compression tests. The principal structure equations of AlCrFe2Ni2(MoNb)0.2 high entropy alloy were constructed using the Arrhenius equation modified by Zener-Hollomon parameters. The decrease of strain rate and the increase of deformation temperature can enhance the continuous dynamic recrystallization (CDRX) and discontinuous dynamic recrystallization (DDRX) processes simultaneously. The power dissipation and instability diagrams were constructed according to the power dissipation theory and instability criterion, and the hot processing diagrams with strains of 0.3–0.6 were obtained by combining with the Dynamic Material Model (DMM) theory. According to the analysis of power dissipation rate and processing safety zone, the optimal hot processing parameters were found to be ε = 0.6 for the true strain, T = 1050–1100 °C, ε˙ = 0.0037–0.031 s−1.

There is a high demand for an optimal drug delivery system to treat androgenetic alopecia. Topical application of ISX9, which is a neurogenesis inducer, has been found to stimulate hair follicle (HF) regrowth by upregulating the Wnt/β-catenin signaling pathway, an essential pathway involved in initiating HF growth and development. In the present study, a temperature-sensitive, biopolymer-based, biocompatible, and eco-friendly drug-delivery system was synthesized. This system comprised chitosan-grafted poly(glycidyl methacrylate-co-N-isopropyl acrylamide) (Poly(GMA-co-NIPAAm)@CS-PGNCS) as the shell component and PF127 as the core polymer. The hydrophobic nature of the PF127 block copolymer efficiently dissolved the partially water-soluble drug, ISX9, and the thermos-responsive shell polymer effectively released the drug at a definite skin temperature. The optimized spherical nanoparticles demonstrated the lowest critical solution temperature (LCST) at 32 ± 2 °C with a diameter of 100–250 nm, which delivered encapsulated ISX9 with greater precision than topical ISX9. In a series of in vivo experiments, we demonstrated that ISX9-coated TBNPs upregulated the expression of β-catenin, active β-catenin, Wnt target genes, stemness marker genes, proliferating cell nuclear antigen, HF stem cell markers, and HF markers including VEGF, TGF, and IGF-1 more effectively than topical ISX9. These results suggest that TBNPs could be employed as a platform for effective transdermal delivery of various hydrophobic drugs.

Pneumatic muscle actuators are widely used in the manufacture of bionic robots and rehabilitation medical equipment. However, due to complicated inherent nonlinearities, time-varying characteristics and uncertainties, it is still a challenge to carry out the accurate dynamic modeling and controller design for PAM systems. To address above issues, we propose an error tracking-based neuro-adaptive iterative learning control scheme to get satisfactory non-uniform angle trajectory tracking performance. First, the error-tracking method is used to overcome the nonzero initial state error in iterative learning controller design for the PAM system. Second, a difference-learning neural network is utilized to compensate for unknown uncertainties in the PAM system dynamics. Moreover, a barrier Lyapunov function is applied to design controller so as to restrict the the difference between system out error and the desired error trajectory within the preset bound during each iteration. And the stability of the closed-loop system is proven theoretically by using Lyapunov synthesis. Finally, simulation results demonstrate the effectiveness of the proposed control scheme.

In harsh battlefield environments, tanks have to encounter some nonlinear characteristics including frictional moment, gear backlash and parameter drifts, etc. The existence of such nonlinear characteristics makes the controller design of tank gun control systems (TGCSs) challenging. In this paper, a barrier neuroadaptive control approach is proposed to handle the uncertainties and nonlinearities, so as to achieve satisfactory tracking performance for TGCSs. With a time-varying barrier Lyapunov function employed in controller design, the output error of TGCS is restricted within the preset bound during the control process. A radial basis function (RBF) neural network is built to approximate the uncertainties in tank gun control systems. An anti-windup control strategy is developed to deal with the input saturation nonlinearity, with a Nussbaum function used to compensate for the nonlinear term arising from input saturation. By reasonably applying filtering error into output-constrained adaptive backstepping control design, the three steps in the traditional backstepping control design are reduced to two steps. The asymptotic stability of the closed-loop TGCSs is proven by Lyapunov theory. Finally, a simulation example is presented to verify the effectiveness of the proposed control scheme.

