Pub Date : 2024-07-01DOI: 10.23919/JCC.ea.2021-0794.202401
Hongfei Zhu, Zhiwei Cao, Yuping Zhao, Li Dou
In this paper, we innovatively associate the mutual information with the frame error rate (FER) performance and propose novel quantized decoders for polar codes. Based on the optimal quantizer of binary-input discrete memoryless channels (B-DMCs), the proposed decoders quantize the virtual subchannels of polar codes to maximize mutual information (MMI) between source bits and quantized symbols. The nested structure of polar codes ensures that the MMI quantization can be implemented stage by stage. Simulation results show that the proposed MMI decoders with 4 quantization bits outperform the existing nonuniform quantized decoders that minimize mean-squared error (MMSE) with 4 quantization bits, and yield even better performance than uniform MMI quantized decoders with 5 quantization bits. Furthermore, the proposed 5-bit quantized MMI decoders approach the floating-point decoders with negligible performance loss.
{"title":"Quantized decoders that maximize mutual information for polar codes","authors":"Hongfei Zhu, Zhiwei Cao, Yuping Zhao, Li Dou","doi":"10.23919/JCC.ea.2021-0794.202401","DOIUrl":"https://doi.org/10.23919/JCC.ea.2021-0794.202401","url":null,"abstract":"In this paper, we innovatively associate the mutual information with the frame error rate (FER) performance and propose novel quantized decoders for polar codes. Based on the optimal quantizer of binary-input discrete memoryless channels (B-DMCs), the proposed decoders quantize the virtual subchannels of polar codes to maximize mutual information (MMI) between source bits and quantized symbols. The nested structure of polar codes ensures that the MMI quantization can be implemented stage by stage. Simulation results show that the proposed MMI decoders with 4 quantization bits outperform the existing nonuniform quantized decoders that minimize mean-squared error (MMSE) with 4 quantization bits, and yield even better performance than uniform MMI quantized decoders with 5 quantization bits. Furthermore, the proposed 5-bit quantized MMI decoders approach the floating-point decoders with negligible performance loss.","PeriodicalId":504777,"journal":{"name":"China Communications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141852359","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 : 2024-07-01DOI: 10.23919/JCC.fa.2024-0104.202407
Mei Miao, Tang Miao, Zhou Long
The telecommunications industry is becoming increasingly aware of potential subscriber churn as a result of the growing popularity of smartphones in the mobile Internet era, the quick development of telecommunications services, the implementation of the number portability policy, and the intensifying competition among operators. At the same time, users' consumption preferences and choices are evolving. Excellent churn prediction models must be created in order to accurately predict the churn tendency, since keeping existing customers is far less expensive than acquiring new ones. But conventional or learning-based algorithms can only go so far into a single subscriber's data; they cannot take into consideration changes in a subscriber's subscription and ignore the coupling and correlation between various features. Additionally, the current churn prediction models have a high computational burden, a fuzzy weight distribution, and significant resource economic costs. The prediction algorithms involving network models currently in use primarily take into account the private information shared between users with text and pictures, ignoring the reference value supplied by other users with the same package. This work suggests a user churn prediction model based on Graph Attention Convolutional Neural Network (GAT-CNN) to address the aforementioned issues. The main contributions of this paper are as follows: Firstly, we present a three-tiered hierarchical cloud-edge cooperative framework that increases the volume of user feature input by means of two aggregations at the device, edge, and cloud layers. Second, we extend the use of users' own data by introducing self-attention and graph convolution models to track the relative changes of both users and packages simultaneously. Lastly, we build an integrated offline-online system for churn prediction based on the strengths of the two models, and we experimentally validate the efficacy of cloud-side collaborative training and inference. In summary, the churn prediction model based on Graph Attention Convolutional Neural Network presented in this paper can effectively address the drawbacks of conventional algorithms and offer telecom operators crucial decision support in developing subscriber retention strategies and cutting operational expenses.
