- 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
-
Routing, spectrum and core assignment algorithms for protection of space division multiplexing elastic optical networks
摘要： Protection is a key issue in optical networks, mainly in spacial division multiplexing (SDM) elastic optical networks (EONs) as these handle the increasing amount of heterogeneous Internet traffic. In this paper, we address protection in SDM-EONs including inter-core crosstalk. We introduce three algorithms, designed to provide 100% protection from single failures. Extensive simulation is used to show that the proposed algorithms prevents the formation of network bottlenecks, thus maintaining the protection of the connections.
关键词： Elastic optical network with space division multiplexing,Survivability,Multi-core fiber
更新于2025-09-23 15:23:52
-
Improved reflection technique for the permittivity measurement of ferrites using slotted coaxial samples
摘要： This paper presents the effect of magnetic permeability on the permittivity measurement using coaxial line reflection technique. It discusses in detail about the design aspects, analysis and simulation of the slotted co-axial sample and fixture for dielectric characterization of the ferrites and garnets possessing both dielectric and magnetic properties. This technique makes use of improved coaxial fixture and APC 07 compatible slotted coaxial sample geometry to measure the complex permittivity of the ferrite material. Permittivity is calculated from the impedance of sample loaded fixture, which is independent of magnetic permeability, because of air slot cut in the coaxial hollow cylindrical sample along the length. Characterization data of dielectrics and ferrites is used in design of ferrite circulators, and pulse magnets for particle accelerator applications. This is also used in many other RF applications including design of dielectric resonator for spin wave line width measurement of ferrites. Design work is aimed at accurate measurement of complex permittivity; using reflection measurement in coaxial fixture over a wide frequency range of 20 kHz to 1 GHz. Reflection measurement technique is further explored for accurate measurement of complex permittivity.
关键词： Complex permittivity,Network analyzer,Coaxial open ended fixture,Wide band measurement technique
更新于2025-09-23 15:23:52
-
Remote sensing images super-resolution with deep convolution networks
摘要： Remote sensing image data have been widely applied in many applications, such as agriculture, military, and land use. It is difficult to obtain remote sensing images in both high spatial and spectral resolutions due to the limitation of implements in image acquisition and the law of energy conservation. Super-resolution (SR) is a technique to improve the resolution from a low-resolution (LR) to a high-resolution (HR). In this paper, a novel deep convolution network (DCN) SR method (SRDCN) is proposed. Based on hierarchical architectures, the proposed SRDCN learns an end-to-end mapping function to reconstruct an HR image from its LR version; furthermore, extensions of SRDCN based on residual learning and multi scale version are investigated for further improvement, namely Developed SRDCN(DSRDCN) and Extensive SRDCN(ESRDCN). Experimental results using different types of remote sensing data (e.g., multispectral and hyperspectral) demonstrate that the proposed methods outperform the traditional sparse representation based methods.
关键词： Convolution neural network,Remote sensing imagery,Super-resolution
更新于2025-09-23 15:23:52
-
On the efficient optimization of unicast, anycast and multicast flows in survivable elastic optical networks
摘要： The paper investigates efficient allocation of three types of flows (unicast, anycast, multicast) in elastic optical network with dedicated path protection. We model the problem as an integer linear programming and propose efficient solution methods: greedy randomized algorithm (GRA) and column generation (CG)-based approach implemented in two versions, which differ in the method used to find a final problem solution for the selected columns. Then, we evaluate in detail methods efficiency with respect to four reference algorithms. What is more, for CG-based methods we use five different algorithms to find initial sets of columns and, by these means, evaluate how the quality of these methods influences the efficiency of CG-based approaches. The simulation results show that the proposed GRA significantly outperforms reference greedy methods and finds very good solutions (the average gap to optimal result was not higher than 13.4%). The CG-based methods allow to further improve results and obtain solutions very close to optimal ones (for the best CG-based version, the highest average gap to optimal result was 2.1%). Moreover, the results show that the traffic pattern influences the algorithms performance. The methods perform the best for scenarios with high amount of multicast volume while high anycast volume brings the most difficult problem instances. Eventually, the study reveals that the efficiency of CG-based methods depends strongly on the quality of initial columns as well as on the method used to find final solution for the selected columns.
