In recent years, Cover Song Identification (CSI) based on Siamese Network and music representation learning has achieved good performance, however, there are still many problems such as limited feature fusion, missing decision threshold and single data label. In this paper, we propose a novel fully fused cover song identification model via feature fusing and clustering. In our proposed model, there are a fusion feature extraction structure, a channel separation decision structure, and a music feature clustering structure. First, we combine the pre-processing features of the dual input along the channel dimension to achieve full feature fusion and increase the fusion degree of the two songs in the feature extraction process. Secondly, we introduce channel separation to calculate multi-channel cross-features to improve the ability of the model to learn the difference between feature channels, and combined with the binary decision network to avoid the shortcomings of lack of decision thresholds in music representation learning. Finally, feature clustering generates invisible feature labels to enriches the types of cover data labels and reduces the difficulty of training. The model is trained in stages to optimize the clustering loss and the classification loss for cover and non-cover pairs, respectively. The model is validated on three public datasets, and experiments show that our model could achieve competitive results.
{"title":"Fully Fused Cover Song Identification Model via Feature Fusing and Clustering","authors":"Qiang Yuan, Shibiao Xu, Li Guo","doi":"10.1145/3571662.3571672","DOIUrl":"https://doi.org/10.1145/3571662.3571672","url":null,"abstract":"In recent years, Cover Song Identification (CSI) based on Siamese Network and music representation learning has achieved good performance, however, there are still many problems such as limited feature fusion, missing decision threshold and single data label. In this paper, we propose a novel fully fused cover song identification model via feature fusing and clustering. In our proposed model, there are a fusion feature extraction structure, a channel separation decision structure, and a music feature clustering structure. First, we combine the pre-processing features of the dual input along the channel dimension to achieve full feature fusion and increase the fusion degree of the two songs in the feature extraction process. Secondly, we introduce channel separation to calculate multi-channel cross-features to improve the ability of the model to learn the difference between feature channels, and combined with the binary decision network to avoid the shortcomings of lack of decision thresholds in music representation learning. Finally, feature clustering generates invisible feature labels to enriches the types of cover data labels and reduces the difficulty of training. The model is trained in stages to optimize the clustering loss and the classification loss for cover and non-cover pairs, respectively. The model is validated on three public datasets, and experiments show that our model could achieve competitive results.","PeriodicalId":235407,"journal":{"name":"Proceedings of the 8th International Conference on Communication and Information Processing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125514153","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}
While MOOC brings a great impact to higher education, there is also the problem of low course completion rate, and it is important to analyze the factors influencing learners' continuous learning and participation in Massive Open Online Course (MOOC) for improving the teaching quality of MOOC. This paper constructs a model to predict and explain learners' MOOC continuous learning intention based on expectation confirmation model, technology acceptance model, planned behavior theory and flow theory, and carries out a questionnaire survey on students of our university who participate in the general elective courses on the platform of Chinese University MOOC. The results based on structural equation modeling show that expected confirmation and perceived ease of use significantly influence learners' perceived usefulness of MOOC; perceived usefulness and perceived ease of use significantly influence learners' attitudes towards MOOC; expected confirmation and perceived usefulness significantly influence learning satisfaction; perceived ease of use, satisfaction, attitude, focus, Perceived behavior control and subjective norms significantly influence learners' MOOC continuous learning intention. Based on the data analysis, the researcher discusses the theoretical and practical significance of this study and proposes the follow-up research plan.