{"title":"User churn prediction hierarchical model based on graph attention convolutional neural networks","authors":"Mei Miao, Tang Miao, Zhou Long","doi":"10.23919/JCC.fa.2024-0104.202407","DOIUrl":"https://doi.org/10.23919/JCC.fa.2024-0104.202407","url":null,"abstract":"The telecommunications industry is becoming increasingly aware of potential subscriber churn as a result of the growing popularity of smartphones in the mobile Internet era, the quick development of telecommunications services, the implementation of the number portability policy, and the intensifying competition among operators. At the same time, users' consumption preferences and choices are evolving. Excellent churn prediction models must be created in order to accurately predict the churn tendency, since keeping existing customers is far less expensive than acquiring new ones. But conventional or learning-based algorithms can only go so far into a single subscriber's data; they cannot take into consideration changes in a subscriber's subscription and ignore the coupling and correlation between various features. Additionally, the current churn prediction models have a high computational burden, a fuzzy weight distribution, and significant resource economic costs. The prediction algorithms involving network models currently in use primarily take into account the private information shared between users with text and pictures, ignoring the reference value supplied by other users with the same package. This work suggests a user churn prediction model based on Graph Attention Convolutional Neural Network (GAT-CNN) to address the aforementioned issues. The main contributions of this paper are as follows: Firstly, we present a three-tiered hierarchical cloud-edge cooperative framework that increases the volume of user feature input by means of two aggregations at the device, edge, and cloud layers. Second, we extend the use of users' own data by introducing self-attention and graph convolution models to track the relative changes of both users and packages simultaneously. Lastly, we build an integrated offline-online system for churn prediction based on the strengths of the two models, and we experimentally validate the efficacy of cloud-side collaborative training and inference. In summary, the churn prediction model based on Graph Attention Convolutional Neural Network presented in this paper can effectively address the drawbacks of conventional algorithms and offer telecom operators crucial decision support in developing subscriber retention strategies and cutting operational expenses.","PeriodicalId":504777,"journal":{"name":"China Communications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141850556","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 : 2024-07-01DOI: 10.23919/JCC.fa.2024-0036.202407
Weijie Yue, Zhongwei Si
Video transmission requires considerable bandwidth, and current widely employed schemes prove inadequate when confronted with scenes featuring prominently. Motivated by the strides in talking-head generative technology, the paper introduces a semantic transmission system tailored for talking-head videos. The system captures semantic information from talking-head video and faithfully reconstructs source video at the receiver, only one-shot reference frame and compact semantic features are required for the entire transmission. Specifically, we analyze video semantics in the pixel domain frame-by-frame and jointly process multi-frame semantic information to seamlessly incorporate spatial and temporal information. Variational modeling is utilized to evaluate the diversity of importance among group semantics, thereby guiding bandwidth resource allocation for semantics to enhance system efficiency. The whole end-to-end system is modeled as an optimization problem and equivalent to acquiring optimal rate-distortion performance. We evaluate our system on both reference frame and video transmission, experimental results demonstrate that our system can improve the efficiency and robustness of communications. Compared to the classical approaches, our system can save over 90% of bandwidth when user perception is close.
{"title":"Variational learned talking-head semantic coded transmission system","authors":"Weijie Yue, Zhongwei Si","doi":"10.23919/JCC.fa.2024-0036.202407","DOIUrl":"https://doi.org/10.23919/JCC.fa.2024-0036.202407","url":null,"abstract":"Video transmission requires considerable bandwidth, and current widely employed schemes prove inadequate when confronted with scenes featuring prominently. Motivated by the strides in talking-head generative technology, the paper introduces a semantic transmission system tailored for talking-head videos. The system captures semantic information from talking-head video and faithfully reconstructs source video at the receiver, only one-shot reference frame and compact semantic features are required for the entire transmission. Specifically, we analyze video semantics in the pixel domain frame-by-frame and jointly process multi-frame semantic information to seamlessly incorporate spatial and temporal information. Variational modeling is utilized to evaluate the diversity of importance among group semantics, thereby guiding bandwidth resource allocation for semantics to enhance system efficiency. The whole end-to-end system is modeled as an optimization problem and equivalent to acquiring optimal rate-distortion performance. We evaluate our system on both reference frame and video transmission, experimental results demonstrate that our system can improve the efficiency and robustness of communications. Compared to the classical approaches, our system can save over 90% of bandwidth when user perception is close.","PeriodicalId":504777,"journal":{"name":"China Communications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141839976","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 : 2024-07-01DOI: 10.23919/JCC.fa.2023-0331.202407
Jigang Wang, Shengyu Cheng, Jicheng Cao, Meihua He
Although static program analysis methods are frequently employed to enhance software quality, their efficiency in commercial settings is limited by their high false positive rate. The EUGENE tool can effectively lower the false positive rate. However, in continuous integration (CI) environments, the code is always changing, and user feedback from one version of the software cannot be applied to a subsequent version. Additionally, people find it difficult to distinguish between true positives and false positives in the analytical output. In this study, we developed the EUGENE-CI technique to address the CI problem and the EUGENE-rank lightweight heuristic algorithm to rate the reports of the analysis output in accordance with the likelihood that they are true positives. On the three projects ethereum, go-cloud, and kuber-netes, we assessed our methodologies. According to the trial findings, EUGENE-CI may drastically reduce false positives while EUGENE-rank can make it much easier for users to identify the real positives among a vast number of reports. We paired our techniques with GoInsight1 and discovered a vulnerability. We also offered a patch to the community.
