Search

Robotic grasping has become increasingly important in many application areas such as industrial manufacturing and logistics. Because of the diversity and uncertainty of objects and environments, common grippers with one single grasping mode face difficulties to fulfill all the tasks. Hence, we proposed a soft gripper with multiple grasping modes in this study. The gripper consists of four modular soft fingers integrated with layer jamming structure and tendon-driven mechanism. Each finger's rotating shaft of the base uses a torsional spring to decouple the bending deformation and relative rotation. An octopus-mimicking vacuum sucker is installed in the fingertip to generate suction. The effectiveness of the bending deformation and variable stiffness of the design were proved by finite element simulation. Thus, the control model of the finger was built, and the control strategy of multimode grasping of the gripper was proposed. Three control modes were designed to realize the four anthropomorphic grasping modes, including wrap, pinch, hook, and suck. Furthermore, the grasping performance was evaluated to show the abilities. The experiments indicated the superior performance of the proposed gripper and the multimode grasping ability that satisfies various grasping tasks.

Automatic matching of multimodal images remains a critical challenging task in many remote sensing and computer vision applications. Due to significant nonlinear radiation distortions (NRDs) between multimodal images, it is difficult for many traditional feature matching methods which are sensitive to NRD to achieve satisfactory matching performance. To cope with this problem, this letter proposes a novel feature matching method named nonlinear consistent feature transform (NCFT) that is robust to large NRD. There are three main contributions to NCFT. First, we propose a new consistent feature map instead of image intensity for feature point detection and description, the consistent feature map encodes the structure information and provides a rich and robust feature. Second, we propose a mean-residual maximum index map (MR-MIM) for feature description and the MR-MIM is constructed from the Log-Gabor convolution sequence on the consistent feature map. Finally, the structure descriptors are built according to the MR-MIM, and multimodal image matching is achieved by computing the correspondence. The extensive experimental results demonstrate that NCFT can effectively overcome the problem of NRD, NCFT outperforms other state-of-the-art methods and improves the matching accuracy and robustness on different multimodal image datasets.

In this paper, a novel robotic grasping system is established to automatically pick up objects in cluttered scenes. A composite robotic hand composed of a suction cup and a gripper is designed for grasping the object stably. The suction cup is used for lifting the object from the clutter first and the gripper for grasping the object accordingly. We utilize the affordance map to provide pixel-wise lifting point candidates for the suction cup. To obtain a good affordance map, the active exploration mechanism is introduced to the system. An effective metric is designed to calculate the reward for the current affordance map, and a deep Q-Network (DQN) is employed to guide the robotic hand to actively explore the environment until the generated affordance map is suitable for grasping. Experimental results have demonstrated that the proposed robotic grasping system is able to greatly increase the success rate of the robotic grasping in cluttered scenes., Comment: has been accepted by IEEE/RSJ International Conference on Intelligent Robots and Systems 2019

The bending of races of the flexible ball bearing in a harmonic reducer inevitably results in significant hoop stresses, which leads to the bearing working under a complex stress state. Studies show that hoop stresses can affect bearing life considerably, and subsurface stresses are the fundamental nature of the bearing failure mechanism. This paper established a simplified theoretical model of subsurface stresses for flexible ball bearing by considering bending deformation and contact deformation. First, the plane curved bar theory was used to solve the hoop stresses of the races caused by bending deformation. Second, the hoop stresses were superimposed on the Hertzian principal stresses generated by the contact load to calculate the maximum shearing stress of the raceway. Then, the influence of hoop stresses on subsurface stresses of both the inner and outer races was analyzed based on the proposed model. The results indicated that the subsurface stresses of the inner race calculated by the model were in good agreement with that of the cam-inner race-single ball contact finite element model. In addition, hoop stresses of the inner race increase the maximum shearing stress but decrease its depth to the contact surface, making the inner race more prone to spalling failure, while the outer race is the opposite. At last, the influence of the design parameters of flexible ball bearing on the subsurface stresses of races was studied to provide a theoretical basis for the optimization design of flexible ball bearing and its fatigue failure analysis.

Metasurfaces have manifested unprecedented capabilities in manipulating light by subwavelength unit cells, facilitating the miniaturization and multifunctions of optical systems. On the other hand, lithium niobate on insulator (LNOI) technology is revolutionizing the integrated photonics, enabling multifunctional devices and applications. Yet the optical interface for coupling and manipulation is not sufficient and versatile. Here, we developed a geometric metasurface interface for LNOI waveguide and demonstrated several on-chip integrated devices for free space light field manipulations. By decorating waveguides with subwavelength optical antennas, we manipulated the guided waves into desired wavefronts in space, achieved complex free-space functions, such as focusing, multichannel vortex beam generation, and holography. Our architecture goes beyond the conventional gratings and enriches the functionalities of metasurface, which would open up a new perspective for future versatile guided-wave driven optical devices.

Ambipolar photoresponsivity mainly originates from intrinsic or interfacial defects. However, these defects are difficult to control and will prolong the response speed of the photodetector. Here, we demonstrate tunable ambipolar photoresponsivity in a photodetector built from vertical p-WSe2/n-InSe heterostructures with photogating effect, exhibiting ultrahigh photoresponsivity from -1.76 × 104 to 5.48 × 104 A/W. Moreover, the photodetector possesses broadband photodetection (365-965 nm), an ultrahigh specific detectivity (D*) of 5.8 × 1013 Jones, an external quantum efficiency of 1.86 × 107%, and a rapid response time of 20.8 ms. The WSe2/InSe vertical architecture has promising potential in developing high-performance nano-optoelectronics.

