Pub Date : 2021-06-01DOI: 10.1109/ICCEA53728.2021.00018
Xie Lei, Ding Dali, Zhang Hongpeng, Wang Jianpu, Zhang Zhuoran
To the problem of low accuracy of unmanned combat aircraft maneuver trajectory, a particle swarm optimization convolutional neural network prediction method is proposed. Firstly, establish a three-degree-of-freedom model of Unmanned Combat Aerial Vehicles (UCAV) with constraints to solve the problem of trajectory source. The structure of the convolutional neural network is analyzed, and the particle swarm optimization algorithm (PSO) is used to replace the backpropagation algorithm to update the internal weights and biases. The PSO is compared with multiple algorithms, and the results show that the PSO updates the weights fast and has small errors. Finally, the prediction is made on a relatively complex and cluttered maneuvering trajectory. The method proposed in this paper is compared with three traditional prediction methods, and the result shows that the method proposed in this paper has small prediction errors.
{"title":"UCAV maneuvering trajectory prediction based on PSO-CNN","authors":"Xie Lei, Ding Dali, Zhang Hongpeng, Wang Jianpu, Zhang Zhuoran","doi":"10.1109/ICCEA53728.2021.00018","DOIUrl":"https://doi.org/10.1109/ICCEA53728.2021.00018","url":null,"abstract":"To the problem of low accuracy of unmanned combat aircraft maneuver trajectory, a particle swarm optimization convolutional neural network prediction method is proposed. Firstly, establish a three-degree-of-freedom model of Unmanned Combat Aerial Vehicles (UCAV) with constraints to solve the problem of trajectory source. The structure of the convolutional neural network is analyzed, and the particle swarm optimization algorithm (PSO) is used to replace the backpropagation algorithm to update the internal weights and biases. The PSO is compared with multiple algorithms, and the results show that the PSO updates the weights fast and has small errors. Finally, the prediction is made on a relatively complex and cluttered maneuvering trajectory. The method proposed in this paper is compared with three traditional prediction methods, and the result shows that the method proposed in this paper has small prediction errors.","PeriodicalId":325790,"journal":{"name":"2021 International Conference on Computer Engineering and Application (ICCEA)","volume":"207 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123266422","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 : 2021-06-01DOI: 10.1109/ICCEA53728.2021.00084
Zeyu Li
Autonomous driving technology aims to make driving decisions based on information about the vehicle’s environment. Navigation-based autonomous driving in urban scenarios has more complex scenarios than in relatively simple scenarios such as highways and parking lots, and is a task that still needs to be explored over time. Imitation learning models based on supervised learning methods are limited by the amount of expert data collected. Models based on reinforcement learning methods are able to interact with the environment, but are data inefficient and require a lot of exploration to learn effective policy. We propose a method that combines imitation learning with reinforcement learning enabling agent to achieve a higher success rate in urban autonomous driving navigation scenarios. To solve the problem of inefficient reinforcement learning data, our method decomposes the action space into low-level action space and high-level actin space, where low-level action space is multiple pre-trained imitation learning action space is a combination of several pre-trained imitation learning action spaces based on different control signals (i.e., follow, straight, turn right, turn left). High-level action space includes different control signals, the agent executes a specific imitation learning policy by selecting control signals from the high-level action space through a DQN-based reinforcement learning approach. Moreover, we propose a new reward for high level action selection. Experiments on the CARLA driving benchmark demonstrate that our approach outperforms both imitation learning methods and reinforcement learning methods on a variety of navigation-based driving tasks.
