This paper investigates a highly spectrally efficient transmission scheme in an integrated satellite and aerial network (ISAN). Specifically, we first propose a novel uplink access framework, where the co-design of communication and over-the-air computation (AirComp) is implemented through layer division multiplexing (LDM) in the aerial network, while the cognitive radio-inspired non-orthogonal multiple access (CR-NOMA) technology is employed in the satellite network. Then, according to the proposed framework, we mathematically formulate a joint optimization problem that aims at maximizing the system achievable sum rate, subject to the constraints of minimal accuracy requirement of AirComp and minimal quality-of-service requirements of communication service. Next, by introducing the inter-network interference-related auxiliary variable, we divide the original optimization problem into two subproblems associated with the optimization of the satellite and aerial networks. To tackle the first subproblem, we propose a beamspace-inspired analog beamforming (BF) method, and derive closed-form expressions for BF vectors and transmit powers to implement the CR-NOMA scheme in the satellite network. Meanwhile, to address the second subproblem, we propose a beamspace-inspired digital BF together with successive convex approximation and alternating optimization approaches, to obtain the BF matrices, transmit power coefficients and AirComp scaling factor, so that the LDM-based communication and computation co-design (CCCD) can be realized in the aerial network. Moreover, for complexity reduction, we propose a beamspace-inspired zero-forcing BF method to calculate the communication BF matrices, and then leverage the orthogonal beam superposition approach to obtain the computation BF matrix, thereby presenting another CCCD scheme. Finally, our simulation results confirm that since the proposed schemes can realize spectrum multiplexing for communication and AirComp services, we achieve higher system spectral efficiency and lower computation error than the benchmarks.

This paper proposes a downlink transmission scheme for intelligent reflecting surface (IRS) enhanced cognitive-satellite-aerial-network to support massive access of Internet-of-Things devices (IoTDs). By sharing the same frequency band with satellite network, the aerial network offers services for IoTDs having line-of-sight links through space division multiple access, and for IoTDs locating in blocked area via IRS-enhanced non-orthogonal multiple access. Assuming that only the imperfect channel state information is available, we formulate a transmit power minimization problem subject to the probabilistic constraints of the quality-of-service requirements for IoTDs, the co-channel interference power limitation, and unit-modulus requirement for IRS. To tackle this mathematically intractable problem, we propose a generalized zero-forcing based low-complexity robust transmission algorithm, integrating the second-order Taylor expansion and Bernstein-type inequality, to obtain a satisfactory performance while reducing the computational load. Finally, simulation results validate the effectiveness and superiority of the proposed robust algorithms compared to existing algorithms.

Cognitive satellite and terrestrial network (CSTN) is considered as a promising technology to provide ubiquitous connectivity for various users within wide-coverage. This paper proposes a robust downlink transmission scheme for multiple intelligent reflecting surfaces (IRSs) assisted CSTN. Here, the satellite network adopts multigroup multicast transmission scheme to serve many earth stations, while the terrestrial network exploits space division multiple access and multi-IRS-enhanced non-orthogonal multiple access technology to communicate with many terrestrial users. By assuming that these two networks share the same frequency band having only the angular information based imperfect channel state information of each user, we formulate an optimization problem to minimize the total transmit power subject to the constraints of quality-of-service requirement for each user, per-antenna transmit power budgets of satellite and BS, and unit-modulus requirement for each reflecting element. To tackle this mathematically intractable problem, we then employ angular discretization together with the successive convex approximation method to obtain the active beamforming (BF) vectors of satellite and BS, the passive BF vector of IRS, and the power allocation coefficients. Moreover, we propose a generalized zero forcing BF and alternative optimization to obtain the suboptimal solutions of the optimization problem with low computational complexity. Finally, simulation results are given to demonstrate the effectiveness and superiority of the proposed two schemes over the benchmarks.

Integrating non-orthogonal multiple access (NOMA) in intelligent reflecting surface (IRS) is expectedly an effective solution to enhance system's spectrum efficiency. In this paper, we investigate joint beamforming and power allocation for uplink NOMA transmission in an IRS-assisted cognitive satellite and terrestrial network operating at millimeter wave frequency band. Specifically, based only on imperfect channel state information in terms of the angular information of both primary users (PUs) and secondary users, we formulate an optimization problem to maximize the sum rate of the PUs in terrestrial network. To handle the resulting intractable optimization problem, we first transform the uncertainty channel vectors into a deterministic form with the aid of angular discretization. Then, by combining successive convex approximation with Taylor expansion and S-procedure methods, we propose an optimization scheme to jointly optimize the beamforming weight vector and power coefficients. Finally, simulation results show that the proposed scheme can achieve outstanding sum rate performance compared to state-of-the-art schemes.

When capturing images in low light condition, due to insufficient lighting, the true color information and texture details of objects are difficult to obtain. Considering that, we propose an end-to-end color channel fusion network (CCFN). Specifically, our proposed method uses partial channel combination inputs to obtain multiple enhancement results. The relevance among RGB channels is maintained by modeling channel interdependencies. Subsequently, a multi-scale feature channel shuffle module (MFCS) is designed to combine image features at different scales, which makes the fusion images hold more rich information. Finally, the output images are generated after detail enhancement. Extensive experiments demonstrate the superiority of our method over several state-of-the-arts in terms of enhancement quality.

This paper proposes an approach that combines a deep learning-based method and a traditional machine learning-based method to efficiently detect malicious requests Web servers received. The first few layers of Convolutional Neural Network for Text Classification (TextCNN) are used to automatically extract powerful semantic features and in the meantime transferable statistical features are defined to boost the detection ability, specifically Web request parameter tampering. The semantic features from TextCNN and transferable statistical features from artificially-designing are grouped together to be fed into Support Vector Machine (SVM), replacing the last layer of TextCNN for classification. To facilitate the understanding of abstract features in form of numerical data in vectors extracted by TextCNN, this paper designs trace-back functions that map max-pooling outputs back to words in Web requests. After investigating the current available datasets for Web attack detection, HTTP Dataset CSIC 2010 is selected to test and verify the proposed approach. Compared with other deep learning models, the experimental results demonstrate that the approach proposed in this paper is competitive with the state-of-the-art.