Pub Date : 2021-09-24DOI: 10.1109/ICISCAE52414.2021.9590705
Wenying Ge, Guoying Liu, Jing Lv
Oracle-bone inscriptions (OBIs), the oldest hieroglyphs in China, were mainly carved on cattle scapulars and tortoise shells, as well as other animal bones. However, automatically extracting OBI characters is a rather complex task due to their differences in character size, orientation, alignment and noisy background. Conventional techniques like Laplacian operation, gradient-edge, or connected component, cannot obtain satisfying results. Therefore, in this paper, instance segmentation methods under deep convolutional neural network were exploited to extract OBIs automatically. More specifically, a SOTA weakly supervised instance segmentation model was introduced to solve this problem, considering that the pixel-level annotation is notoriously time-consuming compared to the bounding boxes annotation, which is extremely serious for the annotation of OBI images because annotators' lack of domain knowledge. The model was trained by 3228 oracle rubbing images and were tested on 312 ones. Results demonstrated that this method can provide a feasible way to automatically extract OBIs from rubbing images (as shown in Fig. 1).
{"title":"Oracle Bone Inscriptions Extraction by Using Weakly Supervised Instance Segmentation under Deep Network","authors":"Wenying Ge, Guoying Liu, Jing Lv","doi":"10.1109/ICISCAE52414.2021.9590705","DOIUrl":"https://doi.org/10.1109/ICISCAE52414.2021.9590705","url":null,"abstract":"Oracle-bone inscriptions (OBIs), the oldest hieroglyphs in China, were mainly carved on cattle scapulars and tortoise shells, as well as other animal bones. However, automatically extracting OBI characters is a rather complex task due to their differences in character size, orientation, alignment and noisy background. Conventional techniques like Laplacian operation, gradient-edge, or connected component, cannot obtain satisfying results. Therefore, in this paper, instance segmentation methods under deep convolutional neural network were exploited to extract OBIs automatically. More specifically, a SOTA weakly supervised instance segmentation model was introduced to solve this problem, considering that the pixel-level annotation is notoriously time-consuming compared to the bounding boxes annotation, which is extremely serious for the annotation of OBI images because annotators' lack of domain knowledge. The model was trained by 3228 oracle rubbing images and were tested on 312 ones. Results demonstrated that this method can provide a feasible way to automatically extract OBIs from rubbing images (as shown in Fig. 1).","PeriodicalId":121049,"journal":{"name":"2021 IEEE 4th International Conference on Information Systems and Computer Aided Education (ICISCAE)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114917920","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 : 2021-09-24DOI: 10.1109/ICISCAE52414.2021.9590720
Yunlong Wang, Lu Yang, Yukun Li, Lei Fu
Convolutional neural network has achieved a lot of success in the field of computer vision in the recent years. With the rapid development of convolutional neural network, most image classification task has achieved significant performance improvement. Although some progress has been made in the research of image classification methods, there are still some deficiencies. For example, many existing methods are difficult to adaptively mine the feature importance within the sample and the feature correlation between sample scales. In order to solve the above shortcomings, this paper mainly studies image classification based on dynamic adaptive learning. In this paper, Multi-Scale Dynamic Convolution (MSDC) is proposed and verified on the standard image classification data set. Our method can be adjusted adaptively according to different scales of input data. The experimental results show that the proposed method exceeds the relevant comparison methods.
