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 ...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 cloudside collaborative training and inference.In summary,the churn prediction model based on Graph Attention Convol展开更多
The penetration of mobile phones is nearly saturated in both developing and developed regions. In such a circumstance, how to prevent subscriber churn has become an important issue for today＇s telecom operators, as t...The penetration of mobile phones is nearly saturated in both developing and developed regions. In such a circumstance, how to prevent subscriber churn has become an important issue for today＇s telecom operators, as the cost to acquire a new subscriber is much higher than that to retain an existing subscriber. In this paper, we propose to leverage the power of big data to mitigate the problem of subscriber churn and enhance the service quality of telecom operators. As the information hub, telecom operators have accumulated a huge volume of valuable data on subscriber behaviors, service usage, and network operations. To enable efficient big data processing, we first build a dedicated distributed cloud infrastructure that integrates both online and offline processing capabilities. Second, we develop a complete churn analysis model based on deep data mining techniques, and utilize inter-subscriber influence to improve prediction accuracy. Finally, we use real datasets obtained from a large telecom operator in China to verify the accuracy of our churn analysis models. The dataset contains the information of over 3.5 million subscribers, which generate over 600 million call detail records （CDRs） per month. The empirical results demonstrate that our proposed method can achieve around 90% accuracy for T ＋ 1 testing periods and identify subscribers with high negative influence successfully.展开更多
According to the security requirement of the short message service （SMS） industry application, a secure short message communication protocol is proposed. This is an application level protocol constructed on the stan...According to the security requirement of the short message service （SMS） industry application, a secure short message communication protocol is proposed. This is an application level protocol constructed on the standard SMS communication protocol using public key authentication and key agreement without the need of wireless public key infrastructure （WPKI）. Secure short message transmission and dynamic key agreement between mobile terminals and the accessing gateway axe realized. The security of the proposed protocol is validated through the BAN logic. Compared with the standard SMS protocol, the effective payload rate of our protocol can reach 91.4%, and subscriber identity module （SIM） tool kit （STK） applications based on our protocol suit well for all kinds of mobile terminals in practical application.展开更多
The margin maximization problem in digital subscriber line（DSL） systems is investigated.The particle swarm optimization（PSO） theory is applied to the nonconvex margin optimization problem with the target power and...The margin maximization problem in digital subscriber line（DSL） systems is investigated.The particle swarm optimization（PSO） theory is applied to the nonconvex margin optimization problem with the target power and rate constraints.PSO is a new evolution algorithm based on the social behavior of swarms, which can solve discontinuous, nonconvex and nonlinear problems efficiently.The proposed algorithm can converge to the global optimal solution, and numerical example demonstrates that the proposed algorithm can guarantee the fast convergence within a few iterations.展开更多
With the rapid development of wireless local area network （WLAN） technology, an important target of indoor positioning systems is to improve the positioning accuracy while reducing the online calibration effort to o...With the rapid development of wireless local area network （WLAN） technology, an important target of indoor positioning systems is to improve the positioning accuracy while reducing the online calibration effort to overcome signal time-varying. A novel fingerprint positioning algorithm, known as the adaptive radio map with updated method based on hidden Markov model （HMM）, is proposed. It is shown that by using a collection of user traces that can be cheaply obtained, the proposed algorithm can take advantage of these data to update the labeled calibration data to further improve the position estimation accuracy. This algorithm is a combination of machine learning, information gain theory and fingerprinting. By collecting data and testing the algorithm in a realistic indoor WLAN environment, the experiment results indicate that, compared with the widely used K nearest neighbor algorithm, the proposed algorithm can improve the positioning accuracy while greatly reduce the calibration effort.展开更多
Cooperation allows wireless network users to benefit from various gains such as an in- crease in the achieved rate or an improvement in the bit error rate. In the paper, we propose a distributed Hierarchical Game （HG...Cooperation allows wireless network users to benefit from various gains such as an in- crease in the achieved rate or an improvement in the bit error rate. In the paper, we propose a distributed Hierarchical Game （HG） theoretic framework over multi-user cooperative communication networks to stimulate cooperation and improve the network performance. First, we study a two- user decision making game in the OFDMA based subscriber cooperative relaying network, in which subscribers transmit their own data in the first phase, while helping to retransmit their partner＇s or choosing to freeride in the second phase. Instead of consulting to a global optimal solution, we decouple the cooperation resource allocation into two level subproblems： a user level Nash game for distributed cooperation decision and a Base Station （BS） level coalition game for centralized resource allocation. In the proposed HG algorithm, where mutual cooperation is preferred and total payoff is transferable, we prove it converges to a unique optimal equilibrium and resolve the subcarrier as-signment and power allocation among the couples. Besides, we discuss the existence of the publishing and rewarding coefficients in order to encourage cooperation. Then, we extend the HG to multi-user cases by coupling among subscribers according to the location information. The simulation results show that the proposed scheme with the distributed HG game achieves a well tradeoff between fairness and efficiency by improving the transmission efficiency of adverse users and outperforms those employing centralized schemes.展开更多
