Pub Date : 2021-01-05DOI: 10.1109/ICCRD51685.2021.9386516
S. Sultana, Boshir Ahmed
In the last two decades, Advanced Driver Assistance Systems (ADAS) has been one of the most actively conducted areas of studies for reducing traffic accidents. Road lane line detection is one of the essential modules of ADAS. Lots of advancement has been already done, but most of the recent papers did not consider the wide variability of challenging nighttime conditions. In this paper, a method to detect nighttime lane line under different challenging conditions proposed. This simple technique can reach the real-time computation for ADAS applications and at the same time, can handle multiple challenges at a time. In the beginning, Bilateral Filter has been used to reduce the noise while preserving the edges. Next, we choose an optimized threshold (OT) for the Canny edge detector, which can detect edges under a wide variability of nighttime illumination conditions. After that Region of Interest (ROI) is selected using an equilateral triangle-shaped mask which helps to reduce computation time and remove unwanted edges. After that, lines are extracted by Probabilistic Hough Transform (PHT). Finally, a robust technique Slope and Angle based Geometric Constraints (SAGC) is proposed to remove the non-lane lines extracted by PHT. SAGC reduce false detection significantly. Experimental results show that the average detection rate is 94.05%, and the average detection time is 26.11ms per frame which outperformed state-of-the-art method.
{"title":"Robust Nighttime Road Lane Line Detection using Bilateral Filter and SAGC under Challenging Conditions","authors":"S. Sultana, Boshir Ahmed","doi":"10.1109/ICCRD51685.2021.9386516","DOIUrl":"https://doi.org/10.1109/ICCRD51685.2021.9386516","url":null,"abstract":"In the last two decades, Advanced Driver Assistance Systems (ADAS) has been one of the most actively conducted areas of studies for reducing traffic accidents. Road lane line detection is one of the essential modules of ADAS. Lots of advancement has been already done, but most of the recent papers did not consider the wide variability of challenging nighttime conditions. In this paper, a method to detect nighttime lane line under different challenging conditions proposed. This simple technique can reach the real-time computation for ADAS applications and at the same time, can handle multiple challenges at a time. In the beginning, Bilateral Filter has been used to reduce the noise while preserving the edges. Next, we choose an optimized threshold (OT) for the Canny edge detector, which can detect edges under a wide variability of nighttime illumination conditions. After that Region of Interest (ROI) is selected using an equilateral triangle-shaped mask which helps to reduce computation time and remove unwanted edges. After that, lines are extracted by Probabilistic Hough Transform (PHT). Finally, a robust technique Slope and Angle based Geometric Constraints (SAGC) is proposed to remove the non-lane lines extracted by PHT. SAGC reduce false detection significantly. Experimental results show that the average detection rate is 94.05%, and the average detection time is 26.11ms per frame which outperformed state-of-the-art method.","PeriodicalId":294200,"journal":{"name":"2021 IEEE 13th International Conference on Computer Research and Development (ICCRD)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116808300","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 : 2021-01-05DOI: 10.1109/ICCRD51685.2021.9386396
Ying Li, Wang Jiamin
Spring is a very popular and strong open-source framework in web application development. It provides most of features about dependency injection (DI) container, but it is weak and defective in concurrent access and cyclic reference among objects. Based on the technique of object dependent graph, an new DI container named as GDCC solves these issues successfully.
