Pub Date : 2020-12-01DOI: 10.1109/InGARSS48198.2020.9358956
Mehran Maneshi, H. Ghassemian, M. Imani
Pansharpening is a notable remote sensing topic in which high spatial resolution panchromatic image and low spatial resolution multi-spectral image are being fused in order to receive the high spatial resolution multi-spectral image. This paper presents a hybrid pansharpening method based on MRA framework and the sparse representation of injected details. To add spatial details of the panchromatic image into the multispectral image more effectively, the injection gains are computed through an iterative full-scale model in which the gains are updated at each iteration relying on its previous iteration’s fusion product. The proposed method is compared with five pansharpening approaches to investigate the effectiveness. Experiments have been implemented on two data sets from the Pleiades and GeoEye-1 satellites both at reduced and full scale. In terms of visual and quantity assessment, the high-resolution MS image produced by the proposed method is more acceptable than those images fused by other rival approaches.
{"title":"Sparse Representation of Injected Details for MRA-Based Pansharpening","authors":"Mehran Maneshi, H. Ghassemian, M. Imani","doi":"10.1109/InGARSS48198.2020.9358956","DOIUrl":"https://doi.org/10.1109/InGARSS48198.2020.9358956","url":null,"abstract":"Pansharpening is a notable remote sensing topic in which high spatial resolution panchromatic image and low spatial resolution multi-spectral image are being fused in order to receive the high spatial resolution multi-spectral image. This paper presents a hybrid pansharpening method based on MRA framework and the sparse representation of injected details. To add spatial details of the panchromatic image into the multispectral image more effectively, the injection gains are computed through an iterative full-scale model in which the gains are updated at each iteration relying on its previous iteration’s fusion product. The proposed method is compared with five pansharpening approaches to investigate the effectiveness. Experiments have been implemented on two data sets from the Pleiades and GeoEye-1 satellites both at reduced and full scale. In terms of visual and quantity assessment, the high-resolution MS image produced by the proposed method is more acceptable than those images fused by other rival approaches.","PeriodicalId":6797,"journal":{"name":"2020 IEEE India Geoscience and Remote Sensing Symposium (InGARSS)","volume":"110 1","pages":"86-89"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73026612","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1109/InGARSS48198.2020.9358945
Jannath Firthouse Mohammed Yashin, Aarthi Deivanayagam, Abdul Rahaman Sheik Mohideen, Jegankumar Rajagopal
The Landuse/Landcover (LULC) changes become more intense in this era due to rapid urbanization, industrialization and over utilization of agricultural land for human wellbeing. This study is an attempt to find an effective approach among various classifiers for the evaluation of spatio-temporal variations in LULC over a part of the East coastal region of Tamil Nadu for the period of 30 years. High and low resolution remote sensing data are used to perform five different LULC classification algorithms: K-means, IsoData, Maximum Likelihood (ML), Parallelepiped (PP) and Support Vector Machine (SVM). The experimental outcomes conclude that the Support vector machine classifier comparatively shows high accuracy and classification performance than others.
{"title":"Comparative Analysis of Classification Algorithms for Landuse / Landcover Change Over A Part of The East Coast Region of Tamil Nadu And Its Environs","authors":"Jannath Firthouse Mohammed Yashin, Aarthi Deivanayagam, Abdul Rahaman Sheik Mohideen, Jegankumar Rajagopal","doi":"10.1109/InGARSS48198.2020.9358945","DOIUrl":"https://doi.org/10.1109/InGARSS48198.2020.9358945","url":null,"abstract":"The Landuse/Landcover (LULC) changes become more intense in this era due to rapid urbanization, industrialization and over utilization of agricultural land for human wellbeing. This study is an attempt to find an effective approach among various classifiers for the evaluation of spatio-temporal variations in LULC over a part of the East coastal region of Tamil Nadu for the period of 30 years. High and low resolution remote sensing data are used to perform five different LULC classification algorithms: K-means, IsoData, Maximum Likelihood (ML), Parallelepiped (PP) and Support Vector Machine (SVM). The experimental outcomes conclude that the Support vector machine classifier comparatively shows high accuracy and classification performance than others.","PeriodicalId":6797,"journal":{"name":"2020 IEEE India Geoscience and Remote Sensing Symposium (InGARSS)","volume":"62 1","pages":"66-69"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77916044","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1109/InGARSS48198.2020.9358916
M. S. Kumar, V. Keerthi, R.N. Anjnai, M. Sarma, V. Bothale
Machine learning algorithms are outstanding predictive powerful tools for classification of hypserspectral images. In this paper we summarize the various classification techniques based on machine learning approaches for space borne hypserspectral images. Random Forest (RF), Support Vector Machine (SVM) and a deep learning technique, Convolution Neural Network (CNN) are explored on HySIS images. CNN shows great potential to yield high performance in hypserspectral image classification. 2-D and 3-D CNN techniques provided robust classification results when compared to RF, SVM methods.