ObjectivesCircular RNAs (circRNAs) have emerged as significant biological regulators. Herein, we aimed to elucidate the role of an unidentified circRNA (circPDE4B) that is reportedly downregulated in osteoarthritis (OA) tissues.MethodsThe effects of circPDE4B were explored in human and mouse chondrocytes in vitro. Specifically, RNA pull-down (RPD)-mass spectrometry analysis (MS), immunoprecipitation, glutathione-S-transferase (GST) pull-down, RNA immunoprecipitation and RPD assays were performed to verify the interactions between circPDE4B and the RIC8 guanine nucleotide exchange factor A (RIC8A)/midline 1 (MID1) complex. A mouse model of OA was also employed to confirm the role of circPDE4B in OA pathogenesis in vivo.ResultscircPDE4B regulates chondrocyte cell viability and extracellular matrix metabolism. Mechanistically, FUS RNA binding protein (FUS) was found to promote the splicing of circPDE4B, while downregulation of circPDE4B in OA is partially caused by upstream inhibition of FUS. Moreover, circPDE4B facilitates the association between RIC8A and MID1 by acting as a scaffold to promote RIC8A degradation through proteasomal degradation. Furthermore, ubiquitination of RIC8A at K415 abrogates RIC8A degradation. The circPDE4B–RIC8A axis was observed to play an important role in regulating downstream p38 mitogen-activated protein kinase (MAPK) signalling. Furthermore, delivery of a circPDE4B adeno-associated virus (AAV) abrogates the breakdown of cartilage matrix by medial meniscus destabilisation in mice, whereas a RIC8A AAV induces the opposite effect.ConclusionThis work highlights the function of the circPDE4B–RIC8A axis in OA joints, as well as its regulation of MAPK-p38, suggesting this axis as a potential therapeutic target for OA.

Multiple myeloma is an incurable hematological malignancy that impacts tens of thousands of people every year in the United States. Treatment for eligible patients involves induction, consolidation with stem cell rescue, and maintenance. High-dose therapy with a DNA alkylating agent, melphalan, remains the primary drug for consolidation therapy in conjunction with autologous stem-cell transplantation; as such, melphalan resistance remains a relevant clinical challenge. Here, we describe a proteometabolomic approach to examine mechanisms of acquired melphalan resistance in two cell line models. Drug metabolism, steady-state metabolomics, activity-based protein profiling (ABPP, data available at PRIDE: PXD019725), acute-treatment metabolomics, and western blot analyses have allowed us to further elucidate metabolic processes associated with melphalan resistance. Proteometabolomic data indicate that drug-resistant cells have higher levels of pentose phosphate pathway metabolites. Purine, pyrimidine, and glutathione metabolisms were commonly altered, and cell-line-specific changes in metabolite levels were observed, which could be linked to the differences in steady-state metabolism of naïve cells. Inhibition of selected enzymes in purine synthesis and pentose phosphate pathways was evaluated to determine their potential to improve melphalan's efficacy. The clinical relevance of these proteometabolomic leads was confirmed by comparison of tumor cell transcriptomes from newly diagnosed MM patients and patients with relapsed disease after treatment with high-dose melphalan and autologous stem-cell transplantation. The observation of common and cell-line-specific changes in metabolite levels suggests that omic approaches will be needed to fully examine melphalan resistance in patient specimens and define personalized strategies to optimize the use of high-dose melphalan.

To measure the 24-h intraocular pressure (IOP) by Icare PRO rebound in healthy and primary open-angle glaucoma (POAG) eyes and compare it with non-contact tonometry (NCT). Thirty POAG patients, who were under IOP-lowering treatment, and 30 healthy subjects were included. Participants were hospitalized overnight for the 24-h IOP measurement. IOPs were measured by Icare PRO and NCT according to a standard protocol every 2 h during 24 h. The 24-h IOP curve and IOP-related parameters were compared between Icare PRO and NCT groups in POAG and healthy eyes. The IOPs measured by Icare PRO in habitual position increased notably at 22:00 in the normal group and at 20:00 in the POAG group, reached peak at 0:00, stayed high until 4:00, and then decreased in both groups (all p

This article studies the continual learning task from the perspective of multimodal fusion. In the multimodal fusion problem, the unified representations of heterogeneous modalities are continuously updated, while the classifier is also constantly refreshed for each multimodal learning task. To tackle this point, we establish a continual learning framework for multimodal learning and design an effective online dictionary updating method. Finally, we experimentally verify a complex material identification task and obtain promising results.

Exoskeleton has been applied in the field of medical rehabilitation and assistance. However, there are still some problems in the interaction between human and exoskeleton, such as time delay, the existence of certain constraints on the human body, and the movement in time is hard to follow. A human motion pattern recognition model based on the long short‐term memory (LSTM) is proposed, which can recognise the state of the human body. Meanwhile, the orthogonalisation method is integrated to make personal‐specific disentangling, and it can effectively improve the generalisation ability of different groups of people, so as to improve the effective follower ability of the exoskeleton. Compared with some other traditional methods, this model has better performance and stronger generalisation ability, which has certain significance in the field of exoskeleton algorithm.

BackgroundAlthough researchers have adopted various methods for the resection and reconstruction of periacetabular tumors, the total incidence rate of complications remains high. Aiming for preserving the acetabulum and reducing the risk of complications, we applied a surgery method using tumor-free autologous femoral head to reconstruct the defective acetabulum after resection of periacetabular tumors followed by performing a conventional total hip arthroplasty (THA). Moreover, we proposed a preliminary classification system for these surgery methods.MethodsWe retrospectively reviewed 6 patients treated with acetabulum reconstruction combined with autologous femoral head following peri-acetabulum resection between April 2010 and May 2018. All patients were diagnosed as periacetabular tumors including chondrosarcoma (n= 5) and chondroblastoma (n= 1). Clinical data such as age, diagnosis, complications, local recurrence or metastasis, and function (Musculoskeletal Tumor Society 1993, MSTS93) were documented. The average time of follow-up was 62.5 months (range, 17 to 106 months).ResultsA total of 5 patients survive with average MSTS93 score of 27.8 points (range, 26–30). One patient, suffering from multiple bone metastasis prior treatment, ended up dying. One who had received radiotherapy before surgery had poor incision healing. Further, a classification system was preliminary proposed in 2 patients involving the pubis (type A) and 4 patients involving ischium (type B).ConclusionsBased on the results, we preliminary proposed a classification system for reconstruction with autologous femoral head after periacetabular low malignant tumors resection. The clinical results suggested that surgery methods involving pubis (type A) and ischium (Type B) are safe and feasible. However, further researches should be conducted to verify our classification system.

The smart city is an integrated environment that heavily relies on intelligent robots, which provides the basis for the warehouse automation. However, a warehouse is a typical unstructured environment, and robotic grasp and manipulation are extremely important for the package, transfer, search, and so on. Currently, the most usual method is to detect the picking or grasping points for some specific end-effector including suction cup, gripper, or robotic hand. The manipulation performance is, therefore, strongly influenced by the visual detector. To tackle this problem, the affordance map has recently been developed. It characterizes the operation possibilities afforded by the operation scene and has been used for several grasp tasks. Nevertheless, the conventional affordance method often fails in complicated environments due to the mistake calculation results. In this article, we develop a novel framework to integrate the interactive exploration with a composite robotic hand for robotic grasping in a complicated environment. The exploration strategy is obtained by a deep reinforcement learning procedure. The developed new composite hand, which integrates the suction cup and grippers, is used to test the merits of the proposed interactive perception method. Experimental results show the proposed method significantly increases the manipulation efficiency and may bring great economic and social and benefits for smart cities.