{"title":"An empirical application of user-guided program analysis","authors":"Jigang Wang, Shengyu Cheng, Jicheng Cao, Meihua He","doi":"10.23919/JCC.fa.2023-0331.202407","DOIUrl":"https://doi.org/10.23919/JCC.fa.2023-0331.202407","url":null,"abstract":"Although static program analysis methods are frequently employed to enhance software quality, their efficiency in commercial settings is limited by their high false positive rate. The EUGENE tool can effectively lower the false positive rate. However, in continuous integration (CI) environments, the code is always changing, and user feedback from one version of the software cannot be applied to a subsequent version. Additionally, people find it difficult to distinguish between true positives and false positives in the analytical output. In this study, we developed the EUGENE-CI technique to address the CI problem and the EUGENE-rank lightweight heuristic algorithm to rate the reports of the analysis output in accordance with the likelihood that they are true positives. On the three projects ethereum, go-cloud, and kuber-netes, we assessed our methodologies. According to the trial findings, EUGENE-CI may drastically reduce false positives while EUGENE-rank can make it much easier for users to identify the real positives among a vast number of reports. We paired our techniques with GoInsight1 and discovered a vulnerability. We also offered a patch to the community.","PeriodicalId":504777,"journal":{"name":"China Communications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141846179","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 : 2024-07-01DOI: 10.23919/JCC.ja.2023-0097
K. Ramya, Senthilselvi Ayothi
The cloud computing technology is utilized for achieving resource utilization of remote-based virtual computer to facilitate the consumers with rapid and accurate massive data services. It utilizes on-demand resource provisioning, but the necessitated constraints of rapid turnaround time, minimal execution cost, high rate of resource utilization and limited makespan transforms the Load Balancing (LB) process-based Task Scheduling (TS) problem into an NP-hard optimization issue. In this paper, Hybrid Prairie Dog and Beluga Whale Optimization Algorithm (HPDBWOA) is propounded for precise mapping of tasks to virtual machines with the due objective of addressing the dynamic nature of cloud environment. This capability of HPDBWOA helps in decreasing the SLA violations and Makespan with optimal resource management. It is modelled as a scheduling strategy which utilizes the merits of PDOA and BWOA for attaining reactive decisions making with respect to the process of assigning the tasks to virtual resources by considering their priorities into account. It addresses the problem of pre-convergence with well-balanced exploration and exploitation to attain necessitated Quality of Service (QoS) for minimizing the waiting time incurred during TS process. It further balanced exploration and exploitation rates for reducing the makespan during the task allocation with complete awareness of VM state. The results of the proposed HPDBWOA confirmed minimized energy utilization of 32.18% and reduced cost of 28.94% better than approaches used for investigation. The statistical investigation of the proposed HPDBWOA conducted using ANOVA confirmed its efficacy over the benchmarked systems in terms of throughput, system, and response time.