{"title":"A Solution for Concurrency and Cyclic Reference of DI Container","authors":"Ying Li, Wang Jiamin","doi":"10.1109/ICCRD51685.2021.9386396","DOIUrl":"https://doi.org/10.1109/ICCRD51685.2021.9386396","url":null,"abstract":"Spring is a very popular and strong open-source framework in web application development. It provides most of features about dependency injection (DI) container, but it is weak and defective in concurrent access and cyclic reference among objects. Based on the technique of object dependent graph, an new DI container named as GDCC solves these issues successfully.","PeriodicalId":294200,"journal":{"name":"2021 IEEE 13th International Conference on Computer Research and Development (ICCRD)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122204546","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 : 2021-01-05DOI: 10.1109/ICCRD51685.2021.9386553
Hongju Gao
As an unsupervised learning method, spatial clustering has emerged to be one of the most important techniques in the field of agriculture for soil data analysis. Soil data analysis is usually related to practice in agricultural production management or discovery in agro-ecosystem process, so it is not easy to obtain labeled data that requires human intervention, and it is also not realistic to set specified pattern in advance. It is desirable to review the research work on soil data analysis using spatial clustering techniques in context of agricultural applications, which is the object of this survey. Soil properties (including physical, chemical, and biological properties) and the characteristics of the spatial soil data are first introduced. Spatial clustering techniques are then summarized in five different categories. Soil data analysis using spatial clustering is reviewed in four categories of agricultural applications: agricultural production management zoning, comprehensive assessment of soil and land, soil and land classification, and correlation study for agro-ecosystem. The traditional clustering algorithms generally work well, and prototype-based clustering methods are more preferred in practice. Some machine learning models can be further introduced into the spatial clustering algorithms for better accommodation to various characteristics of soil dataset.
{"title":"Agricultural Soil Data Analysis Using Spatial Clustering Data Mining Techniques","authors":"Hongju Gao","doi":"10.1109/ICCRD51685.2021.9386553","DOIUrl":"https://doi.org/10.1109/ICCRD51685.2021.9386553","url":null,"abstract":"As an unsupervised learning method, spatial clustering has emerged to be one of the most important techniques in the field of agriculture for soil data analysis. Soil data analysis is usually related to practice in agricultural production management or discovery in agro-ecosystem process, so it is not easy to obtain labeled data that requires human intervention, and it is also not realistic to set specified pattern in advance. It is desirable to review the research work on soil data analysis using spatial clustering techniques in context of agricultural applications, which is the object of this survey. Soil properties (including physical, chemical, and biological properties) and the characteristics of the spatial soil data are first introduced. Spatial clustering techniques are then summarized in five different categories. Soil data analysis using spatial clustering is reviewed in four categories of agricultural applications: agricultural production management zoning, comprehensive assessment of soil and land, soil and land classification, and correlation study for agro-ecosystem. The traditional clustering algorithms generally work well, and prototype-based clustering methods are more preferred in practice. Some machine learning models can be further introduced into the spatial clustering algorithms for better accommodation to various characteristics of soil dataset.","PeriodicalId":294200,"journal":{"name":"2021 IEEE 13th International Conference on Computer Research and Development (ICCRD)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130799516","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 : 2021-01-05DOI: 10.1109/ICCRD51685.2021.9386517
Hai Li, Jian Xu, Shujuan Hou
The accuracy of video-based action recognition depends largely on the extraction and utilization of optical flow, especially in two-stream networks. The original intention of the introduction of optical flow is to use the time information contained in video, however, the subsequent work shows that optical flow is useful for action recognition because it is invariant to appearance. In this article, we study and discuss this point of view, and propose optical flow enhancement algorithms to improve action recognition accuracy. Our enhancement algorithms improve the invariance to appearance of the representation in optical flow without losing time information, and every action recognition network with optical flow can benefit from our algorithms. We conduct a series of experiments to validate the influence of the proposed algorithms with TSN in terms of several datasets and optical flow calculation methods. As a result, we prove that first order differential algorithms are effective, TSN with our enhancement module significantly outperform original network. Based on these experiments, we also verify the importance of invariance to appearance in optical flow, and provide a reference for the follow-up study of improving action recognition accuracy.