Objective Serious bacterial infection (SBI) remains an important cause of morbidity and mortality in preterm infants. The objective of this study was to evaluate the dynamically increased value of the red cell distribution width (RDW) in the diagnosis of SBI. Methods This retrospective study enrolled 334 preterm infants with birth weight less than 1500 g. The initial RDW and the maximum value of RDW during hospitalization were extracted from the MIMIC-III database (version 1.4). Infants were categorized into four groups according to baseline RDW value and ΔRDW (ΔRDW = RDW at maximum- RDW at baseline). Logistic regression analysis was used to assess the risk of developing SBI in each group. A receiver operating characteristic (ROC) curve analysis was used to evaluate the diagnostic value of RDW at baseline alone, ΔRDW alone, and in combination. Results Infants with increased RDW at baseline (> 17%) and ΔRDW > 2% exhibited the highest risk of developing SBI, whereas the patients with normal RDW level at baseline (≤ 17%) and ΔRDW≤2% (the reference group) had the lowest risk. This association remained unaltered even after adjustment in multivariable models. Basing on ROC curve analysis, the area under the curve predicted by the combination of RDW at baseline and ΔRDW for SBI was 0.81 (95% CI, 0.76–0.87). Sensitivity and specificity were 78.16 and 72.47% respectively. Conclusions We observed that combination of elevated RDW at baseline and dynamic increases during hospitalization is significantly associated with SBI. Therefore, that combination could be a promising independent diagnostic indicator of SBI in newborns.

Background Hand, foot, and mouth disease (HFMD) is an acute infectious disease caused by human enterovirus 71 (EV71), coxsackievirus, or echovirus, which is particularly common in preschool children. Severe HFMD is prone to cause pulmonary edema before progressing to respiratory and circulatory failure; thus hemodynamic monitoring and fluid management are important to the treatment process. Methods We did a review of young patients who had been successfully treated in our department for severe HFMD, which had been caused by EV71. A total of 20 patients met the inclusion criteria. Eight cases were monitored by the pulse indicator continuous cardiac output (PiCCO) technique, and fluid management was administered according to its parameters. With regard to the treatment with PiCCO monitoring, patients were divided into two groups: the PiCCO group (8 patients) and the control group (12 patients). The groups were then compared comprehensively to evaluate whether PiCCO monitoring could improve patients’ clinical outcomes. Results After analysis, the findings informed that although PiCCO failed to shorten the length of ICU stay, reduce the days of vasoactive drug usage, or lower the number of cases which required mechanical ventilation, PiCCO did reduce the incidence of fluid overload (p = 0.085) and shorten the days of mechanical ventilation (p = 0.028). After effective treatment, PiCCO monitoring indicated that the cardiac index (CI) increased gradually(p p p < 0.0001), the global end diastolic volume index (GEDVI, p = 0.0043), and the systemic vascular resistance index (SVRI, p < 0.0001), all of which decreased gradually. Conclusion Our study discovered that PiCCO hemodynamic monitoring in young children with severe HFMD has some potential benefits, such as reducing fluid overload and the duration of mechanical ventilation. However, whether it can ameliorate the severity of the disease, reduce mortality, or prevent multiple organ dysfunction remain to be further investigated.

Convolutional neural network (CNN) has been gradually applied to steady-state visual evoked potential (SSVEP) of the brain-computer interface (BCI). Frequency-domain features extracted by fast Fourier Transform (FFT) or time-domain signals are used as network input. In the frequency-domain diagram, the features at the short time-window are not obvious and the phase information of each electrode channel may be ignored as well. Hence we propose a time-domain-based CNN method (tCNN), using the time-domain signal as network input. And the filter bank tCNN (FB-tCNN) is further proposed to improve its performance in the short time-window. We compare FB-tCNN with the canonical correlation analysis (CCA) methods and other CNN methods in our dataset and public dataset. And FB-tCNN shows superior performance at the short time-window in the intra-individual test. At the 0.2 s time-window, the accuracy of our method reaches 88.36 ± 4.89 % in our dataset, 77.78 ± 2.16 % and 79.21 ± 1.80 % respectively in the two sessions of the public dataset, which is higher than other methods. The impacts of training-subject number and data length in inter-individual or cross-individual are studied. FB-tCNN shows the potential in implementing inter-individual BCI. Further analysis shows that the deep learning method is easier in terms of the implementation of the asynchronous BCI system than the training data-driven CCA. The code is available for reproducibility at https://github.com/DingWenl/FB-tCNN.

There were gender differences in the prevalence and severity of allergic diseases. Group 2 innate lymphoid cells (ILC2s) were recently reported to play a critical role in allergic diseases. We investigated the sex-dependent differences in ILC2-dominant allergic airway inflammation model using T\B cell-deficient mice, and determined the gender differences of ILC2 levels in patients with asthma and allergic rhinitis. Female mice exhibited higher levels of inflammatory infiltration and large production of IL-5 and IL-13, especially for ILC2 levels compared to male mice with the induction of IL-33. However, no significant differences were found for the levels of circulating ILC2s between the genders of patients. The treatment of testosterone significantly decreased the intracellular type 2 cytokines in ILC2s and the proliferation of pure ILC2s in response to epithelial cytokines. Our study suggested the sex differences and the involvement of androgen on ILC2s in allergic diseases.

Background: Massive monoclonal or oligoclonal expansion of CD8+ T cells is a notable feature of primary infections of the Epstein–Barr virus (EBV). However, the clinical significance of this expansion is not clear. Results: An increase in the CD8dimCD3+ lymphocyte subset in patients with active EBV infection was due to caspase-8-dependent apoptosis was found using flow cytometry in this study. The number of these cells was associated with the illness severity. Pan-T-cell antigen and receptor analyses were also compared in patients with active EBV infections and T-cell large granular lymphocytic leukemia to provide additional diagnostic information. Conclusion: The increase in CD8dimCD3+ cells could be a biomarker of active EBV infection and an exclusion indicator of T-cell large granular lymphocytic leukemia with flow cytometric analysis.

