- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Screw-Shaped Plastic Optical Fibers for Refractive Index Sensing
摘要： This paper reports a novel nonlinear algorithm for retrieving near surface air temperature over a large area using support vector machines with satellite remote sensing and other types of data. The steps include the following. 1) Establish the 1st sub model learning dataset and validation dataset, then obtain the 2nd to f th sub model learning datasets and validation datasets, using unmanned weather station data and prede?ned in?uential variables. 2) Retrieve Ta of the target area. 3) Correct the generated Ta images based on prediction errors using the inverse distance weighting interpolation. The novelty of this algorithm is to apply multiple sources of remote sensing data combined with data of unmanned weather stations, topography, ground cover, DEM, and astronomy and calendar rules. The results indicated that the model has high accuracy, reliability, and generalization ability. Factors such as cloudiness, ground vegetation, and water vapor show little interference, so the model seems suitable for large area retrieving under natural conditions. The required high-performance computation was achieved by a CPU + GPU isomery and synergy parallel computation system that improved computing speed by more than 1000-fold, with easily extendable computing capability. We found that the current algorithm is superior to seven major split-window algorithms and their best combined algorithms based on prediction errors, root-mean-square errors, and the percentage of data points with <3 ?C absolute error. Our SVM approach overcomes shortcomings of classical temperature remote sensing technologies, and is the ?rst report of such application.
关键词： high-performance computation (HPC),moderate-resolution imaging spectroradiometer (MODIS),digital elevation model (DEM),Area-wide retrieving,GIS spatial analysis,remote sensing,satellite,multivariable analysis,support vector machine (SVM)
更新于2025-09-16 10:30:52
-
Knowledge Discovery in Nanophotonics Using Geometric Deep Learning
摘要： We present here a distinctive approach for using the intelligence aspects of artificial intelligence for knowledge discovery rather than the conventional task of device optimization in electromagnetic (EM) nanostructures. This approach uses training data obtained through full-wave EM simulations of a series of nanostructures to train geometric deep learning algorithms to assess the range of feasible responses as well as the feasibility of a desired response from a class of nanophotonic structures. To facilitate the knowledge discovery and reduce the computation complexity, our approach combines the dimensionality reduction technique (using an autoencoder) with convex-hull and one-class support-vector-machine (SVM) algorithms to find the range of the feasible responses in the latent (or the reduced) response space of the EM nanostructure. We show that by using a small set of training instances (compared to all possible structures), our approach can provide better than 95% accuracy in assessing the feasibility of a given response. More importantly, the one-class SVM algorithm can be trained to provide the degree of feasibility (or unfeasibility) of a response from a given nanostructure. This important information can be used to modify the initial structure to an alternative one that can enable an initially unfeasible response. To show the applicability of our approach, we apply it to two important classes of binary metasurfaces (MSs), formed by an array of plasmonic nanostructures, and periodic MSs formed by an array of dielectric nanopillars. In addition to theoretical results, we show the experimental results obtained by fabricating several MSs of the second class. Our theoretical and experimental results confirm the unique features of this approach for knowledge discovery in nanophotonics applications.
关键词： convex-hull,one-class SVM,geometric deep learning,knowledge discovery,nanophotonics,autoencoder,electromagnetic nanostructures
更新于2025-09-12 10:27:22
-
Determination of the bruise degree for cherry using Vis-NIR reflection spectroscopy coupled with multivariate analysis
摘要： Determination and classification of the bruise degree for cherry can improve consumer satisfaction with cherry quality and enhance the industry’s competiveness and profitability. In this study, visible and near infrared (Vis-NIR) reflection spectroscopy was used for identifying bruise degree of cherry in 350–2500 nm. Sampling spectral data were extracted from normal, slight and severe bruise samples. Principal component analysis (PCA) was implemented to determine the first few principal components (PCs) for cluster analysis among samples. Optimal wavelengths were selected by loadings of PCs from PCA and successive projection algorithm (SPA) method, respectively. Afterwards, these optimal wavelengths were empolyed to establish the classification models as inputs of least square-support vector machine (LS-SVM). Better performance for qualitative discrimination of the bruise degree for cherry was emerged in LS-SVM model based on five optimal wavelengths (603, 633, 679, 1083, and 1803 nm) selected directly by SPA, which showed acceptable results with the classification accuracy of 93.3%. Confusion matrix illustrated misclassification generally occurred in normal and slight bruise samples. Furthermore, the latent relation between spectral property of cherries in varying bruise degree and its firmness and soluble solids content (SSC) was analyzed. The result showed both colour, firmness and SSC were consistent with the Vis-NIR reflectance of cherries. Overall, this study revealed that Vis-NIR reflection spectroscopy integrated with multivariate analysis can be used as a rapid, intact method to determine the bruise degree of cherry, laying a foundation for cherry sorting and postharvest quality control.
