Feature selection is an important issue in the field of machine learning, which can reduce misleading computations and improve classification performance. Generally, feature selection can be considered as a binary optimization problem. Gravitational Search Algorithm (GSA) is a population-based heuristic algorithm inspired by Newton's laws of gravity and motion. Although GSA shows good performance in solving optimization problems, it has a shortcoming of premature convergence. In this paper, the concept of global memory is introduced and the definition of exponential Kbest is used in an improved version of GSA called IGSA. In this algorithm, the position of the optimal solution obtained so far is memorized, which can effectively prevent particles from gathering together and moving slowly. In this way, the exploitation ability of the algorithm gets improved, and a proper balance between exploration and exploitation gets established. Besides, the exponential Kbest can significantly decrease the running time. In order to solve feature selection problem, a binary IGSA (BIGSA) is further introduced. The proposed algorithm is tested on a set of standard datasets and compared with other algorithms. The experimental results confirm the high efficiency of BIGSA for feature selection.

Gravitational search algorithm (GSA) is a population-based heuristic algorithm, which is inspired by Newton's laws of gravity and motion. Although GSA provides a good performance in solving optimization problems, it has a disadvantage of premature convergence. In this paper, the concept of repulsive force is introduced and the definition of exponential Kbest is used in a new version of GSA, which is called repulsive GSA with exponential Kbest (EKRGSA). In this algorithm, heavy particles repulse or attract all particles according to distance, and all particles search the solution space under the combined action of repulsive force and gravitational force. In this way, the exploration ability of the algorithm is improved and a proper balance between exploration and exploitation is established. Moreover, the exponential Kbest significantly decreases the computational time. The proposed algorithm is tested on a set of benchmark functions and compared with other algorithms. The experimental results confirm the high efficiency of EKRGSA.

No abstract

Wireless communication signals are often affected by noise and interference in the channel during transmission, which makes it difficult for the receiver to analyze. The signal enhancement technology can suppress the noise and interference in the signal, so as to improve the communication quality. It is one of the main research directions of signal processing. Classical enhancement methods separate the signals through separable transform domain. Artificial construction of the corresponding separable transform domain requires prior information of noise and interference, but they have the characteristics of randomness. Further, these methods usually use high-level features and rely on statistics, so they can only deal with specific noise conditions. At present, deep learning is increasingly applied in the field of wireless communications due to its powerful feature extraction ability for large sample sets. In this paper, a communication signal enhancement model based on generative adversarial network (GAN) is proposed. Compared with classical methods, the signal is operated directly and the model is trained end-to-end. It can adapt to different noise conditions and avoid the above problems. An independent and invisible test set is used to evaluate several comparative methods. The experimental results confirm the effectiveness of the proposed model.

With the rapid growth of wireless devices, the communication environment gets complex. The detection of interference or unauthorized signals can improve spectrum efficiency, which is a key technology for limited spectrum resources. Traditional detection methods analyze the parameter characteristics of the received signal. But it is difficult to detect interference with the same time and frequency as the original signal by those feature engineering. As a classical problem in deep learning, anomaly detection is usually solved by supervised learning. But a more challenging situation is to detect unknown or invisible anomalies. It means that the number of abnormal samples is insufficient and the data is highly biased toward the normal samples. In this paper, a wireless communication interference detection algorithm based on generative adversarial network (GAN) is proposed. In the semi-supervised learning scenario, the algorithm detects the time-frequency overlapped interference by the reconstruction strategy. The generator adopts the encoder-decoder-encoder architecture. In the training process, the model jointly learns the data distribution of normal samples by minimizing the distance in both the signal space and the latent space. In the inference phase, a large distance metric implies an abnormal sample. Experiments on simulated communication datasets show the superiority of the proposed algorithm.