Skin grafting, although a relatively classic and well-known technique, still has multiple disadvantages such as secondary contracture of the skin graft, sunken depression, poor elasticity, and color mismatch. Adding adipose tissues significantly improved the graft appearance compared to traditional skin grafting methods. Herein, we report two cases of modified skin graft procedures, both showing positive outcomes. In case 1, a mechanically processed fat-derived product was injected into the lower half of the skin graft area. In case 2, left upper eyelid blepharoplasty was performed, and the orbital fat strip was transferred and placed under the recipient area on the right side. Hair growth was observed only in case 1, whereas the extent of sunken depression was significantly reduced in both cases. Compared to traditional skin grafting methods, adding fat components to the skin graft recipient area improved the appearance and blood supply, together with enhancing the regenerative rate.

Myocardial infarction (MI), the leading cause of mortality and disability worldwide, is a disease in which multiple environmental and genetic factors are involved. Recently, researches suggested that insertion/deletion (ins/del) variation of NFKB1 gene rs28362491 is a functional polymorphism. In the present study, we aimed to explore the relation between variation of NFKB1 gene rs28362491 and MI by polymerase chain reaction–restriction fragment length polymorphism (PCR–RFLP) in 359 MI patients and 1085 control participants. Gensini score was used to evaluate the degree of coronary artery stenosis in MI patients. The plasma levels of interleukin-6 (IL-6), IL-8, malonaldehyde (MDA) and superoxide dismutase (SOD) were randomly measured by ELISA both in MI patients and control participants. We found that the detected frequencies of D allele (41.2% vs. 36.4%, P = 0.021) and DD genotype (17.5% vs. 12.0%, P = 0.022) were significantly higher in MI patients than in control participants. Compared with II or ID genotype carriers, the Gensini score in MI patients with DD genotype was 32–43% higher (both P P = 0.001 vs. II or ID genotype). Of note, IL-6 levels in MI patients carrying DD genotype were significantly higher than that in control participants and other genotype carriers in MI patients (both P NFKB1 gene rs28362491 DD genotype was associated with a higher risk of MI and more severe coronary artery lesion, which also had a potential influence on the level of inflammatory cytokine IL-6.

Background: In the nickel foam production process, the detection and identification of surface defects relies heavily upon the operators’ experiences. However, the manual observation is of high labor intensity, low efficiency, strong subjectivity and high error rate. Objective: Therefore, this paper proposes a new method for the nickel foam surface defect detection and identification, based on an improved probability extreme learning machine. Methods: At first, a machine vision system for nickel foam is established, and gray level cooccurrence matrix is used to calculate defect features, which are inputted into extreme learning machine to train the defect classifier. Then a composite differential evolution algorithm is used to optimize the input weights and hidden layer thresholds. Finally, an integrated probabilistic ELM is proposed to avoid misjudgments when multiple probabilities values are almost identical. Conclusion: Experiments show that the proposed method can achieve a defect-identifying accuracy, which meets an enterprise’s needs.

In the recent years, several hashing methods have been proposed for multi-label image retrieval. However, general methods quantify the similarities of image pairs roughly, which only consider the similarities based on category labels. In addition, general pairwise loss functions are not sensitive to the relative order of similar images. To address above problems, we present a deep semantic-aware ranking preserving hashing (DSRPH) method. First, we design a semantic-aware similarity quantization method which can measure fine-grained semantic-level similarity beyond the category based on the cosine similarity of image captions that contain high-level semantic description. Second, we propose a novel weighted pairwise loss function by adding adaptive upper and lower bounds, which can construct a compact zero-loss interval to directly constrain the relative order of similar images. Extensive experiments show that our method can generate high-quality hash codes and yield the state-of-the-art performance.

Wearable sensing devices, which are smart electronic devices that can be worn on the body as implants or accessories, have attracted much research interest in recent years. They are rapidly advancing in terms of technology, functionality, size, and real-time applications along with the fast development of manufacturing technologies and sensor technologies. By covering some of the most important technologies and algorithms of wearable devices, this paper is intended to provide an overview of upper-limb wearable device research and to explore future research trends. The review of the state-of-the-art of upper-limb wearable technologies involving wearable design, sensor technologies, wearable computing algorithms and wearable applications is presented along with a summary of their advantages and disadvantages. Toward the end of this paper, we highlight areas of future research potential. It is our goal that this review will guide future researchers to develop better wearable sensing devices for upper limbs.

Background Cryptogenic multifocal ulcer stenosing enteritis (CMUSE) is a rare disease characterized by multiple superficial ulcers, stenosis, and obstruction of the small intestine of unknown origin, and the course can recur. Case presentation We encountered a 62-year-old male patient with intestinal obstruction. The patient was admitted to the hospital for surgical treatment due to intestinal obstruction, and was diagnosed with cryptogenic multifocal ulcer stenosis enteritis due to comprehensive surgery and postoperative pathological considerations. Conclusion In the future, we will continue to follow up the patient. The present study aims to remind clinicians of this disease, and reduce the incidence of misdiagnosis.

A mixture of Pingdingshan lean coal and acid-treated Huadian oil shale was co-pyrolyzed in a drop-tube fixed-bed reactor in the temperature range of 300 °C–450 °C. To reveal the formation mechanism of the solid co-pyrolysis product, changes in some physico-chemical properties were investigated, using analysis by X-ray diffraction, X-ray photoelectron spectroscopy, scanning electron microscopy, pore analysis, thermogravimetry, and electron spin resonance. X-ray diffraction showed that the lattice plane spacing for the co-pyrolyzed mixture decreased from 0.357 nm to 0.346 nm and the average stacking height increased from 1.509 nm to 1.980 nm in the temperature range of 300 °C–450 °C, suggesting that pyrolysis treatment increased its degree of metamorphism. The amount of oxygen-containing functional groups and pore volume decreased with increasing temperature. Thermogravimetry and electron spin resonance results showed that synergistic effects occurred during the copyrolysis process. A formation mechanism for the solid product was proposed. Hydrogen-rich radicals generated from the pyrolysis of the oil shale were trapped by hydrogen-poor macromolecular radicals of the intermediate metaplast produced from coal pyrolysis, thereby increasing the yield of solid product.

In this paper, we address the learning problem of classifying untouched tactile instance with the help of visual modality. The proposed method is based on dictionary learning and we impose different penalty terms on coding vectors between visual and tactile modalities. Using such structured coding vectors, the visual-tactile cross-modal transfer can be achieved. A set of optimization algorithms are developed to obtain the solutions of the proposed optimization problems. After then, we can use the obtained dictionary to predict the coding vectors of the new untouched tactile samples and further determine its label. Finally, we perform extensive experimental evaluations on publicly available datasets to show the effectiveness of the proposed method.

