Pub Date : 2021-12-17DOI: 10.1109/ICCWAMTIP53232.2021.9674155
Di Liu, Mengjuan Wang, Hao Wang
RF fingerprint technology has received great attention and research due to its security and operability. Early research on radio frequency fingerprints mainly revolved around transient signals, and transient characteristics are currently the most mature research category. With the development of wireless communication technology, the existing radio frequency fingerprint identification technology has gradually been unable to meet practical needs. In recent years, with the rapid development of image recognition technology, some scholars have proposed to apply image recognition technology to RF fingerprint identification, thereby converting radio signal recognition problems into image recognition target detection problems, and making full use of advanced image recognition technology to improve equipment recognition accuracy. This paper proposes to convert the original I/Q signal into a spectrum waterfall diagram and input it into the image recognition model for training and recognition. The experimental results show that this method can effectively improve the accuracy of RF fingerprint recognition.
{"title":"RF Fingerprint Recognition Based On Spectrum Waterfall Diagram","authors":"Di Liu, Mengjuan Wang, Hao Wang","doi":"10.1109/ICCWAMTIP53232.2021.9674155","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP53232.2021.9674155","url":null,"abstract":"RF fingerprint technology has received great attention and research due to its security and operability. Early research on radio frequency fingerprints mainly revolved around transient signals, and transient characteristics are currently the most mature research category. With the development of wireless communication technology, the existing radio frequency fingerprint identification technology has gradually been unable to meet practical needs. In recent years, with the rapid development of image recognition technology, some scholars have proposed to apply image recognition technology to RF fingerprint identification, thereby converting radio signal recognition problems into image recognition target detection problems, and making full use of advanced image recognition technology to improve equipment recognition accuracy. This paper proposes to convert the original I/Q signal into a spectrum waterfall diagram and input it into the image recognition model for training and recognition. The experimental results show that this method can effectively improve the accuracy of RF fingerprint recognition.","PeriodicalId":358772,"journal":{"name":"2021 18th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131303662","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 : 2021-12-17DOI: 10.1109/ICCWAMTIP53232.2021.9674146
Liao Ruikun, Zhang Haitao, Li Yun, Chen Lirong, Zhang Qi
The static interaction method in automobile is difficult to solve the communication requirements of emerging technologies such as Advanced Driving Assistance System (ADAS) and Over-The-Air Technology (OTA). With the development of intelligence, automobiles will occupy an important position in the Internet of Things in the future. Therefore, they need to have the characteristics of openness, connectivity and self-evolution. Further, the design of Service-Oriented Architecture (SOA) is gradually introduced to provide more flexible communication and service call for the Internet of Vehicles. In traditional in-vehicle communication such as the CAN bus, a variety of security and safety mechanisms are adopted to protect the information and functional safety of vehicle. In automotive SOA, potential security threats also need be taken seriously. Aiming at the hidden dangers of unauthorized access in the automobile, we propose an efficient distributed access control architecture. And based on the message dissemination middleware-SOME/IP protocol of automotive SOA, a secure access control protocol-Security Expended SOME/IP (SE-SOME/IP) is designed, which can simultaneously have multiple security mechanisms and provide access control Function. The use of Attribute-Based Access Control and the introduction of Access Vector Cache can greatly shorten the request time of service.
