Pub Date : 2022-09-23DOI: 10.1109/ICACTE55855.2022.9943638
Jiehong Mo, Yongbin Yu, Chen-lei Zhou, Yuanjingyang Zhong, Zipeng Wang
In this paper, a new variant of genetic algorithm, matrix-based genetic algorithm (MGA), is proposed, which represents the population of genetic algorithm by matrix, and achieves evolution by matrix operation. Applying it to the 2D global path planning problem of robot, MGA has better accuracy and running speed than the basic genetic algorithm. Specifically, the average path length obtained after convergence of MGA is closer to the actual shortest path length than that of the basic genetic algorithm, and, due to the parallelism of the MGA in matrix operations, the MGA runs in 1/2 the time of the traditional genetic algorithm when using the NumPy library. Two experiments comparing shortest path lengths demonstrate that MGA has better stability and can cope with complex environments. In order to enable the algorithm to have better accuracy, this paper also explores the effect of whether to use elite strategy on the accuracy of the shortest path of the algorithm. In addition, the effect of different pathfinding algorithms on the computing time of the algorithm is explored to speed up the operation of the algorithm.
{"title":"Matrix-based Genetic Algorithm for Mobile Robot Global Path Planning","authors":"Jiehong Mo, Yongbin Yu, Chen-lei Zhou, Yuanjingyang Zhong, Zipeng Wang","doi":"10.1109/ICACTE55855.2022.9943638","DOIUrl":"https://doi.org/10.1109/ICACTE55855.2022.9943638","url":null,"abstract":"In this paper, a new variant of genetic algorithm, matrix-based genetic algorithm (MGA), is proposed, which represents the population of genetic algorithm by matrix, and achieves evolution by matrix operation. Applying it to the 2D global path planning problem of robot, MGA has better accuracy and running speed than the basic genetic algorithm. Specifically, the average path length obtained after convergence of MGA is closer to the actual shortest path length than that of the basic genetic algorithm, and, due to the parallelism of the MGA in matrix operations, the MGA runs in 1/2 the time of the traditional genetic algorithm when using the NumPy library. Two experiments comparing shortest path lengths demonstrate that MGA has better stability and can cope with complex environments. In order to enable the algorithm to have better accuracy, this paper also explores the effect of whether to use elite strategy on the accuracy of the shortest path of the algorithm. In addition, the effect of different pathfinding algorithms on the computing time of the algorithm is explored to speed up the operation of the algorithm.","PeriodicalId":165068,"journal":{"name":"2022 15th International Conference on Advanced Computer Theory and Engineering (ICACTE)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122490244","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 : 2022-09-23DOI: 10.1109/ICACTE55855.2022.9943717
Ngai Cheong, Lue Li, Xi Wang
Since the concept of “e-government” was put forward, many government agencies around the world have been actively promoting the development of e-government. They are also deeply discussing the development law and direction of e-government, and summed up many valuable suggestions. One of them is to evaluate the development status of e-governments, which can be divided into different stages to scientifically assessment the development current status of e-government development. But now no matter what kind of the methods there are relatively shortcoming, can’t accurately describe the development of e-government, as listed in the paper.Based on the development history of science and technology and the most important electronic technology level in e-government as the basis for distinguishing different development stages and levels of e-government. This paper proposes an evaluation method that it is to divide the development of e-government into six stages and five levels, considered the development history of the e-government in the Macao SAR government and the evolution of IT as an example, a brief description of this suggestion can be used to evaluate the development of e-government more effectively.
