Chaotic signals are spread-spectrum nonlinear signals with initial value sensitivity that can potentially provide safe and anti-jamming digital communication systems. However, to reduce receiver complexity and achieve smooth demodulation, traditional chaos-based wireless communication systems require the transmission of additional chaotic reference signals, which reduces the spectral efficiency and degrades the security characteristics of the chaotic signals. Recent work has explored deep learning (DL)-aided transceivers to address these issues. However, these techniques have not yet fully exploited the inherent characteristics of chaotic signals, e.g., spectral properties. To maximize the potential of chaotic signals in wireless communication, this paper proposes a power spectral density-based deep learning chaos shift keying (PSD-DLCSK) receiver. The proposed PSD-DLCSK scheme effectively utilizes the spectral properties of chaotic signals, where the PSD of received signals serves as input to a deep neural network (DNN) for symbol detection. The proposed DNN architecture combines long short-term memory networks with self-attention mechanisms to effectively capture the temporal dependencies and spectral properties of chaotic signals, enabling reliable intelligent demodulation without chaotic reference signals. Extensive simulations demonstrate that PSD-DLCSK achieves superior bit error rate (BER) performance compared to traditional receivers as well as other DL-aided schemes over additive white Gaussian noise and multipath Rayleigh fading channels.

The rising popularity of tabular data in data science applications has led to a surge of interest in utilizing deep neural networks (DNNs) to address tabular problems. Existing deep neural network methods are not effective in handling two fundamental challenges that are inherent in tabular data: permutation invariance (where the labels remain unchanged regardless of element order) and local dependency (where predictive labels are solely determined by local features). Furthermore, given the inherent heterogeneity among elements in tabular data, effectively capturing heterogeneous feature interactions remains unresolved. In this paper, we propose a novel Multiplex Cross-Feature Interaction Network (MPCFIN) by explicitly and systematically modeling feature relations with interactive graph neural networks. Specifically, MPCFIN first learns the most relevant features associated with individual features, and merges them to form cross-feature embedding. Subsequently, we design a multiplex graph neural network to learn enhanced representation for each sample. Comprehensive experiments on seven datasets demonstrate that MPCFIN exhibits superior performance over deep neural network methods in modeling the tabular data, showcasing consistent interpretability in its cross-feature embedding module for medical diagnosis applications.