{"title":"An Efficient Access Control Framework For Service-Oriented Architecture of Vehicle","authors":"Liao Ruikun, Zhang Haitao, Li Yun, Chen Lirong, Zhang Qi","doi":"10.1109/ICCWAMTIP53232.2021.9674146","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP53232.2021.9674146","url":null,"abstract":"The static interaction method in automobile is difficult to solve the communication requirements of emerging technologies such as Advanced Driving Assistance System (ADAS) and Over-The-Air Technology (OTA). With the development of intelligence, automobiles will occupy an important position in the Internet of Things in the future. Therefore, they need to have the characteristics of openness, connectivity and self-evolution. Further, the design of Service-Oriented Architecture (SOA) is gradually introduced to provide more flexible communication and service call for the Internet of Vehicles. In traditional in-vehicle communication such as the CAN bus, a variety of security and safety mechanisms are adopted to protect the information and functional safety of vehicle. In automotive SOA, potential security threats also need be taken seriously. Aiming at the hidden dangers of unauthorized access in the automobile, we propose an efficient distributed access control architecture. And based on the message dissemination middleware-SOME/IP protocol of automotive SOA, a secure access control protocol-Security Expended SOME/IP (SE-SOME/IP) is designed, which can simultaneously have multiple security mechanisms and provide access control Function. The use of Attribute-Based Access Control and the introduction of Access Vector Cache can greatly shorten the request time of service.","PeriodicalId":358772,"journal":{"name":"2021 18th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115780128","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 : 2021-12-17DOI: 10.1109/ICCWAMTIP53232.2021.9674165
Chenyi Qiang, Liqi Ping, Shui Gang, Wei Zi Hui
With the rapid development of computer network technology, the Internet has covered all aspects of social life. Nowadays, network technology is widely used in various social fields such as economy, military, education, etc. It promotes the rapid development of society and economy, and at the same time brings unprecedented challenges. The security of information transmission and interaction in cyberspace takes network traffic as the carrier, and network traffic contains a large amount of valuable information. How to perceive the current network status through the analysis of network traffic, discover network abnormalities in time is of great significance for maintaining network security. With the rapid development of deep learning in the field of artificial intelligence, researchers have tried to transfer deep learning methods that shine in computer vision processing, natural language recognition and other fields to the field of network flow detection. This paper proposes an ensemble model based on a convolutional neural network, which is integrated on the basis of the CNN model, which reduces the deviation of each basic model and improves the accuracy of the network stream classification results. The main tasks of this paper are as follows: (1) Experiments on the basic model and the integrated model were carried out on the USTC-TFC2016 data set. (2) The experimental results show that the ensemble model reduces the deviation of the basic model and improves the classification accuracy.
{"title":"Ensemble Method For Net Traffic Classification Based On Deep Learning","authors":"Chenyi Qiang, Liqi Ping, Shui Gang, Wei Zi Hui","doi":"10.1109/ICCWAMTIP53232.2021.9674165","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP53232.2021.9674165","url":null,"abstract":"With the rapid development of computer network technology, the Internet has covered all aspects of social life. Nowadays, network technology is widely used in various social fields such as economy, military, education, etc. It promotes the rapid development of society and economy, and at the same time brings unprecedented challenges. The security of information transmission and interaction in cyberspace takes network traffic as the carrier, and network traffic contains a large amount of valuable information. How to perceive the current network status through the analysis of network traffic, discover network abnormalities in time is of great significance for maintaining network security. With the rapid development of deep learning in the field of artificial intelligence, researchers have tried to transfer deep learning methods that shine in computer vision processing, natural language recognition and other fields to the field of network flow detection. This paper proposes an ensemble model based on a convolutional neural network, which is integrated on the basis of the CNN model, which reduces the deviation of each basic model and improves the accuracy of the network stream classification results. The main tasks of this paper are as follows: (1) Experiments on the basic model and the integrated model were carried out on the USTC-TFC2016 data set. (2) The experimental results show that the ensemble model reduces the deviation of the basic model and improves the classification accuracy.","PeriodicalId":358772,"journal":{"name":"2021 18th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115904986","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 : 2021-12-17DOI: 10.1109/ICCWAMTIP53232.2021.9674100
Asamoah Kwame Omono, Yu Wang, Qi Xia, Jianbin Gao
Signcryption is a sophisticated cryptographic tool that combines the benefits of digital signature and data encryption in a single step, resulting in reduced computation and storage cost. However, the existing signcryption techniques do not account for a scenario in which a company must escrow an employee's private encryption key so that the corporation does not lose the capacity to decrypt a ciphertext when the employee or user is no longer available. To circumvent the issue of non-repudiation, the private signing key does not need to be escrowed. As a result, this paper presents an implicit certificate-based signcryption technique with private encryption key escrow, which can assist an organization in preventing the loss of private encryption. A certificate, or more broadly, a digital signature, protects users' public encryption and signature keys from man-in-the-middle attacks under our proposed approach.