Large-scale new energy access to the power grid will cause a series of problems such as the decrease of system frequency and voltage strength, affecting the safe and stable operation of the power grid. The paper analyzes the impact of new energy access to Hunan power grid, reviews the relevant policies of new energy grid-connected operation and management issued by Hunan, analyzes the problems existing in the current Hunan new energy grid-connected operation and management mode, and puts forward measures and suggestions to optimize the grid-connected operation and management in order to provide reference for promoting the high-quality development of new energy.

The AlCrFe2Ni2(MoNb)x multiphase high entropy alloys were designed, prepared and characterized. The synergistic effect of Mo and Nb alloying on microstructures and mechanical properties of AlCrFe2Ni2-based high entropy alloy were investigated. By synergistic alloying with Mo and Nb, the volume fraction of the BCC phase increased, and a novel Laves phase with hexagonal close-packed(HCP) structure was formed. With the increase of Mo and Nb content, the alloys dramatically transformed from equiaxed grain with multiple phases to dendrites with the spinodal decomposition structure of the A2 phase and B2 phase, as well as inter-dendrites with the eutectic structure of the FCC phase and Laves phase. Furthermore, the solidification behavior of the alloys varied considerably as the increase of Mo and Nb content. The coexisting solidification microstructure of the eutectic structure and spinodal decomposition structure in the AlCrFe2Ni2(MoNb)0.3, AlCrFe2Ni2(MoNb)0.5 and AlCrFe2Ni2(MoNb)0.7 alloys have hardly been observed in other HEAs. The increase of Mo and Nb elements tends to segregate in the front of the liquid–solid interface, which hinders the growth of the FCC phase and leads to the formation of fine rod-like morphology. The synergistic effect of the fine grain strengthening and the solid solution strengthening resulted in high yield strength and fracture strength of 878 MPa and 2830 MPa, maintaining high plastic strain of 43.7%. Further increasing the content of Mo and Nb would lead to the increase of brittle Laves phase, with the second phase strengthening becoming the dominant strengthening mechanism, resulting in an increase in yield strength to 1549 MPa and a decrease in plastic strain to 8.6%. The investigation results would provide a guide for strengthening the macroscopic mechanical properties of eutectic high entropy alloys through synergistic alloying effect.

The grain size plays a pivotal role in determining the properties of the alloy. The grain size can be significantly decreased by adding inoculants. Aiming to address the shortcomings of existing inoculants, the Al3Ti-Al2O3/Al inoculant was successfully prepared using Al-Ti master alloy and Al2O3 whiskers as raw materials. With the aid of ultrasonic energy, the Al2O3 whiskers were uniformly dispersed within the inoculants. Under the combined action of ultrasonic and titanium, the Al2O3 whiskers were broken into small particles at high temperature. To enhance the morphology of Al3Ti and achieve even particle dispersion throughout the matrix, vacuum rapid quenching treatment was applied to the inoculant. The SEM test results indicated a significant reduction in particle size after vacuum rapid quenching. The Al3Ti-Al2O3/Al inoculants exhibited excellent grain refinement effects on the weldable Al-Cu-Mn alloy. Crystallographic calculations and HRTEM analysis revealed that Al2O3 and Al have orientation relationships, indicating their potential as effective heterogeneous nucleation sites. The mechanical properties of the Al-Cu-Mn alloy were obviously improved after the Al3Ti-Al2O3/Al inoculant was added.

Nanocomposite (NC) printing emerged as a major approach to translate nanomaterial properties to 3D geometries but printing of conventional NCs lacks control over nanomaterial connection. Here, the authors develop viscoelastic Pickering emulgels as NC inks through jamming nanomaterials on interfaces and in continuous phase

This work proposes a new morphological random walker (MRW) method for hyperspectral anomaly detection. The proposed method introduces a morphology-based objective function into a random walker (RW) algorithm, sufficiently exploiting spatial morphological property and spatial similarity of HSIs for detection. The MRW method comprises two major stages. Firstly, we employ the extended morphological profiles (EMPs) and different operations to extract the spatial morphological property of HSIs. Second, according to the morphological property, we construct a morphology-based objective function. This function is incorporated into the RW-based optimization model, encoding the spatial similarity of HSIs in a weighted graph. Two factors determine the class of test pixels, including the spatial morphological information learned by EMPs, and the spatial correlation among adjoining pixels modeled by the weighted graph. Since the two factors are well considered in the MRW method, the proposed method illustrates outstanding detection performances for several widely used real HSIs.