{"title":"Evalution of Machine Learning Methods for Hyperspectral Image Classification","authors":"M. S. Kumar, V. Keerthi, R.N. Anjnai, M. Sarma, V. Bothale","doi":"10.1109/InGARSS48198.2020.9358916","DOIUrl":"https://doi.org/10.1109/InGARSS48198.2020.9358916","url":null,"abstract":"Machine learning algorithms are outstanding predictive powerful tools for classification of hypserspectral images. In this paper we summarize the various classification techniques based on machine learning approaches for space borne hypserspectral images. Random Forest (RF), Support Vector Machine (SVM) and a deep learning technique, Convolution Neural Network (CNN) are explored on HySIS images. CNN shows great potential to yield high performance in hypserspectral image classification. 2-D and 3-D CNN techniques provided robust classification results when compared to RF, SVM methods.","PeriodicalId":6797,"journal":{"name":"2020 IEEE India Geoscience and Remote Sensing Symposium (InGARSS)","volume":"9 1","pages":"225-228"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84324324","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1109/InGARSS48198.2020.9358954
Chandni C K, Shashi Kumar
Fernandina is the westernmost and the most active volcano in the Galapagos archipelago. It is a basaltic shield volcano with a summit caldera of dimension 5 x 6.5 km. Recently, the volcano erupted on January 12, 2020, preceded by a seismic shock of magnitude 4.7 at a depth of 5 km. The subsequent seismic activities have led to the formation of a circumferential fissure below the La Cumbre crater's eastern rim, at an elevation of 1.3-1.4 km. The lava flow has occurred down the flank to the sea through this fissure. This volcanic episode has continued up to 9 hours. The InSAR time series method is a multi-temporal InSAR technique used to detect slowly occurring deformations with a millimeter level of precision using a stack of SAR interferograms. In this paper, the Differential InSAR has been used to analyze Fernandina volcano's surface deformation due to this recent eruption. The interferograms of the volcano before, during, and after the eruption have been analyzed in detail using the freely available Sentinel 1 C- band datasets from 2019 December 17 to 2020 February 09. The integration of all these analyses gives an insight into the underground magma conduit system, the correlation between the magmatic and seismic activities, surface deformations, and the lava flow channels, which have been discussed in detail in this paper.