SUMMARYThe various vision-based tactile sensors have been developed for robotic perception in recent years. In this paper, the novel soft robotic finger embedded with the visual sensor is proposed for perception. It consists of a colored soft inner chamber, an outer structure, and an endoscope camera. The bending perception algorithm based on image preprocessing and deep learning is proposed. The boundary of color regions and the position of marker dots are extracted from the inner chamber image and label image, respectively. Then the convolutional neural network with multi-task learning is trained to obtain bending states of the finger. Finally, the experiments are implemented to verify the effectiveness of the proposed method.

Friction field distribution is a critical factor in the drafting process, as it affects the fiber bundle movement in the main draft zone. In this paper, a modified draft device, named the multivariate principle curve draft device, which extends the friction field and condenses fiber bundles, has been employed to produce colored spun yarns. To analyze the effect of the modified draft device in the spinning process, mechanical analysis and finite element simulation were applied. In the mechanical analysis, the curvature surfaces of the grooved compactor exert friction force on the fiber bundles to restrain the peripheral fibers, and the relation between the friction and angles of the contact surfaces was concluded. In the numerical simulation, the result shows that the friction force distribution in the curved drafting channel is extended and enhanced, which leads to the forward distribution of the fiber accelerated points. Meanwhile, 28.1 tex blended colored yarns (cotton/polyester/viscose 30/30/40) and 19.7 tex pure viscose colored yarns were spun by the modified and conventional draft sets on a ring spinning machine. The comparative results imply that the modified device ensures outstanding yarn properties, such as yarn evenness, hairiness and imperfections, although there is some decrease in the yarn strength.

This paper focuses on multi-modal Information Perception (IP) for Soft Robotic Hands (SRHs) using Machine Learning (ML) algorithms. A flexible Optical Fiber-based Curvature Sensor (OFCS) is fabricated, consisting of a Light-Emitting Diode (LED), photosensitive detector, and optical fiber. Bending the roughened optical fiber generates lower light intensity, which reflecting the curvature of the soft finger. Together with the curvature and pressure information, multi-modal IP is performed to improve the recognition accuracy. Recognitions of gesture, object shape, size, and weight are implemented with multiple ML approaches, including the Supervised Learning Algorithms (SLAs) of K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Logistic Regression (LR), and the unSupervised Learning Algorithm (un-SLA) of K-Means Clustering (KMC). Moreover, Optical Sensor Information (OSI), Pressure Sensor Information (PSI), and Double-Sensor Information (DSI) are adopted to compare the recognition accuracies. The experiment results demonstrate that the proposed sensors and recognition approaches are feasible and effective. The recognition accuracies obtained using the above ML algorithms and three modes of sensor information are higher than 85 percent for almost all combinations. Moreover, DSI is more accurate when compared to single modal sensor information and the KNN algorithm with a DSI outperforms the other combinations in recognition accuracy.

Objective: To assess sodium ferulate’s effect on cognitive function and p38MAPK signaling in hippocampus of rats with chronic cerebral hypoperfusion (CCH). Methods: 45 male Sprague-Dawley (SD) rats were separated into sham-operation group, CCH model group and treatment group (intraperitoneal injection of 50 mg/kg sodium ferulate). The cognitive function was detected via open-field test, novel object recognition test and Morris water maze test. The activity of superoxide dismutase (SOD) in hippocampal tissues was detected using ELISA kit. Moreover, the neuronal damage in hippocampal tissues was assessed by immunohistochemical method, and apoptosis was assessed via TUNEL staining. Finally, p-p38MAPK signaling protein level in hippocampal tissues was detected via Western blotting. Results: No difference was found in rat autonomic activity among three groups (P > 0.05). The novel object recognition ability of model rats was significantly impaired along with longer escape latency and shorter retention time in the target quadrant (P < 0.01), which were all improved after sodium ferulate treatment (P < 0.01). SOD activity in hippocampal tissues in model rats was significantly reduced and sodium ferulate could significantly increase SOD activity (P < 0.01). There were a large number of damaged neurons and apoptotic cells in hippocampal tissues in model group and sodium ferulate could protect neurons (P < 0.01). The levels of p-p38MAPK, GSP3β and P-tau protein in hippocampal tissues in model group were significantly increased, which were significantly reduced after treatment with sodium ferulate (P < 0.01). Conclusion: Sodium ferulate can protect the CCH-induced cognitive impairment in rats and reduce the CCH-induced damage and apoptosis of hippocampal neurons, possibly through inhibition of p38MAPK signaling pathway.

In this study, on the basis of the various contact angles and the hybrid theory, a new mathematic model without the raceway control hypothesis is proposed for the analysis of ball bearing under the combined axial, radial and moment loads. Instead of the orthogonal decomposition method, the triangular geometric theorem and vector diagram method have been used in the force analysis of local ball to improve the computation efficiency of bearing analysis. For validation purpose, the comparative analysis of the ball-raceway contact angles and loads of ball bearing under different operation conditions obtained by the proposed model and the Jones’ model with different raceway control hypotheses has been conducted. The results show that the proposed model has a higher applicability and rationality compared to the Jones’ model, and a proper moment load can be used to improve the load distribution and service performance of ball bearing subjected to the radial load.

The contamination status of H5 avian influenza viruses and distribution of subtypes of H5N1 and H5N6 in poultry-related environment of Hubei areas were investigated. Urban and rural live poultry markets, poultry farms, intensive livestock farms and other monitoring types of 103 counties in 17 cities were selected in Hubei. Wiping samples from cage surface, wiping samples from chopping board, fecal specimens and other environmental samples were collected and tested by real-time RT-PCR using primers and probes of influenza A, avian influenza of H5, N1 and N6 from December 2017 to March 2018. The avian influenza virus positive rate was compared among different monitoring sites, samples, time and regions. Totally, 7132 environmental samples were collected in 1634 monitoring points with a positive rate of 2.24%. The positive rate of H5 avian influenza virus was the highest in urban and rural live poultry markets (3.44%, χ2=61.329, P

One major reason for the success of convolutional neural networks (CNNs) is the availability of large-scale labeled data. Effective training of CNNs relies on large annotated data. Unfortunately, large amounts of data with corresponding annotations are too expensive to obtain in some real-world applications. One reasonable alternative is to use data augmentation techniques to automatically generate annotated samples. In this paper, a novel data augmentation framework based on perspective transformation is proposed. This method automatically generates new annotated data without extra manual labeling, thus effectively extends the inadequate dataset. Perspective transformation can produce new images captured from any cameras viewpoints. Therefore, our method can mimic images taken at the angle that the camera cannot reach. Extensive experimental results on several datasets have demonstrated that our perspective transformation data augmentation strategy is an effective tool when using deep CNNs on small or imbalance datasets.

