To avoid the difficulty of image processing in the gigapixel optical system, this paper proposes a CUDA-based acceleration strategy for the rapid mosaic of a large-scale image and realizes the rapid mosaic of a large-scale image using the collaborative processing of CPU and GPU. Finally, the author designed an electronic hardware and software system and a fast splicing algorithm suitable for the rapid processing of large-scale image-based on a 100-megapixel monocentric multiscale optical system. And the real-time processing of data from nine 12 million pixel sub-cameras at 7.5 frames per second is completed to realize the real-time splicing of the video in the whole field of view.
{"title":"Design of Rapid Image Mosaic Based on CUDA by 100-Megapixel Optical System","authors":"Zhao-yi Tang, Yuan Tian, Zhennan Wang, Mingfei Xu, Ying-Yu Wang, Weiqun Ma, Xiaolong Wang","doi":"10.1145/3424978.3425105","DOIUrl":"https://doi.org/10.1145/3424978.3425105","url":null,"abstract":"To avoid the difficulty of image processing in the gigapixel optical system, this paper proposes a CUDA-based acceleration strategy for the rapid mosaic of a large-scale image and realizes the rapid mosaic of a large-scale image using the collaborative processing of CPU and GPU. Finally, the author designed an electronic hardware and software system and a fast splicing algorithm suitable for the rapid processing of large-scale image-based on a 100-megapixel monocentric multiscale optical system. And the real-time processing of data from nine 12 million pixel sub-cameras at 7.5 frames per second is completed to realize the real-time splicing of the video in the whole field of view.","PeriodicalId":178822,"journal":{"name":"Proceedings of the 4th International Conference on Computer Science and Application Engineering","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122965697","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}
By investigating the status of data commodity delivery after the completion of payment transactions by mainstream data trading platforms at home and abroad, this paper proposes an end-to-end data commodity delivery solution based on metadata. Designed and developed a secure, automated and standardized data service API interface specification from the two aspects of data commodity content description and acquisition method, and recorded data products, transactions and delivery process information on the blockchain. Effectively support the registration and authentication of data products, transaction process management, data demanders' understanding and use of purchased data, and market supervision.
{"title":"End-to-End Data Commodity Delivery Based on Metadata","authors":"Yaqing Si, Yuqian Huang, Tao Wang, Jing Su","doi":"10.1145/3424978.3425014","DOIUrl":"https://doi.org/10.1145/3424978.3425014","url":null,"abstract":"By investigating the status of data commodity delivery after the completion of payment transactions by mainstream data trading platforms at home and abroad, this paper proposes an end-to-end data commodity delivery solution based on metadata. Designed and developed a secure, automated and standardized data service API interface specification from the two aspects of data commodity content description and acquisition method, and recorded data products, transactions and delivery process information on the blockchain. Effectively support the registration and authentication of data products, transaction process management, data demanders' understanding and use of purchased data, and market supervision.","PeriodicalId":178822,"journal":{"name":"Proceedings of the 4th International Conference on Computer Science and Application Engineering","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115963828","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}
Minjie Wu, Zhenshan Zheng, Quan Wang, Tianzhen Meng
Most ready-made signal sorting algorithms does not perform well when the pulse repetition frequency (PRF) jitter and the PRF stagger signals impinging on the radar simultaneously. In view of this, an effective and fast signal sorting method based on dual-PRI Transform is proposed. In this correspondence, we fully exploit the differences between the jittered and the staggered signals to segment the mixed signals. The proposed algorithm consecutively implements two pulse repetition interval (PRI) transforms, followed by the first order sequential difference (SDIF) histogram, to analyze the signals. The experimental results verify the proposed method is simple and easy to implement, and the accuracy is high.
