- 标题
- 摘要
- 关键词
- 实验方案
- 产品
过滤筛选
- 2018
- Conditional Random Fields (CRF)
- Convolutional Neural Network (CNN)
- Fine Classification
- Airborne hyperspectral
- green tide
- Elegant End-to-End Fully Convolutional Network (E3FCN)
- deep learning
- remote sensing
- Moderate Resolution Imaging Spectroradiometer (MODIS)
- Optoelectronic Information Science and Engineering
- Ocean University of China
- Wuhan University
- Central South University
- Hubei University
-
Prediction of two-dimensional topography of laser cladding based on neural network
摘要： The two-dimensional morphology of the cladding layer has an important influence on the quality of the cladding layer and the crack tendency. Using the powerful nonlinear processing ability of the single hidden layer feedforward neural network, a prediction model between the cladding technological parameters and the two-dimensional morphology of the cladding layer is established. Taking the cladding parameters as the input and the two-dimensional morphology of the cladding as the output, the experimental data is used to train the network to achieve a high-level mapping of the input and output. On this basis, the algorithm of extreme learning machine is used to optimize the single hidden layer feedforward neural network to overcome the problems of slow convergence speed, more network training parameters and easy local convergence in back-propagation algorithm. The results show that the relationship between the cladding process parameters and the two-dimensional morphology of the cladding layer can be roughly reflected by the back-propagation algorithm. However, the prediction results are not stable and the error rate is between 10% and 40%. The neural network optimized by the extreme learning machine is utilized to get a better prediction result. The error rate is 10–20%.
关键词： extreme learning machine.,BP neural network,Layer cladding,morphology prediction
更新于2025-11-28 14:24:20
-
Liquid Crystal-Induced Myoblast Alignment
摘要： The ability to control cell alignment represents a fundamental requirement toward the production of tissue in vitro but also to create biohybrid materials presenting the functional properties of human organs. However, cell cultures on standard commercial supports do not provide a selective control on the cell organization morphology, and different techniques, such as the use of patterned or stimulated substrates, are developed to induce cellular alignment. In this work, a new approach toward in vitro muscular tissue morphogenesis is presented exploiting liquid crystalline networks. By using smooth polymeric films with planar homogeneous alignment, a certain degree of cellular order is observed in myoblast cultures with direction of higher cell alignment corresponding to the nematic director. The molecular organization inside the polymer determines such effects since no cell organization is observed using homeotropic or isotropic samples. These findings represent the first example of cellular alignment induced by the interaction with a nematic polymeric scaffold, setting the stage for new applications of liquid crystal polymers as active matter to control tissue growth.
关键词： liquid crystalline alignments,liquid crystalline network,cell alignment,biomaterials,muscular tissue engineering
更新于2025-11-21 11:01:37
-
Heterochiral Doped Supramolecular Coordination Networks for High-Performance Optoelectronics
摘要： Chiral self-sorting has great potential for constructing new complex structures and determining chirality-dependent properties in multicomponent mixtures. However, it is still of great challenge to achieve high fidelity chiral self-discrimination. Besides, the researches on the coordination polymers or metal-organic frameworks (CPs/MOFs) for micro-/nano-optoelectronics are still rare due to their low conductivity and difficulty in developing a rapid and simple scale-up synthetic method. Here, heterochiral supramolecular coordination networks (SCNs) were synthesized by the solvothermal reaction of naphthalene diimide enantiomers and cadmium iodide, using the chirality as a synthetic tuning parameter to control the morphologies. Intriguingly, heterochiral micro-/nanocrystals exhibited photochromic and photodetecting properties. Furthermore, we also developed a simple and efficient doping method to enhance the conductivity and photoresponsivity of micro-/nanocrystals using hydrazine. From experimental and theoretical studies, the mechanism was suggested as follows: the radicals in the singly occupied molecular orbital (SOMO) level of the ligands provide charge carriers that can undergo “through-space” transport between π–π stacked ligands and the electron transfer from adsorbed hydrazine to the SCNs results in reduction of energy gap, leading to increased conductivity. Our findings demonstrate a simple and powerful strategy for implementing coordination networks with redox ligands for micro-/nano-optoelectronic applications.