{"title":"Optical Flow Enhancement and Effect Research in Action Recognition","authors":"Hai Li, Jian Xu, Shujuan Hou","doi":"10.1109/ICCRD51685.2021.9386517","DOIUrl":"https://doi.org/10.1109/ICCRD51685.2021.9386517","url":null,"abstract":"The accuracy of video-based action recognition depends largely on the extraction and utilization of optical flow, especially in two-stream networks. The original intention of the introduction of optical flow is to use the time information contained in video, however, the subsequent work shows that optical flow is useful for action recognition because it is invariant to appearance. In this article, we study and discuss this point of view, and propose optical flow enhancement algorithms to improve action recognition accuracy. Our enhancement algorithms improve the invariance to appearance of the representation in optical flow without losing time information, and every action recognition network with optical flow can benefit from our algorithms. We conduct a series of experiments to validate the influence of the proposed algorithms with TSN in terms of several datasets and optical flow calculation methods. As a result, we prove that first order differential algorithms are effective, TSN with our enhancement module significantly outperform original network. Based on these experiments, we also verify the importance of invariance to appearance in optical flow, and provide a reference for the follow-up study of improving action recognition accuracy.","PeriodicalId":294200,"journal":{"name":"2021 IEEE 13th International Conference on Computer Research and Development (ICCRD)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126700344","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 : 2021-01-05DOI: 10.1109/iccrd51685.2021.9386419
{"title":"ICCRD 2021 Preface","authors":"","doi":"10.1109/iccrd51685.2021.9386419","DOIUrl":"https://doi.org/10.1109/iccrd51685.2021.9386419","url":null,"abstract":"","PeriodicalId":294200,"journal":{"name":"2021 IEEE 13th International Conference on Computer Research and Development (ICCRD)","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115013840","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 : 2021-01-05DOI: 10.1109/ICCRD51685.2021.9386549
Pan Zhang, Yang Zhang, Xichi Hu
Multiple object tracking is a crucial task in the field of computer vision. In conventional tracking algorithms, frequent detections are required to achieve a good tracking performance, which makes the process time consuming and unable to be applied in real-time applications. Since the adjacent frames are highly relevant and the relevant motion vector can be extracted directly from compressed videos without extra calculation, we present a fast tracking algorithm based on the relevant motion vector to reduce the detection frequency. In the proposed algorithm, the video is divided into key and non-key frames. For the key frames, the objects are detected on the RGB images based on detection method. For the non-key frames, the objects are tracked based on transformation information calculated on motion vector. In order to combine the detection results and the tracking results, data association is performed for the key frames based on Hungarian algorithm. Evaluations on a video dataset show that our proposed algorithm achieves better efficiency and comparable accuracy than the previous algorithm.
{"title":"Fast Multiple Object Tracking Using Relevant Motion Vector","authors":"Pan Zhang, Yang Zhang, Xichi Hu","doi":"10.1109/ICCRD51685.2021.9386549","DOIUrl":"https://doi.org/10.1109/ICCRD51685.2021.9386549","url":null,"abstract":"Multiple object tracking is a crucial task in the field of computer vision. In conventional tracking algorithms, frequent detections are required to achieve a good tracking performance, which makes the process time consuming and unable to be applied in real-time applications. Since the adjacent frames are highly relevant and the relevant motion vector can be extracted directly from compressed videos without extra calculation, we present a fast tracking algorithm based on the relevant motion vector to reduce the detection frequency. In the proposed algorithm, the video is divided into key and non-key frames. For the key frames, the objects are detected on the RGB images based on detection method. For the non-key frames, the objects are tracked based on transformation information calculated on motion vector. In order to combine the detection results and the tracking results, data association is performed for the key frames based on Hungarian algorithm. Evaluations on a video dataset show that our proposed algorithm achieves better efficiency and comparable accuracy than the previous algorithm.","PeriodicalId":294200,"journal":{"name":"2021 IEEE 13th International Conference on Computer Research and Development (ICCRD)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126117384","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 : 2021-01-05DOI: 10.1109/iccrd51685.2021.9386711
{"title":"ICCRD 2021 Title Page","authors":"","doi":"10.1109/iccrd51685.2021.9386711","DOIUrl":"https://doi.org/10.1109/iccrd51685.2021.9386711","url":null,"abstract":"","PeriodicalId":294200,"journal":{"name":"2021 IEEE 13th International Conference on Computer Research and Development (ICCRD)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133087036","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 : 2021-01-05DOI: 10.1109/ICCRD51685.2021.9386501