{"title":"A Pulse Repetition Frequency Sorting Algorithm Based on Dual-PRI Transform","authors":"Minjie Wu, Zhenshan Zheng, Quan Wang, Tianzhen Meng","doi":"10.1145/3424978.3424995","DOIUrl":"https://doi.org/10.1145/3424978.3424995","url":null,"abstract":"Most ready-made signal sorting algorithms does not perform well when the pulse repetition frequency (PRF) jitter and the PRF stagger signals impinging on the radar simultaneously. In view of this, an effective and fast signal sorting method based on dual-PRI Transform is proposed. In this correspondence, we fully exploit the differences between the jittered and the staggered signals to segment the mixed signals. The proposed algorithm consecutively implements two pulse repetition interval (PRI) transforms, followed by the first order sequential difference (SDIF) histogram, to analyze the signals. The experimental results verify the proposed method is simple and easy to implement, and the accuracy is high.","PeriodicalId":178822,"journal":{"name":"Proceedings of the 4th International Conference on Computer Science and Application Engineering","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130909597","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}
To solve the problem of insufficient number of check equation in the reconstruction of high order interfered scrambling code sequence, a reconstruction algorithm is proposed. Firstly, the check relationships based on the scrambling code generator polynomial are used to construct the factor graph, and the factor graph iteration method is used to estimate the scrambling code sequences. Secondly, the check relationship inspection method is used to evaluate the compatibility between the iterative estimation sequences and the generator polynomial, and select the best continuous codeword to restore the scrambler initial state. Finally, the optimal reconstruction sequence is selected from the scrambling code for initial state recovery according to the principle of minimum Hamming distance. Simulation results show that the algorithm can effectively solve the problem of reconstruction by using a limited number of check equations.
{"title":"Iterative Recovery for Interfered Scrambling Code Sequence on Factor Graph","authors":"Hongbo Hu, Zhengbo Sun, Yuxiang Yang, Bing Deng","doi":"10.1145/3424978.3425037","DOIUrl":"https://doi.org/10.1145/3424978.3425037","url":null,"abstract":"To solve the problem of insufficient number of check equation in the reconstruction of high order interfered scrambling code sequence, a reconstruction algorithm is proposed. Firstly, the check relationships based on the scrambling code generator polynomial are used to construct the factor graph, and the factor graph iteration method is used to estimate the scrambling code sequences. Secondly, the check relationship inspection method is used to evaluate the compatibility between the iterative estimation sequences and the generator polynomial, and select the best continuous codeword to restore the scrambler initial state. Finally, the optimal reconstruction sequence is selected from the scrambling code for initial state recovery according to the principle of minimum Hamming distance. Simulation results show that the algorithm can effectively solve the problem of reconstruction by using a limited number of check equations.","PeriodicalId":178822,"journal":{"name":"Proceedings of the 4th International Conference on Computer Science and Application Engineering","volume":"50 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130910707","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}
Intelligent interconnection put forward new requirements to power terminals, and the reconfigurable development mode, where "hardware as a platform and software to app" is the key to intelligent development, virtualization technology provides the possibility for the realization. This paper analyzes the problems and development trend of intelligent distribution transformer terminals in the new situation, based on the development of virtualization technology; it gives the terminal development proposal for realization of independent hardware and software environment through container technology. In addition, it analyzes the virtualization requirements of intelligent terminal. Finally, customized develops the software platform to adapt to the intelligent distribution transformer terminal. The experimental application results of terminal prototype, which is developed by integrated MCU chip, show that the virtualization technology is beneficial to realize "once encapsulation and running everywhere", and then conducive to the intelligent development of distribution transformer terminal.
{"title":"Research and Implementation on Intelligent Terminal Virtualization Technology","authors":"H. Bai, Chao Huo, Ganghong Zhang, Jinhong He, Jian Gao, Zhibin Yin","doi":"10.1145/3424978.3425163","DOIUrl":"https://doi.org/10.1145/3424978.3425163","url":null,"abstract":"Intelligent interconnection put forward new requirements to power terminals, and the reconfigurable development mode, where \"hardware as a platform and software to app\" is the key to intelligent development, virtualization technology provides the possibility for the realization. This paper analyzes the problems and development trend of intelligent distribution transformer terminals in the new situation, based on the development of virtualization technology; it gives the terminal development proposal for realization of independent hardware and software environment through container technology. In addition, it analyzes the virtualization requirements of intelligent terminal. Finally, customized develops the software platform to adapt to the intelligent distribution transformer terminal. The experimental application results of terminal prototype, which is developed by integrated MCU chip, show that the virtualization technology is beneficial to realize \"once encapsulation and running everywhere\", and then conducive to the intelligent development of distribution transformer terminal.","PeriodicalId":178822,"journal":{"name":"Proceedings of the 4th International Conference on Computer Science and Application Engineering","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125383574","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}
Aiming at solving problem of multi-attribute decision making of q-rung orthopair fuzzy, the method based on Hamacher norm and improved MULTIMOORA is proposed. Firstly, q-rung orthopair fuzzy Hamacher weighted average operator and q-rung orthopair fuzzy Hamacher weighted geometric average operator are proposed, and their properties are studied. Secondly, the reference point method in the MULTIMOORA method only calculates the distance between each scheme and the positive ideal scheme, ignores the distance between each scheme and the negative ideal scheme, so an improved MULTIMOORA method was put forward, and then alternative from multiple perspectives is chosen and compared by using the improved MULTIMOORA method and two operators. Finally, through an example, this method is compared with other q-ROF decision-making methods, and the sensitivity of the algorithm is analyzed.