MOOC在给高等教育带来巨大影响的同时,也存在着课程完成率低的问题,分析影响学习者持续学习和参与大规模在线开放课程(Massive Open Online course, MOOC)的因素,对于提高MOOC的教学质量具有重要意义。本文基于期望确认模型、技术接受模型、计划行为理论和流理论构建了预测和解释学习者MOOC持续学习意愿的模型,并对我校在中国大学MOOC平台上参加普通选修课的学生进行了问卷调查。基于结构方程模型的研究结果表明,期望确认和感知易用性显著影响学习者对MOOC的感知有用性;感知有用性和感知易用性显著影响学习者对MOOC的态度;期望确认和感知有用性显著影响学习满意度;感知易用性、满意度、态度、关注点、感知行为控制和主观规范显著影响学习者的MOOC持续学习意愿。在数据分析的基础上,探讨了本研究的理论意义和现实意义,并提出了后续的研究计划。
{"title":"Analysis of MOOC's Continuous Learning Intention and Its Influencing Factors of Higher Vocational Students","authors":"Fengmei Zhao, Yong Hu","doi":"10.1145/3571662.3571681","DOIUrl":"https://doi.org/10.1145/3571662.3571681","url":null,"abstract":"While MOOC brings a great impact to higher education, there is also the problem of low course completion rate, and it is important to analyze the factors influencing learners' continuous learning and participation in Massive Open Online Course (MOOC) for improving the teaching quality of MOOC. This paper constructs a model to predict and explain learners' MOOC continuous learning intention based on expectation confirmation model, technology acceptance model, planned behavior theory and flow theory, and carries out a questionnaire survey on students of our university who participate in the general elective courses on the platform of Chinese University MOOC. The results based on structural equation modeling show that expected confirmation and perceived ease of use significantly influence learners' perceived usefulness of MOOC; perceived usefulness and perceived ease of use significantly influence learners' attitudes towards MOOC; expected confirmation and perceived usefulness significantly influence learning satisfaction; perceived ease of use, satisfaction, attitude, focus, Perceived behavior control and subjective norms significantly influence learners' MOOC continuous learning intention. Based on the data analysis, the researcher discusses the theoretical and practical significance of this study and proposes the follow-up research plan.","PeriodicalId":235407,"journal":{"name":"Proceedings of the 8th International Conference on Communication and Information Processing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129267912","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}
Popularity prediction of micro videos on multimedia is a hotly studied topic due to the widespread use of video upload sharing services. It’s also a challenging task because popular pattern is affected by multiple factors and is hard to be modeled. The goal of this paper is to use feature extraction techniques and variation auto-encoder (VAE) framework to predict the popularity of online micro-videos. First, we identify four declarable modalities that are important for adaptability and expansibility. Then, we design a multi-modal based VAE regression model (MASSL) to exploit the domestic and foreign information extracted from heterogeneous features. The model can be applied to large-scale multimedia platforms, even the modality absence scenarios. With extensive experiments conducted on the dataset, which was originally generated from the most popular video-sharing website in China, the result demonstrates the effectiveness of our proposed model by comparing with baseline approaches.
{"title":"Multi-modal Variational Auto-Encoder Model for Micro-video Popularity Prediction","authors":"Zhuoran Zhang, Shibiao Xu, Li Guo, Wenke Lian","doi":"10.1145/3571662.3571664","DOIUrl":"https://doi.org/10.1145/3571662.3571664","url":null,"abstract":"Popularity prediction of micro videos on multimedia is a hotly studied topic due to the widespread use of video upload sharing services. It’s also a challenging task because popular pattern is affected by multiple factors and is hard to be modeled. The goal of this paper is to use feature extraction techniques and variation auto-encoder (VAE) framework to predict the popularity of online micro-videos. First, we identify four declarable modalities that are important for adaptability and expansibility. Then, we design a multi-modal based VAE regression model (MASSL) to exploit the domestic and foreign information extracted from heterogeneous features. The model can be applied to large-scale multimedia platforms, even the modality absence scenarios. With extensive experiments conducted on the dataset, which was originally generated from the most popular video-sharing website in China, the result demonstrates the effectiveness of our proposed model by comparing with baseline approaches.","PeriodicalId":235407,"journal":{"name":"Proceedings of the 8th International Conference on Communication and Information Processing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133527235","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}
A large number of diverse data sets are necessary for networks to predict human body parameters and reconstruct 3D body models from images. Due to the high cost of motion capture and body scanning, high precision pose and body shape parameters are difficult to obtain. Meanwhile, existing datasets cannot meet the requirements in terms of diversity, size, and data accuracy for practical applications. Inspired by the construction schemes of various datasets, we design and construct a large multi-view 3D human body reconstruction dataset (3DMVHumanBP) with more types of supervised data. By recording the different poses of 25 women and 25 men in a green screen laboratory from six perspectives, we constructed a complete large multi-view 3D body posture dataset containing 340, 000 images. It is worth noting that, we innovatively propose a body dimension prior to the constrained human parametric model construction strategy to provide high-precision ground truth parameters of the human body SMPL models. In addition, we also designed a dense UV data generation method based on human body boundary and mask mapping to provide high-quality dense UV data, which more closely fits the features of the human images. It makes up for the defect that few existing data sets can only provide sparse UV data. In the experiment, the effectiveness and advantages of the data set constructed by us in network training are verified. Compared with the training of existing datasets, the mainstream network models trained on our datasets can significantly improve their prediction accuracy and robustness, thanks to the monitoring data of multiple kinds of high-precision human model parameters provided by 3DMVHumanBP. We hope that the human body dataset construction scheme we designed can provide ideas for building large-scale high precision human body datasets in the future.