{"title":"DInSAR based Analysis of January 2020 Eruption of Fernandina Volcano, Galapagos","authors":"Chandni C K, Shashi Kumar","doi":"10.1109/InGARSS48198.2020.9358954","DOIUrl":"https://doi.org/10.1109/InGARSS48198.2020.9358954","url":null,"abstract":"Fernandina is the westernmost and the most active volcano in the Galapagos archipelago. It is a basaltic shield volcano with a summit caldera of dimension 5 x 6.5 km. Recently, the volcano erupted on January 12, 2020, preceded by a seismic shock of magnitude 4.7 at a depth of 5 km. The subsequent seismic activities have led to the formation of a circumferential fissure below the La Cumbre crater's eastern rim, at an elevation of 1.3-1.4 km. The lava flow has occurred down the flank to the sea through this fissure. This volcanic episode has continued up to 9 hours. The InSAR time series method is a multi-temporal InSAR technique used to detect slowly occurring deformations with a millimeter level of precision using a stack of SAR interferograms. In this paper, the Differential InSAR has been used to analyze Fernandina volcano's surface deformation due to this recent eruption. The interferograms of the volcano before, during, and after the eruption have been analyzed in detail using the freely available Sentinel 1 C- band datasets from 2019 December 17 to 2020 February 09. The integration of all these analyses gives an insight into the underground magma conduit system, the correlation between the magmatic and seismic activities, surface deformations, and the lava flow channels, which have been discussed in detail in this paper.","PeriodicalId":6797,"journal":{"name":"2020 IEEE India Geoscience and Remote Sensing Symposium (InGARSS)","volume":"188 1","pages":"250-253"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85459326","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1109/InGARSS48198.2020.9358975
H. Kumar, A. Rajawat
Muscovite is an important mineral commonly found in hydrothermal systems of Earth and Mars. Reflectance spectra of muscovite has several diagnostic absorption features in wavelength range 0.4-2.5 µm. The absorption feature near 2.20 µm is sensitive to alumina content variations. In this study, we use reflectance spectra of powdered muscovite and geochemical datasets to quantify the relationship between spectral shift and alumina content. Imaginary index of refraction (k) was derived from reflectance spectra and a linear model was proposed relating alumina content and k. Reflectance spectra of muscovite was modelled for varying alumina content and grain size using Hapke model. Modelled spectra shows shift in wavelength position of 2.20 µm with varying alumina content and deepening of absorption features with increase in grain size. The results shall be helpful in interpretation of reflectance spectra acquired from space borne and airborne platforms.
{"title":"Modelling Reflectance Spectra of Muscovite as Function of Aluminium Content and Grain Size Using Hapke Model","authors":"H. Kumar, A. Rajawat","doi":"10.1109/InGARSS48198.2020.9358975","DOIUrl":"https://doi.org/10.1109/InGARSS48198.2020.9358975","url":null,"abstract":"Muscovite is an important mineral commonly found in hydrothermal systems of Earth and Mars. Reflectance spectra of muscovite has several diagnostic absorption features in wavelength range 0.4-2.5 µm. The absorption feature near 2.20 µm is sensitive to alumina content variations. In this study, we use reflectance spectra of powdered muscovite and geochemical datasets to quantify the relationship between spectral shift and alumina content. Imaginary index of refraction (k) was derived from reflectance spectra and a linear model was proposed relating alumina content and k. Reflectance spectra of muscovite was modelled for varying alumina content and grain size using Hapke model. Modelled spectra shows shift in wavelength position of 2.20 µm with varying alumina content and deepening of absorption features with increase in grain size. The results shall be helpful in interpretation of reflectance spectra acquired from space borne and airborne platforms.","PeriodicalId":6797,"journal":{"name":"2020 IEEE India Geoscience and Remote Sensing Symposium (InGARSS)","volume":"43 2 1","pages":"122-125"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80092594","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1109/InGARSS48198.2020.9358948
N. Aburaed, M. Al-Saad, Marwa Chendeb El Rai, S. Al Mansoori, H. Al-Ahmad, S. Marshall
Object detection in remote sensing images has been a topic of interest that has gradually gained attention over the years due to the wide variety of related applications. Even though there is an extensive number of methods developed for object detection, there are still several challenges that remain unsolved, such as visual appearance variations, occlusions, and background clutter. Satellite images reveal a texture problem; it is difficult to differentiate between the background and the object of interest. In order to overcome this problem and exploit more of the spectral features of images, Discrete Wavelet Transform (DWT) is embedded into one of the most superior methods for object detection, which is Faster Region-based Convolutional Network (FRCNN). The accuracy of FRCNN is boosted by introducing the wavelet decomposition. The performance of the proposed strategy is tested, evaluated, and compared to the original FRCNN using two different datasets.