This study focuses on the generation of the bubble-free layer during the fabrication of the metal foam using the direct melt foaming method. The theoretical models for the three stages during the foaming process have been established, and the boundary conditions have been discussed. The results from the theoretical study indicated that the bubble number of the liquid foam played a critical role in the generation of the bubble-free layer, thus, improving the bubble number retards the velocity of the bubble-free layer generation. The liquid film rupture led to the expansion of the local cross-sectional area of the Plateau border channel and increased the drainage velocity, thus, resulting in an enhancement in the bubble-free layer. Additionally, the verification experiments were conducted by employing the graphene nanoflakes (GNFs) as the heterogeneous nucleation agent. The findings indicated that the generation of the bubble-free layer was hindered, and the bubble-free layer was altogether absent in case the content of the heterogeneous nucleation agent was enhanced.

This paper proposes an adaptive learning control scheme to solve high-precision velocity tracking problem for tank gun control servo systems. Lyapunov approach is used to design the learning controller, with alignment condition used to cope with initial problem of iterative learning control. Robust control technique and adaptive learning control technique are synthesized to handle nonlinear uncertainties and external disturbances. The unknown parameters are estimated according to the full saturation difference learning strategy. As the iteration number increases, the system state can accurately track the reference signal over the whole time interval, and all signal are guaranteed to be bounded.

Lung cancer is a life-threatening disease and its diagnosis is of great significance. Data scarcity and unavailability of datasets is a major bottleneck in lung cancer research. In this paper, we introduce a dataset of pulmonary lesions for designing the computer-aided diagnosis (CAD) systems. The dataset has fine contour annotations and nine attribute annotations. We define the structure of the dataset in detail, and then discuss the relationship of the attributes and pathology, and the correlation between the nine attributes with the chi-square test. To demonstrate the contribution of our dataset to computer-aided system design, we define four tasks that can be developed using our dataset. Then, we use our dataset to model multi-attribute classification tasks. We discuss the performance in 2D, 2.5D, and 3D input modes of the classification model. To improve performance, we introduce two attention mechanisms and verify the principles of the attention mechanisms through visualization. Experimental results show the relationship between different models and different levels of attributes.

Alzheimer's disease (AD) is an irreversible brain disease that severely damages human thinking and memory. Early diagnosis plays an important part in the prevention and treatment of AD. Neuroimaging-based computer-aided diagnosis (CAD) has shown that deep learning methods using multimodal images are beneficial to guide AD detection. In recent years, many methods based on multimodal feature learning have been proposed to extract and fuse latent representation information from different neuroimaging modalities including magnetic resonance imaging (MRI) and 18-fluorodeoxyglucose positron emission tomography (FDG-PET). However, these methods lack the interpretability required to clearly explain the specific meaning of the extracted information. To make the multimodal fusion process more persuasive, we propose an image fusion method to aid AD diagnosis. Specifically, we fuse the gray matter (GM) tissue area of brain MRI and FDG-PET images by registration and mask coding to obtain a new fused modality called “GM-PET.” The resulting single composite image emphasizes the GM area that is critical for AD diagnosis, while retaining both the contour and metabolic characteristics of the subject's brain tissue. In addition, we use the three-dimensional simple convolutional neural network (3D Simple CNN) and 3D Multi-Scale CNN to evaluate the effectiveness of our image fusion method in binary classification and multi-classification tasks. Experiments on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset indicate that the proposed image fusion method achieves better overall performance than unimodal and feature fusion methods, and that it outperforms state-of-the-art methods for AD diagnosis.