{"title":"Multi-view 3D Human Physique Dataset Construction For Robust Digital Human Modeling of Natural Scenes","authors":"Weitao Lin, Jiguang Zhang, Zhaohui Zhang, Shibiao Xu, Hao Xu, Xiaopeng Zhang","doi":"10.1145/3571662.3571675","DOIUrl":"https://doi.org/10.1145/3571662.3571675","url":null,"abstract":"A large number of diverse data sets are necessary for networks to predict human body parameters and reconstruct 3D body models from images. Due to the high cost of motion capture and body scanning, high precision pose and body shape parameters are difficult to obtain. Meanwhile, existing datasets cannot meet the requirements in terms of diversity, size, and data accuracy for practical applications. Inspired by the construction schemes of various datasets, we design and construct a large multi-view 3D human body reconstruction dataset (3DMVHumanBP) with more types of supervised data. By recording the different poses of 25 women and 25 men in a green screen laboratory from six perspectives, we constructed a complete large multi-view 3D body posture dataset containing 340, 000 images. It is worth noting that, we innovatively propose a body dimension prior to the constrained human parametric model construction strategy to provide high-precision ground truth parameters of the human body SMPL models. In addition, we also designed a dense UV data generation method based on human body boundary and mask mapping to provide high-quality dense UV data, which more closely fits the features of the human images. It makes up for the defect that few existing data sets can only provide sparse UV data. In the experiment, the effectiveness and advantages of the data set constructed by us in network training are verified. Compared with the training of existing datasets, the mainstream network models trained on our datasets can significantly improve their prediction accuracy and robustness, thanks to the monitoring data of multiple kinds of high-precision human model parameters provided by 3DMVHumanBP. We hope that the human body dataset construction scheme we designed can provide ideas for building large-scale high precision human body datasets in the future.","PeriodicalId":235407,"journal":{"name":"Proceedings of the 8th International Conference on Communication and Information Processing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131103639","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}
While reducing costs and improving data security, the new generation of informatics technologies such as blockchain also face problems of operation efficiency and privacy leakage, which have attracted extensive attention from researchers. Digital signature is one of the key technologies to solve the above problems. The group signature algorithm has the dual characteristics of protecting the privacy of signer identity and tracing effectively when disputes occur. The scheme we proposed can simultaneously solve the low efficiency of signature verification caused by the high time-consuming bilinear pairwise operation in existing group signature algorithms and the privacy leakage of signers caused by the vulnerability of single group administrators to malicious attacks. Compared with the SM2 digital signature algorithm of Chinese cryptographic standard, the proposed scheme increases the signature anonymization while maintaining the same signature and verification efficiency as the SM2 signature algorithm. Compared with Yang et al. 's scheme, the main computation overhead and communication bandwidth of the proposed protocol are significantly reduced. Therefore, the design scheme in this paper has stronger practicability and is more suitable for scenarios that require both efficiency and strong privacy protection, such as blockchain, anonymous certificate, electronic cash and electronic voting.