{"title":"A Hierarchical Autonomous Driving Framework Combining Reinforcement Learning and Imitation Learning","authors":"Zeyu Li","doi":"10.1109/ICCEA53728.2021.00084","DOIUrl":"https://doi.org/10.1109/ICCEA53728.2021.00084","url":null,"abstract":"Autonomous driving technology aims to make driving decisions based on information about the vehicle’s environment. Navigation-based autonomous driving in urban scenarios has more complex scenarios than in relatively simple scenarios such as highways and parking lots, and is a task that still needs to be explored over time. Imitation learning models based on supervised learning methods are limited by the amount of expert data collected. Models based on reinforcement learning methods are able to interact with the environment, but are data inefficient and require a lot of exploration to learn effective policy. We propose a method that combines imitation learning with reinforcement learning enabling agent to achieve a higher success rate in urban autonomous driving navigation scenarios. To solve the problem of inefficient reinforcement learning data, our method decomposes the action space into low-level action space and high-level actin space, where low-level action space is multiple pre-trained imitation learning action space is a combination of several pre-trained imitation learning action spaces based on different control signals (i.e., follow, straight, turn right, turn left). High-level action space includes different control signals, the agent executes a specific imitation learning policy by selecting control signals from the high-level action space through a DQN-based reinforcement learning approach. Moreover, we propose a new reward for high level action selection. Experiments on the CARLA driving benchmark demonstrate that our approach outperforms both imitation learning methods and reinforcement learning methods on a variety of navigation-based driving tasks.","PeriodicalId":325790,"journal":{"name":"2021 International Conference on Computer Engineering and Application (ICCEA)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116247302","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 : 2021-06-01DOI: 10.1109/ICCEA53728.2021.00068
Chun Long, Xisheng Xiao, Wei Wan, Jing Zhao, Jinxia Wei, Guanyao Du
With the development of botnets, detecting and preventing botnet attacks has become an important task of network security research. Existing works rarely consider timing patterns in botnets, and thus are not effective in realistic botnet detection, nor can they detect unknown botnets. To deal with these problems, this paper proposes a flow summary and graph sampling based botnet detection method using machine learning algorithms. Firstly, the network flow data is aggregated according to the source host IPs, and the flow summary records are generated within a duration of time window. Meanwhile, we use graph sampling technology to obtain a subset of entire graph, obtaining 4 graph features which are added to the flow summary records. Afterwards, decision tree, random forest and XGBoost machine learning classification models are built to validate the performance of our method. The experimental results on the Bot- IoT and CTU-13 datasets show that the method we proposed can effectively detect botnet traffic and unknown botnets.
{"title":"Botnet Detection Based on Flow Summary and Graph Sampling with Machine Learning","authors":"Chun Long, Xisheng Xiao, Wei Wan, Jing Zhao, Jinxia Wei, Guanyao Du","doi":"10.1109/ICCEA53728.2021.00068","DOIUrl":"https://doi.org/10.1109/ICCEA53728.2021.00068","url":null,"abstract":"With the development of botnets, detecting and preventing botnet attacks has become an important task of network security research. Existing works rarely consider timing patterns in botnets, and thus are not effective in realistic botnet detection, nor can they detect unknown botnets. To deal with these problems, this paper proposes a flow summary and graph sampling based botnet detection method using machine learning algorithms. Firstly, the network flow data is aggregated according to the source host IPs, and the flow summary records are generated within a duration of time window. Meanwhile, we use graph sampling technology to obtain a subset of entire graph, obtaining 4 graph features which are added to the flow summary records. Afterwards, decision tree, random forest and XGBoost machine learning classification models are built to validate the performance of our method. The experimental results on the Bot- IoT and CTU-13 datasets show that the method we proposed can effectively detect botnet traffic and unknown botnets.","PeriodicalId":325790,"journal":{"name":"2021 International Conference on Computer Engineering and Application (ICCEA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122501118","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 : 2021-06-01DOI: 10.1109/ICCEA53728.2021.00087
Jing Liu
With the continuous improvement of China’s social and economic level, people’s aesthetic ability is also constantly improving. At present, the full application of computer graphics and illustration art in the process of commercial design is positively helpful to improve the level of commercial design. In order to fully grasp the practical points of computer graphic illustration art in commercial design, we need to conduct research from the main role of computer graphic illustration art in the process of commercial design. At the same time, we want to analyze the challenges faced by computer graphic illustration art in the business process, and explore the practical points of illustration art in commercial design. Only in this way can the creative level of computer graphic illustration art be improved and the long-term development of the illustration art market can be promoted.