{"title":"Hybrid Prairie Dog and Beluga Whale optimization algorithm for multi-objective load balanced-task scheduling in cloud computing environments","authors":"K. Ramya, Senthilselvi Ayothi","doi":"10.23919/JCC.ja.2023-0097","DOIUrl":"https://doi.org/10.23919/JCC.ja.2023-0097","url":null,"abstract":"The cloud computing technology is utilized for achieving resource utilization of remote-based virtual computer to facilitate the consumers with rapid and accurate massive data services. It utilizes on-demand resource provisioning, but the necessitated constraints of rapid turnaround time, minimal execution cost, high rate of resource utilization and limited makespan transforms the Load Balancing (LB) process-based Task Scheduling (TS) problem into an NP-hard optimization issue. In this paper, Hybrid Prairie Dog and Beluga Whale Optimization Algorithm (HPDBWOA) is propounded for precise mapping of tasks to virtual machines with the due objective of addressing the dynamic nature of cloud environment. This capability of HPDBWOA helps in decreasing the SLA violations and Makespan with optimal resource management. It is modelled as a scheduling strategy which utilizes the merits of PDOA and BWOA for attaining reactive decisions making with respect to the process of assigning the tasks to virtual resources by considering their priorities into account. It addresses the problem of pre-convergence with well-balanced exploration and exploitation to attain necessitated Quality of Service (QoS) for minimizing the waiting time incurred during TS process. It further balanced exploration and exploitation rates for reducing the makespan during the task allocation with complete awareness of VM state. The results of the proposed HPDBWOA confirmed minimized energy utilization of 32.18% and reduced cost of 28.94% better than approaches used for investigation. The statistical investigation of the proposed HPDBWOA conducted using ANOVA confirmed its efficacy over the benchmarked systems in terms of throughput, system, and response time.","PeriodicalId":504777,"journal":{"name":"China Communications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141848284","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 : 2024-07-01DOI: 10.23919/JCC.fa.2023-0125.202407
Zhang Han, Wang Yu, Liu Hao, Hongyu Lin, Liquan Chen
The conventional dynamic heterogeneous redundancy (DHR) architecture suffers from the security threats caused by the stability differences and similar vulnerabilities among the executors. To overcome these challenges, we propose an intelligent DHR architecture, which is more feasible by intelligently combining the random distribution based dynamic scheduling algorithm (RD-DS) and information weight and heterogeneity based arbitrament (IWHA) algorithm. In the proposed architecture, the random distribution function and information weight are employed to achieve the optimal selection of executors in the process of RD-DS, which avoids the case that some executors fail to be selected due to their stability difference in the conventional DHR architecture. Then, through introducing the heterogeneity to restrict the information weights in the procedure of the IWHA, the proposed architecture solves the common mode escape issue caused by the existence of multiple identical error output results of similar vulnerabilities. The experimental results characterize that the proposed architecture outperforms in heterogeneity, scheduling times, security, and stability over the conventional DHR architecture under the same conditions.
{"title":"Intelligent dynamic heterogeneous redundancy architecture for IoT systems","authors":"Zhang Han, Wang Yu, Liu Hao, Hongyu Lin, Liquan Chen","doi":"10.23919/JCC.fa.2023-0125.202407","DOIUrl":"https://doi.org/10.23919/JCC.fa.2023-0125.202407","url":null,"abstract":"The conventional dynamic heterogeneous redundancy (DHR) architecture suffers from the security threats caused by the stability differences and similar vulnerabilities among the executors. To overcome these challenges, we propose an intelligent DHR architecture, which is more feasible by intelligently combining the random distribution based dynamic scheduling algorithm (RD-DS) and information weight and heterogeneity based arbitrament (IWHA) algorithm. In the proposed architecture, the random distribution function and information weight are employed to achieve the optimal selection of executors in the process of RD-DS, which avoids the case that some executors fail to be selected due to their stability difference in the conventional DHR architecture. Then, through introducing the heterogeneity to restrict the information weights in the procedure of the IWHA, the proposed architecture solves the common mode escape issue caused by the existence of multiple identical error output results of similar vulnerabilities. The experimental results characterize that the proposed architecture outperforms in heterogeneity, scheduling times, security, and stability over the conventional DHR architecture under the same conditions.","PeriodicalId":504777,"journal":{"name":"China Communications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141841981","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 : 2024-07-01DOI: 10.23919/JCC.ja.2023-0189
Yiting Feng, Zhaofeng Ma, Pengfei Duan, Shoushan Luo
The widespread adoption of blockchain technology has led to the exploration of its numerous applications in various fields. Cryptographic algorithms and smart contracts are critical components of blockchain security. Despite the benefits of virtual currency, vulnerabilities in smart contracts have resulted in substantial losses to users. While researchers have identified these vulnerabilities and developed tools for detecting them, the accuracy of these tools is still far from satisfactory, with high false positive and false negative rates. In this paper, we propose a new method for detecting vulnerabilities in smart contracts using the BERT pre-training model, which can quickly and effectively process and detect smart contracts. More specifically, we preprocess and make symbol substitution in the contract, which can make the pre-training model better obtain contract features. We evaluate our method on four datasets and compare its performance with other deep learning models and vulnerability detection tools, demonstrating its superior accuracy.