{"title":"Evaluation in Development of E-Government: Taking Macao E-Government as An Example","authors":"Ngai Cheong, Lue Li, Xi Wang","doi":"10.1109/ICACTE55855.2022.9943717","DOIUrl":"https://doi.org/10.1109/ICACTE55855.2022.9943717","url":null,"abstract":"Since the concept of “e-government” was put forward, many government agencies around the world have been actively promoting the development of e-government. They are also deeply discussing the development law and direction of e-government, and summed up many valuable suggestions. One of them is to evaluate the development status of e-governments, which can be divided into different stages to scientifically assessment the development current status of e-government development. But now no matter what kind of the methods there are relatively shortcoming, can’t accurately describe the development of e-government, as listed in the paper.Based on the development history of science and technology and the most important electronic technology level in e-government as the basis for distinguishing different development stages and levels of e-government. This paper proposes an evaluation method that it is to divide the development of e-government into six stages and five levels, considered the development history of the e-government in the Macao SAR government and the evolution of IT as an example, a brief description of this suggestion can be used to evaluate the development of e-government more effectively.","PeriodicalId":165068,"journal":{"name":"2022 15th International Conference on Advanced Computer Theory and Engineering (ICACTE)","volume":"07 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122651587","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 : 2022-09-23DOI: 10.1109/icacte55855.2022.9943632
{"title":"ICACTE 2022 Cover Page","authors":"","doi":"10.1109/icacte55855.2022.9943632","DOIUrl":"https://doi.org/10.1109/icacte55855.2022.9943632","url":null,"abstract":"","PeriodicalId":165068,"journal":{"name":"2022 15th International Conference on Advanced Computer Theory and Engineering (ICACTE)","volume":"134 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117317162","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 : 2022-09-23DOI: 10.1109/ICACTE55855.2022.9943659
D. Cui, Guoqing Sun, Xiaotiao Zhan
Compared with the general yard, the prevention responsibility of dangerous goods container yard is heavier, safety control is greater, the consequences of safety accidents are more serious, so the safety management of dangerous goods container yard is particularly important. Complex network, as a kind of network of self-similar, self-organized or all nature, is widely used in various security systems. Therefore, this paper builds a security system of dangerous container yard based on complex network technology, monitors dangerous goods using Internet technology, acquires environmental information and location information of dangerous goods preservation and transportation, queries and stores various information, so as to improve the security of dangerous goods management.
{"title":"Research on the Security System of Dangerous Goods Container Yard Based on Complex Network","authors":"D. Cui, Guoqing Sun, Xiaotiao Zhan","doi":"10.1109/ICACTE55855.2022.9943659","DOIUrl":"https://doi.org/10.1109/ICACTE55855.2022.9943659","url":null,"abstract":"Compared with the general yard, the prevention responsibility of dangerous goods container yard is heavier, safety control is greater, the consequences of safety accidents are more serious, so the safety management of dangerous goods container yard is particularly important. Complex network, as a kind of network of self-similar, self-organized or all nature, is widely used in various security systems. Therefore, this paper builds a security system of dangerous container yard based on complex network technology, monitors dangerous goods using Internet technology, acquires environmental information and location information of dangerous goods preservation and transportation, queries and stores various information, so as to improve the security of dangerous goods management.","PeriodicalId":165068,"journal":{"name":"2022 15th International Conference on Advanced Computer Theory and Engineering (ICACTE)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130072095","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 : 2022-09-23DOI: 10.1109/ICACTE55855.2022.9943660
Jiawei Cao, Z. Tang, Feng He, Sudan Li, Tianhang Guo, Yan Gao, Peng Xun
At present, people’s demand for the Internet is increasing day by day, and the scale of the Internet is exploding at an incredible speed. This also leads to the increasingly serious problem of routing scalability and mobility. The birth of the LISP network architecture provides an effective method to solve problems stated above. Consistency testing technology is the key technology to ensure the interconnection of network devices under the new network architecture. In this paper, aiming at the typical LISP mapping distribution protocol - LISP-ALT (RFC6836), a conformance testing system is designed and many testcases are implemented by standard TTCN-3 test language and open-source TITAN platform. Finally, a typical testcase is verified and analyzed for demonstration.