{"title":"The Practice of Computer Graphic Illustration Art in Commercial Design","authors":"Jing Liu","doi":"10.1109/ICCEA53728.2021.00087","DOIUrl":"https://doi.org/10.1109/ICCEA53728.2021.00087","url":null,"abstract":"With the continuous improvement of China’s social and economic level, people’s aesthetic ability is also constantly improving. At present, the full application of computer graphics and illustration art in the process of commercial design is positively helpful to improve the level of commercial design. In order to fully grasp the practical points of computer graphic illustration art in commercial design, we need to conduct research from the main role of computer graphic illustration art in the process of commercial design. At the same time, we want to analyze the challenges faced by computer graphic illustration art in the business process, and explore the practical points of illustration art in commercial design. Only in this way can the creative level of computer graphic illustration art be improved and the long-term development of the illustration art market can be promoted.","PeriodicalId":325790,"journal":{"name":"2021 International Conference on Computer Engineering and Application (ICCEA)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125207666","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 : 2021-06-01DOI: 10.1109/ICCEA53728.2021.00064
Lifan Zeng, Junjie Wu
Gradual adoption of Artificial intelligence (AI) and its potential impact have received considerable attention in the business and societal landscape. Grounded on extensive literature review, this paper proposes a two-dimensional framework to address the dark side of emergent AI technology applications. This work not only enhance our understanding of the technological rhetoric-reality gap between high expectations and potential negative issues of AI but also highlight the areas that future research might focus on.
{"title":"A wo-dimensional research framework for analysing dark side of AI","authors":"Lifan Zeng, Junjie Wu","doi":"10.1109/ICCEA53728.2021.00064","DOIUrl":"https://doi.org/10.1109/ICCEA53728.2021.00064","url":null,"abstract":"Gradual adoption of Artificial intelligence (AI) and its potential impact have received considerable attention in the business and societal landscape. Grounded on extensive literature review, this paper proposes a two-dimensional framework to address the dark side of emergent AI technology applications. This work not only enhance our understanding of the technological rhetoric-reality gap between high expectations and potential negative issues of AI but also highlight the areas that future research might focus on.","PeriodicalId":325790,"journal":{"name":"2021 International Conference on Computer Engineering and Application (ICCEA)","volume":"149 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120869821","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 : 2021-06-01DOI: 10.1109/ICCEA53728.2021.00047
Duling Xv, Li Yang
In recent years, audio classification has been extensively studied, and the classification of urban sounds has great application requirements in criminal investigation and environmental protection. In this paper, a multi-feature hybrid description method is used to classify target city sounds with a multi-layer residual network structure. Firstly, a plurality of feature extraction results were compared with a conventional single feature. Secondly, different network models are studied, and their performance under different characteristics is tested and compared. Finally, comparing Resnet and multi-layer perceptrons, it is found that the Resnet50v2 method under mixed features has a better classification effect on the Ubansound8k data set, reaching 90.7%.
{"title":"Research on Urban Audio Classification Based on Residual Neural Network","authors":"Duling Xv, Li Yang","doi":"10.1109/ICCEA53728.2021.00047","DOIUrl":"https://doi.org/10.1109/ICCEA53728.2021.00047","url":null,"abstract":"In recent years, audio classification has been extensively studied, and the classification of urban sounds has great application requirements in criminal investigation and environmental protection. In this paper, a multi-feature hybrid description method is used to classify target city sounds with a multi-layer residual network structure. Firstly, a plurality of feature extraction results were compared with a conventional single feature. Secondly, different network models are studied, and their performance under different characteristics is tested and compared. Finally, comparing Resnet and multi-layer perceptrons, it is found that the Resnet50v2 method under mixed features has a better classification effect on the Ubansound8k data set, reaching 90.7%.","PeriodicalId":325790,"journal":{"name":"2021 International Conference on Computer Engineering and Application (ICCEA)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126721040","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 : 2021-06-01DOI: 10.1109/ICCEA53728.2021.00077
Chenglong Wang, Le Kang, Zhihong Zhang, Zhaohui Zhang, Xiaofeng Wang
With the development of the financial sector, the growing complexity of financial transaction network, effectively identify a trading network of key trader has a important significance. Trading network abstraction for complex networks, traders abstraction for nodes, trandings between traders abstraction for the edges. The method of degree centrality, clustering coefficient, betweenness centrality, closeness centrality and the like is not sufficient to evaluate the importance of the node. Therefore, we propose a novel algorithm to evaluate the importance of nodes in undirected and unweighted network. We take the degree centrality and clustering coefficient of the nodes as the evaluation indicators, and combine the importance contribution of the nearest and the next nearest nodes. Through normalization and averaging, the benchmark ranking of node importance is obtained, which comprehensively considers the global and local features of the nodes. We used the real trading network data from Zhengzhou Commodity Exchange (ZCE) to conduct three comparative experiments and analyses. The experiment results show that our method has achieved better results, and can effectively identify key trading traders in ZCE.