Background: Early hematoma expansion (HE) occurs in patients with intracerebral hemorrhage (ICH) within the first few hours from ICH onset. Hematoma expansion has been considered as an independent predictor of poor clinical outcome and mortality after ICH. Island sign (IS) on the non-contrast computed tomography (NCCT) appears to increase the rate of detection of HE. However, there is insufficient evidence to declare that IS is an independent predictor for ICH patients prognosis and classification.Objectives: To investigate whether IS on NCCT could predict HE and functional outcome following ICH.Methods: Major databases were systematically searched, including PubMed, EMBASE, Cochrane library, and the Chinese database (CNKI, VIP, and Wanfang databases). Studies about the associations between IS and HE or IS and clinical outcome were included. The pooled result used the odds ratio (OR) with a 95% confidence interval (CI) as effect size. Heterogeneity and publication bias were assessed. Subgroup analysis and meta-regression were applied to detect potential factors of heterogeneity.Results: Eleven studies with 4,310 patients were included in the final analysis. The average incidence rate of IS and HE were 21.58 and 33%, respectively. The ideal timing for assessing HE was also not uniform or standardized. We separately performed two meta-analyses. First, 10 studies were included to estimate the association between IS and HE. The pooled OR was statistically significant (OR = 7.61, 95% CI = 3.10–18.67, P < 0.001). Second, four studies were included in the meta-analysis, and the pooled result showed that IS had a significantly positive relationship with poor outcome (OR = 3.83, 95% CI = 2.51–5.85, P < 0.001).Conclusions: This meta-analysis showed that NCCT IS is of great importance and value for evaluation of HE and poor outcome in patients with ICH. Future studies should focus on developing consensus guidelines, and more studies with large sample size and longitudinal design are needed to validate the conclusions.

Eosinophils are important mediators of allergic responses, but how they are recruited to the inflamed site is still unclear. Here the authors show that CD103+ cDC1 cells secrete CCL17 and CCL22 for eosinophil recruitment, with this process promoted by CD24−CD11b+ DC2s in the early phase but suppressed by CD24+ cDC2s in the late phase.

Deep convolutional neural networks (DCNNs) have been driving significant advances in semantic image segmentation due to their powerful feature representation for recognition. However, their performance in preserving object boundaries is still not satisfactory. Visual mechanism theory indicates that image segmentation tasks require not only recognition, like DCNNs, but also local visual attention capability. Considering that superpixel is good at grasping detailed local structure, we propose a probabilistic superpixel-based dense conditional random field model (PSP-CRF) to refine label assignments as a postprocessing optimization method. First, the well-known fully convolutional networks (FCN) and Deeplab-ResNet are employed to produce coarse prediction probabilistic maps at each pixel. Second, we construct a fully connected CRF model based on the PSP generated by the simple linear iterative clustering algorithm. In our approach, an effective refining algorithm with entropy is developed to convert the pixel-level appearance and position features to the normalized PSP, which works well for CRF. Third, our method optimizes the PSP-CRF to obtain the final label assignment results by employing a highly efficient mean field inference algorithm and some quadratic programming relaxation related algorithms. The experiments on the PASCAL VOC segmentation dataset demonstrate the effectiveness of our methods which can improve the segmentation performance of DCNNs to 82% in mIoU while increasing the computational efficiency by 47%.

Due to the development of the computer vision, machine learning, and deep learning technologies, the research community focuses not only on the traditional SLAM problems, such as geometric mapping and localization, but also on semantic SLAM. In this paper, we propose a Semantic SLAM system which builds the semantic maps with object-level entities, and it is integrated into the RGB-D SLAM framework. The system combines object detection module that is realized by the deep-learning method, and localization module with RGB-D SLAM seamlessly. In the proposed system, object detection module is used to perform object detection and recognition, and localization module is utilized to get the exact location of the camera. The two modules are integrated together to obtain the semantic maps of the environment. Furthermore, to improve the computational efficiency of the framework, an improved Octomap based on the Fast Line Rasterization Algorithm is constructed. Meanwhile, for the sake of accuracy and robustness of the semantic map, conditional random field is employed to do the optimization. Finally, we evaluate our Semantic SLAM through three different tasks, i.e., localization, object detection, and mapping. Specifically, the accuracy of localization and the mapping speed is evaluated on TUM data set. Compared with ORB-SLAM2 and original RGB-D SLAM, our system, respectively, got 72.9% and 91.2% improvements in dynamic environments localization evaluated by root-mean-square error. With the improved Octomap, the proposed Semantic SLAM is 66.5% faster than the original RGB-D SLAM. We also demonstrate the efficiency of object detection through quantitative evaluation in an automated inventory management task on a real-world data sets recorded over a realistic office.

