The interaction between non-coding RNA (ncRNA) and protein (ncRPI) plays a crucial role in many physiological activities and disease progression. To identify ncRPIs on a large scale by computational methods based on deep learning is a common practice. However, existing computational methods face challenges such as low feature expression and redundant suppression capability when processing high dimensional feature data. To this end, we propose a new prediction model, called FSKansformer, in which a feature salience module is introduced to highlight useful information and suppress noise of multi-view feature matrices. In order to reduce the loss of feature information caused by serial extraction of global feature and local feature, we propose an parallel extraction framework in which a improved Kansformer is designed to extract global high-dimensional features, BiLSTM and LSTM techniques are used to extract local high-dimensional features simultaneously. Finally, the fused global-local high-dimensional features are input into the three-layer KAN network for dimensionality reduction to generate the final prediction score. Experiment results show that FSKansformer achieves state-of-the-art performance on five benchmark datasets compared with other models.

In this study, the authors investigate the user selection (US), beamforming (BF) and power allocation (PA) problems for the downlink multiple‐input–single‐output‐based non‐orthogonal multiple‐access system. For the US problem, they matched the BF and PA schemes with different US schemes to achieve the best spectral efficiency performance. For the BF and PA problems, they derive a non‐normalised BF scheme to accomplish the BF and PA problems jointly. The non‐normalised BF scheme requires much lower computational complexity than the duality BF scheme. According to their simulation results, the non‐normalised BF scheme can achieve the same or better spectral efficiency performance than the duality BF scheme. When the number of users sharing the same time–frequency resource is large, both the duality BF scheme and the singular value decomposition (SVD)‐based BF scheme cannot obtain spectral efficiency advantage over the OMA scheme. However, the non‐normalised BF scheme can maintain the advantage over the OMA scheme.

The authors investigate the beamforming (BF) problem to minimise the power consumption for the downlink 2‐user multiple input single output‐based non‐orthogonal multiple access system. Inspired from the conventional zero‐forcing (ZF) scheme, they propose the Half‐ZF scheme which only mitigates the interference introduced by the signal of the cell‐interior user through the ZF method. Meanwhile, the interference introduced by the signal of the cell‐edge user is removed through the SIC technology. We derive the closed‐form expression for the BF vectors of the two users under the Half‐ZF scheme. The optimal power consumption for the Half‐ZF scheme is analysed and the corresponding solution of the BF factors are also obtained. Compared with the conventional ZF scheme, both the Half‐ZF scheme and the existing quasi‐degradation (QD) scheme can achieve lower power consumption than the ZF scheme. However, the Half‐ZF scheme can achieve this advantage under more relaxed conditions. Consequently, the Half‐ZF scheme consumes lower power than the QD scheme when combined with the ZF scheme in practical systems.

In this study, the authors investigate the resource allocation (RA) problem for the downlink orthogonal frequency division multiplexing based non‐orthogonal multiple access (OFDM‐NOMA) system. The RA problem is decomposed into two subproblems of subcarrier allocation (SA) and power allocation (PA). For the SA, a user grouping based greedy algorithm is proposed under the assumption that power is uniformly distributed among all the selected users. For the PA, the authors propose the iterative water‐filling and specific user rate maximising criterion with minimum rate constraints (iterative WF + SURMC‐MRC) scheme to jointly consider the PA problem among the selected users on one subcarrier and the PA problem among subcarriers. The simulation results show that the spectral efficiency performance of the proposed iterative WF + SURMC‐MRC scheme outperforms those of the (non‐iterative) WF + SURMC‐MRC scheme and the uniform distribution (UD) + SURMC‐MRC scheme. Moreover, the iterative WF + SURMC‐MRC scheme has advantages in resisting against the user overloading compared with the (non‐iterative) WF + SURMC‐MRC scheme.

In this study, the authors investigate the power allocation (PA) problem and spectral efficiency (SE) analysis for the single antenna downlink non‐orthogonal multiple access (NOMA) system under the sum rate maximising criteria with minimum rate constraints (SRMC‐MRC). For the PA problem, they propose the duality scheme for SRMC‐MRC which is considered as the optimal solution for the PA problem on one orthogonal subband in the single antenna NOMA system. They propose the specific user rate maximising criteria with minimum rate constraints (SURMC‐MRC) scheme to decrease the computational complexity of SRMC‐MRC. The PA problem on one subband under SURMC‐MRC is proved to be equivalent to SRMC‐MRC. Numerical results show that both the SE and fairness performance for SURMC‐MRC can strictly approach to those of the duality scheme in the whole signal‐to‐noise ratio (SNR) region. They prove that NOMA under SRMC‐MRC can obtain SE performance advantage in the high SNR region but accompany with some disadvantages in the low SNR region over the orthogonal multiple access system. This conclusion is verified through numerical results under different parameter conditions.

This paper investigates the resource allocation (RA) problem for the downlink multiple input multiple output-based non-orthogonal multiple access (MIMO-NOMA) system, which is usually solved through a beamforming (BF) process and a user selection (US) process. In this paper, we propose the multiple-user channel state information (CSI)-based singular value decomposition (MU-CSI-SVD) BF scheme and the minimization of power (Min-Power) US scheme. Under perfect CSI scenarios, the proposed MU-CSI-SVD achieves near optimal sum rate performance with the high-complexity BF scheme while has the same level computational complexity as the low-complexity BF scheme. For imperfect CSI scenarios, the proposed MU-CSI-SVD also achieves better outage probability performance but requires the same level computational complexity as the existing low-complexity BF scheme. Moreover, MU-CSI-SVD is helpful to decrease the computational complexity for solving the Min-Power US problem. Compared with existing US schemes, the proposed Min-Power scheme can achieve larger sum rate or lower outage probability with limited computational complexity increment. Therefore, in this paper, we develop a complete RA scheme for 5G MIMO-NOMA systems, which has excellent performance while with low computational complexity for both perfect and imperfect CSI scenarios.

In this paper, we investigate the resource allocation problem for the downlink non-orthogonal multiple access (NOMA) system with imperfect channel state information (CSI). We first derive closed-form expressions for the outage probabilities with and without the estimated instantaneous channel fading coefficient for each user. Upper bounds on both of the probability expressions above are proposed. Based on the outage probability bounds, we propose the power allocation scheme which is combined with a user selection step to minimize the maximum of the outage probability bounds of all the users. Simulation results show that the maximum outage probability can be significantly decreased by exploiting the priori knowledge of the estimated instantaneous channel fading coefficient for each user.