{"title":"Multi-Scale Dynamic Convolution for Classification","authors":"Yunlong Wang, Lu Yang, Yukun Li, Lei Fu","doi":"10.1109/ICISCAE52414.2021.9590720","DOIUrl":"https://doi.org/10.1109/ICISCAE52414.2021.9590720","url":null,"abstract":"Convolutional neural network has achieved a lot of success in the field of computer vision in the recent years. With the rapid development of convolutional neural network, most image classification task has achieved significant performance improvement. Although some progress has been made in the research of image classification methods, there are still some deficiencies. For example, many existing methods are difficult to adaptively mine the feature importance within the sample and the feature correlation between sample scales. In order to solve the above shortcomings, this paper mainly studies image classification based on dynamic adaptive learning. In this paper, Multi-Scale Dynamic Convolution (MSDC) is proposed and verified on the standard image classification data set. Our method can be adjusted adaptively according to different scales of input data. The experimental results show that the proposed method exceeds the relevant comparison methods.","PeriodicalId":121049,"journal":{"name":"2021 IEEE 4th International Conference on Information Systems and Computer Aided Education (ICISCAE)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127339717","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 : 2021-09-24DOI: 10.1109/ICISCAE52414.2021.9590692
Guoying Liu, Wenying Ge, Bingxin Du
Oracle bone inscriptions (OBIs) are the origin of Chinese characters and play a pivotal role in the study of Chinese civilization and the world civilization. The automatic recognition of OBI character (OBIC) images is very import to the research and promotion of OBI culture. However, a large amount of these ancient characters have variants with totally different appearance, which brings very serious negative impact on the OBI studies. In this paper, we proposed to recognize variants of OBICs by combining deep convolutional neural networks (DCNNs) with spectral clustering (SC). The former is employed to provide accurate descriptions for OBIC images, and the latter is used to find variants of each OBIC class. More specifically, the pretrained ResNet50 is exploited to obtain image features, and the normalized graph cuts is employed to find variants. Besides, a label propagation algorithm is used to find the label of test OBICs based on the clustering results. The proposed method is tested on an OBIC image set, in which all images are cropped from OBI rubbing images. Experimental results have shown that our method has the ability to recognize OBIC's variants.
{"title":"Recognition of OBIC's Variants by Using Deep Neural Networks and Spectral Clustering","authors":"Guoying Liu, Wenying Ge, Bingxin Du","doi":"10.1109/ICISCAE52414.2021.9590692","DOIUrl":"https://doi.org/10.1109/ICISCAE52414.2021.9590692","url":null,"abstract":"Oracle bone inscriptions (OBIs) are the origin of Chinese characters and play a pivotal role in the study of Chinese civilization and the world civilization. The automatic recognition of OBI character (OBIC) images is very import to the research and promotion of OBI culture. However, a large amount of these ancient characters have variants with totally different appearance, which brings very serious negative impact on the OBI studies. In this paper, we proposed to recognize variants of OBICs by combining deep convolutional neural networks (DCNNs) with spectral clustering (SC). The former is employed to provide accurate descriptions for OBIC images, and the latter is used to find variants of each OBIC class. More specifically, the pretrained ResNet50 is exploited to obtain image features, and the normalized graph cuts is employed to find variants. Besides, a label propagation algorithm is used to find the label of test OBICs based on the clustering results. The proposed method is tested on an OBIC image set, in which all images are cropped from OBI rubbing images. Experimental results have shown that our method has the ability to recognize OBIC's variants.","PeriodicalId":121049,"journal":{"name":"2021 IEEE 4th International Conference on Information Systems and Computer Aided Education (ICISCAE)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126609803","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 : 2021-09-24DOI: 10.1109/ICISCAE52414.2021.9590648
W. Wen, Z. Wang, Z. Gu, Xiaoxia Xing
Under the environment of the new round of power system reform, the accounting mode of power grid is changed from price difference to cost plus income, and the competition on the power selling side is released, which greatly affects the income of regional power grids, thus greatly reducing the profit margin of power grid enterprises and greatly restricting the investment capacity. The new power reform also proposes to strengthen the overall planning of power. The investment decision-making problem of new power system is a high-dimensional, nonconvex and multi-constrained optimization problem, and the integration of wind farms further increases the difficulty of the problem. In order to optimize the problem better and enhance the convergence performance of the algorithm, based on DE(Differential Evolution) algorithm, some improvement measures such as shared fitness and adaptive adjustment of control parameters are introduced. The research results show that the improved algorithm proposed in this paper improves the convergence speed of DE algorithm, shortens the operation time to a certain extent, and obtains better optimization results, which verifies the effectiveness of the method.