关键词： Network optimization,Multicast traffic,Anycast traffic,Column generation technique,Elastic optical networks,Dedicated path protection
更新于2025-09-23 15:23:52
-
Stability and Spectral Properties of General Tree-Shaped Wave Networks with Variable Coefficients
摘要： The stability of general tree-shaped wave networks with variable coefficients under boundary feedback controls is considered. Making full use of the tree-shaped structures, we present a detailed asymptotic spectral analysis of the networks. By proposing the from-root-to-leaf calculating technique, we deduce an explicit recursive expression for the asymptotic characteristic equation and the spectral properties are further obtained. We show that the spectrum-determined-growth (SDG) condition holds. Thus the stability analysis of the closed-loop system can be completely converted to the infimum estimation of the asymptotic characteristic equation. Especially, we further show that the infimum is positive so as to obtain the exponential stability by estimating the recursive expression in from-leaf-to-root order. Some numerical simulations are presented to illustrate and support the theoretical results.
关键词： Exponential stability,Variable coefficient,Spectrum-determined-growth (SDG) condition,Recursive characteristic equation,Feedback control,Wave network
更新于2025-09-23 15:23:52
-
Disparate effects of DOM extracted from coastal seawaters and freshwaters on photodegradation of 2,4-Dihydroxybenzophenone
摘要： As the rapid development of deep learning techniques, extensive interest has been taken into the applications of deep learning methods on challenging problems of different domains. In view of the recent success of convolutional neural network (CNN) in various tasks of audio analysis, a comparative performance study of different the-state-of-the-art CNN architectures on a large-scale whale-call classification task is investigated in this paper. On the basis of deep neural network models, distinctive features of whale sub-populations are extracted to obtain higher level abstract representations for the accurate classification, which is significantly superior to the traditional classification approaches using manual features based on expert knowledge. In particular, a large open-source acoustic dataset recorded by audio sensors carried by whales in different locations is employed for performance comparison. Based on the experiments, it is found that the advancement of popular CNN architectures significantly improve the accuracy on the whale-call classification task. The accuracy and computational efficiency varies with the change of the CNN architectures. Xception provides the best performance among all four CNN architectures while an ensemble of CNN models can produce even better results.
关键词： deep learning,whale call classification,convolutional neural network
更新于2025-09-23 15:23:52
-
Syntheses, Crystal Structures, and Fluorescence Properties of Two 2D→2D Coordination Polymers Based on the Flexible 4-Substituted Bis(1,2,4-triazole) Ligand
摘要： Two new 2D → 2D zinc(II) coordination polymers, [Zn(btre)0.5(nbdc)(H2O)]n (1) and {[Zn(btre)0.5(MeOip)(H2O)2]·H2O}n (2) (btre = 1,2-bis(1,2,4-triazol-4-yl)ethane, nbdc=3-nitro-1,2-benzenedicarboxylate, MeOip=4-methoxybenzene-1,3-dicarboxylate) were synthesized at room temperature condition and characterized by IR spectra, elemental analyses, single-crystal and powder X-ray diffractions. Three sets of equivalent 2D (6, 3) networks parallel polycatenated with each other to give a 2D → 2D network in 1 and 2. There are strong π-π interactions and hydrogen bonding interactions between adjacent parallel polycatenated 2D (6, 3) network in 1. Only hydrogen bonding interactions exist in 2. Thermal stabilities and luminescence of 1 and 2 were investigated.
关键词： 2D (6, 3) network,luminescence,1,2-bis(1,2,4-triazol-4-yl)ethane,3-fold interpenetration
更新于2025-09-23 15:23:52
-
DeepSpectra: An end-to-end deep learning approach for quantitative spectral analysis
摘要： Learning patterns from spectra is critical for the development of chemometric analysis of spectroscopic data. Conventional two-stage calibration approaches consist of data preprocessing and modeling analysis. Misuse of preprocessing may introduce artifacts or remove useful patterns and result in worse model performance. An end-to-end deep learning approach incorporated Inception module, named DeepSpectra, is presented to learn patterns from raw data to improve the model performance. DeepSpectra model is compared to three CNN models on the raw data, and 16 preprocessing approaches are included to evaluate the preprocessing impact by testing four open accessed visible and near infrared spectroscopic datasets (corn, tablets, wheat, and soil). DeepSpectra model outperforms the other three convolutional neural network models on four datasets and obtains better results on raw data than in preprocessed data for most scenarios. The model is compared with linear partial least square (PLS) and nonlinear artificial neural network (ANN) methods and support vector machine (SVR) on raw and preprocessed data. The results show that DeepSpectra approach provides improved results than conventional linear and nonlinear calibration approaches in most scenarios. The increased training samples can improve the model repeatability and accuracy.
