Due to the advantages of deep learning, in this paper, a regularized deep feature extraction (FE) method is presented for hyperspectral image (HSI) classification using a convolutional neural network ...(CNN). The proposed approach employs several convolutional and pooling layers to extract deep features from HSIs, which are nonlinear, discriminant, and invariant. These features are useful for image classification and target detection. Furthermore, in order to address the common issue of imbalance between high dimensionality and limited availability of training samples for the classification of HSI, a few strategies such as L2 regularization and dropout are investigated to avoid overfitting in class data modeling. More importantly, we propose a 3-D CNN-based FE model with combined regularization to extract effective spectral-spatial features of hyperspectral imagery. Finally, in order to further improve the performance, a virtual sample enhanced method is proposed. The proposed approaches are carried out on three widely used hyperspectral data sets: Indian Pines, University of Pavia, and Kennedy Space Center. The obtained results reveal that the proposed models with sparse constraints provide competitive results to state-of-the-art methods. In addition, the proposed deep FE opens a new window for further research.
The multisensory fusion of remote sensing data has obtained a great attention in recent years. In this letter, we propose a new feature fusion framework based on deep neural networks (DNNs). The ...proposed framework employs deep convolutional neural networks (CNNs) to effectively extract features of multi-/hyperspectral and light detection and ranging data. Then, a fully connected DNN is designed to fuse the heterogeneous features obtained by the previous CNNs. Through the aforementioned deep networks, one can extract the discriminant and invariant features of remote sensing data, which are useful for further processing. At last, logistic regression is used to produce the final classification results. Dropout and batch normalization strategies are adopted in the deep fusion framework to further improve classification accuracy. The obtained results reveal that the proposed deep fusion model provides competitive results in terms of classification accuracy. Furthermore, the proposed deep learning idea opens a new window for future remote sensing data fusion.
We report epidemiologic, laboratory, and clinical findings for 7 patients with 2019 novel coronavirus disease in a 2-family cluster. Our study confirms asymptomatic and human-to-human transmission ...through close contacts in familial and hospital settings. These findings might also serve as a practical reference for clinical diagnosis and medical treatment.
With the rapid development of “Internet plus”, medical care has entered the era of big data. However, there is little research on medical big data (MBD) from the perspectives of bibliometrics and ...visualization. The substantive research on the basic aspects of MBD itself is also rare. This study aims to explore the current status of medical big data through visualization analysis on the journal papers related to MBD. We analyze a total of 988 references which were downloaded from the Science Citation Index Expanded and the Social Science Citation Index databases from Web of Science and the time span was defined as “all years”. The GraphPad Prism 5, VOSviewer and CiteSpace softwares are used for analysis. Many results concerning the annual trends, the top players in terms of journal and institute levels, the citations and H-index in terms of country level, the keywords distribution, the highly cited papers, the co-authorship status and the most influential journals and authors are presented in this paper. This study points out the development status and trends on MBD. It can help people in the medical profession to get comprehensive understanding on the state of the art of MBD. It also has reference values for the research and application of the MBD visualization methods.
2D heterostructured materials combining ultrathin nanosheet morphology, defined pore configuration, and stable hybrid compositions, have attracted increasing attention for fast mass transport and ...charge transfer, which are highly desirable features for efficient energy storage. Here, the chemical space of 2D–2D heterostructures is extended by covalently assembling covalent organic frameworks (COFs) on MXene nanosheets. Unlike most COFs, which are generally produced as solid powders, ultrathin 2D COF‐LZU1 grows in situ on aminated Ti3C2Tx nanosheets with covalent bonding, producing a robust MXene@COF heterostructure with high crystallinity, hierarchical porosity, and conductive frameworks. When used as lithium hosts in Li metal batteries, lithium storage and charge transport are significantly improved. Both spectroelectrochemical and theoretical analyses demonstrate that lithiated COF channels are important as fast Li+ transport layers, by which Li ions can be precisely nucleated. This affords dendrite‐free and fast‐charging anodes, which would be difficult to achieve using individual components.
Nanoporous 2D MXene@COF heterostructures are synthesized through the covalent assembly of COF‐LZU1 with an interface‐initiated imine bonding. MXene@COF exhibits high crystallinity, stability, and hierarchical porosity. The ordered 2D channels and uniform nucleation sites boost the Li deposition kinetics, resulting in dendrite‐free and fast‐charging lithium metal batteries.
Display omitted
•Successful preparation of a fluorine-free V2CTx@VOx via molten salt etching.•Exceptional performance of V2CTx@VOx in Zn ion electrolytes across broad pH range.•Achievement of a ...maximum specific capacity of 172 mAhg−1 in 1 M ZnBr2 solution.•Superior performance of V2CTx@VOx compared to V2CTx MXene prepared by HF solution.
The development of MXenes using Lewis acidic salts for etching (MS-MXenes) in molten salts presents a novel, fluorine-free method attracting considerable interest. However, the behavior of various MS-MXenes and their derivatives in aqueous environments remains largely unexplored. Particularly, vanadium-based MXenes demonstrate intriguing properties in Zn ion aqueous electrolytes. Herein, a fluorine-free V2CTx MXene@VOx is synthesized by molten salt etching under an argon atmosphere. The electrochemical properties of V2CTx@VOx are tested in various aqueous electrolytes, including Zn(TFSI)2, ZnSO4, ZnBr2, ZnAc2, and ZnCl2 solutions. The V2CTx@VOx shows high redox capacities in all these Zn ion electrolytes, with the peak performance observed in 1 M ZnBr2, achieving a maximum capacity of 172 mAh g−1 at 1 mV s−1. This performance rivals that of V2CTx MXene prepared through wet-chemical methods. These results underscore the potential of MS-MXenes materials in aqueous energy storage applications.