{"title":"An Identity-based Group Signature Approach on Decentralized System and Chinese Cryptographic SM2","authors":"Jiaxi Liu, Tianyu Kang, LingNa Guo","doi":"10.1145/3571662.3571683","DOIUrl":"https://doi.org/10.1145/3571662.3571683","url":null,"abstract":"While reducing costs and improving data security, the new generation of informatics technologies such as blockchain also face problems of operation efficiency and privacy leakage, which have attracted extensive attention from researchers. Digital signature is one of the key technologies to solve the above problems. The group signature algorithm has the dual characteristics of protecting the privacy of signer identity and tracing effectively when disputes occur. The scheme we proposed can simultaneously solve the low efficiency of signature verification caused by the high time-consuming bilinear pairwise operation in existing group signature algorithms and the privacy leakage of signers caused by the vulnerability of single group administrators to malicious attacks. Compared with the SM2 digital signature algorithm of Chinese cryptographic standard, the proposed scheme increases the signature anonymization while maintaining the same signature and verification efficiency as the SM2 signature algorithm. Compared with Yang et al. 's scheme, the main computation overhead and communication bandwidth of the proposed protocol are significantly reduced. Therefore, the design scheme in this paper has stronger practicability and is more suitable for scenarios that require both efficiency and strong privacy protection, such as blockchain, anonymous certificate, electronic cash and electronic voting.","PeriodicalId":235407,"journal":{"name":"Proceedings of the 8th International Conference on Communication and Information Processing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132122655","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 recognition of communication relationships under Non-cooperative conditions is significant for understanding the network composition of unknown targets, inferring network topology, and identifying key nodes, which is a prerequisite and basis for conducting efficient electronic countermeasures. However, under Non-cooperative conditions, for prior knowledge related to the target network is difficult to obtain, the communication relationships recognition faces enormous challenges. To address this issue, we construct a system model, analyze the mechanism of wireless communication interaction, extract feature series of signals from spectrum monitoring data, and propose a Transformer-based algorithm for recognizing target network communication relationships. This paper conducts simulation experiments in different scenarios to compare the Transformer-based communication relation recognition algorithm with the other four methods, such as SVM, CNN-based recognition algorithm, ResNet-based recognition algorithm, and LSTM-based recognition algorithm, respectively. And results demonstrate that the proposed algorithm shows high recognition accuracy, good anti-interference performance, and robustness.
{"title":"Recognition of Non-cooperative Radio Communication Relationships Based on Transformer","authors":"Dejun He, Xinrong Wu, Lu Yu, Tianchi Wang","doi":"10.1145/3571662.3571688","DOIUrl":"https://doi.org/10.1145/3571662.3571688","url":null,"abstract":"The recognition of communication relationships under Non-cooperative conditions is significant for understanding the network composition of unknown targets, inferring network topology, and identifying key nodes, which is a prerequisite and basis for conducting efficient electronic countermeasures. However, under Non-cooperative conditions, for prior knowledge related to the target network is difficult to obtain, the communication relationships recognition faces enormous challenges. To address this issue, we construct a system model, analyze the mechanism of wireless communication interaction, extract feature series of signals from spectrum monitoring data, and propose a Transformer-based algorithm for recognizing target network communication relationships. This paper conducts simulation experiments in different scenarios to compare the Transformer-based communication relation recognition algorithm with the other four methods, such as SVM, CNN-based recognition algorithm, ResNet-based recognition algorithm, and LSTM-based recognition algorithm, respectively. And results demonstrate that the proposed algorithm shows high recognition accuracy, good anti-interference performance, and robustness.","PeriodicalId":235407,"journal":{"name":"Proceedings of the 8th International Conference on Communication and Information Processing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132243782","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}
Chi Jiang, Li Xiao Zhang, Wu Yong Zhao, Jie Shu Lei, Wei Zhi Huang
Aiming at the uniform circular array model of conformal antenna array, we proposed a spatial spectrum estimation algorithm of polarization sensitive array based on compensating spatial domain manifold matrix. Because the conformal antenna is highly sensitive to the polarization information of the incident signal, traditional spatial spectrum direction-finding algorithm is not suitable. Meanwhile, when the classical polarization sensitive array spatial spectrum estimation algorithm is adopted, the interference generated by the anti-radiation detection system in the case of multipath, signal refraction and diffraction will be directly introduced into the model of the polarization sensitive array spatial spectrum finding theory, and then, resulting in a large estimation error of direction of arrival (DOA) and polarization parameters. The algorithm compensates the spatial domain components of the spatial domain array manifold matrix, which combine with the multiple signal classification (MUSIC) DOA estimation algorithm to construct a four-dimensional polarization sensitive array spatial spectrum function. And then, applying the reducing dimension spectral peak search to achieve the two-dimensional DOA and polarization parameters estimation of the target signal. Compared with the classical polarization sensitive array MUSIC direction-finding algorithm, the algorithm we explored can suppress the front-end error of the system, avoid the mismatch between the spatial domain components and the theoretical model of the algorithm, and realize the high precision direction-finding and tracking of the target signal.