{"title":"Key Node Detection in Financial Complex Network","authors":"Chenglong Wang, Le Kang, Zhihong Zhang, Zhaohui Zhang, Xiaofeng Wang","doi":"10.1109/ICCEA53728.2021.00077","DOIUrl":"https://doi.org/10.1109/ICCEA53728.2021.00077","url":null,"abstract":"With the development of the financial sector, the growing complexity of financial transaction network, effectively identify a trading network of key trader has a important significance. Trading network abstraction for complex networks, traders abstraction for nodes, trandings between traders abstraction for the edges. The method of degree centrality, clustering coefficient, betweenness centrality, closeness centrality and the like is not sufficient to evaluate the importance of the node. Therefore, we propose a novel algorithm to evaluate the importance of nodes in undirected and unweighted network. We take the degree centrality and clustering coefficient of the nodes as the evaluation indicators, and combine the importance contribution of the nearest and the next nearest nodes. Through normalization and averaging, the benchmark ranking of node importance is obtained, which comprehensively considers the global and local features of the nodes. We used the real trading network data from Zhengzhou Commodity Exchange (ZCE) to conduct three comparative experiments and analyses. The experiment results show that our method has achieved better results, and can effectively identify key trading traders in ZCE.","PeriodicalId":325790,"journal":{"name":"2021 International Conference on Computer Engineering and Application (ICCEA)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127221657","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 : 2021-06-01DOI: 10.1109/ICCEA53728.2021.00066
Tianqi Li, Shifeng Yang, Zhidong Guo, Zhe Sheng
In view of the actual use of height limiting devices at home and abroad and the requirements of relevant standards, the system uses three-axis acceleration sensors and high-definition network cameras as the state detection devices of height limiting devices. When an accident occurs when an ultra-high vehicle hits height limiting equipment, the acceleration sensors collect the spatial position information and acceleration information of height limiting devices and transmit them to the cloud through NB-Iot. At the same time, the 4g network camera is ordered to collect pictures and video information within the specified time and transmit them to the cloud server, and all data in the cloud server are obtained at the management terminal, which is convenient for comprehensive analysis of accident information and unified command and dispatch. Experiment show that that system can stably monitor the health status of height limiting device, and give timely and accurate remote alarm in case of super-high accident, It is a safe and effective monitoring system for height limiting devices.