Limited data are available for clinical characteristics of patients with coronavirus disease 2019 (COVID-19) outside Wuhan. This study aimed to describe the clinical characteristics of COVID-19 and ...identify the risk factors for severe illness of COVID-19 in Jiangsu province, China. Clinical data of hospitalized COVID-19 patients were retrospectively collected in 8 hospitals from 8 cities of Jiangsu province, China. Clinical findings of COVID-19 patients were described and risk factors for severe illness of COVID-19 were analyzed. By Feb 10, 2020, 202 hospitalized patients with COVID-19 were enrolled. The median age of patients was 44.0 years (interquartile range, 33.0-54.0). 55 (27.2%) patients had comorbidities. At the onset of illness, the common symptoms were fever (156 77.2%) and cough (120 59.4%). 66 (32.7%) patients had lymphopenia. 193 (95.5%) patients had abnormal radiological findings. 11 (5.4%) patients were admitted to the intensive care unit and none of the patients died. 23 (11.4%) patients had severe illness. Severe illness of COVID-19 was independently associated with body mass index (BMI) ≥ 28 kg/m2 (odds ratio OR, 9.219; 95% confidence interval CI, 2.731 to 31.126; P<0.001) and a known history of type 2 diabetes (OR, 4.326; 95% CI, 1.059 to 17.668; P = 0.041). In this case series in Jiangsu Province, COVID-19 patients had less severe symptoms and had better outcomes than the initial COVID-19 patients in Wuhan. The BMI ≥ 28 kg/m2 and a known history of type 2 diabetes were independent risk factors of severe illness in patients with COVID-19.
In this study, a novel stable Ag-Titanium-oxo-cluster (Ag-TOC, Ag9Ti4) with excellent antibacterial performance and anti-inflammatory was developed by one-step solvothermal method. Hydrogel based ...Ag9Ti4 under NIR condition demonstrated better anti-inflammatory and wound healing ability.
Display omitted
•A novel stable, excellent antibacterial Ag-Titanium-oxo-cluster (Ag-TOC, Ag9Ti4) with active site Ag and salicylic acid was developed.•Hydrogel based Ag9Ti4 cluster system has good antibacterial and photothermal properties.•Hydrogel based Ag9Ti4 system under NIR condition showed better anti-inflammatory and wound healing ability.
Titanium-oxo-clusters (TOCs), due to its precise, tunable structure and rich properties, have been widely used in many fields. However, application of TOCs is greatly limited in biomedical area owing to the impact of its own performances, for example, unstable structure, lack of antibacterial and anti-inflammatory properties required as biomedical materials. In this work, we developed a novel stable, excellent antibacterial and anti-inflammatory properties Ag-Titanium-oxo-cluster (Ag-TOC, Ag9Ti4) with active site Ag and salicylic acid by one-step solvothermal method, through introducing silver and salicylic acid. Then, the Ag9Ti4 cluster was introduced into the dopamine-containing hydrogel system, the results in vitro indicated this Ag9Ti4 cluster hydrogel system possesses good antibacterial and photothermal properties. Moreover, the results in vivo indicated the Ag9Ti4 hydrogel system showed better anti-inflammatory and wound healing ability under NIR condition. Combined with its excellent properties, we believed that the construction of antibacterial, photothermal and stable Ag-TOC hydrogel system can provide a new strategy for the expanding biomedical applications of TOCs.
Synapses are essential for the transmission of neural signals. Synaptic plasticity allows for changes in synaptic strength, enabling the brain to learn from experience. With the rapid development of ...neuromorphic electronics, tremendous efforts have been devoted to designing and fabricating electronic devices that can mimic synapse operating modes. This growing interest in the field will provide unprecedented opportunities for new hardware architectures for artificial intelligence. In this review, we focus on research of three-terminal artificial synapses based on two-dimensional (2D) materials regulated by electrical, optical and mechanical stimulation. In addition, we systematically summarize artificial synapse applications in various sensory systems, including bioplastic bionics, logical transformation, associative learning, image recognition, and multimodal pattern recognition. Finally, the current challenges and future perspectives involving integration, power consumption and functionality are outlined.
Microrobots have received great attention due to their great potential in the biomedical field, and there has been extraordinary progress on them in many respects, making it possible to use them in ...vivo clinically. However, the most important question is how to get microrobots to a given position accurately. Therefore, autonomous actuation technology based on medical imaging has become the solution receiving the most attention considering its low precision and efficiency of manual control. This paper investigates key components of microrobot’s autonomous actuation systems, including actuation systems, medical imaging systems, and control systems, hoping to help realize system integration of them. The hardware integration has two situations according to sharing the transmitting equipment or not, with the consideration of interference, efficiency, microrobot’s material and structure. Furthermore, system integration of hybrid actuation and multimodal imaging can improve the navigation effect of the microrobot. The software integration needs to consider the characteristics and deficiencies of the existing actuation algorithms, imaging algorithms, and the complex 3D working environment in vivo. Additionally, considering the moving distance in the human body, the autonomous actuation system combined with rapid delivery methods can deliver microrobots to specify position rapidly and precisely.