关键词： model accuracy,Inception,convolutional neural network,chemometrics,repeatability
更新于2025-09-23 15:23:52
-
FRED-Net: Fully Residual Encoder-Decoder Network for Accurate Iris Segmentation
摘要： Iris recognition is now developed enough to recognize a person from a distance. The process of iris segmentation plays a vital role in maintaining the accuracy of the iris-based recognition systems by limiting the errors at the current stage. However, its performance is affected by non-ideal situations created by environmental light noise and user non-cooperation. The existing local feature-based segmentation methods are unable to find the true iris boundary in these non-ideal situations, and the error created at the segmentation stage traverses to all the subsequent stages, which results in reduced accuracy and reliability. In addition, it is necessary to segment the true iris boundary without the extra cost of denoising as preprocessing. To overcome these challenging issues during iris segmentation, a deep learning-based fully residual encoder-decoder network (FRED-Net) is proposed to determine the true iris region with the flow of high-frequency information from the preceding layers via residual skip connection. The main four impacts and significances of this study are as follows. First, FRED-Net is an end-to-end semantic segmentation network that does not use conventional image processing schemes, and does not have a preprocessing overhead. It is a standalone network in which eyelid, eyelash, and glint detections are not required to obtain the true iris boundary. Second, the proposed FRED-Net is the final resultant structure of a step-by-step development, and in each step, a new complete variant network is created for semantic segmentation considering the detailed descriptions of the networks. Third, FRED-Net uses the residual connectivity between convolutional layers by the residual shortcut for both encoder and decoder, which enables a high-frequency component to flow through the network and achieve higher accuracy with few layers. Fourth, the performance of the proposed FRED-Net is tested with five different iris datasets under visible and NIR light environments, and two general road scene segmentation datasets. To achieve fair comparisons with other studies, our trained FRED-Net models, along with the algorithms, are made publicly available through our website (Dongguk FRED-Net Model with Algorithm. accessed on 16 May 2018). The experiments include two datasets: Noisy Iris Challenge Evaluation - Part II (NICE-II) selected from the UBIRIS.v2 database and Mobile Iris Challenge Evaluation (MICHE-I), for the visible light environment and three datasets: Institute of Automation, Chinese Academy of Sciences (CASIA) v4.0 interval, v4.0 distance, and IIT Delhi v1.0, for the near-infrared (NIR) light environment. Moreover, to evaluate the performance of the proposed network in general segmentation, experiments with two famous road scene segmentation datasets: Cambridge-driving Labeled Video Database (CamVid) and Karlsruhe Institute of Technology and Toyota Technological Institute at Chicago (KITTI), are included. The experimental results showed the optimum performance of the proposed FRED-Net on the above-mentioned seven datasets of iris and general road scene segmentation.
关键词： iris segmentation,full residual encoder-decoder network,Iris recognition,semantic segmentation
更新于2025-09-23 15:23:52
-
Polarization Reconfigurable Corner Truncated Square Microstrip Array Antenna
摘要： In this paper, a simple 2 × 2 polarization reconfigurable planar microstrip array antenna is presented. It is based on electrical switching technology using PIN diodes. Each element of the array is excited with the aid of the corporate feed technique. Each element of the proposed structure consists of a corner truncated square patch connected to parasitic triangular conductors by means of PIN diodes. The array element is configured to facilitate linear polarization (LP), right-hand circular polarization (RHCP) or left-hand circular polarization (LHCP) by means of 4 independently biased PIN diodes. The proposed antenna is designed and simulated using electromagnetic simulation software CST Microwave Studio. In order to experimentally validate the design, a prototype is fabricated on a 1.6 mm thick RT Duroid substrate of relative permittivity εr = 2.2. The performance of the antenna is validated experimentally using 16 PIN diodes. The simulation and measured results for all the polarization states of the array antenna are found to be in good agreement. The measured results have established the polarization reconfigurable ability of the antenna for 5.7–6.0 GHz operating band. The proposed antenna is suitable for C-band point-to-point communication applications.
关键词： PIN diode switch,polarization reconfigurable,corporate feed network,reconfigurable antenna,Array antenna,circular polarization
更新于2025-09-23 15:23:52