WiFi-based sensing technology has become a popular research direction in the Internet of Things (IoT) field. However, the accuracy of action sensing across different environmental domains is severely degraded when the model is deployed at the real IoT edge. Existing cross-domain sensing methods are unsuitable for real-life applications due to the large amount of expensive channel state information (CSI) data required for training. Meanwhile, pre-trained predictive models in the cloud may not perform well in edge-side deployment environments. To address these issues, we propose a few-shot cross-domain WiFi sensing (FewCS) system with online learning. The model aggregates unlabelled samples from the same target domain and separates samples from different domains while minimizing sample cost and training an accurate WiFi-sensing system. The core idea of FewCS is to capture the sensing features of data through intra-domain prototype clustering and perform cross-domain prototype extraction in a shared embedding space of multiple data. Moreover, we extend the model to the IoT edge segment for online learning and fine-tune the model parameters to fit the new domain on the cloud by using data collected in the field. Extensive experimental results on real datasets show that the proposed scheme significantly outperforms the current state-of-the-art WiFi sensing methods in terms of sensing accuracy and achieves satisfactory online learning performance with fewer training samples and times.

Recently, Human Pose Prediction (HPP) using image frames captured by cameras has been widely used in the smart home sector. Combining deep learning vision processing with HPP and using the Graph Convolutional Network (GCN) to extract temporal and spatial features of human actions has achieved satisfactory accuracy. However, there is still a lack of sufficient interpretability to translate theoretical findings into human-centric consumer applications. In this paper, a novel Interpretable GCN-based HPP (IGCN-HPP) model is proposed to address the above problem. Specifically, a multi-layer spatio-temporal convolution is first constructed to capture the depth features in human action data for prediction. Secondly, a GCN Explainer is proposed to assist in model training. When pre-processed graphics frames are fed into the GCN model, it generates various subgraphs. What’s more, using Shapley values from game theory and specific graph rules to assess each subgraph’s contribution to HPP, the neighborhood relationships between subgraphs and among nodes are estimated with the contribution optimization algorithm (COA). The reasonable interpretation of the predicted human pose is obtained by extracting and aggregating the subgraphs that contributed most to the proper prediction category. Qualitative and quantitative experimental results show that the proposed IGCN-HPP outperforms the baseline model in terms of predictive performance.

Security and privacy are vital challenges in Industrial Internet of Things (IIoT) systems due to the inherent broadcast property of industrial wireless communication. Therefore, how to improve the security of smart devices in IIoT systems has attracted widespread attention. In this article, a novel security optimization scheme for space shift keying (SSK)-based IIoT systems is proposed by applying secrecy enhancing techniques in the physical layer. Specifically, two methods are adopted in the proposed optimization scheme. First, the sender transmits artificial noise (AN) to interfere with the eavesdropper, while the legitimate receiver can eliminate AN. Second, the sender can select optimal antennas based on the proposed minmax criteria to transmit AN and information, which further promotes the security of industrial wireless communication. The optimal antenna selection pattern increases the difference of the average mutual information between the legitimate receiver and the eavesdropper. In addition, the proposed minmax antenna selection approach only requires the channel state information of the legitimate receiver, which satisfies the application scenario of unknown eavesdropper attacks in IIoT. Finally, we adopt a deep learning-based maximum likelihood (ML) detection algorithm to detect the optimal antenna index and analyze the bit error rate (BER) and secrecy rate (SR) of the proposed optimization scheme. Simulation results show that the proposed scheme can achieve similar SR improvements and superior BER performance compared with the state-of-the-art scheme, namely the signal-leakage-to-noise ratio (SLNR) scheme. The BER performance of the proposed scheme achieves a maximum of 100 times superior to that of the SLNR scheme when the signal-to-noise ratio (SNR) is 27 dB. Moreover, the proposed scheme outperforms the traditional antenna selection scheme (random selection) in terms of BER and SR.

Integrated sensing and communication (ISAC) enabled by backscatter communication is emerging as a promising paradigm for dynamic vehicular networks. However, the inherent decision latency in such systems poses a critical performance challenge, causing a mismatch between the executed decision and the actual channel state. To tackle this challenge, we propose a novel deep learning (DL)-based predictive framework utilizing a customized long short-term memory (LSTM) network to accurately forecast the continuous kinematic evolution of the system states from sequential historical measurements. These predictions then enable proactive transmit beamforming, which in turn effectively compensates for system latency to maximize end-to-end performance. Comprehensive simulation results demonstrate that the proposed predictive method achieves near-optimal performance and exhibits significant superiority in dynamic vehicular scenarios.