{"title":"Research on a new dynamic model of power system investment decision based on differential evolution algorithm","authors":"W. Wen, Z. Wang, Z. Gu, Xiaoxia Xing","doi":"10.1109/ICISCAE52414.2021.9590648","DOIUrl":"https://doi.org/10.1109/ICISCAE52414.2021.9590648","url":null,"abstract":"Under the environment of the new round of power system reform, the accounting mode of power grid is changed from price difference to cost plus income, and the competition on the power selling side is released, which greatly affects the income of regional power grids, thus greatly reducing the profit margin of power grid enterprises and greatly restricting the investment capacity. The new power reform also proposes to strengthen the overall planning of power. The investment decision-making problem of new power system is a high-dimensional, nonconvex and multi-constrained optimization problem, and the integration of wind farms further increases the difficulty of the problem. In order to optimize the problem better and enhance the convergence performance of the algorithm, based on DE(Differential Evolution) algorithm, some improvement measures such as shared fitness and adaptive adjustment of control parameters are introduced. The research results show that the improved algorithm proposed in this paper improves the convergence speed of DE algorithm, shortens the operation time to a certain extent, and obtains better optimization results, which verifies the effectiveness of the method.","PeriodicalId":121049,"journal":{"name":"2021 IEEE 4th International Conference on Information Systems and Computer Aided Education (ICISCAE)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123590542","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 : 2021-09-24DOI: 10.1109/ICISCAE52414.2021.9590789
Hao Wen, Zhiwei Xu, Xiaoming Zhang
When measuring a complex surface, the probe must move gradually in the opposite direction of the normal vector of the surface to touch the work-piece surface and measure the actual spatial position of the measuring point. However, the triangular mesh is unavailable to obtain the normal vector directly and the normal vector of the corresponding facet will be used instead. This paper proposes a direct retrieving facet method of measuring the complex mesh surface. Through the operation of facet data acquisition, vector cross product calculation and selected facet judgement, the corresponding facet of the measuring point can be directly retrieved and the normal vector of the facet can be used to drive the movement of the probe for accuracy detection. Finally, the proposed method is programed and verified in IDEL by some test data. This method will be valuable for the high-speed precision detection and can be used for the complete development of the complex mesh surface measuring system.
{"title":"A Direct Retrieving Facet Method of Measuring the Complex Mesh Surface","authors":"Hao Wen, Zhiwei Xu, Xiaoming Zhang","doi":"10.1109/ICISCAE52414.2021.9590789","DOIUrl":"https://doi.org/10.1109/ICISCAE52414.2021.9590789","url":null,"abstract":"When measuring a complex surface, the probe must move gradually in the opposite direction of the normal vector of the surface to touch the work-piece surface and measure the actual spatial position of the measuring point. However, the triangular mesh is unavailable to obtain the normal vector directly and the normal vector of the corresponding facet will be used instead. This paper proposes a direct retrieving facet method of measuring the complex mesh surface. Through the operation of facet data acquisition, vector cross product calculation and selected facet judgement, the corresponding facet of the measuring point can be directly retrieved and the normal vector of the facet can be used to drive the movement of the probe for accuracy detection. Finally, the proposed method is programed and verified in IDEL by some test data. This method will be valuable for the high-speed precision detection and can be used for the complete development of the complex mesh surface measuring system.","PeriodicalId":121049,"journal":{"name":"2021 IEEE 4th International Conference on Information Systems and Computer Aided Education (ICISCAE)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133849537","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 : 2021-09-24DOI: 10.1109/ICISCAE52414.2021.9590765
Feifan Wang, Shuo Wang, Qingguo Tang, Yongjie Du
As a structured semantic knowledge system, knowledge graph mainly uses symbols to present physical concepts in real life, which involves three aspects: triples, entities and the network structure connected with related number structures. Although there is a wide range of research on knowledge graph at present, most of the research on knowledge graph in China is of general type. Therefore, on the basis of clarifying the construction method of required knowledge graph, this paper, aiming at the overall formal representation and construction framework of knowledge graph, makes clear the specific representation mode of pattern layer and data layer from the logical perspective, and then verifies and analyzes the proposed method.