{"title":"Implicit Certificate Based Signcryption for a Secure Data Sharing in Clouds","authors":"Asamoah Kwame Omono, Yu Wang, Qi Xia, Jianbin Gao","doi":"10.1109/ICCWAMTIP53232.2021.9674100","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP53232.2021.9674100","url":null,"abstract":"Signcryption is a sophisticated cryptographic tool that combines the benefits of digital signature and data encryption in a single step, resulting in reduced computation and storage cost. However, the existing signcryption techniques do not account for a scenario in which a company must escrow an employee's private encryption key so that the corporation does not lose the capacity to decrypt a ciphertext when the employee or user is no longer available. To circumvent the issue of non-repudiation, the private signing key does not need to be escrowed. As a result, this paper presents an implicit certificate-based signcryption technique with private encryption key escrow, which can assist an organization in preventing the loss of private encryption. A certificate, or more broadly, a digital signature, protects users' public encryption and signature keys from man-in-the-middle attacks under our proposed approach.","PeriodicalId":358772,"journal":{"name":"2021 18th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114804348","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 : 2021-12-17DOI: 10.1109/ICCWAMTIP53232.2021.9674076
Emmanuel Agyei, Xiaoling Zhang, S. B. Yussif, B. L. Y. Agbley
Recent years, Neural Machine Translation outperforms the existing traditional-based models for language translation with the use of sequential architecture. However, low resource languages, such as Akan-Twi, lack structured language resources largely due to the limited amount of research geared towards their revival and resuscitation. In an effort to mitigate the issue of low resource language translation from Akan-Twi to English in machine learning, we utilize the low resource parallel corpus for the translation setting of Akan-English. Using our proposed training process and Transformer-based model, we generate augmented corpus which is used to improve the performance of our final translation model. We achieved best BLEU score of 12.96 and 17.57 for the Akan-English and English-Akan, respectively.
{"title":"Akan-English: Transformer for Low Resource Translation","authors":"Emmanuel Agyei, Xiaoling Zhang, S. B. Yussif, B. L. Y. Agbley","doi":"10.1109/ICCWAMTIP53232.2021.9674076","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP53232.2021.9674076","url":null,"abstract":"Recent years, Neural Machine Translation outperforms the existing traditional-based models for language translation with the use of sequential architecture. However, low resource languages, such as Akan-Twi, lack structured language resources largely due to the limited amount of research geared towards their revival and resuscitation. In an effort to mitigate the issue of low resource language translation from Akan-Twi to English in machine learning, we utilize the low resource parallel corpus for the translation setting of Akan-English. Using our proposed training process and Transformer-based model, we generate augmented corpus which is used to improve the performance of our final translation model. We achieved best BLEU score of 12.96 and 17.57 for the Akan-English and English-Akan, respectively.","PeriodicalId":358772,"journal":{"name":"2021 18th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116379990","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 : 2021-12-17DOI: 10.1109/ICCWAMTIP53232.2021.9674174
Xiaoniu Zhang, Zhiqin Zhao
A new method based on Contraction Integral Equation (CIE) is proposed here to solve the highly nonlinear electromagnetic inverse scattering problems with strong noise disturbance. The high-frequency components can be quite sensitive to noise. Since noise is inevitable for a practical ISP, in view of this characteristic, those high-frequency components could easily lead the third round of optimization to converge to a noise-polluted result. Furthermore, when the noise interference is significant, the algorithm cannot even achieve convergence of the iteration. Since the low-frequency components used in these rounds are not sensitive to noise, there is no need to weaken the weight of the data equation mismatch term. Finally, the effectiveness and versatility of the new method is verified through numerical analysis.
