Background:Triple-negative breast cancer (TNBC) is an aggressive cancer with unfavorable outcome and it is useful to explore noninvasive biomarkers for its early diagnosis. Here, we identified differentially expressed long noncoding RNAs (lncRNAs) in blood samples of patients with TNBC to assess their diagnostic value.Methods:Differential expression of lncRNAs in plasma of patients with TNBC (n = 25) and non-TNBC (NTNBC; n = 35) and in healthy controls was compared by microarray analysis and validated by real-time PCR. lncRNA expression between plasma and BC tissues was compared using Pearson correlation test. Logit model was used to obtain a new lncRNA-based score. Receiver operating characteristic analysis was performed to assess the diagnostic value of the selected lncRNAs.Results:Microarray data showed that 41 lncRNAs were aberrantly expressed. Among these, antisense noncoding RNA in the INK4 locus (ANRIL), hypoxia inducible factor 1alpha antisense RNA-2 (HIF1A-AS2), and urothelial carcinoma-associated 1 (UCA1) were markedly upregulated in plasma of patients with TNBC compared with patients with NTNBC (P < 0.01). HIF1A-AS2 expression was positively associated with its tissue levels (r = 0.670, P < 0.01). AUC (95% CI) of ANRIL, HIF1A-AS2, and UCA1 was 0.785 (0.660–0.881), 0.739 (0.610–0.844), and 0.817 (0.696–0.905), respectively. TNBCSigLnc-3, a new score obtained using the logit model, showed excellent diagnostic performance, with AUC of 0.934 (0.839–0.982), sensitivity of 76.0%, and specificity of 97.1%.Conclusion:ANRIL, HIF1A-AS2, and UCA1 expression was significantly increased in plasma of patients with TNBC, suggesting their use as TNBC-specific diagnostic biomarkers.

Network slicing (NS) has been widely identified as a key architectural technology for 5G-and-beyond systems by supporting divergent requirements in a sustainable way. In radio access network (RAN) slicing, due to the device-base station (BS)-NS three layer association relationship, device association (including access control and handoff management) becomes an essential yet challenging issue. With the increasing concerns on stringent data security and device privacy, exploiting local resources to solve device association problem while enforcing data security and device privacy becomes attractive. Fortunately, recently emerging federated learning (FL), a distributed learning paradigm with data protection, provides an effective tool to address this type of issues in mobile networks. In this paper, we propose an efficient device association scheme for RAN slicing by exploiting a hybrid FL reinforcement learning (HDRL) framework, with the aim to improve network throughput while reducing handoff cost. In our proposed framework, individual smart devices train a local machine learning model based on local data and then send the model features to the serving BS/encrypted party for aggregation, so as to efficiently reduce bandwidth consumption for learning while enforcing data privacy. Specifically, we use deep reinforcement learning to train the local model on smart devices under a hybrid FL framework, where horizontal FL is employed for parameter aggregation on BS, while vertical FL is employed for NS/BS pair selection aggregation on the encrypted party. Numerical results show that the proposed HDRL scheme can achieve significant performance gain in terms of network throughput and communication efficiency in comparison with some state-of-the-art solutions.

No abstract

Deploying ultra-dense networks that operate on millimeter wave (mmWave) band is a promising way to address the tremendous growth on mobile data traffic. However, one key challenge of ultra-dense mmWave network (UDmmN) is beam management due to the high propagation delay, limited beam coverage as well as numerous beams and users. In this paper, a novel systematic beam control scheme is presented to tackle the beam management problem which is difficult due to the nonconvex objective function. We employ double deep Q-network (DDQN) under a federated learning (FL) framework to address the above optimization problem, and thereby fulfilling adaptive and intelligent beam management in UDmmN. In the proposed beam management scheme based on FL (BMFL), the non-rawdata aggregation can theoretically protect user privacy while reducing handoff cost. Moreover, we propose to adopt a data cleaning technique in the local model training for BMFL, with the aim to further strengthen the privacy protection of users while improving the learning convergence speed. Simulation results demonstrate the performance gain of our proposed scheme.