Conventionally, we usually carry out Q estimation first and then perform seismic attenuation compensation (Ac). In this paper, we propose a method based on semi-supervised multi-task 2D V-Net combined with transfer learning to simultaneously conduct Q estimation and Ac for seismic data. The semi-supervised network consists of an inversion network and a forward network, both of which are 2D V-Net. And two channels are used to accomplish two tasks. The network pretrained on the synthetic data generated by the typical model is transferred to the target field data. The loss between the predictions of the inversion network and the label data, along with the loss between the seismic data obtained by the forward network and the input seismic data, is utilized to jointly guide the network training. As a result of fully exploiting the synthetic data, labeled data, and unlabeled seismic data for network training, the demand for labeled data is reduced. For the situation where the number of well logs is extremely small, a two-step strategy is developed. Firstly, a certain number of labels are generated using conventional method based on stratigraphic structure constrained molecular decomposition to train the network, and then the labels produced by well logs are used to further train the network. Both synthetic and field examples demonstrate that the two-step strategy enables our method to simultaneously achieve Q and compensated seismic data with high accuracy using attenuated seismic data, even with only one well log. Moreover, this approach exhibits good robustness against noise.

Massive MIMO systems are vulnerable to pilot spoofing attacks (PSAs) since the estimated channel state information can be contaminated by the eavesdropping link, thus incurring severe information leakage in downlink transmission. To safeguard legitimate communications, this paper proposes a PSA detection method which relies on pilot manipulation. Specifically, users randomly partition pilot sequences into two parts, where the first part remains unchanged and the second one is multiplied with a diagonal matrix. Although a malicious node may follow the same way to send pilots, this makes it more likely to be detected. According to the principle of the likelihood-ratio test, the proposed detector is designed based on a decision metric that does not include the legitimate channel. This feature differentiates our scheme from existing ones and remarkably improves the detection accuracy. Besides, the possibility of performance enhancement by joint detection is discussed. Furthermore, based on pilot manipulation, a jamming-resistant receiver is designed. The key of this receiver is a new channel estimator that is robust to the PSA. Finally, extensive simulations are carried out to validate our proposed algorithms.

To secure the legitimate communication, this paper proposes a pilot spoofing attack detection algorithm in massive MIMO systems, in which the information of channel statistics is unknown. First, users send pilots to the base station (BS), then the BS transmits the conjugate of its received signal (which may contain spoofing signal) back to users, where the final decision on detection is made. Analytical analysis with respect to probabilities of detection (PD) and false alarm is conducted. It is revealed that PDconverges in regimes of high signal-to-noise ratio (SNR) and large number of BS antennas, while the channel statistics from the active attacker to the BS influences the performance greatly.

In recent studies, a simple non-coherent communication scheme based on energy detection is proposed in massive single-input multiple-output (SIMO) systems. Before data transmission, the transmitter sends pilots to the receiver for the purpose of estimating the channel statistics. However, this training phase unintentionally provides opportunity for a malicious jammer to attack legitimate communication. In order to secure the legitimate communication, this paper proposes a jamming detection method in non-coherent SIMO systems, in which the information of channel statistics is not required. First, the transmitter sends pilots to the receiver, then the receiver sends the conjugate of its received signal (which may contain jammer signal) back to the transmitter, where the final decision on jamming detection is made. According to the likelihood ratio test principle, two detectors based on variance and standard variance normalization are proposed. The performance analysis indicates that these two detectors are of similar detection performance but of different complexity. Furthermore, it is revealed that the probability of detection initially grows with the number of receive antennas but converges quickly then, whereas the channel statistics from the jammer to the receiver always greatly influences the performance. Finally, the numerical simulations are carried out to validate the proposed detection method.

In reinforcement learning tasks with continuous state-action, parameterized policy search has been known to be a powerful method. Applying NeuroEvolution (NE) to optimizing the policy represented by artificial neural network (ANN) is a particularly active research field. In most cases, NE algorithms cost a large amount of trial-and-error (episode) to optimize policies. However, due to time and cost constraints, researchers and practitioners cannot repeat a number of episodes on physical robots. Thus, choosing an efficient NE algorithm is a key to optimize policies with limited time and cost. In this work, our goal is to help users to choose an efficient NE algorithm. We compare and analyze sample efficiency of two successful state-of-the-art NE algorithms: CMA-NeuroES and NEAT in a gait generation task of a quadruped robot. Moreover, we run both algorithms with various initial topologies in order to analyze the performance difference between each topology. From experimental results, we show CMA-NeuroES outperforms NEAT regardless of initial topologies when the limited number of episodes can be executed. Additional experiments conclude that the optimization method for connection weights in NEAT results in its inferior performance to CMA-NeuroES, while a probability-weighted averaging characteristic and self-adaptive factors make CMA-NeuroES to be advantageous.