{"title":"Automated vulnerability detection of blockchain smart contacts based on BERT artificial intelligent model","authors":"Yiting Feng, Zhaofeng Ma, Pengfei Duan, Shoushan Luo","doi":"10.23919/JCC.ja.2023-0189","DOIUrl":"https://doi.org/10.23919/JCC.ja.2023-0189","url":null,"abstract":"The widespread adoption of blockchain technology has led to the exploration of its numerous applications in various fields. Cryptographic algorithms and smart contracts are critical components of blockchain security. Despite the benefits of virtual currency, vulnerabilities in smart contracts have resulted in substantial losses to users. While researchers have identified these vulnerabilities and developed tools for detecting them, the accuracy of these tools is still far from satisfactory, with high false positive and false negative rates. In this paper, we propose a new method for detecting vulnerabilities in smart contracts using the BERT pre-training model, which can quickly and effectively process and detect smart contracts. More specifically, we preprocess and make symbol substitution in the contract, which can make the pre-training model better obtain contract features. We evaluate our method on four datasets and compare its performance with other deep learning models and vulnerability detection tools, demonstrating its superior accuracy.","PeriodicalId":504777,"journal":{"name":"China Communications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141844267","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 facilitate emerging applications and demands of edge intelligence (EI)-empowered 6G networks, model-driven semantic communications have been proposed to reduce transmission volume by deploying artificial intelligence (AI) models that provide abilities of semantic extraction and recovery. Nevertheless, it is not feasible to preload all AI models on resource-constrained terminals. Thus, in-time model transmission becomes a crucial problem. This paper proposes an intellicise model transmission architecture to guarantee the reliable transmission of models for semantic communication. The mathematical relationship between model size and performance is formulated by employing a recognition error function supported with experimental data. We consider the characteristics of wireless channels and derive the closed-form expression of model transmission outage probability (MTOP) over the Rayleigh channel. Besides, we define the effective model accuracy (EMA) to evaluate the model transmission performance of both communication and intelligence. Then we propose a joint model selection and resource allocation (JMSRA) algorithm to maximize the average EMA of all users. Simulation results demonstrate that the average EMA of the JMSRA algorithm outperforms baseline algorithms by about 22%.
为了促进边缘智能（EI）赋能的 6G 网络的新兴应用和需求，有人提出了模型驱动语义通信，通过部署具有语义提取和恢复能力的人工智能（AI）模型来减少传输量。然而，在资源有限的终端上预载所有人工智能模型是不可行的。因此，及时传输模型成为一个关键问题。本文提出了一种智能模型传输架构，以保证语义通信模型的可靠传输。通过使用实验数据支持的识别误差函数，提出了模型大小与性能之间的数学关系。我们考虑了无线信道的特性，并推导出了瑞利信道上模型传输中断概率（MTOP）的闭式表达式。此外，我们还定义了有效模型精度（EMA）来评估通信和智能的模型传输性能。然后，我们提出了一种联合模型选择和资源分配（JMSRA）算法，以最大化所有用户的平均 EMA。仿真结果表明，JMSRA 算法的平均 EMA 优于基准算法约 22%。
{"title":"Intellicise model transmission for semantic communication in intelligence-native 6G networks","authors":"Yining Wang, Shujun Han, Xiaodong Xu, Meng Rui, Haotai Liang, Dong Chen, Zhang Ping","doi":"10.23919/JCC.fa.2023-0759.202407","DOIUrl":"https://doi.org/10.23919/JCC.fa.2023-0759.202407","url":null,"abstract":"To facilitate emerging applications and demands of edge intelligence (EI)-empowered 6G networks, model-driven semantic communications have been proposed to reduce transmission volume by deploying artificial intelligence (AI) models that provide abilities of semantic extraction and recovery. Nevertheless, it is not feasible to preload all AI models on resource-constrained terminals. Thus, in-time model transmission becomes a crucial problem. This paper proposes an intellicise model transmission architecture to guarantee the reliable transmission of models for semantic communication. The mathematical relationship between model size and performance is formulated by employing a recognition error function supported with experimental data. We consider the characteristics of wireless channels and derive the closed-form expression of model transmission outage probability (MTOP) over the Rayleigh channel. Besides, we define the effective model accuracy (EMA) to evaluate the model transmission performance of both communication and intelligence. Then we propose a joint model selection and resource allocation (JMSRA) algorithm to maximize the average EMA of all users. Simulation results demonstrate that the average EMA of the JMSRA algorithm outperforms baseline algorithms by about 22%.","PeriodicalId":504777,"journal":{"name":"China Communications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141838995","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 : 2024-07-01DOI: 10.23919/JCC.fa.2023-0757.202407
Zijian Liang, Niu Kai, Zhang Ping
As a novel paradigm, semantic communication provides an effective solution for breaking through the future development dilemma of classical communication systems. However, it remains an unsolved problem of how to measure the information transmission capability for a given semantic communication method and subsequently compare it with the classical communication method. In this paper, we first present a review of the semantic communication system, including its system model and the two typical coding and transmission methods for its implementations. To address the unsolved issue of the information transmission capability measure for semantic communication methods, we propose a new universal performance measure called Information Conductivity. We provide the definition and the physical significance to state its effectiveness in representing the information transmission capabilities of the semantic communication systems and present elaborations including its measure methods, degrees of freedom, and progressive analysis. Experimental results in image transmission scenarios validate its practical applicability.