{"title":"A Novel Method Using Contraction Integral Equation For Inversion Of Two-Dimensional Dielectric Scatterers","authors":"Xiaoniu Zhang, Zhiqin Zhao","doi":"10.1109/ICCWAMTIP53232.2021.9674174","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP53232.2021.9674174","url":null,"abstract":"A new method based on Contraction Integral Equation (CIE) is proposed here to solve the highly nonlinear electromagnetic inverse scattering problems with strong noise disturbance. The high-frequency components can be quite sensitive to noise. Since noise is inevitable for a practical ISP, in view of this characteristic, those high-frequency components could easily lead the third round of optimization to converge to a noise-polluted result. Furthermore, when the noise interference is significant, the algorithm cannot even achieve convergence of the iteration. Since the low-frequency components used in these rounds are not sensitive to noise, there is no need to weaken the weight of the data equation mismatch term. Finally, the effectiveness and versatility of the new method is verified through numerical analysis.","PeriodicalId":358772,"journal":{"name":"2021 18th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123430900","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 : 2021-12-17DOI: 10.1109/ICCWAMTIP53232.2021.9673711
Yue Zhou, Si Han Du, Yuan Gao, Fei Xiao, Gong Kai, Jian Ping Li
With the rapid development of the central air conditioning technology and wisdom city new concept propulsion, central air conditioning is increasingly used to different occasions, and then the energy loss is also associated with increased, so how to establish good central air-conditioning optimization control strategy become a problem we must solve, this article aims to reduce the wastage of the energy efficiency of air conditioning system. First will be the method of using multiple regression to affect the controlled variable of the dependent variable changes after fitting of uncontrollable variables by calculation of each variable and dependent variable (cooling load and the total power consumption) dimension reduction, the correlation coefficient between combination of selected indicators of than the big, determine all the characteristics of the index of the closely associated with the dependent variable, and multiple regression analysis is used to determine the dependent variable and all related controllable and uncontrollable variables between the final fitting relation, and to remove equipment control parameters of the day's other variable data, using the K - means clustering algorithm to get 5 groups cluster value. Finally, the optimal speed control strategy is obtained by solving the model with genetic algorithm, and the system efficiency is further improved by combining with simulated annealing algorithm.
{"title":"Study On Efficiency Optimization Strategy Of Central Air-Conditioning System","authors":"Yue Zhou, Si Han Du, Yuan Gao, Fei Xiao, Gong Kai, Jian Ping Li","doi":"10.1109/ICCWAMTIP53232.2021.9673711","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP53232.2021.9673711","url":null,"abstract":"With the rapid development of the central air conditioning technology and wisdom city new concept propulsion, central air conditioning is increasingly used to different occasions, and then the energy loss is also associated with increased, so how to establish good central air-conditioning optimization control strategy become a problem we must solve, this article aims to reduce the wastage of the energy efficiency of air conditioning system. First will be the method of using multiple regression to affect the controlled variable of the dependent variable changes after fitting of uncontrollable variables by calculation of each variable and dependent variable (cooling load and the total power consumption) dimension reduction, the correlation coefficient between combination of selected indicators of than the big, determine all the characteristics of the index of the closely associated with the dependent variable, and multiple regression analysis is used to determine the dependent variable and all related controllable and uncontrollable variables between the final fitting relation, and to remove equipment control parameters of the day's other variable data, using the K - means clustering algorithm to get 5 groups cluster value. Finally, the optimal speed control strategy is obtained by solving the model with genetic algorithm, and the system efficiency is further improved by combining with simulated annealing algorithm.","PeriodicalId":358772,"journal":{"name":"2021 18th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP)","volume":"130 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121966015","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 : 2021-12-17DOI: 10.1109/ICCWAMTIP53232.2021.9674101
Zhang Ping, Wu Jinfa
Electronic Medical Records (EMR) run through every link in the whole medical activities. How to find the required EMR quickly and accurately has become a difficult point in the process of EMR retrieval. This paper introduces a method to optimize the sorting of search results in Chinese electronic medical record search engine system by using the sorting learning AdaRank retrieval algorithm. In 248 Chinese electronic medical records manually annotated, five sorting learning methods were used for training and testing. Our AdaRank sorting algorithm achieved NDCG@10 of 0.28178, ERR@10 of 0.38038 and MAP@10 of 0.59368. Compared with RankNet, the sorting learning model, LambdaRank, ListNet and LambdaMART, AdaRank methods have better sorting effect.