Crosstalk is the main degrading factor in Digital Subscriber Line (DSL) systems which are the result of electromagnetic coupling between two adjacent twisted pairs in a cable. Very-high bit-rate Digital Subscriber Lin...Crosstalk is the main degrading factor in Digital Subscriber Line (DSL) systems which are the result of electromagnetic coupling between two adjacent twisted pairs in a cable. Very-high bit-rate Digital Subscriber Line (VDSL) systems which use higher frequencies for data transmission than the other DSL systems, this effect is more considerable in Bit Error Rate (BER) degradation. This paper considers a complete adaptive iterative water-filling (IWF) algorithm for Resolving Upstream Near-Far Problem in VDSL Systems. The new distributed dynamic spectrum management algorithm is proposed, which improve achievable bit rate of iterative water-filling algorithm. The paper proffers a new power back-off strategy of the spectral mask at the near-end users, in order to protect the far-end users. Simulation of the proposed algorithm indicates that the bit rate is increased considerably rather the IWF and adaptive water-filling (AIWF) algorithms by keeping their low complexity. Furthermore, by adding the number of users in network, the new algorithm achieves performance gains over the AIWF, completely adaptive.展开更多
Traceability precept is a broadcast encryption technique that content suppliers can trace malicious authorized users who leak the decryption key to an unauthorized user. To protect the data from eavesdropping, the con...Traceability precept is a broadcast encryption technique that content suppliers can trace malicious authorized users who leak the decryption key to an unauthorized user. To protect the data from eavesdropping, the content supplier encrypts the data and broadcast the cryptograph that only its subscribers can decrypt. However, a traitor may clone his decoder and sell the pirate decoders for profits. The traitor can modify the private key and the decryption program inside the pirate decoder to avoid divulging his identity. Furthermore, some traitors may fabricate a new legal private key together that cannot be traced to the creators. So in this paper, a renewed precept is proposed to achieve both revocation at a different level of capacity in each distribution and black-box tracing against self-protective pirate decoders. The rigorous mathematical deduction shows that our algorithm possess security property.展开更多
Insertion loss （IL） is one of the important parameters of asymmetrical digital subscriber loop （ADSL） transformers. In different frequency bands, the factors that affect insertion loss are different. Windings main...Insertion loss （IL） is one of the important parameters of asymmetrical digital subscriber loop （ADSL） transformers. In different frequency bands, the factors that affect insertion loss are different. Windings mainly affect insertion loss in mid and high frequency bands. The effects of winding ways, winding wire diameter and winding turns on insertion loss were discussed. The presented experiment shows that the insertion loss of an ADSL transformer could be under 0.4 dB in mid frequency band when the winding is 30 turns, in which the ADSL transformer satisfies the requirement of total harmonic distortion （THD）. Our experiments also show that the sandwich winding structure is better than the side by side winding structure and the twisted-pair winding structure, and the increase of winding diameter is one means to reduce insertion losses of an ADSL transformer in mid frequency band.展开更多
The global system for mobile communication(GSM)is planned to meet the needs of the whole subscribers.The number of subscribers increased as the population increased due to the acceptance of GSM services by the subscri...The global system for mobile communication(GSM)is planned to meet the needs of the whole subscribers.The number of subscribers increased as the population increased due to the acceptance of GSM services by the subscribers.Thus,there should be a way to monitor base stations that will meet the increasing demand of subscribers in any area as a population surge will lead to more subscriptions.This will allow GSM network operators to serve their subscribers better and ease network congestion.This work presents a review of mobile evolution from the first generation to the fifth generation.A review of global positioning system(GPS)technology and its applications to geographic information systems(GIS)was done.The coordinates of these base stations were taken using a GPS device.These base station coordinates were then exported to QGIS for the design of the map.Thereafter,the output map was then integrated into the website.The discussions on the results followed and some useful suggestions given will go a long way to help the operators of GSM in Nigeria and in general.If the propositions given are adhered to,it will go a long way to help the operators reduce congestion on their network and thereby increase the satisfaction of the subscribers.展开更多
基金supported by National Key R&D Program of China(No.2022YFB3104500)Natural Science Foundation of Jiangsu Province(No.BK20222013)Scientific Research Foundation of Nanjing Institute of Technology(No.3534113223036)。
文摘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 cloudside collaborative training and inference.In summary,the churn prediction model based on Graph Attention Convol
基金This work was supported in part by the National Natural Science Foundation of China under Grant Nos. 61272397, 61472454, and 61572538, and the Guangdong Natural Science Funds for Distinguished Young Scholar under Grant No. S20120011187.