Industrial wastewaters threatening the sustainability of society have increasingly become a key social issue across the globe. Consequently, countermeasures have been suggested across a broad range of research fields and policy cycles in both industrialized and industrializing countries. Thus, identifying factors that drive reductions in industrial wastewater discharge is a key task in the water research and policymaking fields. In contrast to previous studies that have focused on reducing industrial wastewater discharge through techniques, policy, management, and other tools, the aim of this study was to investigate the effect of transport infrastructure development, particularly high-speed railways (HSR), on industrial sewage discharge. Given the rapid development of high-speed railways in China and the country’s severe water pollution, China was our research context, and our sample was 298 prefecture-level Chinese cities during the period 1999–2018. The empirical results show that cities with high-speed railways have greater reductions in industrial wastewaters, and that these effects are weakened in cities with a more developed economy and information environment. The results are consistent when using different methods to test their robustness, such as time-varying difference-in-difference (DID), instrumental variables, and placebo tests. These findings offer useful guidance for practitioners and policymakers in the management of water resources and the development of transport infrastructure in cities. These results contribute to the literature in the field of water management and to the assessment of the broader effect of high-speed railways.

In order to systematically study the application of groove pressing in preparing bulk mass ultra-fine grain sheet metal, the fundamental principles, plastic mechanics analysis and classification of groove pressing are introduced, and on the basis of which, the influence rules and mechanism of processing factors such as pass number, deformation temperature and die structure on groove pressing are reviewed, and some key problems such as thermal stability of processed materials, process improvements and deformation path, deformation homogeneity analysis and process optimization are summarized. The research trends of groove pressing in the fields of application to sheet metals difficult to deform at room temperature, improvement of ductility, toughness and formability of processed sheets as well as its plastic deformation mechanism are prospected: in the future, groove pressing will be used for sheet metals which have limited formability but wide industrial applications such as magnesium alloys and titanium alloys, and much attention should be paid to investigation on performance adjustment mechanism and methods for processed sheets and exploration of effective technological measures for preventing cracks; meanwhile, the evolution mechanism of microstructure and properties of groove pressed materials must be systematically and thoroughly revealed.

Dendritic cells (DCs) play an important role in controlling T cell-mediated adaptive immunity in atherogenesis. However, the role of the basic leucine zipper transcription factor, ATF-like 3 (Batf3)-dependent CD8α+ DC subset in atherogenesis remains unclear. Here we show that Batf3−/−Apoe−/− mice, lacking CD8α+ DCs, exhibited a significant reduction in atherogenesis and T help 1 (Th1) cells compared with Apoe−/− controls. Then, we found that CD8α+ DCs preferentially induce Th1 cells via secreting interleukin-12 (IL-12), and that the expression of interferon-gamma (IFN-γ)or chemokine (C-C motif) ligand 5 (CCL5) in aorta were significantly decreased in Batf3−/−Apoe−/− mice. We further demonstrated that macrophages were the major CCL5-expressing cells in the plaque, which was significantly reduced in Batf3−/−Apoe−/− mice. Furthermore, we found CCL5 expression in macrophages was promoted by IFN-γ. Finally, we showed that Batf3−/−Apoe−/− mice displayed decreased infiltration of leukocytes in the plaque. Thus, CD8α+ DCs aggravated atherosclerosis, likely by inducing Th1 cell response, which promoted CCL5 expression in macrophages and increased infiltration of leukocytes and lesion inflammation.

Gesture recognition aims to recognize meaningful movements of human bodies, and is of utmost importance in intelligent human-computer/robot interactions. In this paper, we present a multimodal gesture recognition method based on 3-D convolution and convolutional long-short-term-memory (LSTM) networks. The proposed method first learns short-term spatiotemporal features of gestures through the 3-D convolutional neural network, and then learns long-term spatiotemporal features by convolutional LSTM networks based on the extracted short-term spatiotemporal features. In addition, fine-tuning among multimodal data is evaluated, and we find that it can be considered as an optional skill to prevent overfitting when no pre-trained models exist. The proposed method is verified on the ChaLearn LAP large-scale isolated gesture data set (IsoGD) and the Sheffield Kinect gesture (SKIG) data set. The results show that our proposed method can obtain the state-of-the-art recognition accuracy (51.02% on the validation set of IsoGD and 98.89% on SKIG).