{"title":"Information conductivity: Universal performance measure for semantic communications","authors":"Zijian Liang, Niu Kai, Zhang Ping","doi":"10.23919/JCC.fa.2023-0757.202407","DOIUrl":"https://doi.org/10.23919/JCC.fa.2023-0757.202407","url":null,"abstract":"As a novel paradigm, semantic communication provides an effective solution for breaking through the future development dilemma of classical communication systems. However, it remains an unsolved problem of how to measure the information transmission capability for a given semantic communication method and subsequently compare it with the classical communication method. In this paper, we first present a review of the semantic communication system, including its system model and the two typical coding and transmission methods for its implementations. To address the unsolved issue of the information transmission capability measure for semantic communication methods, we propose a new universal performance measure called Information Conductivity. We provide the definition and the physical significance to state its effectiveness in representing the information transmission capabilities of the semantic communication systems and present elaborations including its measure methods, degrees of freedom, and progressive analysis. Experimental results in image transmission scenarios validate its practical applicability.","PeriodicalId":504777,"journal":{"name":"China Communications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141850679","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 : 2024-07-01DOI: 10.23919/JCC.fa.2023-0755.202407
Zhang Xi, Yiqian Zhang, Congduan Li, Ma Xiao
Recently, deep learning-based semantic communication has garnered widespread attention, with numerous systems designed for transmitting diverse data sources, including text, image, and speech, etc. While efforts have been directed toward improving system performance, many studies have concentrated on enhancing the structure of the encoder and decoder. However, this often overlooks the resulting increase in model complexity, imposing additional storage and computational burdens on smart devices. Furthermore, existing work tends to prioritize explicit semantics, neglecting the potential of implicit semantics. This paper aims to easily and effectively enhance the receiver's decoding capability without modifying the encoder and decoder structures. We propose a novel semantic communication system with variational neural inference for text transmission. Specifically, we introduce a simple but effective variational neural inferer at the receiver to infer the latent semantic information within the received text. This information is then utilized to assist in the decoding process. The simulation results show a significant enhancement in system performance and improved robustness.
{"title":"Variational neural inference enhanced text semantic communication system","authors":"Zhang Xi, Yiqian Zhang, Congduan Li, Ma Xiao","doi":"10.23919/JCC.fa.2023-0755.202407","DOIUrl":"https://doi.org/10.23919/JCC.fa.2023-0755.202407","url":null,"abstract":"Recently, deep learning-based semantic communication has garnered widespread attention, with numerous systems designed for transmitting diverse data sources, including text, image, and speech, etc. While efforts have been directed toward improving system performance, many studies have concentrated on enhancing the structure of the encoder and decoder. However, this often overlooks the resulting increase in model complexity, imposing additional storage and computational burdens on smart devices. Furthermore, existing work tends to prioritize explicit semantics, neglecting the potential of implicit semantics. This paper aims to easily and effectively enhance the receiver's decoding capability without modifying the encoder and decoder structures. We propose a novel semantic communication system with variational neural inference for text transmission. Specifically, we introduce a simple but effective variational neural inferer at the receiver to infer the latent semantic information within the received text. This information is then utilized to assist in the decoding process. The simulation results show a significant enhancement in system performance and improved robustness.","PeriodicalId":504777,"journal":{"name":"China Communications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141843562","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：