{"title":"Design of Monitoring System for Height Limiting Device Based on Acceleration Sensor","authors":"Tianqi Li, Shifeng Yang, Zhidong Guo, Zhe Sheng","doi":"10.1109/ICCEA53728.2021.00066","DOIUrl":"https://doi.org/10.1109/ICCEA53728.2021.00066","url":null,"abstract":"In view of the actual use of height limiting devices at home and abroad and the requirements of relevant standards, the system uses three-axis acceleration sensors and high-definition network cameras as the state detection devices of height limiting devices. When an accident occurs when an ultra-high vehicle hits height limiting equipment, the acceleration sensors collect the spatial position information and acceleration information of height limiting devices and transmit them to the cloud through NB-Iot. At the same time, the 4g network camera is ordered to collect pictures and video information within the specified time and transmit them to the cloud server, and all data in the cloud server are obtained at the management terminal, which is convenient for comprehensive analysis of accident information and unified command and dispatch. Experiment show that that system can stably monitor the health status of height limiting device, and give timely and accurate remote alarm in case of super-high accident, It is a safe and effective monitoring system for height limiting devices.","PeriodicalId":325790,"journal":{"name":"2021 International Conference on Computer Engineering and Application (ICCEA)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130593383","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 : 2021-06-01DOI: 10.1109/ICCEA53728.2021.00010
Zhiang Xu, Zhiqiang Fan
With the development of information technology and the transformation of war concepts, the traditional combat method centered on weapons and equipment platforms has gradually transformed into network-centric information operations, among which military communication networks are the basis of military command and control in information warfare. Firstly, this article analyzes the basic characteristics and formation mechanism of the military communication network model, and then analyzes the performance indicators of the communication network model from the perspective of information flow integrity, information timeliness, and network anti-destructive ability. Secondly, this article obtains the optimization goal of the military communication network. And starting from the network topology, an innovative genetic algorithm is designed to adapt to the network model. Finally, this paper compares the optimization effects of genetic algorithm and other heuristic algorithms through a series of simulation experiments. The experiment proves that the improved genetic algorithm performs best in the optimization effect. This method provides theoretical guidance for the optimization of the topological structure of military communication networks.
{"title":"Topological structure optimization algorithm of military communication network based on genetic algorithm","authors":"Zhiang Xu, Zhiqiang Fan","doi":"10.1109/ICCEA53728.2021.00010","DOIUrl":"https://doi.org/10.1109/ICCEA53728.2021.00010","url":null,"abstract":"With the development of information technology and the transformation of war concepts, the traditional combat method centered on weapons and equipment platforms has gradually transformed into network-centric information operations, among which military communication networks are the basis of military command and control in information warfare. Firstly, this article analyzes the basic characteristics and formation mechanism of the military communication network model, and then analyzes the performance indicators of the communication network model from the perspective of information flow integrity, information timeliness, and network anti-destructive ability. Secondly, this article obtains the optimization goal of the military communication network. And starting from the network topology, an innovative genetic algorithm is designed to adapt to the network model. Finally, this paper compares the optimization effects of genetic algorithm and other heuristic algorithms through a series of simulation experiments. The experiment proves that the improved genetic algorithm performs best in the optimization effect. This method provides theoretical guidance for the optimization of the topological structure of military communication networks.","PeriodicalId":325790,"journal":{"name":"2021 International Conference on Computer Engineering and Application (ICCEA)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133554298","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 : 2021-06-01DOI: 10.1109/ICCEA53728.2021.00096
Cao Xin, Zhou Yuan, Chen Yi, Mai Weiqiang
Aiming at the path planning problem of UUV under obstacles constrait, this paper proposes a simple and feasible algorithm. The optimal path plan is obtained through the tangent theory based on the principle of minimum turning radius, and a detailed mathematical proof is given. The UUV multi-task route planning problem is transformed into a TSP model solution through the continuous Hopfield neural net-work. The simulation results show that the method can quickly and accurately solve UUV multi tasking route planning problem.
{"title":"UUV multi-task route planning under obstacles constrait","authors":"Cao Xin, Zhou Yuan, Chen Yi, Mai Weiqiang","doi":"10.1109/ICCEA53728.2021.00096","DOIUrl":"https://doi.org/10.1109/ICCEA53728.2021.00096","url":null,"abstract":"Aiming at the path planning problem of UUV under obstacles constrait, this paper proposes a simple and feasible algorithm. The optimal path plan is obtained through the tangent theory based on the principle of minimum turning radius, and a detailed mathematical proof is given. The UUV multi-task route planning problem is transformed into a TSP model solution through the continuous Hopfield neural net-work. The simulation results show that the method can quickly and accurately solve UUV multi tasking route planning problem.","PeriodicalId":325790,"journal":{"name":"2021 International Conference on Computer Engineering and Application (ICCEA)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133275138","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：