Many clinical applications based on deep learning and pertaining to radiology have been proposed and studied in radiology for classification, risk assessment, segmentation tasks, diagnosis, prognosis, and even prediction of therapy responses. There are many other innovative applications of AI in various technical aspects of medical imaging, particularly applied to the acquisition of images, ranging from removing image artifacts, normalizing/harmonizing images, improving image quality, lowering radiation and contrast dose, and shortening the duration of imaging studies. This article will address this topic and will seek to present an overview of deep learning applied to neuroimaging techniques.

Background and Purpose: Cerebral hemorrhage is a serious potential complication of stroke revascularization, especially in patients receiving intra-arterial tissue-type plasminogen activator (tPA) therapy. We investigated the optimal pre-intervention delay time (DT) of computed tomography perfusion (CTP) measurement to predict cerebral parenchymal hematoma (PH) in acute ischemic stroke (AIS) patients after intra-arterial tissue plasminogen activator (tPA) treatment.Methods: The study population consisted of a series of patients with AIS who received intra-arterial tPA treatment and had CTP and follow-up computed tomography/magnetic resonance imaging (CT/MRI) to identify hemorrhagic transformation. The association of increasing DT thresholds (>2, >4, >6, >8, and >10 s) with PH was examined using receiver operating characteristic (ROC) analysis and logistic regression.Results: Of 94 patients, 23 developed PH on follow-up imaging. Receiver operating characteristic analysis revealed that the greatest area under the curve for predicting PH occurred at DT > 4 s (area under the curve, 0.66). At this threshold of > 4 s, DT lesion volume ≥ 30.85 mL optimally predicted PH with 70% sensitivity and 59% specificity. DT > 4 s volume was independently predictive of PH in a multivariate logistic regression model (P < 0.05).Conclusions: DT > 4 s was the parameter most strongly associated with PH. The volume of moderate, not severe, hypo-perfusion on DT is more strongly associated and may allow better prediction of PH after intra-arterial tPA thrombolysis.

Internet of Things (IoT) is driving innovation in an ever-growing set of application domains such as intelligent processing for autonomous robots. For an autonomous robot, one grand challenge is how to sense its surrounding environment effectively. The Simultaneous Localization and Mapping with RGB-D Kinect camera sensor on robot, called RGB-D SLAM, has been developed for this purpose but some technical challenges must be addressed. Firstly, the efficiency of the algorithm cannot satisfy real-time requirements; secondly, the accuracy of the algorithm is unacceptable. In order to address these challenges, this paper proposes a set of novel improvement methods as follows. Firstly, the ORiented Brief (ORB) method is used in feature detection and descriptor extraction. Secondly, a bidirectional Fast Library for Approximate Nearest Neighbors (FLANN) k-Nearest Neighbor (KNN) algorithm is applied to feature match. Then, the improved RANdom SAmple Consensus (RANSAC) estimation method is adopted in the motion transformation. In the meantime, high precision General Iterative Closest Points (GICP) is utilized to register a point cloud in the motion transformation optimization. To improve the accuracy of SLAM, the reduced dynamic covariance scaling (DCS) algorithm is formulated as a global optimization problem under the G2O framework. The effectiveness of the improved algorithm has been verified by testing on standard data and comparing with the ground truth obtained on Freiburg University’s datasets. The Dr Robot X80 equipped with a Kinect camera is also applied in a building corridor to verify the correctness of the improved RGB-D SLAM algorithm. With the above experiments, it can be seen that the proposed algorithm achieves higher processing speed and better accuracy.

Continuous human action recognition (CHAR) is more practical in human-robot interactions. In this paper, an online CHAR algorithm is proposed based on skeletal data extracted from RGB-D images captured by Kinect sensors. Each human action is modeled by a sequence of key poses and atomic motions in a particular order. In order to extract key poses and atomic motions, feature sequences are divided into pose feature segments and motion feature segments, by use of the online segmentation method based on potential differences of features. Likelihood probabilities that each feature segment can be labeled as the extracted key poses or atomic motions, are computed in the online model matching process. An online classification method with variable-length maximal entropy Markov model (MEMM) is performed based on the likelihood probabilities, for recognizing continuous human actions. The variable-length MEMM method ensures the effectiveness and efficiency of the proposed CHAR method. Compared with the published CHAR methods, the proposed algorithm does not need to detect the start and end points of each human action in advance. The experimental results on public datasets show that the proposed algorithm is effective and highly-efficient for recognizing continuous human actions.