Macrophage migration inhibitory factor (MIF) has been recognized as a major player in the pathogenesis of atherosclerosis. This study determined the association between polymorphisms of MIF gene and acute coronary syndrome (ACS). The polymorphism of MIF gene (rs755622, rs1007888 and rs2096525) was analyzed in 1153 healthy controls and 699 ACS cases in Chinese Han population. Plasma MIF level was also measured in part of ACS patients (139/19.9%) and healthy controls (129/11.2%) randomly. Most participants including healthy controls and ACS patients carried rs755622 GG (63.1% vs. 56.7%) and CG genotypes (33.1% vs. 38.9%) and G allele of rs755622 (79.6% vs. 76.1%, respectively), while CC genotype (3.8% vs. 4.4%) and C allele (20.4% vs. 23.9%) carriers were the lowest. Multivariate logistic regression analysis showed that carriers with rs755622 C allele had a higher risk of ACS compared to other genotypes (AOR = 1.278, 95% CI: 1.042–1.567). In addition, CC genotype carriers had the highest plasma levels of MIF than other genotype carriers. The MIF level in ACS patients with CC genotype was significantly higher than ACS patients carrying GG genotype and healthy controls carrying 3 different genotypes of MIF gene rs755622. Our findings indicate that MIF gene rs755622 variant C allele is associated with increased risk of ACS. Identification of this MIF gene polymorphism may help for predicting the risk of ACS.

This paper propose a buck-type pulse power supply with a reverse voltage circuit for finishing machining of High-Speed Wire-Electrical-Discharge-Machining (HSWEDM). A gap breakdown point detection circuit is added to control the discharge energy. When the gap breakdown is detected, the pulse power supply cut off the energy deliver immediately, and the energy stored in the cable inductance dissipates in the gap with limited time period. Meanwhile, in order to further reduce the pulse width, a reverse voltage source is applied on the connect cable and the discharge gap to reduce the discharge current and shorten the discharge time. The experimental verification showed the validity of the proposed converter and its control strategy.

Stably grasping objects for a specific task is a hot research topic in robotics due to multiple degrees of freedom of hand kinematics, various shapes of objects, and incomplete visual sensing of objects (partial point clouds). This paper proposes an effective grasp planning method by integrating the crucial grasp cues (positions and orientations of thumb fingertips and the wrist) from humans’ grasp experience. This approach has multiple advantages: greatly reducing the search space of the hand kinematics; no reconstruction or registration; being able to directly perform on the partial point cloud of objects. Meanwhile, for various shapes of objects which are partially observable in the single-view visual sensing, the presented approach learns the “thumb” grasp point employing a signature of histograms of orientations shape descriptor based on objects’ category level. This method recognizes the grasp point according to the shape affordance at each point on the object, which performs the grasp point generalization on the familiar objects. Finally, we verify the developed methods via both simulations and experiments by grasping various shapes of objects.

Cardiorespiratory fitness, anaerobic power, and lower extremity strength are essential for soccer players at all levels. An effective program should be developed to improve physical strength for adolescent soccer players who need to combine academic and technical training. This study analyzed the impact of short-term high intensity interval training (HIIT) training and traditional moderate intensity continuous training (MICT) on adolescent soccer players. Participants included 56 adolescent soccer players who were divided into HIIT and MICT groups. The training program was conducted 3 times a week for 4 weeks using cycle ergometer. Each session included the same resistance training program, and the characteristics of HIIT and MICT were applied to improve cardiorespiratory fitness and anaerobic power. Body composition analysis, graded exercise test for peak oxygen uptake (VO2 peak), Wingate anaerobic power test, and isokinetic knee strength test were performed. VO2 peak was improved in HIIT and MICT, but anaerobic threshold and heart rate recovery significantly improved in the HIIT group. Wingate anaerobic peak power had increased significantly in sets 1, 2, and 3 in the HIIT group, but showed significant improvement only in set 1 in the MICT group. The isokinetic strength improved significantly in the HIIT group at 60°/s and in the MICT group at 240°/s. There was no significant change in body composition in either group. In conclusion, short-term HIIT administered to adolescent soccer players effectively improved cardiorespiratory fitness in HIIT and MICT groups. While HIIT increased anaerobic threshold and power, MICT effectively improved muscle endurance. Short-term intensive training can be considered a time-efficient training strategy.

Antimicrobial prescriptions are relatively common in urologic outpatients. Therefore, it is necessary to investigate the impact of antimicrobial stewardship program (ASP) interventions.In urology outpatients, antimicrobial use density (AUD), antimicrobial agent costs, isolation of urinary tract infection (UTI)-causing organisms and their antimicrobial susceptibilities were compared between intervention by infection control team (ICT) era (pre-2014) and ASP era (post-2014) in 2739 patients with lower urinary tract symptoms, including neurogenic bladder patients with UTI or suspected UTI, from 2011 to 2020.In the ASP, overall AUD (P.001), cefotiam (CTM) (P=.0013), 2nd-generation cephalosporins (P=.026), cefdinir (CFDN) (P.001), levofloxacin (LVFX) (P.001), sitafloxacin (STFX) (P=.0016), and tosufloxacin (TFLX) (P=.0044) showed a significant decrease, but cefaclor (P=.019) showed a significant increase. Regarding antimicrobial agent costs, overall (P=.016), CTM (P=.021), 2nd-generation cephalosporins (P=.033), CFDN (P=.016), LVFX (P=.016), STFX (P=.033), and TFLX (P=.033) showed a significant decrease in the ASP. UTI-causing antimicrobial susceptibilities, CTM (P=.035), LVFX (P=.026) and sulfamethoxazole/trimethoprim (P=.048) in E. coli, and minocycline (P=.026) in K. pneumoniae showed a significant improve in the ASP.ASP contributed to decrease AUD and antimicrobial agent costs, and to improve antimicrobial susceptibilities of E. coli and K. pneumoniae to several antibiotics, compared to ICT. Further prospective studies are necessary for definitive conclusions.