{"title":"Study on the Construction Method of Requirement Knowledge Atlas Based on Graph Neural Network","authors":"Feifan Wang, Shuo Wang, Qingguo Tang, Yongjie Du","doi":"10.1109/ICISCAE52414.2021.9590765","DOIUrl":"https://doi.org/10.1109/ICISCAE52414.2021.9590765","url":null,"abstract":"As a structured semantic knowledge system, knowledge graph mainly uses symbols to present physical concepts in real life, which involves three aspects: triples, entities and the network structure connected with related number structures. Although there is a wide range of research on knowledge graph at present, most of the research on knowledge graph in China is of general type. Therefore, on the basis of clarifying the construction method of required knowledge graph, this paper, aiming at the overall formal representation and construction framework of knowledge graph, makes clear the specific representation mode of pattern layer and data layer from the logical perspective, and then verifies and analyzes the proposed method.","PeriodicalId":121049,"journal":{"name":"2021 IEEE 4th International Conference on Information Systems and Computer Aided Education (ICISCAE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130766338","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 : 2021-09-24DOI: 10.1109/ICISCAE52414.2021.9590658
Xingtong Chen, Yanfei Gong
When a circuit breaker switches on high voltage shunt capacitors, high inrush current will occur and may induce restrike, which will harm the power system and some electrical devices. This paper firstly calculates the expression of the capacitive current accurately when the high voltage shunt capacitor switches on, and get the steady component and the transient component of the capacitive current respectively. Then proposes a precharge strategy to suppress the inrush current caused by capacitor switching on according to the calculation results. The proposed strategy can make the transient component of closing current zero or minimum. The target value of precharge is obtained by the theoretical derivation. Then a precharge strategy for single-phase, two-phase and three-phase precharging is proposed and a topology of precharge device is put forward based on the target value. Finally a PSCAD simulation model is built to validate the proposed precharge strategy. The simulation results show that the inrush current can be limited under 1.7p.u. The single-phase precharge can reduce the inrush current by 70%, and two-phase precharge can make the three-phase closing inrush surge rate over 50%. The duration time of closing transient is sharply shortened as well. Thereby the effectiveness of the proposed precharge strategy is verified.
{"title":"Precharge Switch: A Strategy to Suppress the Inrush Current of High Voltage Capacitor","authors":"Xingtong Chen, Yanfei Gong","doi":"10.1109/ICISCAE52414.2021.9590658","DOIUrl":"https://doi.org/10.1109/ICISCAE52414.2021.9590658","url":null,"abstract":"When a circuit breaker switches on high voltage shunt capacitors, high inrush current will occur and may induce restrike, which will harm the power system and some electrical devices. This paper firstly calculates the expression of the capacitive current accurately when the high voltage shunt capacitor switches on, and get the steady component and the transient component of the capacitive current respectively. Then proposes a precharge strategy to suppress the inrush current caused by capacitor switching on according to the calculation results. The proposed strategy can make the transient component of closing current zero or minimum. The target value of precharge is obtained by the theoretical derivation. Then a precharge strategy for single-phase, two-phase and three-phase precharging is proposed and a topology of precharge device is put forward based on the target value. Finally a PSCAD simulation model is built to validate the proposed precharge strategy. The simulation results show that the inrush current can be limited under 1.7p.u. The single-phase precharge can reduce the inrush current by 70%, and two-phase precharge can make the three-phase closing inrush surge rate over 50%. The duration time of closing transient is sharply shortened as well. Thereby the effectiveness of the proposed precharge strategy is verified.","PeriodicalId":121049,"journal":{"name":"2021 IEEE 4th International Conference on Information Systems and Computer Aided Education (ICISCAE)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132147000","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 : 2021-09-24DOI: 10.1109/ICISCAE52414.2021.9590697
Shengqiang Bao
With the improvement of industrial automation level and the progress of science and technology, the number of robots is increasing, the application scenarios are becoming more and more complex, and the requirements for automation, intelligence, precision, stability and flexibility of robots are also increasing. Machine vision refers to the use of machines instead of human eyes for measurement and judgment. The ultimate goal of machine vision is to enable machines to observe and understand the input image data accurately like human eyes, and finally make decisions to achieve the purpose of adapting to the environment autonomously. In the traditional industrial production line, the task of sorting workpieces is carried out manually, which is not only inefficient but also costly. It is the trend of industrial automation to apply machine vision technology to sorting tasks of industrial robots. According to the actual needs of China's production industry, based on advanced technologies such as deep learning algorithm and machine vision, this paper constructs a high-speed robot sorting system for product production to improve the overall operation effect of the robot sorting system.