关键词： LS-SVM,Vis-NIR reflection spectroscopy,cherry,bruise degree,multivariate analysis
更新于2025-09-12 10:27:22
-
Fault diagnosis method of photovoltaic array based on support vector machine
摘要： Photovoltaic (PV) arrays are prone to various faults due to the hostile working environment. This paper presents the fault diagnosis algorithm based on support vector machine (SVM) to detect short circuit, open circuit, and lack of irradiation faults that occurred in PV arrays. By analyzing these faults and I–V characteristic curves of PV arrays, the short-circuit current, open-circuit voltage, maximum-power current, and maximum-power voltage are chosen as input parameters of SVM-based fault diagnosis algorithm. The data pre-processing methods are used to improve the quality of fault data set considering the effects of the quality on the performance of SVM-based fault diagnosis algorithm. The grid search and k-fold cross-validation methods are proposed to optimize the parameters of the SVM-based fault diagnosis algorithm. It gets test accuracy of 97% by testing the trained SVM-based fault diagnosis algorithm with 400 data. The experimental results indicate that the SVM-based fault diagnosis algorithm has higher accuracy and generalization ability than other algorithm for fault diagnosis of PV arrays.
关键词： k-fold cross-validation,PV arrays,data preprocessing,grid search,SVM-based fault diagnosis algorithm
更新于2025-09-12 10:27:22
-
[IEEE 2018 7th International Conference on Agro-geoinformatics (Agro-geoinformatics) - Hangzhou (2018.8.6-2018.8.9)] 2018 7th International Conference on Agro-geoinformatics (Agro-geoinformatics) - Study on Extraction Methods of Rape Area Based on GF-1 Satellite Image
摘要： The GF-1 WFV image on April 3, 2017 was selected to extract the cultivated area of rape in Haimen city of Jiangsu province. Vegetation indexes and texture features were extracted from the original spectrum data in order to extract rape area with Maximum Likelihood Classifier (MLC) and Support Vector Machine (SVM). The extraction accuracy of rape was verified through on-site GPS measurement of 4 ground samples area with the scale of 500 m × 500 m. The rape area extraction accuracy of the combination which contained spectrum and vegetation indexes was 71.28% that was the highest among all combinations. It indicated that the GF-1 satellite image can be used for monitoring the cultivated area of rape and it has higher accuracy and broad application prospects in the field of agriculture remote sensing monitoring.
关键词： classification characteristic,SVM,MLC,rape
更新于2025-09-11 14:15:04
-
Image-Based Visibility Estimation Algorithm for Intelligent Transportation Systems
摘要： Posted road speed limits contribute to the safety of driving, yet when certain driving conditions occur, such as fog or severe darkness, they become less meaningful to the drivers. To overcome this limitation, there is a need for adaptive speed limits system to improve road safety under varying driving conditions. In that vein, a visibility range estimation algorithm for real-time adaptive speed limits control in intelligent transportation systems is proposed in this paper. The information required to specify the speed limit is captured via a road side unit that collects environmental data and captures road images, which are then analyzed locally or on the cloud. The proposed analysis is performed using two image processing algorithms, namely, the improved dark channel prior (DCP) and weighted image entropy (WIE), and the support vector machine (SVM) classi?er is used to produce a visibility indicator in real-time. Results obtained from the analysis of various parts of highways in Canada, provided by the Ministry of Transportation of Ontario (MTO), show that the proposed technique can generate credible visibility indicators to motorists. The analytical results corroborated by extensive ?eld measurements con?rmed the advantage of the proposed system when compared to other visibility estimation methods such as the conventional DCP and WIE, where the proposed system results exhibit about 25% accuracy enhancement over the other considered techniques. Moreover, the proposed DCP is about 26% faster than the conventional DCP. The obtained promising results potentiate the integration of the proposed technique in real-life scenarios.
