Learning-Based User Clustering and Link Allocation for Content Recommendation Based on D2D Multicast Communications

Yang, Lianxin; Wu, Dan; Cai, Yueming; Shi, Xin; Wu, Yan

doi:10.1109/tmm.2019.2949434

Cited by 17 publications

(8 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 2 plots the COP of SU receivers N and M versus SNR for different power allocation ratio a 2 =a 1 , where Q = 20dB and T N , T M ð Þ= 2, 4 ð Þ. The analysis points are calculated from equations (25) and (32). We observe that the COP of user N and user M decreases with the increasing of SNR.…”

Section: Numerical Resultsmentioning

confidence: 96%

“…The COP of user M can be written as equation (32). Remark 1: In the above analysis, it can be easily found that connection outage would occur at user N when u 1 \0 and u 2 \0.…”

Section: Lemmamentioning

confidence: 99%

“…Then, the user N as a relay sensor node uses the DF mode to forward the signal of the only user M (at user N) to the user M, like device-todevice or unmanned aerial vehicle (UAV)-based relay communication network. [32][33][34] Our preliminary analysis only considers two SU receivers user N and user M, and multiple user nodes will be considered in the later research. 35,36 In FD-C-NOMA networks, the channel coefficient are denoted by scalars h SE , h SP , and h NP , T N 3 1 vector…”

Section: System Model and The Proposed Transmission Strategymentioning

confidence: 99%

See 2 more Smart Citations

Physical layer security in cognitive NOMA sensor networks with full-duplex technique

Shang

Zhang

Tao

et al. 2021

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

This article studies the physical layer security in a downlink full-duplex cognitive non-orthogonal multiple access sensor networks (FD-C-NOMA). Compared with the existing works, this article proposes a FD-C-NOMA transmission scheme with a primary user (PU) and secondary user (SU) sensor nodes in the presence of an eavesdropper. The zero-forcing beamforming design problems of FD operation are investigated subject to the practical secrecy rate and the quality of services of PU. To characterize the security reliability trade-off of the FD-C-NOMA scheme, we first derive the closed-form expressions of connection outage probability (COP), the secrecy outage probability (SOP), and effective secrecy throughput (EST) of each SU in the NOMA networks. Then the impacts of the system parameters on the COP, SOP, and EST are investigated to evaluate the security and reliability in the FD-C-NOMA networks. Furthermore, in order to further verify the security and reliability of our considered network, an OMA scheme of FD operation is provided in the simulation for the purpose of comparison. Results demonstrate that the NOMA-based cognitive sensor networks of FD operation outperforms the OMA system in terms of EST. Finally, simulations are performed to validate the accuracy of our analysis results of the proposed scheme.

show abstract

Section: Numerical Resultsmentioning

confidence: 96%

“…The COP of user M can be written as equation (32). Remark 1: In the above analysis, it can be easily found that connection outage would occur at user N when u 1 \0 and u 2 \0.…”

Section: Lemmamentioning

confidence: 99%

Section: System Model and The Proposed Transmission Strategymentioning

confidence: 99%

See 1 more Smart Citation

Physical layer security in cognitive NOMA sensor networks with full-duplex technique

Shang

Zhang

Tao

et al. 2021

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

show abstract

“…Several other researchers argued different users may have similar preferences to items. Consequently, Yang et al [16] and Chen et al [17] clustered the users into several groups according to their historical item interactions and separately captured the common preferences of users in each group. Recently, due to the great performance of graph convolutional networks, many approaches have resorted to constructing a graph of users and items according to their historical interactions, and exploring the high-order connectivity from user-item interaction [5], [6], [7], [18], [19].…”

Section: Related Workmentioning

confidence: 99%

“…( 9) from 0 to 1 with the stride of 0.1 for each dataset, and the dimension D in Eqn. (2) from [2,4,8,16,32].…”

Section: Experimental Settingsmentioning

confidence: 99%

Dual Preference Distribution Learning for Item Recommendation

Duan¹,

Song²,

Zheng³

et al. 2022

Preprint

View full text Add to dashboard Cite

Recommender systems can automatically recommend users items that they probably like, for which the goal is to represent the user and item as well as model their interaction. Existing methods have primarily learned the user's preferences and item's features with vectorized representations, and modeled the user-item interaction by the similarity of their representations. In fact, the user's different preferences are related and capturing such relations could better understand the user's preferences for a better recommendation. Toward this end, we propose to represent the user's preference with multi-variant Gaussian distribution, and model the user-item interaction by calculating the probability density at the item in the user's preference distribution. In this manner, the mean vector of the Gaussian distribution is able to capture the center of the user's preferences, while its covariance matrix captures the relations of these preferences. In particular, in this work, we propose a dual preference distribution learning framework (DUPLE), which captures the user's preferences to both the items and attributes by a Gaussian distribution, respectively. As a byproduct, identifying the user's preference to specific attributes enables us to provide the explanation of recommending an item to the user. Extensive quantitative and qualitative experiments on six public datasets show that DUPLE achieves the best performance over all state-of-the-art recommendation methods.

show abstract

Content Independent Location Based Clustering for 5G Device to Device Communications

Mukherjee

2021

Wireless Pers Commun

View full text Add to dashboard Cite

Learning-Based User Clustering and Link Allocation for Content Recommendation Based on D2D Multicast Communications

Cited by 17 publications

References 40 publications

Physical layer security in cognitive NOMA sensor networks with full-duplex technique

Physical layer security in cognitive NOMA sensor networks with full-duplex technique

Dual Preference Distribution Learning for Item Recommendation

Content Independent Location Based Clustering for 5G Device to Device Communications

Contact Info

Product

Resources

About