目前，人们对互联网的需求日益增加，互联网的规模正以惊人的速度爆发。这也导致了路由可伸缩性和可移动性日益严重的问题。LISP网络体系结构的诞生为解决上述问题提供了一种有效的方法。一致性测试技术是保证新网络架构下网络设备互联互通的关键技术。本文针对典型的LISP映射分发协议LISP- alt (RFC6836)，设计了一个一致性测试系统，并利用标准的TTCN-3测试语言和开源的TITAN平台实现了多个测试用例。最后，对一个典型的测试用例进行了验证和分析。
{"title":"Design and Implementation of Conformance Test for LISP Mapping Distribution Protocol","authors":"Jiawei Cao, Z. Tang, Feng He, Sudan Li, Tianhang Guo, Yan Gao, Peng Xun","doi":"10.1109/ICACTE55855.2022.9943660","DOIUrl":"https://doi.org/10.1109/ICACTE55855.2022.9943660","url":null,"abstract":"At present, people’s demand for the Internet is increasing day by day, and the scale of the Internet is exploding at an incredible speed. This also leads to the increasingly serious problem of routing scalability and mobility. The birth of the LISP network architecture provides an effective method to solve problems stated above. Consistency testing technology is the key technology to ensure the interconnection of network devices under the new network architecture. In this paper, aiming at the typical LISP mapping distribution protocol - LISP-ALT (RFC6836), a conformance testing system is designed and many testcases are implemented by standard TTCN-3 test language and open-source TITAN platform. Finally, a typical testcase is verified and analyzed for demonstration.","PeriodicalId":165068,"journal":{"name":"2022 15th International Conference on Advanced Computer Theory and Engineering (ICACTE)","volume":"18 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132568578","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 : 2022-09-23DOI: 10.1109/ICACTE55855.2022.9943608
Xiao Ge, Q. Zhang
With the increasing functionalities of mobile terminals, computation offloading has become a good way to alleviate the limitation of terminal computing resource and improve terminal performance. In this paper, we propose an efficient computation offloading strategy for multi-cloud system to minimize makespan with terminal energy consumption constraint. The proposed strategy first sorts tasks and establishes paths. Then tasks on each established path are counted as an integrated task and assigned to a worker node with less completion time iteratively. After the initial task assignment, performance optimization is performed to satisfy energy consumption constraint and further decrease makespan. Experimental results show that the proposed approach has better performance compared to genetic algorithm and greedy algorithm.
{"title":"Efficient Computation Offloading with Energy Consumption Constraint for Multi-Cloud System","authors":"Xiao Ge, Q. Zhang","doi":"10.1109/ICACTE55855.2022.9943608","DOIUrl":"https://doi.org/10.1109/ICACTE55855.2022.9943608","url":null,"abstract":"With the increasing functionalities of mobile terminals, computation offloading has become a good way to alleviate the limitation of terminal computing resource and improve terminal performance. In this paper, we propose an efficient computation offloading strategy for multi-cloud system to minimize makespan with terminal energy consumption constraint. The proposed strategy first sorts tasks and establishes paths. Then tasks on each established path are counted as an integrated task and assigned to a worker node with less completion time iteratively. After the initial task assignment, performance optimization is performed to satisfy energy consumption constraint and further decrease makespan. Experimental results show that the proposed approach has better performance compared to genetic algorithm and greedy algorithm.","PeriodicalId":165068,"journal":{"name":"2022 15th International Conference on Advanced Computer Theory and Engineering (ICACTE)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127148785","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 : 2022-09-23DOI: 10.1109/ICACTE55855.2022.9943601
Pei Li, A. He, Yunlong Zhao, G. Jiang
With the increasing investment amount of power grid companies in recent years to improve the efficiency of construction and transformation of distribution network, the scale of distribution network construction is expanding and the number of investment projects is increasing. It is urgent to optimize the project investment management, ensure the correctness of investment strategy and achieve the expected goal of project investment. In this paper, a regional optimization model was established, which includes three factors: the promotion of three-effect indicators, the promotion of power supply capacity, the contribution of meeting political and economic situation, and the contribution of meeting the company’s development strategy. Based on entropy method, the contribution degree of a single project was calculated, thus providing an optimal reference for project investment.
