- 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
-
[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) - Lightweight Security Signaling Mechanism in Optical Network for Smart Power Grid
摘要： The communication security issue brought by Smart Grid is of great importance and should not be ignored in backbone optical networks. With the aim to solve this problem, this paper firstly conducts deep analysis into the security challenge of optical network under smart power grid environment and proposes a so-called lightweight security signaling mechanism of multi-domain optical network for Energy Internet. The proposed scheme makes full advantage of current signaling protocol with some necessary extensions and security improvement. Thus, this lightweight security signaling protocol is designed to make sure the end-to-end trusted connection. Under the multi-domain communication services of smart power grid, evaluation simulation for the signaling interaction is conducted. Simulation results show that this proposed approach can greatly improve the security level of large-scale multi-domain optical network for smart power grid with better performance in term of connection success rate performance.
关键词： Smart grid,security signaling,signaling encryption,multi-domain optical network,trusted connection
更新于2025-09-23 15:22:29
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Integration of Worldview-2 and Lidar Data to MAP a Subtropical Forest Area: Comparison of Machine Learning Algorithms
摘要： This work is committed to explore the integration of airborne LiDAR data and WorldView-2 (WV-2) images to classify land cover and land use in a rural area with the presence of a subtropical forest. Different methods were used for this purpose: two artificial neural networks (ANN) and three decision trees forests. The results demonstrated that the inclusion of LiDAR data significantly improved the classifications in all methods. Excluding the Convolutional Neural Network, the classification algorithms had a nearly similar performance, and none of them achieved the best accuracy for all adopted classes. Forest by Penalizing Attributes (FPA) attained the best general result, with a Kappa index of 0.92, while Rotation Forest obtained the best result in the classification of the two vegetation classes.
关键词： Artificial Neural Network,Data fusion,Forest succession stages,Decision Forest
更新于2025-09-23 15:22:29
-
High Efficient Deep Feature Extraction and Classification of Spectral-Spatial Hyperspectral Image Using Cross Domain Convolutional Neural Networks
摘要： Recently, numerous remote sensing applications highly depend on the hyperspectral image (HSI). HSI classification, as a fundamental issue, has attracted increasing attention and become a hot topic in the remote sensing community. We implemented a regularized convolutional neural network (CNN), which adopted dropout and regularization strategies to address the overfitting problem of limited training samples. Although many kinds of the literature have confirmed that it is an effective way for HSI classification to integrate spectrum with spatial context, the scaling issue is not fully exploited. In this paper, we propose a high efficient deep feature extraction and the classification method for the spectral-spatial HSI, which can make full use of multiscale spatial feature obtained by guided filter. The proposed approach is the first attempt to lean a CNN for spectral and multiscale spatial features. Compared to its counterparts, experimental results show that the proposed method can achieve 3% improvement in accuracy, according to various datasets such as Indian Pines, Pavia University, and Salinas.
关键词： Convolutional neural network (CNN),hyperspectral image (HSI) classification,guided filter,spectral-spatial fusion
更新于2025-09-23 15:22:29
-
Experimental study and prediction on impact scratching of single abrasive for K9 glass
摘要： The orthogonal test L16 (43) was designed, and the impact scratching experiment for K9 glass was carried out by using Vickers diamond indenter on the DMG ULTRASONIC 70-5 linear. The three-dimensional morphology of the surface for glass was observed by scanning electron microscope (SEM), which was compared with that in the quasi static state. The strain rate of the grinding process was obtained by choosing the contact zone length as the impact contact length, which was the evaluation Index of impact. The relationships between strain rate and the depth of radial crack, strain rate and the depth of transverse crack, strain rate and normal scratching force were first analysed. The results showed that the depth of radial of crack, the depth of transversal crack and the normal scratching force decreased with the increase of strain rate. The two-layer BP neural network was established, which took the strain rate as input variables. The depth of radial crack, the depth of transversal crack and normal scratching force were predicted and the errors were within 10%, which indicated that the prediction results of BP neural network were reliable.