Wenxin Shi, Yun Gong, Mengjia Yang, Tengfei Liu
In view of the unsatisfactory effect of the RIFT algorithm on local image registration, this paper introduces an improved RIFT algorithm based on the thin plate spline model for point cloud depth map and optical image registration method. To solve the problem of RIFT algorithm registration model, the thin-plate spline model is used instead of the rigid registration model to improve the algorithm. After image feature matching, the thin-plate spline is used to construct the image transformation model, and the image space transformation is decomposed into global affine transformation and local non-affine transformation, and the whole image and local mapping transformation are realized at the same time without local distortion. Experiments show that the improved algorithm can increase the CMR by 5%. The specific registration strategy is as follows: firstly, two kinds of data are preprocessed, and the image of the cloud depth map of the production point of the regular-grid resampling model is used. Then, the improved RIFT algorithm is used to extract corner points and edge points as registration elements, and Euclidean distance is used as similarity measure to achieve the registration of point cloud depth map and optical image, and then indirectly achieve the registration of laser point cloud and optical image. Finally, the registration accuracy is analyzed from the visual level and pixel level. The results show that the improved RIFT algorithm has favorable registration effect on point cloud depth map and optical image, and the proposed method has exceptional validity and reliability.
{"title":"Point Cloud Depth Map and Optical Image Registration Based on Improved RIFT Algorithm","authors":"Wenxin Shi, Yun Gong, Mengjia Yang, Tengfei Liu","doi":"10.1109/ICCRD51685.2021.9386501","DOIUrl":"https://doi.org/10.1109/ICCRD51685.2021.9386501","url":null,"abstract":"In view of the unsatisfactory effect of the RIFT algorithm on local image registration, this paper introduces an improved RIFT algorithm based on the thin plate spline model for point cloud depth map and optical image registration method. To solve the problem of RIFT algorithm registration model, the thin-plate spline model is used instead of the rigid registration model to improve the algorithm. After image feature matching, the thin-plate spline is used to construct the image transformation model, and the image space transformation is decomposed into global affine transformation and local non-affine transformation, and the whole image and local mapping transformation are realized at the same time without local distortion. Experiments show that the improved algorithm can increase the CMR by 5%. The specific registration strategy is as follows: firstly, two kinds of data are preprocessed, and the image of the cloud depth map of the production point of the regular-grid resampling model is used. Then, the improved RIFT algorithm is used to extract corner points and edge points as registration elements, and Euclidean distance is used as similarity measure to achieve the registration of point cloud depth map and optical image, and then indirectly achieve the registration of laser point cloud and optical image. Finally, the registration accuracy is analyzed from the visual level and pixel level. The results show that the improved RIFT algorithm has favorable registration effect on point cloud depth map and optical image, and the proposed method has exceptional validity and reliability.","PeriodicalId":294200,"journal":{"name":"2021 IEEE 13th International Conference on Computer Research and Development (ICCRD)","volume":"220 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115246004","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 : 2021-01-05DOI: 10.1109/ICCRD51685.2021.9386658
Haleh Shahzad, A. Sattar, Janahan Skandaraniyam
Various families of malware use domain generation algorithms (DGAs) to generate a large number of pseudo-random domain names to connect to malicious command and control servers (C&Cs). These domain names are used to evade domain based security detection and mitigation controls such as firewall controls. Existing prevalent techniques to detect DGA domains such as reverse engineering malware samples and statistical analysis techniques are time consuming, can be easily circumvented by attackers, and need contextual information which is not easily or feasibly obtained. Due to this, the use of machine learning and deep learning techniques to detect DGA domains has picked up significant interest in the cyber security and analytics communities. The ultimate goal is to detect DGA domains on a per domain basis using the domain name only, with no additional information. As with all techniques, there is the possibility of false positives: valid domains being detected as DGA domains. This paper explores the possible use cases that can result in false positives for DGA domain detection using machine learning and deep learning techniques, and how such use cases, if not uniquely addressed within an automated system or model or technique, can also be used as attack vectors by attackers using DGA domains.