{"title":"Spatial spectrum estimation algorithm of polarization sensitive array based on compensating spatial domain manifold matrix","authors":"Chi Jiang, Li Xiao Zhang, Wu Yong Zhao, Jie Shu Lei, Wei Zhi Huang","doi":"10.1145/3571662.3571684","DOIUrl":"https://doi.org/10.1145/3571662.3571684","url":null,"abstract":"Aiming at the uniform circular array model of conformal antenna array, we proposed a spatial spectrum estimation algorithm of polarization sensitive array based on compensating spatial domain manifold matrix. Because the conformal antenna is highly sensitive to the polarization information of the incident signal, traditional spatial spectrum direction-finding algorithm is not suitable. Meanwhile, when the classical polarization sensitive array spatial spectrum estimation algorithm is adopted, the interference generated by the anti-radiation detection system in the case of multipath, signal refraction and diffraction will be directly introduced into the model of the polarization sensitive array spatial spectrum finding theory, and then, resulting in a large estimation error of direction of arrival (DOA) and polarization parameters. The algorithm compensates the spatial domain components of the spatial domain array manifold matrix, which combine with the multiple signal classification (MUSIC) DOA estimation algorithm to construct a four-dimensional polarization sensitive array spatial spectrum function. And then, applying the reducing dimension spectral peak search to achieve the two-dimensional DOA and polarization parameters estimation of the target signal. Compared with the classical polarization sensitive array MUSIC direction-finding algorithm, the algorithm we explored can suppress the front-end error of the system, avoid the mismatch between the spatial domain components and the theoretical model of the algorithm, and realize the high precision direction-finding and tracking of the target signal.","PeriodicalId":235407,"journal":{"name":"Proceedings of the 8th International Conference on Communication and Information Processing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120915517","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}
More and more complex services composed of a series of sequentially arranged middleboxes which are mainly used to meet the requirements of advanced services such as security services, auditing services, monitoring services, personalized enterprise services, and so forth, are increasingly deployed in cloud data centers of public cloud. SFC (Service Function Chaining) is a technique that facilitates the enforcement of complex services and differentiated traffic forwarding policies, dynamically steering the traffic through an ordered list of service functions. Flow table-based traffic steering scheme is commonly adopted in SDN-enabled scenarios, which consumes too many flow entries and is unsuitable for large-scale public clouds in steering traffic between VNFs (Virtual Network Function) inside of VPC (Virtual Private Cloud). Legacy PBR (Policy-based Routing) based schemes which are widely used in traditional physical networks cannot fulfill the requirements of fully distributed routing architectures of large-scale public clouds. In this paper, we present a PBR and unsymmetrical NAT (Network Address Translation) converged scheme to structure SFC in a fully distributed routing architecture. The scheme uses distributed PBR rules to steer traffic between an ordered list of VNFs located on different nodes while performing NAT on different nodes for ingress/egress traffic of a specific flow to avoid asymmetry of packet headers which may lead to failures of communication. The proposed scheme brings no overhead in data transmission, eliminates extra configurations on each middle box of the chain, and is scalable to support the scenarios of large-scale public cloud.
{"title":"Traffic Steering in Large-scale Public Cloud","authors":"Zhangfeng Hu, Siqing Sun, Ping Yin, Yanjun Li, Qiuzheng Ren, Baozhu Li, Xiong Li","doi":"10.1145/3571662.3571691","DOIUrl":"https://doi.org/10.1145/3571662.3571691","url":null,"abstract":"More and more complex services composed of a series of sequentially arranged middleboxes which are mainly used to meet the requirements of advanced services such as security services, auditing services, monitoring services, personalized enterprise services, and so forth, are increasingly deployed in cloud data centers of public cloud. SFC (Service Function Chaining) is a technique that facilitates the enforcement of complex services and differentiated traffic forwarding policies, dynamically steering the traffic through an ordered list of service functions. Flow table-based traffic steering scheme is commonly adopted in SDN-enabled scenarios, which consumes too many flow entries and is unsuitable for large-scale public clouds in steering traffic between VNFs (Virtual Network Function) inside of VPC (Virtual Private Cloud). Legacy PBR (Policy-based Routing) based schemes which are widely used in traditional physical networks cannot fulfill the requirements of fully distributed routing architectures of large-scale public clouds. In this paper, we present a PBR and unsymmetrical NAT (Network Address Translation) converged scheme to structure SFC in a fully distributed routing architecture. The scheme uses distributed PBR rules to steer traffic between an ordered list of VNFs located on different nodes while performing NAT on different nodes for ingress/egress traffic of a specific flow to avoid asymmetry of packet headers which may lead to failures of communication. The proposed scheme brings no overhead in data transmission, eliminates extra configurations on each middle box of the chain, and is scalable to support the scenarios of large-scale public cloud.","PeriodicalId":235407,"journal":{"name":"Proceedings of the 8th International Conference on Communication and Information Processing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134082757","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}