关键词： impact scratching,depth of crack,strain rate,BP neural network,K9 glass
更新于2025-09-23 15:22:29
-
Fuzzy neural network vibration control on a piezoelectric flexible hinged plate using stereo vision detection
摘要： Vibration control on a two-connected piezoelectric flexible hinged plate is investigated, using a fuzzy neural network algorithm based on binocular vision measurement. As for vision sensing, a method to acquire vibration signals of the low frequency bending and torsional mode is investigated. To damp out the residual vibration quickly, the fuzzy neural network is applied to ensure the stability and control effect adaptively. To verify the stereo vision measurement method and the applied controller, an experimental setup of the piezoelectric flexible hinged plate with a binocular stereo vision is constructed. Experiments are conducted by using the binocular stereo vision measurement system and the adopted controller. The experimental results demonstrate the feasibility of the visual measurement method. Furthermore, the designed fuzzy neural network can attenuate the bending and torsional vibrations quickly, in comparison with proportional and derivative control, particularly for the small-level residual vibration.
关键词： Piezoelectric flexible hinged plate,binocular vision measurement,experiments,vibration control,fuzzy neural network algorithm
更新于2025-09-23 15:22:29
-
Automatic thyroid nodule recognition and diagnosis in ultrasound imaging with the YOLOv2 neural network
摘要： Background: In this study, images of 2450 benign thyroid nodules and 2557 malignant thyroid nodules were collected and labeled, and an automatic image recognition and diagnosis system was established by deep learning using the YOLOv2 neural network. The performance of the system in the diagnosis of thyroid nodules was evaluated, and the application value of artificial intelligence in clinical practice was investigated. Methods: The ultrasound images of 276 patients were retrospectively selected. The diagnoses of the radiologists were determined according to the Thyroid Imaging Reporting and Data System; the images were automatically recognized and diagnosed by the established artificial intelligence system. Pathological diagnosis was the gold standard for the final diagnosis. The performances of the established system and the radiologists in diagnosing the benign and malignant thyroid nodules were compared. Results: The artificial intelligence diagnosis system correctly identified the lesion area, with an area under the receiver operating characteristic (ROC) curve of 0.902, which is higher than that of the radiologists (0.859). This finding indicates a higher diagnostic accuracy (p = 0.0434). The sensitivity, positive predictive value, negative predictive value, and accuracy of the artificial intelligence diagnosis system for the diagnosis of malignant thyroid nodules were 90.5%, 95.22%, 80.99%, and 90.31%, respectively, and the performance did not significantly differ from that of the radiologists (p > 0.05). The artificial intelligence diagnosis system had a higher specificity (89.91% vs 77.98%, p = 0.026). Conclusions: Compared with the performance of experienced radiologists, the artificial intelligence system has comparable sensitivity and accuracy for the diagnosis of malignant thyroid nodules and better diagnostic ability for benign thyroid nodules. As an auxiliary tool, this artificial intelligence diagnosis system can provide radiologists with sufficient assistance in the diagnosis of benign and malignant thyroid nodules.
关键词： Thyroid nodules,Ultrasound,Artificial intelligence,Computer-aided diagnosis systems,YOLOv2 neural network
更新于2025-09-23 15:22:29
-
Three-Dimensional Resource Allocation in Space Division Multiplexing Elastic Optical Networks
摘要： In this paper, we present a comprehensive model to address three-dimensional resource assignment (3D-RA) in space division multiplexing elastic optical networks using few-mode multi-core fibers (FM-MCFs). Accordingly, we present new 3D-RA algorithms in which the consequential resources include the spectrum, modes, and cores. We consider all spectral and spatial diversity types in FM-MCFs and introduce five 3D-RA scenarios including (i) single-mode and single-core (SMSC), (ii) single-mode and multi-core (SMMC), (iii) multi-mode and single-core (MMSC), (iv) multi-mode and multi-core (MMMC), and finally, (v) hybrid 3D-RA. In each scenario, the fractional joint (FrJ-) and independent (Ind-) switching (Sw) schemes are introduced and explored for the proposed scenarios. By using the FrJ- and Ind-Sw schemes, we performed the simulation process for the above-mentioned scenarios. The simulation results confirm the efficiency of the proposed 3D-RA algorithms. Furthermore, various 3D-RA scenarios are comprehensively compared using the obtained results in terms of vital metrics introduced in this work. It is also indicated that the SMSC and MMSC scenarios present superior performance for Ind-Sw and FrJ-Sw 3D-RA scenarios, respectively, in comparison to other proposed non-hybrid scenarios. The obtained results also reveal that the quad-hybrid 3D-RA scenario results in the lowest blocking probability in comparison with all other introduced scenarios in both switching schemes. These results recommend an efficient simulation system for compatible transceivers for Ind- and FrJ-Sw schemes.