{"title":"Autonomous Object Detection in Satellite Images Using Wfrcnn","authors":"N. Aburaed, M. Al-Saad, Marwa Chendeb El Rai, S. Al Mansoori, H. Al-Ahmad, S. Marshall","doi":"10.1109/InGARSS48198.2020.9358948","DOIUrl":"https://doi.org/10.1109/InGARSS48198.2020.9358948","url":null,"abstract":"Object detection in remote sensing images has been a topic of interest that has gradually gained attention over the years due to the wide variety of related applications. Even though there is an extensive number of methods developed for object detection, there are still several challenges that remain unsolved, such as visual appearance variations, occlusions, and background clutter. Satellite images reveal a texture problem; it is difficult to differentiate between the background and the object of interest. In order to overcome this problem and exploit more of the spectral features of images, Discrete Wavelet Transform (DWT) is embedded into one of the most superior methods for object detection, which is Faster Region-based Convolutional Network (FRCNN). The accuracy of FRCNN is boosted by introducing the wavelet decomposition. The performance of the proposed strategy is tested, evaluated, and compared to the original FRCNN using two different datasets.","PeriodicalId":6797,"journal":{"name":"2020 IEEE India Geoscience and Remote Sensing Symposium (InGARSS)","volume":"31 1","pages":"106-109"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80360950","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1109/InGARSS48198.2020.9358952
H. Srivastava, T. Pant
In this paper, the vegetation cover of Prayagraj, Uttar Pradesh has been studied with the time series data. For the study, MODIS NDVI 250m time series data have been used. For the classification, a pixel based SVM classifier is applied on 20 images of the data set. The classified images are used pairwise as pre and post harvesting outputs to generate change detection map, and to calculate the percentage vegetation cover of the study area. Further, a data set containing 158 samples with ARIMA time series model has been tested. The high vegetation class for the testing samples is predicted with mean squared error of 0.00604.
{"title":"A Time Series based Study of MODIS NDVI for Vegetation Cover","authors":"H. Srivastava, T. Pant","doi":"10.1109/InGARSS48198.2020.9358952","DOIUrl":"https://doi.org/10.1109/InGARSS48198.2020.9358952","url":null,"abstract":"In this paper, the vegetation cover of Prayagraj, Uttar Pradesh has been studied with the time series data. For the study, MODIS NDVI 250m time series data have been used. For the classification, a pixel based SVM classifier is applied on 20 images of the data set. The classified images are used pairwise as pre and post harvesting outputs to generate change detection map, and to calculate the percentage vegetation cover of the study area. Further, a data set containing 158 samples with ARIMA time series model has been tested. The high vegetation class for the testing samples is predicted with mean squared error of 0.00604.","PeriodicalId":6797,"journal":{"name":"2020 IEEE India Geoscience and Remote Sensing Symposium (InGARSS)","volume":"79 1","pages":"21-24"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83915910","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1109/InGARSS48198.2020.9358920
M. Kanthi, T. Sarma, C. Bindu
Hyperspectral image consists of huge spectral and special information. Deep learning models, such as deep convolutional neural networks (CNNs) being widely used for HSI classification. Most of the approaches are based on 2D CNN. Whereas, the HSI classification performance depends on both spatial and spectral information. This paper proposes a new 3D-Deep Feature Extraction CNN model for the HSI classification which uses both spectral and spatial information. Here the HSI data is divided into 3D patches and fed into the proposed model for deep feature extractions. Experimental results show that the performance of HSI classification is improved significantly with the proposed model. The experimental results on the publicly available HSI datasets, viz., Indian Pines(IP), Pavia University scene(PU) and Salinas scene(SA), are compared with the contemporary models. The current results indicates that the proposed model provides comparatively better results than the state-of-the-art methods.