{"title":"Multiple-attribute Decision-making of Q-Rung Orthopair Fuzzy Sets Based on Hamacher Norm and Improved MULTIMOORA","authors":"Yahui Zhu","doi":"10.1145/3424978.3425145","DOIUrl":"https://doi.org/10.1145/3424978.3425145","url":null,"abstract":"Aiming at solving problem of multi-attribute decision making of q-rung orthopair fuzzy, the method based on Hamacher norm and improved MULTIMOORA is proposed. Firstly, q-rung orthopair fuzzy Hamacher weighted average operator and q-rung orthopair fuzzy Hamacher weighted geometric average operator are proposed, and their properties are studied. Secondly, the reference point method in the MULTIMOORA method only calculates the distance between each scheme and the positive ideal scheme, ignores the distance between each scheme and the negative ideal scheme, so an improved MULTIMOORA method was put forward, and then alternative from multiple perspectives is chosen and compared by using the improved MULTIMOORA method and two operators. Finally, through an example, this method is compared with other q-ROF decision-making methods, and the sensitivity of the algorithm is analyzed.","PeriodicalId":178822,"journal":{"name":"Proceedings of the 4th International Conference on Computer Science and Application Engineering","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126221316","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}
This paper presents two models for high-speed railway image enhancement. The basic model is inspired by some neuroelectrophysiological experiments on retinal ganglion cell's non-classical receptive field that reveals dis-inhibitory properties of inhibitory subunits. In view of the fact that there are different Gaussian channels in the model of receptive field, we improve the basic model to change the inhibitory effects by means of the potential function designed to show variations of inhibitory intensity adaptively. In order to validate the models, lots of highspeed railway image enhancement experiments are presented to show preferable results obtained by our models.
{"title":"Non-classical Receptive Field Models with Inhibitory Subunits for High-speed Railway Image Enhancement","authors":"Xinyu Du, Yu Cheng, Zichen Gu","doi":"10.1145/3424978.3425113","DOIUrl":"https://doi.org/10.1145/3424978.3425113","url":null,"abstract":"This paper presents two models for high-speed railway image enhancement. The basic model is inspired by some neuroelectrophysiological experiments on retinal ganglion cell's non-classical receptive field that reveals dis-inhibitory properties of inhibitory subunits. In view of the fact that there are different Gaussian channels in the model of receptive field, we improve the basic model to change the inhibitory effects by means of the potential function designed to show variations of inhibitory intensity adaptively. In order to validate the models, lots of highspeed railway image enhancement experiments are presented to show preferable results obtained by our models.","PeriodicalId":178822,"journal":{"name":"Proceedings of the 4th International Conference on Computer Science and Application Engineering","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116025296","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}
Aiming at vehicles in the dense environment of tunnels, viaducts, mountainous areas, and high-rise buildings, GPS signals often suffer from short-term lock-out. A strong tracking unscented Kalman filter (STUKF) integrated navigation algorithm derived from Back Propagation neural network was proposed. This paper combines the idea of strong tracking filtering with the idea of unscented Kalman filtering, with the assistance of BP-neural network, and applies it to GPS/SINS integrated navigation with complementary advantages. The availability and reliability of the algorithm are tested by experimental simulation. Compared with the influence of BP neural network training before and after training on the accuracy of integrated navigation, the test results that this algorithm not only overcomes the shortcomings of GPS signal unlocking in harsh environment and Kalman filter fluctuates greatly in nonlinear environment, but also immensely improves the positioning precision of integrated navigation system, and provides new ideas for intelligent navigation fields such as unmanned vehicles and drones.