关键词： Spectral and spatial resource allocation,Few mode-multi core fiber,Space division multiplexing,Elastic optical network
更新于2025-09-23 15:22:29
-
Infrared super-resolution imaging using multi-scale saliency and deep wavelet residuals
摘要： Infrared (IR) imaging systems with low-density focal plane arrays produce images with poor spatial resolution. To address this limitation, super-resolution (SR) algorithms can be applied on IR-low resolution (LR) images. In this paper, we present a new SR technique based on the multi-scale saliency detection and the residuals learned by the deep convolutional neural network (CNN) in the wavelet domain (DWCNN). The input LR image is processed in the transformed domain by applying 2D discrete wavelet transform. It decomposes an image into its low-frequency and high-frequency subbands. The multi-scale saliency detection is used to extract small scale and large scale salient feature maps from the bicubic upscaled LR image. These maps are incorporated in the high-frequency subbands of the LR image. Furthermore, the low-frequency and high-frequency subands are re?ned using the residuals learned by the DWCNN in training phase. The proposed algorithm is compared with the conventional and state-of-the-art SR methods. Results indicate that our method yields good reconstruction quality with high peak signal to ratio, structural similarity and low blur indices. Besides, our method requires less computational time.
关键词： Infrared imaging,Convolutional neural network,Discrete wavelet transform,Multi-scale saliency,Super-resolution
更新于2025-09-23 15:22:29
-
[IEEE 2018 26th European Signal Processing Conference (EUSIPCO) - Rome (2018.9.3-2018.9.7)] 2018 26th European Signal Processing Conference (EUSIPCO) - DeepMQ: A Deep Learning Approach Based Myelin Quantification in Microscopic Fluorescence Images
摘要： Oligodendrocytes wrap around the axons and form the myelin. Myelin facilitates rapid neural signal transmission. Any damage to myelin disrupts neuronal communication leading to neurological diseases such as multiple sclerosis (MS). There is no cure for MS. This is, in part, due to lack of an efficient method for myelin quantification during drug screening. In this study, an image analysis based myelin sheath detection method, DeepMQ, is developed. The method consists of a feature extraction step followed by a deep learning based binary classification module. The images, which were acquired on a confocal microscope contain three channels and multiple z-sections. Each channel represents either oligodendroyctes, neurons, or nuclei. During feature extraction, 26-neighbours of each voxel is mapped onto a 2D feature image. This image is, then, fed to the deep learning classifier, in order to detect myelin. Results indicate that 93.38% accuracy is achieved in a set of fluorescence microscope images of mouse stem cell-derived oligodendroyctes and neurons. To the best of authors’ knowledge, this is the first study utilizing image analysis along with machine learning techniques to quantify myelination.
关键词： neural network,microscopic fluorescence imaging,myelin,deep learning,LeNet
更新于2025-09-23 15:22:29
-
[IEEE 2017 International Conference on Optical Network Design and Modeling (ONDM) - Budapest (2017.5.15-2017.5.18)] 2017 International Conference on Optical Network Design and Modeling (ONDM) - Orchestrating data-intensive vNF service chains in inter-DC elastic optical networks
摘要： We investigate the problem of data-intensive vNF service chain (vNF-SC) orchestration in inter-datacenter EONs. After analyzing the N P-hardness of this problem, we solve it in a sequential manner by optimizing both the request serving sequence and the data-intensive vNF-SC orchestration. Specifically, we propose a request sorting algorithm and a data-intensive vNF-SC orchestration algorithm based on dynamic programming to minimize the service completion time. We conduct simulations to evaluate the proposed algorithms, and simulation results verify their effectiveness.
关键词： Network Function Virtualization,vNF Service Chain,Bulk-Data Transfer,Elastic optical networks
更新于2025-09-23 15:22:29