{"title":"Research on Machine Vision Technology of High Speed Robot Sorting System Based on Deep Learning","authors":"Shengqiang Bao","doi":"10.1109/ICISCAE52414.2021.9590697","DOIUrl":"https://doi.org/10.1109/ICISCAE52414.2021.9590697","url":null,"abstract":"With the improvement of industrial automation level and the progress of science and technology, the number of robots is increasing, the application scenarios are becoming more and more complex, and the requirements for automation, intelligence, precision, stability and flexibility of robots are also increasing. Machine vision refers to the use of machines instead of human eyes for measurement and judgment. The ultimate goal of machine vision is to enable machines to observe and understand the input image data accurately like human eyes, and finally make decisions to achieve the purpose of adapting to the environment autonomously. In the traditional industrial production line, the task of sorting workpieces is carried out manually, which is not only inefficient but also costly. It is the trend of industrial automation to apply machine vision technology to sorting tasks of industrial robots. According to the actual needs of China's production industry, based on advanced technologies such as deep learning algorithm and machine vision, this paper constructs a high-speed robot sorting system for product production to improve the overall operation effect of the robot sorting system.","PeriodicalId":121049,"journal":{"name":"2021 IEEE 4th International Conference on Information Systems and Computer Aided Education (ICISCAE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129790913","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 : 2021-09-24DOI: 10.1109/ICISCAE52414.2021.9590735
Wenqi Wu
The purpose of the application of UAV navigation system is to accurately judge the position of UAV in horizontal space and ensure that it can fly according to the expected set course. Although the inertia-satellite (GPS) navigation system design proposed in the past is in line with the development needs of the traditional market, in the new era, as small unmanned aerial vehicles enter the field of vision of researchers, experts begin to carry out a new design of the countermeasures and algorithms of the navigation control system. Therefore, this paper analyzes how to design and implement the navigation algorithm of small unmanned aerial vehicles (U AVs) based on expert PID combined with the design method of expert PID navigation control law while understanding the design scheme and basic principles of the existing navigation algorithm of small unmanned aerial vehicles (UAVs).
{"title":"Design of Small Unmanned Aerial Vehicle Navigation Algorithm Based on Control PID","authors":"Wenqi Wu","doi":"10.1109/ICISCAE52414.2021.9590735","DOIUrl":"https://doi.org/10.1109/ICISCAE52414.2021.9590735","url":null,"abstract":"The purpose of the application of UAV navigation system is to accurately judge the position of UAV in horizontal space and ensure that it can fly according to the expected set course. Although the inertia-satellite (GPS) navigation system design proposed in the past is in line with the development needs of the traditional market, in the new era, as small unmanned aerial vehicles enter the field of vision of researchers, experts begin to carry out a new design of the countermeasures and algorithms of the navigation control system. Therefore, this paper analyzes how to design and implement the navigation algorithm of small unmanned aerial vehicles (U AVs) based on expert PID combined with the design method of expert PID navigation control law while understanding the design scheme and basic principles of the existing navigation algorithm of small unmanned aerial vehicles (UAVs).","PeriodicalId":121049,"journal":{"name":"2021 IEEE 4th International Conference on Information Systems and Computer Aided Education (ICISCAE)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133147961","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}
The rapid development of general aviation leads to many problems in air traffic management. The efficient and accurate flight trajectory prediction is the key technology to improve the safety and management efficiency of general aviation flight. Aiming at the problem that the communication signal of general aviation flying at low altitude is affected by factors such as mountains and buildings, this paper proposes a short-term flight trajectory prediction method based on log short term memory (LSTM) by adding the characteristics of displacement at adjacent moments on the basis of real-time flight trajectory data of general aviation aircraft. The results show that the flight trajectory prediction model based on LSTM has a high accuracy (81.65%). The predicted flight trajectory is consistent with the actual flight trajectory and the latitude and longitude positions are close. This method meets the requirements of real-time flight trajectory of general aviation aircraft.
{"title":"Flight Trajectory Prediction of General Aviation Aircraft Based on LSTM Model","authors":"Biao Wang, Zhengang Zhai, Renhao Xiong, Bingtao Gao","doi":"10.1109/ICISCAE52414.2021.9590656","DOIUrl":"https://doi.org/10.1109/ICISCAE52414.2021.9590656","url":null,"abstract":"The rapid development of general aviation leads to many problems in air traffic management. The efficient and accurate flight trajectory prediction is the key technology to improve the safety and management efficiency of general aviation flight. Aiming at the problem that the communication signal of general aviation flying at low altitude is affected by factors such as mountains and buildings, this paper proposes a short-term flight trajectory prediction method based on log short term memory (LSTM) by adding the characteristics of displacement at adjacent moments on the basis of real-time flight trajectory data of general aviation aircraft. The results show that the flight trajectory prediction model based on LSTM has a high accuracy (81.65%). The predicted flight trajectory is consistent with the actual flight trajectory and the latitude and longitude positions are close. This method meets the requirements of real-time flight trajectory of general aviation aircraft.","PeriodicalId":121049,"journal":{"name":"2021 IEEE 4th International Conference on Information Systems and Computer Aided Education (ICISCAE)","volume":"44 51","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134225390","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：