Tactile sensing plays an important role in robotic perception and manipulation tasks. To overcome the real-world limitations of data collection, simulating tactile response in a virtual environment comes as a desirable direction of robotic research. In this paper, we propose Elastic Interaction of Particles (EIP) for tactile simulation. Most existing works model the tactile sensor as a rigid multi-body, which is incapable of reflecting the elastic property of the tactile sensor as well as characterizing the fine-grained physical interaction between the two objects. By contrast, EIP models the tactile sensor as a group of coordinated particles, and the elastic property is applied to regulate the deformation of particles during contact. With the tactile simulation by EIP, we further propose a tactile-visual perception network that enables information fusion between tactile data and visual images. The perception network is based on a global-to-local fusion mechanism where multi-scale tactile features are aggregated to the corresponding local region of the visual modality with the guidance of tactile positions and directions. The fusion method exhibits superiority regarding the 3D geometric reconstruction task., ACMMM 2021 (Oral). Code available at https://github.com/yikaiw/EIP. arXiv admin note: substantial text overlap with arXiv:2011.11528

The human hand can adjust stiffness freely to realize different grasp modes, which is beneficial to adapting to different weights of objects. Therefore, humans have been trying different strategies to simulate hand, such as various rigid hand or soft hand, using different structure designs and materials. In this paper, we propose a novel five-finger soft hand. The layer jamming structure is used to increase stiffness and the vision-based tactile sensor is used to provide perception in the soft hand. Through the grasping experiment, the results show that the soft hand can effectively transmit into different grasping modes and adaptively grasp objects of different shapes. Besides, the tactile data is collected by the sensor and a recognition model is built. Through the test, the accuracy is up to 98.75%. In summary, the grasping ability of the soft hand is satisfied, and the combination of tactile sensor and variable stiffness improves performance further.

A hollow core–shell potassium phosphomolybdate (KMoP)@cadmium sulfide (CdS)@bismuth sulfide (Bi2S3) Z-scheme tandem heterojunction is fabricated by a simple hydrothermal strategy and kept in a water bath to continue the reaction. At the same time, the ternary structure combined Keggin-type polyoxometalate with two photosensitive sulfide semiconductors to form a stable hollow core–shell heterojunction. KMoP@CdS@Bi2S3 with a narrow band gap of ∼ 1.2 eV also has excellent photothermal performance, which may further promote photocatalytic efficiency. The hollow core–shell KMoP@CdS@Bi2S3 tandem heterojunction shows excellent H2 production performance, CrVI reduction ability and photocatalytic degradation performance of highly toxic tetracycline (TC). Under visible light irradiation, the photocatalytic H2 generation rate of the KMoP@CdS@Bi2S3 tandem heterojunction reaches 831 μmol h−1, which is 103 times higher than that of pristine KMoP. The photocatalytic reduction efficiency of CrVI and degradation efficiency of TC are as high as 95.5 and 97.51%, ∼4 times higher than that of KMoP. The boosted photocatalytic performance can be ascribed to the formation of core–shell Z-scheme tandem heterojunctions favoring spatial charge separation and the narrow band gap, which extends the photoresponse to visible light/NIR regions. When TC and CrVI exist at the same time, the reduction efficiency of CrVI can be as high as 99.64% because the intermediate of TC degradation can promote the reduction of CrVI. In addition, the photocatalytic performance of the KMoP@CdS@Bi2S3 heterojunction remains nearly constant after 4 recycles, which indicates high stability. The design strategy may provide new insights for preparing other high-performance core–shell tandem heterojunction photocatalysts for solar energy conversion.

According to the nickel foam surface defect images with the typical characteristics of complex geometry and texture distribution, a nickel foam surface defect detection method based on spatial-frequency multi-scale block local binary pattern is proposed. First, nonsubsampled contourlet is used to carry out foam nickel image multi-scale decomposition, and therefore, low-frequency sub-band images and high-frequency sub-band images are obtained. The multi-scale block local binary pattern is then used to extract the feature histogram vectors of each block region of low- and high-frequency sub-bands, and the histogram feature vectors of the whole image after cascade are formed. The kernel principal component analysis and support vector machine are adopted to reduce the dimension of the feature histogram vectors and used for the defect classification. Experimental results show that the proposed method of feature extraction can extract more detailed texture information, and the average recognition rate reaches to 90%, which meets an enterprise’s needs.

Excessive oxidative stress and inflammation are the key early events in the development of intervertebral disc degeneration (IVDD). The NACHT, LRR, and PYD domain-containing protein 3 (NLRP3) inflammasome has been identified as the major source of oxidative stress and the inflammatory responses and thus is an attractive therapeutic target for IVDD. However, currently, there are no reports on the use of mesenchymal stem cell (MSC)-derived exosomes to reduce NLRP3 inflammasome expression for IVDD treatment. The present study aimed to investigate the therapeutic effect of exosomes for use as IVDD therapeutics. We first manufactured and evaluated the characteristics of exosomes. Then, we investigated the effects of exosomes on H2O2-induced nucleus pulposus (NP) cell inflammation. Third, we tested the function of exosomes with respect to H2O2-induced ROS production and mitochondrial dysfunction. Finally, the therapeutic effect of exosomes on IVDD was investigated using a rabbit IVDD model. Results showed that exosomes play an anti-inflammatory role in pathological NP cells by suppressing inflammatory mediators and NLRP3 inflammasome activation. Moreover, it was suggested that exosomes might supply mitochondrial proteins to NP cells, and that the damaged mitochondria could be restored with this supplement. Further, in the rabbit IVDD model, exosomes significantly prevented the progression of degenerative changes. Our results confirmed that the NLRP3 inflammasome is an effective target for IVDD treatment and that the injection of exosomes could be a promising therapeutic strategy.