文摘The penetration of mobile phones is nearly saturated in both developing and developed regions. In such a circumstance, how to prevent subscriber churn has become an important issue for today＇s telecom operators, as the cost to acquire a new subscriber is much higher than that to retain an existing subscriber. In this paper, we propose to leverage the power of big data to mitigate the problem of subscriber churn and enhance the service quality of telecom operators. As the information hub, telecom operators have accumulated a huge volume of valuable data on subscriber behaviors, service usage, and network operations. To enable efficient big data processing, we first build a dedicated distributed cloud infrastructure that integrates both online and offline processing capabilities. Second, we develop a complete churn analysis model based on deep data mining techniques, and utilize inter-subscriber influence to improve prediction accuracy. Finally, we use real datasets obtained from a large telecom operator in China to verify the accuracy of our churn analysis models. The dataset contains the information of over 3.5 million subscribers, which generate over 600 million call detail records （CDRs） per month. The empirical results demonstrate that our proposed method can achieve around 90% accuracy for T ＋ 1 testing periods and identify subscribers with high negative influence successfully.
基金This work was supported by the Mobile Police Project of China(No.J1GAB23W013)National High Technology Research and Development Program of China(863 Program,No.2007AA01Z479).
文摘According to the security requirement of the short message service （SMS） industry application, a secure short message communication protocol is proposed. This is an application level protocol constructed on the standard SMS communication protocol using public key authentication and key agreement without the need of wireless public key infrastructure （WPKI）. Secure short message transmission and dynamic key agreement between mobile terminals and the accessing gateway axe realized. The security of the proposed protocol is validated through the BAN logic. Compared with the standard SMS protocol, the effective payload rate of our protocol can reach 91.4%, and subscriber identity module （SIM） tool kit （STK） applications based on our protocol suit well for all kinds of mobile terminals in practical application.
基金supported by the National Natural Science Foundation of China for Distinguished Young Scholars (60525303)the National Natural Science Foundation of China (60904048+2 种基金 60404022 60604012)the Natural Science Foundation of Hebei province (F2005000390)
文摘The margin maximization problem in digital subscriber line（DSL） systems is investigated.The particle swarm optimization（PSO） theory is applied to the nonconvex margin optimization problem with the target power and rate constraints.PSO is a new evolution algorithm based on the social behavior of swarms, which can solve discontinuous, nonconvex and nonlinear problems efficiently.The proposed algorithm can converge to the global optimal solution, and numerical example demonstrates that the proposed algorithm can guarantee the fast convergence within a few iterations.
基金supported by the National Natural Science Foundation of China(61571162)the Major National Science and Technology Project(2014ZX03004003-005)
文摘With the rapid development of wireless local area network （WLAN） technology, an important target of indoor positioning systems is to improve the positioning accuracy while reducing the online calibration effort to overcome signal time-varying. A novel fingerprint positioning algorithm, known as the adaptive radio map with updated method based on hidden Markov model （HMM）, is proposed. It is shown that by using a collection of user traces that can be cheaply obtained, the proposed algorithm can take advantage of these data to update the labeled calibration data to further improve the position estimation accuracy. This algorithm is a combination of machine learning, information gain theory and fingerprinting. By collecting data and testing the algorithm in a realistic indoor WLAN environment, the experiment results indicate that, compared with the widely used K nearest neighbor algorithm, the proposed algorithm can improve the positioning accuracy while greatly reduce the calibration effort.
基金Acknowledgements This work is supported by the National Natural Science Foundation of China under Grant No. 60971083, National High-Tech Research and Development Plan of China under Grant No. 2009AA01Z206 and National International Science and Technology Cooperation Project under Granted NO.2008DFA12090.