{"title":"A Regional Optimization Model of Distribution Network Planning Project Based on Entropy Method","authors":"Pei Li, A. He, Yunlong Zhao, G. Jiang","doi":"10.1109/ICACTE55855.2022.9943601","DOIUrl":"https://doi.org/10.1109/ICACTE55855.2022.9943601","url":null,"abstract":"With the increasing investment amount of power grid companies in recent years to improve the efficiency of construction and transformation of distribution network, the scale of distribution network construction is expanding and the number of investment projects is increasing. It is urgent to optimize the project investment management, ensure the correctness of investment strategy and achieve the expected goal of project investment. In this paper, a regional optimization model was established, which includes three factors: the promotion of three-effect indicators, the promotion of power supply capacity, the contribution of meeting political and economic situation, and the contribution of meeting the company’s development strategy. Based on entropy method, the contribution degree of a single project was calculated, thus providing an optimal reference for project investment.","PeriodicalId":165068,"journal":{"name":"2022 15th International Conference on Advanced Computer Theory and Engineering (ICACTE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129224902","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}
In the drawing process of Thangka, the painter can draw different types of Thangka on the same line drawing, but the painter needs to redraw an identical line drawing every time. The drawing and coloring of the line draft are time-consuming and laborious. Therefore, in view of the difficulty in obtaining the real line drawing image data of Thangka and the distortion of the effect of the existing line drawing extraction methods, this paper proposes a Thangka line drawing extraction method based on Transformer: ETLTER. By introducing Vision Transformer, ETLTER captures coarse-grained global context, medium-grained local context, and fine-grained detail context features simultaneously in the three stages. In addition, the feature fusion module (FFM) fuses the feature information extracted from the three stages to predict the final Thangka manuscript effect. Through the processing results of the above three stages, ETLTER can generate clear and concise Thangka line drawings. Based on our own Thangka image dataset TK1500, the Thangka line drawings extracted by the model in this paper have less noise, and clear lines and are close to the line drawings drawn by the real Thangka painter compared with the existing line drawings extraction methods. The average rank of manuscript images extracted by this method is 1.167, ranking first among the 30 methods. The comprehensive evaluation results show that our methods achieve the state-of-art performance in Thangka line drawing extraction, and ETLTER is of great significance to the training of new Thangka painters.
{"title":"Image Extraction of Thangka Line Drawings with Transformer","authors":"Fubo Wang, Shenglin Geng, Dan Zhang, Mingquan Zhou, Lujia Li, Wei Nian","doi":"10.1109/ICACTE55855.2022.9943668","DOIUrl":"https://doi.org/10.1109/ICACTE55855.2022.9943668","url":null,"abstract":"In the drawing process of Thangka, the painter can draw different types of Thangka on the same line drawing, but the painter needs to redraw an identical line drawing every time. The drawing and coloring of the line draft are time-consuming and laborious. Therefore, in view of the difficulty in obtaining the real line drawing image data of Thangka and the distortion of the effect of the existing line drawing extraction methods, this paper proposes a Thangka line drawing extraction method based on Transformer: ETLTER. By introducing Vision Transformer, ETLTER captures coarse-grained global context, medium-grained local context, and fine-grained detail context features simultaneously in the three stages. In addition, the feature fusion module (FFM) fuses the feature information extracted from the three stages to predict the final Thangka manuscript effect. Through the processing results of the above three stages, ETLTER can generate clear and concise Thangka line drawings. Based on our own Thangka image dataset TK1500, the Thangka line drawings extracted by the model in this paper have less noise, and clear lines and are close to the line drawings drawn by the real Thangka painter compared with the existing line drawings extraction methods. The average rank of manuscript images extracted by this method is 1.167, ranking first among the 30 methods. The comprehensive evaluation results show that our methods achieve the state-of-art performance in Thangka line drawing extraction, and ETLTER is of great significance to the training of new Thangka painters.","PeriodicalId":165068,"journal":{"name":"2022 15th International Conference on Advanced Computer Theory and Engineering (ICACTE)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125379223","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 : 2022-09-23DOI: 10.1109/ICACTE55855.2022.9943631
Zhibo Chen, Jun-Shon Huang, Ya Wang
In view of the problem of error propagation caused by the traditional word segmentation error, and the insufficient application of the word vector in the Chinese named entity recognition, this paper proposes an improvement method based on location information and word frequency. Enter it in terms of characters, match the single character and the vocabulary in the vocabulary bank, classify the matched vocabulary according to the position of the characters in the vocabulary, calculate the weight according to the vocabulary of different positions, fuse it with each word vector, and finally join it with the word vector. The splicing results were taken as input to the bidirectional long and short-term network and finally decoded through a conditional random field. Simulations performed on the People’s Daily dataset achieved 95.80% F1 values, better than BiLSTM-CRF, BiLSTM-CNN, etc.