关键词： chiral self-discrimination,doping,micro-/nano-devices,optoelectronics,supramolecular coordination network
更新于2025-11-19 16:56:35
-
Effect of K2O addition on glass structure, complex impedance and energy storage density of NaNbO3 based glass-ceramics
摘要： (40-x)Na2O-xK2O-40Nb2O5-20SiO2 (x=0, 5, 10, 15mol%) glass-ceramics are synthesized by traditional melts method. The glass-ceramics are tested by X-ray diffraction (XRD) techniques, and NaNbO3 as major phase led a high permittivity. A microstructure with nanoscale grains enclosed by glass phase is observed by scanning electron microscope (SEM). With the increase of content of K2O, a relaxed glass network structure is obtained, and more kinds of phase are formed. Permittivity comes to 174 approximately when x=5mol%. In addition, the activation energy (Ea) of residual glass phase for Na2O-K2O-Nb2O5-SiO2 glass-ceramics firstly increase then decrease. Breakdown strength (BDS) of all samples increase and then decrease with the increase of content of K2O, and maximum BDS is obtained when x=10mol%. And maximum theoretical energy density is 1.43J/cm3 when x=5mol%.
关键词： breakdown strength,glass network structure,Na2O-K2O-Nb2O5-SiO2 glass-ceramics
更新于2025-11-14 17:28:48
-
TiO2-Coated Core-Shell Ag Nanowire Networks for Robust and Washable Flexible Transparent Electrodes
摘要： Silver nanowires (AgNWs) are the most promising materials to fabricate flexible transparent electrodes (FTEs) used in next-generation electronics. However, there are several bottlenecks for AgNWs-based FTEs to achieve large-scale applications, which are the thermal instability and rough surface topography of AgNWs and the poor interfacial adhesion between AgNWs and used substrate. To simultaneously address these aforementioned issues, a robust and washable FTE is prepared based on AgNW@TiO2 core-shell network embedding in polyimide (PI) substrate through a facile and scalable solution-based process. After treating with TiO2 sol, an ultra-thin, conformal, and continuous TiO2 shell is coated on AgNWs, which can effectively suppress the atomic surface diffusion. In comparison with pristine AgNW network that breaks into nanorods and nanospheres at 250 °C for 10 min, the AgNW@TiO2 core-shell network is stable at 300 °C, and its resistance just increases by a factor of 11 after annealing at 400 °C for 1 h. Furthermore, the TiO2 shell simultaneously increases the electrical and optical properties of AgNW network. After flowing PI precursors, drying, and thermally curing, the AgNW@TiO2 core-shell network is embedded on the surface of PI substrate with surface roughness of 1.9 nm. In addition to high thermal stability, the conductivity of the AgNWs@TiO2-PI composite FTE remains almost unchanged after repeated 3M tape peeling off cycles and mechanical bending cycles. It is also demonstrated that the AgNWs@TiO2-PI composite FTE is washable, and the relative change in resistance (?R/R0) is ~12% after 100 washing cycles in which a variety of stress situations occurring in combination.
关键词： flexible transparent electrodes,peeling off and mechanical stabilities,TiO2 sol,silver nanowire@TiO2 core-shell network,thermal and washing stabilities
更新于2025-11-14 14:32:36
-
Single infrared image enhancement using a deep convolutional neural network
摘要： In this paper, we propose a deep learning method for single infrared image enhancement. A fully convolutional neural network (CNN) is used to produce images with enhanced contrast and details. The conditional generative adversarial networks are incorporated into the optimization framework to avoid the background noise being amplified and further enhance the contrast and details. The existing convolutional neural network architectures, such as residual architectures and encoder–decoder architectures, fail to achieve the best results both in terms of network performance and application scope for infrared image enhancement task. To address this problem, we specifically design a new refined convolutional neural architecture that produces visually very appealing results with higher contrast and sharper details compared to other network architectures. Visible images are used for training since there are fewer infrared images. Proper training samples are generated to ensure that the network trained on visible images can be well applied to infrared images. Experiments demonstrate that our approach outperforms existing image enhancement algorithms in terms of contrast and detail enhancement. Code is available at https://github.com/Kuangxd/IE-CGAN.