{"title":"From Real Malicious Domains to Possible False Positives in DGA Domain Detection","authors":"Haleh Shahzad, A. Sattar, Janahan Skandaraniyam","doi":"10.1109/ICCRD51685.2021.9386658","DOIUrl":"https://doi.org/10.1109/ICCRD51685.2021.9386658","url":null,"abstract":"Various families of malware use domain generation algorithms (DGAs) to generate a large number of pseudo-random domain names to connect to malicious command and control servers (C&Cs). These domain names are used to evade domain based security detection and mitigation controls such as firewall controls. Existing prevalent techniques to detect DGA domains such as reverse engineering malware samples and statistical analysis techniques are time consuming, can be easily circumvented by attackers, and need contextual information which is not easily or feasibly obtained. Due to this, the use of machine learning and deep learning techniques to detect DGA domains has picked up significant interest in the cyber security and analytics communities. The ultimate goal is to detect DGA domains on a per domain basis using the domain name only, with no additional information. As with all techniques, there is the possibility of false positives: valid domains being detected as DGA domains. This paper explores the possible use cases that can result in false positives for DGA domain detection using machine learning and deep learning techniques, and how such use cases, if not uniquely addressed within an automated system or model or technique, can also be used as attack vectors by attackers using DGA domains.","PeriodicalId":294200,"journal":{"name":"2021 IEEE 13th International Conference on Computer Research and Development (ICCRD)","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122622898","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}
With the development of science and technology, RFID based indoor positioning technology is more and more widely used, among which LANDMARC indoor positioning system nearest neighbor algorithm has become the mainstream algorithm, aiming at the classic land The existence of multipath effect, noise random variable and various kinds of obstacles in the VIRE, Marc and its improved algorithm, makes reader reading ability decrease, affects the selection of nearest label, and then makes the positioning accuracy of the system decrease. This paper presents a new improvement scheme. Firstly, the RSSI is preprocessed by Gaussian filter, then the adaptive threshold is set, and the RSSI value of virtual reference label is obtained by Newton interpolation method. Then the positioning results are corrected by position correction. At the same time, the boundary virtual reference label is set, and the accuracy of RSSI is improved by these methods, and the coverage of reference label is increased. The simulation results show that the improved algorithm has higher positioning accuracy and stronger stability than LANDMARC and VIRE algorithm.
{"title":"Optimization of Indoor Positioning Algorithm Based on LANDMARC","authors":"Xiaoqing Zhou, Jiaxiu Sun, Zhiyong Zhou, Jianqong Xiao","doi":"10.1109/ICCRD51685.2021.9386433","DOIUrl":"https://doi.org/10.1109/ICCRD51685.2021.9386433","url":null,"abstract":"With the development of science and technology, RFID based indoor positioning technology is more and more widely used, among which LANDMARC indoor positioning system nearest neighbor algorithm has become the mainstream algorithm, aiming at the classic land The existence of multipath effect, noise random variable and various kinds of obstacles in the VIRE, Marc and its improved algorithm, makes reader reading ability decrease, affects the selection of nearest label, and then makes the positioning accuracy of the system decrease. This paper presents a new improvement scheme. Firstly, the RSSI is preprocessed by Gaussian filter, then the adaptive threshold is set, and the RSSI value of virtual reference label is obtained by Newton interpolation method. Then the positioning results are corrected by position correction. At the same time, the boundary virtual reference label is set, and the accuracy of RSSI is improved by these methods, and the coverage of reference label is increased. The simulation results show that the improved algorithm has higher positioning accuracy and stronger stability than LANDMARC and VIRE algorithm.","PeriodicalId":294200,"journal":{"name":"2021 IEEE 13th International Conference on Computer Research and Development (ICCRD)","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132414520","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：