{"title":"Chinese Named Entity Recognition Based on Location Information and Word Frequency","authors":"Zhibo Chen, Jun-Shon Huang, Ya Wang","doi":"10.1109/ICACTE55855.2022.9943631","DOIUrl":"https://doi.org/10.1109/ICACTE55855.2022.9943631","url":null,"abstract":"In view of the problem of error propagation caused by the traditional word segmentation error, and the insufficient application of the word vector in the Chinese named entity recognition, this paper proposes an improvement method based on location information and word frequency. Enter it in terms of characters, match the single character and the vocabulary in the vocabulary bank, classify the matched vocabulary according to the position of the characters in the vocabulary, calculate the weight according to the vocabulary of different positions, fuse it with each word vector, and finally join it with the word vector. The splicing results were taken as input to the bidirectional long and short-term network and finally decoded through a conditional random field. Simulations performed on the People’s Daily dataset achieved 95.80% F1 values, better than BiLSTM-CRF, BiLSTM-CNN, etc.","PeriodicalId":165068,"journal":{"name":"2022 15th International Conference on Advanced Computer Theory and Engineering (ICACTE)","volume":"02 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129853025","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 : 2022-09-23DOI: 10.1109/ICACTE55855.2022.9943594
Zichen Wang, Jianzhong Qiao
Few-shot remote sensing scene classification is one of the research topics in the field of computer vision and few-shot learning, aiming to classify remote sensing scene through few training samples. The current methods of few-shot remote sensing scene classification use single metric, thus the classification accuracy is affected for the features cannot be effectively extracted. Therefore, we propose multi-metric fusion networks (MMFN) to address the problem via assembling a feature map multi encoder (FMME) and relation attention networks (RAN) to extract the features effectively and improve the classification accuracy. The FMME is designed to further encode the feature map which is extracted in the embedding phase to get different meaningful features. The RAN is aiming to calculate the similarity between features via fusing results of multiple methods based on image attention mechanism. Experimental results on three remote sensing data sets show that the multi-metric fusion method can extract meaningful features and effectively improve the classification performance of few-shot remote sensing scene.
{"title":"Few-Shot Remote Sensing Scene Classification with Multi-Metric Fusion","authors":"Zichen Wang, Jianzhong Qiao","doi":"10.1109/ICACTE55855.2022.9943594","DOIUrl":"https://doi.org/10.1109/ICACTE55855.2022.9943594","url":null,"abstract":"Few-shot remote sensing scene classification is one of the research topics in the field of computer vision and few-shot learning, aiming to classify remote sensing scene through few training samples. The current methods of few-shot remote sensing scene classification use single metric, thus the classification accuracy is affected for the features cannot be effectively extracted. Therefore, we propose multi-metric fusion networks (MMFN) to address the problem via assembling a feature map multi encoder (FMME) and relation attention networks (RAN) to extract the features effectively and improve the classification accuracy. The FMME is designed to further encode the feature map which is extracted in the embedding phase to get different meaningful features. The RAN is aiming to calculate the similarity between features via fusing results of multiple methods based on image attention mechanism. Experimental results on three remote sensing data sets show that the multi-metric fusion method can extract meaningful features and effectively improve the classification performance of few-shot remote sensing scene.","PeriodicalId":165068,"journal":{"name":"2022 15th International Conference on Advanced Computer Theory and Engineering (ICACTE)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125726699","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：