关键词： image processing,dark channel prior,intelligent transportation system,SVM,Visibility,smart cities,entropy,machine learning
更新于2025-09-11 14:15:04
-
Coarse-to-Fine Extraction of Small-Scale Lunar Impact Craters From the CCD Images of the Chang'E Lunar Orbiters
摘要： Lunar impact craters form the basis for lunar geological stratigraphy, and small-scale craters further enrich the basic statistical data for the estimation of local geological ages. Thus, the extraction of lunar impact craters is an important branch of modern planetary studies. However, few studies have reported on the extraction of small-scale craters. Therefore, this paper proposes a coarse-to-fine resolution method to automatically extract small-scale impact craters from charge-coupled device (CCD) images using histogram of oriented gradient (HOG) features and a support vector machine (SVM) classifier. First, large-scale craters are extracted as samples from the Chang'E-1 images with spatial resolutions of 120 m. The SVM classifier is then employed to establish the criteria for classifying craters and noncraters from the HOG features of the extracted samples. The criteria are then used to extract small-scale craters from higher resolution Chang'E-2 CCD images with spatial resolutions of 1.4, 7, and 50 m. The sample database is updated with the newly extracted small-scale craters for the purpose of the progressive optimization of the extraction. The proposed method is tested on both simulated images and multiple resolutions of real CCD images acquired by the Chang'E orbiters and provides high accuracy results in the extraction of the small-scale impact craters, the smallest of which is 20 m.
关键词： small-scale impact craters,Chang'E satellites,charge-coupled device (CCD) images,support vector machine (SVM) classifier,histogram of oriented gradient (HOG) feature
更新于2025-09-11 14:15:04
-
PERBANDINGAN TINGKAT PENGENALAN CITRA DIABETIC RETINOPATHY PADA KOMBINASI PRINCIPLE COMPONENT DARI 4 CIRI BERBASIS METODE SVM (SUPPORT VECTOR MACHINE)
摘要： Pattern recoqnition methods for image of diabetic retinopaty are influenced by differences in pigmentation. To help diabetic retinopathy image recognition is required a software. This paper presents the results of research on pattern recognition image of diabetic retinopathy,This study used the image of the yellow canal with Gabor filter.Characteristics that are taken from each image is characteristic of the mean, variance, skewness and entropy, followed by feature extraction with PCA (Principle Component Analysis).At PCA feature extraction, square matrix whose number of columns equal to the number of features is generated.There are four features used. These features are 4 PCs (Principle Component), ie, PC1, PC2, PC3 and PC4.From the combination of these features, we obtained six pairs that consist of two traits. By using a linear model of SVM will been selected the pair with the highest accuracy value. Based on the analysis, we obtained a couple PC1 and PC2 models that have the highest levels of learning (100%) and the fastest recognition time, which is explicitly indicated by the smallest amount of support vector.
关键词： Kanal Kuning,PCA,diabetic retinopathy,SVM
更新于2025-09-11 14:15:04
-
[IEEE 2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC) - Chongqing (2018.6.27-2018.6.29)] 2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC) - A New Strategy to Detect Lung Cancer on CT Images
摘要： Lung cancer has a very low cure rate in the advanced stages, with effective early detection, the survival rate of lung cancer could be highly raised. Detection of lung cancer in the early stages plays a vital role for human health. Computed tomography (CT) images, which provide electronic densities of tissues, are widely applied in radiotherapy planning. The proposed system based on CT technology consists of image acquisition, preprocessing, feature extraction, and classification. In the preprocessing stage, RGB images are converted to grayscale images, the median filter and the Wiener filter are used to uproot noises, Otsu thresholding method is applied to convert CT images, and REGIONPROPS function is used to exact body region from binary images. In the feature extraction stage, features, like Contrast, Correlation, Energy, Homogeneity, are extracted through statistic method Gray Level Co-occurrence Matrix (GLCM). In the final stage, extracted features, together with Support Vector Machine (SVM) and Back Propagation Neural Network (BPNN), are used to identify lung cancer from CT images. The performance of the proposed system shows satisfactory results of 96.32% accuracy on SVM and 83.07% accuracy on BPNN respectively.
关键词： BPNN,SVM,image processing,lung cancer detection,GLCM
更新于2025-09-10 09:29:36
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Detection of Fusarium Wilt on Phalaenopsis Stem Base Region Using Band Selection Techniques
摘要： Phalaenopsis is a significant agriculture product with high economic value in Taiwan. However, the fusarium wilt causes Phalaenopsis leaves turning yellow, thinning, water loss, and finally died. This paper presents an emerging method to detect fusarium wilt on Phalaenopsis stem base. In order to build the detection models, the hyperspectral databases are generated form two statues of Phalaenopsis samples, which are health and disease sample. We applied band selection (BS) processing base on band prioritization (BP) and band de-correlation (BD) to extract the significant bands and eliminate the redundant bands. Then, three algorithms were used, orthogonal subspace projection (OSP), constrain energy minimization (CEM), and support vector machine (SVM) to detect the fusarium wilt.
关键词： OSP,SVM,Hyperspectral image,Phalaenopsis,Band selection,fusarium wilt,CEM
更新于2025-09-10 09:29:36