With the rise of location-based services and the rapidly growing requirements related to their applications, indoor localization based on channel state information–multiple-input multiple-output (CSI-MIMO) has become an important research topic. However, indoor localization based on CSI-MIMO has some disadvantages, including noise and high data dimensions. To overcome the above drawbacks, we proposed a novel method of indoor localization based on CSI-MIMO, named SICD. For SICD, a novel localization fingerprint was first designed which can reflect the time–frequency and space–frequency characteristics of CSI-MIMO under a single access point (AP). To reduce the redundancy in the data of CSI-MIMO amplitude, we developed a data dimensionality reduction algorithm. Moreover, by leveraging a log-normal distribution, we calculated the conditional probability of the naive Bayes classifier, which was used to predict the moving object’s location. Compared with other state-of-the-art methods, the results of the experiment confirm that the SICD effectively improves localization accuracy.

The universality of intelligent indoor localization based on WIFI has increasingly emerged as a multifold challenge. However, in practical applications, its indoor localization accuracy is limited by noises, diffractions, and multipath effects. To overcome these drawbacks, we design a new intelligent indoor localization system based on channel state information (CSI) of the wireless signal from multiple-input multiple-output (MIMO): IILC. In IILC, the initial amplitude information is first processed in the measured CSI data, which can effectively suppress the impact from noise and other interferences. Next, we devised a method to construct radio images. It can fully use space-frequency and time-frequency information from CSI-MIMO to obtain more location information. Next, we design a new deep learning network to determine the optimal effectiveness of radio image classification. Subsequently, a mixed norm is proposed to impose sparsity penalty and overfit constraint on the loss function, making the valuable feature units active and the others inactive. The experimental results verify that the IILC system exhibits excellent performance. The overall localization accuracy of the IILC in the office scene can reach 97.10%, and the probability of localization error within 1.2 m is 86.21%.

Determining the number of sources under low signal-to-noise ratio (SNR) and signal interference with the same frequency and modulation presents a significant challenge. To address this challenge, we propose a novel method for detecting the number of signal sources from single-channel that leverages signal reconstruction and deep learning. The method employs subspace projection based on the Hankel matrix to reconstruct the measured single-channel signals, effectively suppressing noise. Furthermore, we incorporate the correlation of information and the integrity of feature in the signal, by fusing the in-phase component, quadrature component, and frequency spectrum feature of the reconstructed complex signal into a one-dimensional feature suitable for convolutional neural network (CNN). To address the source number detection task, we design a one-dimensional CNN based on convolutional block attention module, transforming it into a classification problem. Finally, experimental measurements demonstrate the effectiveness of our proposed method, with an detection accuracy of 94% even at an SNR of −10 dB.

In non-cooperative wireless communications, carrier frequency offset (CFO) arises from oscillator mismatch, doppler effect and time-varying channels. Along with noise, they can degrade signal quality and hampers subsequent signal processing. In this letter, we propose a robust carrier frequency offset estimation (CFOE) method under low signal-to-noise ratio (SNR) by leveraging hybrid denoising scheme and dual-channel convolutional attention network (DCA). To enhance noise robustness, we develop a hybrid denoising scheme combining adaptive dual-tree complex wavelet transform with phase-space reconstruction. The designed DCA model can extract deep features from the multi-domain features of the denoised signal. It employs an attention-based parallel dual-pooling mechanism to preserve local-global feature correlation during downsampling. In addition, the composite loss function is used to improve generalization ability and reduce overfitting. Compared with existing blind estimation methods, the experimental results demonstrate the effectiveness and robustness of the proposed CFOE method.