高光谱图像包含大量的光谱信息和特殊信息。深度学习模型，如深度卷积神经网络(cnn)被广泛用于恒生指数分类。大多数方法都是基于二维CNN的。然而，恒指分类性能取决于空间和光谱信息。本文提出了一种新的3D-Deep Feature Extraction CNN模型，该模型利用光谱和空间信息进行HSI分类。在这里，HSI数据被分割成3D块，并输入到所提出的模型中进行深度特征提取。实验结果表明，该模型显著提高了HSI分类的性能。在公开的HSI数据集，即Indian Pines(IP)， Pavia University (PU)和Salinas (SA)上的实验结果与当代模型进行了比较。目前的结果表明，所提出的模型提供了相对较好的结果比最先进的方法。
{"title":"A 3d-Deep CNN Based Feature Extraction and Hyperspectral Image Classification","authors":"M. Kanthi, T. Sarma, C. Bindu","doi":"10.1109/InGARSS48198.2020.9358920","DOIUrl":"https://doi.org/10.1109/InGARSS48198.2020.9358920","url":null,"abstract":"Hyperspectral image consists of huge spectral and special information. Deep learning models, such as deep convolutional neural networks (CNNs) being widely used for HSI classification. Most of the approaches are based on 2D CNN. Whereas, the HSI classification performance depends on both spatial and spectral information. This paper proposes a new 3D-Deep Feature Extraction CNN model for the HSI classification which uses both spectral and spatial information. Here the HSI data is divided into 3D patches and fed into the proposed model for deep feature extractions. Experimental results show that the performance of HSI classification is improved significantly with the proposed model. The experimental results on the publicly available HSI datasets, viz., Indian Pines(IP), Pavia University scene(PU) and Salinas scene(SA), are compared with the contemporary models. The current results indicates that the proposed model provides comparatively better results than the state-of-the-art methods.","PeriodicalId":6797,"journal":{"name":"2020 IEEE India Geoscience and Remote Sensing Symposium (InGARSS)","volume":"18 1","pages":"229-232"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89732427","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1109/InGARSS48198.2020.9358963
Palla Parasuram Yadav, Amba Shetty, B. Raghavendra, A. Narasimhadhan
In multispectral and hyperspectral remote sensing, classification of pixels is obtained by means of spectral similarity of known field or library spectra to unknown image spectra. Endmember extraction is the most decisive task in hyperspectral image analysis. Endmember initialization algorithms (EIAs) play a key role and support endmember extraction algorithms (EEAs) in extracting near optimal set of endmembers. Though there are few endmember initialization techniques available, similarity measures are not explored in detail in target generation. Hence, in this paper, it is proposed to explore similarity measures in identifying spectrally distinct signatures to use them as initial endmembers. Individual similarity measures are combined to form hybrid similarity measures to confirm their effectiveness in generating spectrally distinct targets. Initial set of endmembers extracted by proposed algorithm are used for initializing classical EEA, the NFINDR, which is sensitive to endmember initialization, and their performance in final endmembers selection is verified. Experimental results on two hyperspectral data sets show the superior performance of the similarity based endmember initialization algorithm (SMEIA).
{"title":"Similarity Measures in Generating Spectrally Distinct Targets","authors":"Palla Parasuram Yadav, Amba Shetty, B. Raghavendra, A. Narasimhadhan","doi":"10.1109/InGARSS48198.2020.9358963","DOIUrl":"https://doi.org/10.1109/InGARSS48198.2020.9358963","url":null,"abstract":"In multispectral and hyperspectral remote sensing, classification of pixels is obtained by means of spectral similarity of known field or library spectra to unknown image spectra. Endmember extraction is the most decisive task in hyperspectral image analysis. Endmember initialization algorithms (EIAs) play a key role and support endmember extraction algorithms (EEAs) in extracting near optimal set of endmembers. Though there are few endmember initialization techniques available, similarity measures are not explored in detail in target generation. Hence, in this paper, it is proposed to explore similarity measures in identifying spectrally distinct signatures to use them as initial endmembers. Individual similarity measures are combined to form hybrid similarity measures to confirm their effectiveness in generating spectrally distinct targets. Initial set of endmembers extracted by proposed algorithm are used for initializing classical EEA, the NFINDR, which is sensitive to endmember initialization, and their performance in final endmembers selection is verified. Experimental results on two hyperspectral data sets show the superior performance of the similarity based endmember initialization algorithm (SMEIA).","PeriodicalId":6797,"journal":{"name":"2020 IEEE India Geoscience and Remote Sensing Symposium (InGARSS)","volume":"12 1","pages":"221-224"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90102118","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：