{"title":"Research on Strong Tracking UKF Algorithm of Integrated Navigation Based on BP Neural Network","authors":"Shuai Li, C. Cai","doi":"10.1145/3424978.3425162","DOIUrl":"https://doi.org/10.1145/3424978.3425162","url":null,"abstract":"Aiming at vehicles in the dense environment of tunnels, viaducts, mountainous areas, and high-rise buildings, GPS signals often suffer from short-term lock-out. A strong tracking unscented Kalman filter (STUKF) integrated navigation algorithm derived from Back Propagation neural network was proposed. This paper combines the idea of strong tracking filtering with the idea of unscented Kalman filtering, with the assistance of BP-neural network, and applies it to GPS/SINS integrated navigation with complementary advantages. The availability and reliability of the algorithm are tested by experimental simulation. Compared with the influence of BP neural network training before and after training on the accuracy of integrated navigation, the test results that this algorithm not only overcomes the shortcomings of GPS signal unlocking in harsh environment and Kalman filter fluctuates greatly in nonlinear environment, but also immensely improves the positioning precision of integrated navigation system, and provides new ideas for intelligent navigation fields such as unmanned vehicles and drones.","PeriodicalId":178822,"journal":{"name":"Proceedings of the 4th International Conference on Computer Science and Application Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123403943","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 this paper, we put forward a novel deep learning approach with Lp / L2 regularization based on sparse autoencoders network, trained by a nonnegativity constraint algorithm. Since L2 norm regularization penalizes the negative weights with smaller magnitudes much weaker than those with bigger magnitudes, lots of the weights could take small negative values. In order to address this issue, non-Lipschitz nonconvex LP norm (0
{"title":"Deep Learning Approach of Sparse Autoencoders with Lp/L2 Regularization","authors":"Ziheng Wu, Cong Li, Baigen Pan","doi":"10.1145/3424978.3425011","DOIUrl":"https://doi.org/10.1145/3424978.3425011","url":null,"abstract":"In this paper, we put forward a novel deep learning approach with Lp / L2 regularization based on sparse autoencoders network, trained by a nonnegativity constraint algorithm. Since L2 norm regularization penalizes the negative weights with smaller magnitudes much weaker than those with bigger magnitudes, lots of the weights could take small negative values. In order to address this issue, non-Lipschitz nonconvex LP norm (0<p<1) regularization which could force most of the negative weights to become non-negative is introduced, and the combination of LP/L2 norm regularization is applied for nonnegativity constraint. The proposed approach is analyzed for accuracy on the MNIST dataset for image classification, the experimental results have indicated that using both LP and L2 regularizations could induce non-negativity of weights and have promising performance.","PeriodicalId":178822,"journal":{"name":"Proceedings of the 4th International Conference on Computer Science and Application Engineering","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115340496","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}
This paper considers a slender fish swimming without using its tail fin, middle fin or other fins, but waving its body to move. The kinematic and dynamic models of fish are established, by assuming the fish consist of many rigid parts. Slender-body theory is used to calculate the hydrodynamics of fish. The fish is controlled by swinging its body to swim toward a specified target, based on the Actor-Critic method.
{"title":"Simulation of a Slender Fish Swimming Based on Machine Learning Method","authors":"Jian Zhu, Yingyu Hou, Ziqiang Liu","doi":"10.1145/3424978.3425062","DOIUrl":"https://doi.org/10.1145/3424978.3425062","url":null,"abstract":"This paper considers a slender fish swimming without using its tail fin, middle fin or other fins, but waving its body to move. The kinematic and dynamic models of fish are established, by assuming the fish consist of many rigid parts. Slender-body theory is used to calculate the hydrodynamics of fish. The fish is controlled by swinging its body to swim toward a specified target, based on the Actor-Critic method.","PeriodicalId":178822,"journal":{"name":"Proceedings of the 4th International Conference on Computer Science and Application Engineering","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124841599","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：