Blind signal processing techniques of channel and noise power estimation, modulation and channel coding scheme (MCS) recognition, and data detection have played crucial roles in wireless transmission scenarios, where the receiver cannot obtaina prioriinformation of the incoming signals. Each of these blind signal processing tasks has been extensively studied in the literature. Few works studied the combination of partial tasks jointly. However, to the best of our knowledge, an overall problem that involves all the aforementioned tasks has not been investigated previously. Simply cascading the solution of each individual task is apparently not a suitable approach for the overall problem. To address the above issues, we design a jointblindreceiver that jointly improves the performance of parameterestimation, MCSrecognition, and datadetection. Thus, we refer to it as theblind estimation,recognition, anddetection (BERD)receiver. The multipath fading channel, noise power, and MCS of the transmitter are all unknown to the receiver side; the required side information is only the pool of MCS candidates and perfect synchronization. In this BERD receiver, we first propose an expectation-maximization-based channel and noise power estimator block, which solves the non-convex maximum likelihood estimation problem in a tractable way. Then, a soft-information detector and regenerator block is designed to detect the transmitted information bits and regenerate more reliable symbols. The BERD receiver iterates between these two blocks, and consequently, the accuracy of channel estimation is improved and in turn helps the data detection. Finally, a multistage likelihood-based fusion and decision block is proposed to make the final decision on the adopted MCS, the information bits, and the unknown channel information. Numerical results are provided to show the superior performance of the proposed BERD receiver compared to the existing schemes, in terms of data detection, MCS recognition, and channel estimation.

Multi-user integrated sensing and communication (ISAC) assisted by intelligent reflecting surface (IRS) has been recently investigated to provide a high spectral and energy efficiency transmission. This paper proposes a practical channel estimation approach for the first time to an IRS-assisted multi-user ISAC system. The estimation problem in such a system is challenging since the sensing and communication (SAC) signals interfere with each other, and the passive IRS lacks signal processing ability. A two-stage approach is proposed to transfer the overall estimation problem into sub-ones, successively including the direct and reflected channels estimation. Based on this scheme, the ISAC base station (BS) estimates all the SAC channels associated with the target and uplink users, while each downlink user estimates the downlink communication channels individually. Considering a low-cost demand of the ISAC BS and downlink users, the proposed two-stage approach is realized by an efficient neural network (NN) framework that contains two different extreme learning machine (ELM) structures to estimate the above SAC channels. Moreover, two types of input-output pairs to train the ELMs are carefully devised, which impact the estimation accuracy and computational complexity under different system parameters. Simulation results reveal a substantial performance improvement achieved by the proposed ELM-based approach over the least-squares and NN-based benchmarks, with reduced training complexity and faster training speed.

Integrated sensing and communication (ISAC) and intelligent reflecting surface (IRS) are viewed as promising technologies for future generations of wireless networks. This paper investigates the channel estimation problem in an IRS-assisted ISAC system. A deep-learning framework is proposed to estimate the sensing and communication (S&C) channels in such a system. Considering different propagation environments of the S&C channels, two deep neural network (DNN) architectures are designed to realize this framework. The first DNN is devised at the ISAC base station for estimating the sensing channel, while the second DNN architecture is assigned to each downlink user equipment to estimate its communication channel. Moreover, the input-output pairs to train the DNNs are carefully designed. Simulation results show the superiority of the proposed estimation approach compared to the benchmark scheme under various signal-to-noise ratio conditions and system parameters.

As the advent of cognitive radios, blind encoder identification has attracted increasingly attentions since it plays an important role in blind signal processing. The existing works mainly focus on additive white Gaussian noise (AWGN) channel, while the blind identification in multipath scenarios has not been sufficiently investigated. In this paper, we consider the blind low-density parity-check (LDPC) codes identification in the presence of unknown multipath fading channel. Then, a likelihood-based classifier is proposed using the expectation maximization (EM) algorithm to obtain the maximum likelihood estimates of the unknown parameters, including multipath fading channel and modulated symbols. Then, we adopt an average log-likelihood ratio (LLR) estimator to classify the unknown encoder. Numerical results show that the proposed algorithm provides promising identification performance in multipath channels, especially in the low signal- to-noise ratio region.