Tomography is an informative imaging modality that is usually implemented by mechanical scanning, owing to the limited depth-of-field (DOF) in conventional systems. However, recent imaging systems are working towards more compact and stable architectures; therefore, developing nonmotion tomography is highly desirable. Here, we propose a metalens-based spectral imaging system with an aplanatic GaN metalens (NA = 0.78), in which large chromatic dispersion is used to access spectral focus tuning and optical zooming in the visible spectrum. After the function of wavelength-switched tomography was confirmed on cascaded samples, this aplanatic metalens is utilized to image microscopic frog egg cells and shows excellent tomographic images with distinct DOF features of the cell membrane and nucleus. Our approach makes good use of the large diffractive dispersion of the metalens and develops a new imaging technique that advances recent informative optical devices., Bioimaging: metalenses make 3D analysis effortless An ultrathin “metalens” that uses semiconductor nanostructures to focus light can help microscopes resolve detailed images of live cells without complex mechanical components. In conventional tomographic imaging, a scanning instrument passes over the sample and takes multiple cross-sectional images, which are then reconstructed into a 3D picture. Tao Li from Nanjing University in China and colleagues have now simplified this technique by fabricating lenses patterned with concentric rings of gallium nitride nanopillars. The lens made of nanopillars has wavelength-dependent properties that enable focusing on different regions of a target simply by sweeping through the visible light spectrum. Experiments with frog egg cells demonstrated this approach could zoom in and obtain detailed, high quality images of the inner membrane and nucleus without harming the sample or moving the metalens.

With the development of robotics, the application of robots has gradually evolved from industrial scenes to more intelligent service scenarios. For multitasking operations of robots in complex and uncertain environments, the traditional manual coding method is not only cumbersome but also unable to adapt to sudden changes in the environment. Imitation learning that avoids learning skills from scratch by using the expert demonstration has become the most effective way for robotic manipulation. The paper is intended to provide the survey of imitation learning of robotic manipulation and explore the future research trend. The review of the art of imitation learning for robotic manipulation involves three aspects that are demonstration, representation and learning algorithms. Towards the end of the paper, we highlight areas of future research potential.

This paper proposes an improved Retinex theory based on a weighted guided filter method to enhance images in low-light conditions. The captured images under low illumination can cause dimness, distortion or details loss. We use the weighted guided filter method to perform illumination estimation and the original image is regarded as the guidance image, which can avoid color distortion and over-enhancement. It can adjust the regularization parameter adaptively based on the image content. Perceptual contrast is improved by using an illumination enhancement method with dynamic adjustment. To test the validness of our algorithm, the weighted guided filter method proposed in this paper is compared with bilateral filter and the guided filter method. Finally, experiment under low illumination is implemented on a NAO robot by using the proposed weighted guided filter method based on EKF-SLAM. The experiment result demonstrates that the proposed weighted guided filter method is feasible and effective in low-light environment.

Broad-band radio frequency (RF) detection is of great interest for its potential applications in wireless charging and energy harvesting. Here, we demonstrate that the bandwidth of broad-band RF detection in spin-torque diodes based on magnetic tunnel junctions (MTJs) can be enhanced through engineering the interface perpendicular magnetic anisotropy (PMA) between the CoFeB free layer and the MgO tunnel barrier. An ultrawide RF detection bandwidth of over 3 GHz is observed in the MTJs, and the broad-band RF detection behavior can be modulated by tuning the free layer PMA. Furthermore, a wide RF detection bandwidth (about 1.8 GHz) can be realized even without any external bias field for free layers with a thickness of about 1.65 nm. Finally, the dependence of the broad-band RF detection bandwidth on external magnetic field and RF power is discussed. Our results pave the way for RF energy harvesting for future portable nanoelectronics.

Objectives: To assess the insertion and ventilation of the laryngeal mask airway (LMA) classic while using different head positions with or without muscle relaxant. Methods: This is a double-blind randomized clinical trial. Patients scheduled for ureteral calculus surgery at Shanghai General Hospital, Shanghai, China were recruited between November 2017 and November 2018. A total of 132 adults were consecutively selected. Patients were randomly divided into 4 groups according to head positioning and muscle relaxant use. An 8-cm-high pillow was used to achieve the sniffing position. The insertion time, initial peak pressure (Ppeak), mean pressure (Pmean) of the airway during intermittent positive pressure ventilation (primary endpoint) and fiberoptic score of the LMA position (secondary endpoint) were evaluated via electronic bronchoscopy through the mask bar. All adverse events were recorded. Results: Data were analyzed by ANOVA, 2-way ANOVA, Chi-squared, Cochran-Mantel-Haenszel, and Kruskal-Wallis tests. The insertion time required for the first attempt, fiberoptic score, Ppeak and Pmean did not differ among the groups. However, the incidence of adverse events in groups not using muscle relaxant was higher than in those using muscle relaxant. Conclusion: Use of a sniffing position and muscle relaxant slightly eased the insertion of the LMA but did not affect the fiberoptic score or ventilation parameters. Using a muscle relaxant, but not the sniffing position, reduced the incidence of adverse effects. Saudi Med J 2019; Vol. 40 (7): 687-693 doi: 10.15537/smj.2019.7.24299 How to cite this article: An G, Fang B, Wang Z . Comparing the inseertion and ventilation of laryngeal mask airway according to the patient's head position and muscle relaxation use. Saudi Med J 2019; 40 (7): 687-693. doi: 10.15537/smj.2019.7.24299.

The local spatio-temporal descriptor and feature encoding algorithm are two crucial key steps for human action recognition based on spatio-temporal interest points (STIP). Since the local descriptors for STIP are essentially a type of motion information based on the texture, the key point of local feature description is to extract invariable, robust and distinguishable local texture features and motion information in reference spatio-temporal volume. Scattering transform is an image transform method based on directional wavelet transform and scale convolution, which has local translation invariance, rotation invariance and elastic deformation stability for local texture features. A novel local descriptor for STIP based on spatio-temporal three-dimensional scattering transform is proposed in this paper, which extends the original scattering transform to spatio-temporal three-dimensional space. Compared to the traditional descriptors, such as HOG, HOF and so on, the proposed scattering transform coefficients based histogram of oriented gradients (STC-HOG) descriptor can capture more robust and distinguishable motion information of local texture for STIP. In order to incorporate the local descriptors into action video representation, the feature encoding algorithm is indispensable. For the problem that vector of locally aggregated descriptors (VLAD) loses feature distribution location information during feature encoding, a histogram of distribution vector of locally aggregated descriptors (HOD-VALD) based on Gaussian kernel is proposed. We validated the proposed algorithm for human action recognition on multiple public available datasets, such as KTH, UCF Sports, HMDB51 and so on. The evaluation experiment results indicate that the proposed descriptor and encoding method can improve the efficiency of human action recognition and the recognition accuracy.

Automatic liver tumour segmentation is an important step towards digital medical research, clinical diagnosis and therapy planning. However, the existence of noise, low contrast and heterogeneity m...