关键词： Residual network,Enhancement,Infrared images,Deep learning,Encoder–decoder network,Generative adversarial network
更新于2025-09-23 15:23:52
-
[IEEE 2018 IEEE International Conference on Computer and Communication Engineering Technology (CCET) - Beijing, China (2018.8.18-2018.8.20)] 2018 IEEE International Conference on Computer and Communication Engineering Technology (CCET) - Elastic Optical Network Spectrum Fragmentation Algorithm
摘要： Aiming at spectrum allocation problem in elastic optical networks, a spectrum allocation method that combines the advantages of genetic algorithm and ant colony algorithm is proposed. This method uses genetic algorithm to generate the initial solution with rapid random population global search ability. Then the initial solution of the genetic algorithm is transformed into the initial distribution of pheromone required by the ant colony algorithm using the cohesion strategy. Finally, the positive feedback and efficient convergence of the ant colony algorithm are used. Features Find the optimal solution and provide a solution for improving network efficiency
关键词： Network Spectrum,Elastic Optical Network,Fragmentation Algorithm
更新于2025-09-23 15:23:52
-
Biometric iris recognition using radial basis function neural network
摘要： The consistent and efficient method for the identification of biometrics is the iris recognition in view of the fact that it has richness in texture information. A good number of features performed in the past are built on handcrafted features. The proposed method is based on the feed-forward architecture and uses k-means clustering algorithm for the iris patterns classification. In this paper, segmentation of iris is performed using the circular Hough transform that realizes the iris boundaries in the eye and isolates the region of iris with no eyelashes and other constrictions. Moreover, Daugman's rubber sheet model is used to transform the resultant iris portion into polar coordinates in the process of normalization. A unique iris code is generated by log-Gabor filter to extract the features. The classification is achieved using neural network structures, the feed-forward neural network and the radial basis function neural network. The experiments have been conducted using the Chinese Academy of Sciences Institute of Automation (CASIA) iris database. The proposed system decreases computation time, size of the database and increases the recognition accuracy as compared to the existing algorithms.
关键词： Feed-forward neural network (FNN),Iris segmentation,Normalization,Biometrics,Radial basis function neural network (RBFNN),Iris recognition
更新于2025-09-23 15:23:52
-
Analysis of the Cost and Energy Efficiency of Future Hybrid and Heterogeneous Optical Networks
摘要： Orthogonal frequency division multiplexing (OFDM) promises to provide the necessary boost in the core networks’ capacity along with the required flexibility in order to cope with the Internet’s growing heterogeneous traffic. At the same time, wavelength division multiplexing (WDM) technology remains a cost-effective and reliable solution especially for long-haul transmission. Due to the higher implementation cost of optical OFDM transmission technology, it is expected that OFDM-based bandwidth variable transponders (BVT) will co-exist with conventional WDM ones. In this paper, we provide an integer linear programming (ILP) formulation that minimizes the cost and power consumption of such hybrid architecture and then a comparison is made with a pure OFDM-based elastic optical network (EON) and a mixed line rate (MLR) WDM optical network in order to evaluate their cost and energy efficiency.
关键词： ILP,WDM,Hybrid Optical Network,Elastic Optical Network,Bandwidth Variable Transponder
更新于2025-09-23 15:23:52
-
[IEEE 2018 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI) - Guangzhou, China (2018.10.8-2018.10.12)] 2018 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI) - An Efficient Recognition Method for Incomplete Iris Image Based on CNN Model
摘要： The iris of the eye is a research hot spot in the field of biometric identification because of its uniqueness, non-contact and bioactivity. The incompleteness of the iris caused by the acquisition process has brought great uncertainty to the subsequent iris region segmentation and iris code matching, thereby reducing the efficiency of iris recognition. This paper describes a deep convolution neural network model with adaptive incomplete iris preprocessing mechanism. Based on the normalization of the iris image, the incomplete iris preprocessing mechanism adopts the method of making the inner circle or the outer circle. The iris region can be segmented by the line fitting and the circle fitting method for extracting as many iris features as possible. The deep convolution neural network then uses pixel coding of Irregular iris regions to complete the iris pattern classification. The model fully utilizes the characteristics of deep learning, local feature characterization and weight sharing, and realizes the problem of using large sample to compensate the incomplete feature of local feature. The experimental results show that this method has significant accuracy improvement compared with the traditional algorithms.
关键词： iris recognition,convolution neural network,iris image normalization,algorithm
更新于2025-09-23 15:23:52