文摘Cooperation allows wireless network users to benefit from various gains such as an in- crease in the achieved rate or an improvement in the bit error rate. In the paper, we propose a distributed Hierarchical Game （HG） theoretic framework over multi-user cooperative communication networks to stimulate cooperation and improve the network performance. First, we study a two- user decision making game in the OFDMA based subscriber cooperative relaying network, in which subscribers transmit their own data in the first phase, while helping to retransmit their partner＇s or choosing to freeride in the second phase. Instead of consulting to a global optimal solution, we decouple the cooperation resource allocation into two level subproblems： a user level Nash game for distributed cooperation decision and a Base Station （BS） level coalition game for centralized resource allocation. In the proposed HG algorithm, where mutual cooperation is preferred and total payoff is transferable, we prove it converges to a unique optimal equilibrium and resolve the subcarrier as-signment and power allocation among the couples. Besides, we discuss the existence of the publishing and rewarding coefficients in order to encourage cooperation. Then, we extend the HG to multi-user cases by coupling among subscribers according to the location information. The simulation results show that the proposed scheme with the distributed HG game achieves a well tradeoff between fairness and efficiency by improving the transmission efficiency of adverse users and outperforms those employing centralized schemes.
文摘Crosstalk is the main degrading factor in Digital Subscriber Line (DSL) systems which are the result of electromagnetic coupling between two adjacent twisted pairs in a cable. Very-high bit-rate Digital Subscriber Line (VDSL) systems which use higher frequencies for data transmission than the other DSL systems, this effect is more considerable in Bit Error Rate (BER) degradation. This paper considers a complete adaptive iterative water-filling (IWF) algorithm for Resolving Upstream Near-Far Problem in VDSL Systems. The new distributed dynamic spectrum management algorithm is proposed, which improve achievable bit rate of iterative water-filling algorithm. The paper proffers a new power back-off strategy of the spectral mask at the near-end users, in order to protect the far-end users. Simulation of the proposed algorithm indicates that the bit rate is increased considerably rather the IWF and adaptive water-filling (AIWF) algorithms by keeping their low complexity. Furthermore, by adding the number of users in network, the new algorithm achieves performance gains over the AIWF, completely adaptive.
基金This work was supported by the Large-Scale Security SoC Project of Wuhan Science and Technology Bureau of China under Grand No. 20061005119.
文摘Traceability precept is a broadcast encryption technique that content suppliers can trace malicious authorized users who leak the decryption key to an unauthorized user. To protect the data from eavesdropping, the content supplier encrypts the data and broadcast the cryptograph that only its subscribers can decrypt. However, a traitor may clone his decoder and sell the pirate decoders for profits. The traitor can modify the private key and the decryption program inside the pirate decoder to avoid divulging his identity. Furthermore, some traitors may fabricate a new legal private key together that cannot be traced to the creators. So in this paper, a renewed precept is proposed to achieve both revocation at a different level of capacity in each distribution and black-box tracing against self-protective pirate decoders. The rigorous mathematical deduction shows that our algorithm possess security property.
文摘Insertion loss （IL） is one of the important parameters of asymmetrical digital subscriber loop （ADSL） transformers. In different frequency bands, the factors that affect insertion loss are different. Windings mainly affect insertion loss in mid and high frequency bands. The effects of winding ways, winding wire diameter and winding turns on insertion loss were discussed. The presented experiment shows that the insertion loss of an ADSL transformer could be under 0.4 dB in mid frequency band when the winding is 30 turns, in which the ADSL transformer satisfies the requirement of total harmonic distortion （THD）. Our experiments also show that the sandwich winding structure is better than the side by side winding structure and the twisted-pair winding structure, and the increase of winding diameter is one means to reduce insertion losses of an ADSL transformer in mid frequency band.
文摘The global system for mobile communication(GSM)is planned to meet the needs of the whole subscribers.The number of subscribers increased as the population increased due to the acceptance of GSM services by the subscribers.Thus,there should be a way to monitor base stations that will meet the increasing demand of subscribers in any area as a population surge will lead to more subscriptions.This will allow GSM network operators to serve their subscribers better and ease network congestion.This work presents a review of mobile evolution from the first generation to the fifth generation.A review of global positioning system(GPS)technology and its applications to geographic information systems(GIS)was done.The coordinates of these base stations were taken using a GPS device.These base station coordinates were then exported to QGIS for the design of the map.Thereafter,the output map was then integrated into the website.The discussions on the results followed and some useful suggestions given will go a long way to help the operators of GSM in Nigeria and in general.If the propositions given are adhered to,it will go a long way to help the operators reduce congestion on their network and thereby increase the satisfaction of the subscribers.