{"title":"Research on Search Ranking Technology of Chinese Electronic Medical Record Based on Adarank","authors":"Zhang Ping, Wu Jinfa","doi":"10.1109/ICCWAMTIP53232.2021.9674101","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP53232.2021.9674101","url":null,"abstract":"Electronic Medical Records (EMR) run through every link in the whole medical activities. How to find the required EMR quickly and accurately has become a difficult point in the process of EMR retrieval. This paper introduces a method to optimize the sorting of search results in Chinese electronic medical record search engine system by using the sorting learning AdaRank retrieval algorithm. In 248 Chinese electronic medical records manually annotated, five sorting learning methods were used for training and testing. Our AdaRank sorting algorithm achieved NDCG@10 of 0.28178, ERR@10 of 0.38038 and MAP@10 of 0.59368. Compared with RankNet, the sorting learning model, LambdaRank, ListNet and LambdaMART, AdaRank methods have better sorting effect.","PeriodicalId":358772,"journal":{"name":"2021 18th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122082833","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 : 2021-12-17DOI: 10.1109/ICCWAMTIP53232.2021.9674110
Huiyu Xiong
In daily life, it is important to interpret information correctly from different types of texts. After applying the neural network to object detection, a breakthrough has been made in natural scene text detection. However, only a few research has focused on dense, long segments of Chinese text. Moreover, there are hardly any datasets that include Chinese text boxes with large gap in aspect ratio and short interval. Considering these, we propose a Network to Detect Chinese Long text (DCLnet) and a Chinese Long and Dense text Dataset (CLD). It can not only accurately detect long and dense Chinese text, but also predict text in arbitrary directions using rotated quadrilateral shapes. In this method, we have improved AdvancedEAST model. The feature extraction part selects Resnet50, one of the latest networks. Additionally, reduce-redundancy module is added before the prediction stage to reduce redundant computations. We conduct several experiments on datasets including ICDAR2015 and CLD. Through comparative analysis, the detection accuracy of the algorithm for long and dense Chinese text is obviously better than the previous methods. It achieves a competitive F-score of 0.761 on CLD dataset.
{"title":"Text Detection of a Chinese Long and Dense Text Dataset","authors":"Huiyu Xiong","doi":"10.1109/ICCWAMTIP53232.2021.9674110","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP53232.2021.9674110","url":null,"abstract":"In daily life, it is important to interpret information correctly from different types of texts. After applying the neural network to object detection, a breakthrough has been made in natural scene text detection. However, only a few research has focused on dense, long segments of Chinese text. Moreover, there are hardly any datasets that include Chinese text boxes with large gap in aspect ratio and short interval. Considering these, we propose a Network to Detect Chinese Long text (DCLnet) and a Chinese Long and Dense text Dataset (CLD). It can not only accurately detect long and dense Chinese text, but also predict text in arbitrary directions using rotated quadrilateral shapes. In this method, we have improved AdvancedEAST model. The feature extraction part selects Resnet50, one of the latest networks. Additionally, reduce-redundancy module is added before the prediction stage to reduce redundant computations. We conduct several experiments on datasets including ICDAR2015 and CLD. Through comparative analysis, the detection accuracy of the algorithm for long and dense Chinese text is obviously better than the previous methods. It achieves a competitive F-score of 0.761 on CLD dataset.","PeriodicalId":358772,"journal":{"name":"2021 18th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125026679","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 : 2021-12-17DOI: 10.1109/ICCWAMTIP53232.2021.9674060
Jian Jiangwei, H. Bang, Wang Wen-Qin
In this paper, we study the secrecy capacity for frequency diverse array relaying and simultaneous wireless information and power transfer jointed communication system under the power splitting protocol. The decode-and-forward strategy and direction modulation technique are jointly utilized for relaying to forward signals. We derive closed-form expressions for the ergodic secrecy capacity of the system. Moreover, the impacts of frequency diverse array parameters on the system security performances are also analyzed. The numerical results show that the system security performance under power splitting protocol outperforms time splitting protocol. Meanwhile, the frequency diverse array relaying achieves better security performance than traditional phased-array relaying.
{"title":"Secrecy Capacity Analysis of FDA Relaying Swipt System with Power Splitting Protocol","authors":"Jian Jiangwei, H. Bang, Wang Wen-Qin","doi":"10.1109/ICCWAMTIP53232.2021.9674060","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP53232.2021.9674060","url":null,"abstract":"In this paper, we study the secrecy capacity for frequency diverse array relaying and simultaneous wireless information and power transfer jointed communication system under the power splitting protocol. The decode-and-forward strategy and direction modulation technique are jointly utilized for relaying to forward signals. We derive closed-form expressions for the ergodic secrecy capacity of the system. Moreover, the impacts of frequency diverse array parameters on the system security performances are also analyzed. The numerical results show that the system security performance under power splitting protocol outperforms time splitting protocol. Meanwhile, the frequency diverse array relaying achieves better security performance than traditional phased-array relaying.","PeriodicalId":358772,"journal":{"name":"2021 18th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128659074","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：