Radio Frequency Fingerprint (RFF) identification plays a critical role in physical-layer security by enabling the identification of wireless devices. Recent advances have leveraged deep learning (DL) to enhance performance and robustness. However, existing DL-based RFF identification methods rely heavily on large-scale labeled signal datasets, making data annotation costly and challenging, particularly in complex electromagnetic environments. To address this limitation, we propose a self-supervised RFF identification method based on Time-Frequency Contrastive Learning (TFCL), designed to operate on unlabeled signal samples. The framework consists of two key modules: (1) a time-frequency contrastive self-supervised learning module, which constructs robust RFF feature embeddings from unlabeled signals, and (2) a CutMix-based regularized finetuning module, which enhances robustness through regularized training. Moreover, we introduce parameter freezing integrated with CutMix to adapt to diverse downstream scenarios. Extensive experiments demonstrate that the proposed TFCL-based method achieves superior feature embedding quality and identification accuracy compared to four competitive baselines, highlighting its effectiveness in real-world applications.

Heart rate variability (HRV) is an essential indicator of cardiovascular and nervous system function, with wide applications in health monitoring and disease management. Traditional contact-based methods like electrocardiograms (ECG) and photoplethysmography (PPG), while effective, face significant limitations in user experience, such as discomfort during prolonged use, and challenges in long-term, continuous monitoring. Meanwhile, contactless wireless sensing based on mmWave radar offers a promising alternative but is hindered by issues of directional sensing and noise interference. In this paper, we propose mmCG (mmWave Cardiac Gram), a contactless HRV monitoring system. Specifically, it integrates a heartbeat spatial localization method for directional sensing, which significantly improves the SNR, and a dynamic peak search algorithm that leverages heartbeat temporal correlations to effectively mitigate the impact of artifacts. Experimental results show that mmCG achieves advanced performance, reducing the IBI error to 9.44ms, a 51.29% improvement over existing methods. With its lightweight design and enhanced accuracy, mmCG offers a practical solution for daily HRV monitoring, with potential applications in stress management, personalized healthcare, and cardiovascular disease monitoring.

Cuff-less methods, especially pulse wave analysis (PWA) techniques with PPG/mmWave sensing, have shown great potential for non-intrusive blood pressure (BP) monitoring. However, the state-of-the-art solutions are only validated on small-scale healthy subjects, neglecting patients with abnormal BP and thus a more urgent need for BP monitoring. To bridge the gap, we first build the largest mmWave-BP dataset to our knowledge, including 930 real patients with cardiovascular diseases, and perform extensive experiments, which reveals that all existing PWA methods exhibit far less satisfactory performance with standard deviation errors (STD) exceeding 16 mmHg for systolic BP (SBP) and 11mmHg for diastolic BP (DBP). An in-depth investigation shows that physiological factors have complex effect on vascular elasticity and structure, thus people with very different BP values may exhibit extremely similar pulse waveform, which leads to confusion in model learning. In this work, we propose BP3, which fuses physiological factors into sensing-data-driven deep-learning framework, so as to capture the intricate effect of physiological factors during the whole process of learning pulse waveforms. Evaluation results show that BP3 achieves the mean errors of-1.57 mmHg and -0.34 mmHg, STD of 9.77 mmHg and 7.93 mmHg for SBP and DBP, respectively. Moreover importantly, BP3 shows remarkable gain particularly for subjects with abnormal BP, achieving mean errors that are only 0.48% ~ 20.86% of the state-of-the-art solutions.

Network traffic classification is a key technology in network communication management, which is of great significance for building intelligent communication and so on. Due to the difficult and time-consuming process of network traffic labeling, it is difficult to obtain any labeled traffic data in some special networks. At the same time, in a real network environment, there are multiple network traffic domains, and the data distribution of each network traffic domain is different, making it extremely difficult to train a network traffic classification model that performs well on multiple traffic domains simultaneously. Therefore, this paper proposes a network traffic classification method in unsupervised scenarios, aiming to study how to learn traffic knowledge from multiple source traffic domains and achieve accurate classification of unlabeled network traffic without labeled traffic data in the target traffic domain. This paper divides three traffic domains from the data set, namely VPN, nonVPN and nonTor. And three traffic classification tasks of unsupervised multi-source domain are constructed. The accuracy of traffic classification tasks in the source traffic domain is nonTor and nonVPN, and the target traffic domain is VPN reaches 89.76%. The source traffic domain is VPN and nonTor, the accuracy of the classification task is 91.73% when the target traffic domain is nonVPN, and 90.35% when the source traffic domain is VPN and nonVPN, and the target traffic domain is nonTor. Experimental results show the effectiveness of the network traffic classification algorithm proposed in this paper.

Network traffic classification is a key foundation of traffic management and network security. With the development of traffic encryption technologies and more attention given to user privacy, traditional rule-based and payload-based traffic classification methods have become less effective. To address this problem, recent studies have introduced deep learning-based methods. However, most of these studies do not consider both the flow-level and packet-level characteristics, which we believe are significant in network traffic classification. To further improve the accuracy of traffic classification, this paper proposed DM-HNN, a hybrid neural network based on dual-mode features. First, we treat the packet length sequence as the flow-level feature and the initial byte of the packet as the packet-level feature. Then, we diverge into two paths to analyze the dual-mode features using neural networks. Finally, we combine the two-path features and output the final classification results. We have performed the experiments on public datasets, the results comparing to single-mode and dual-mode traffic classifiers indicate that DM-HNN can achieve excellent performance and has certain effectiveness.

Discovering new intents is a crucial task in dialogue systems. Most existing methods are limited in transferring the prior knowledge from known intents to new intents. These methods also have difficulties in providing high-quality supervised signals to learn clustering-friendly features for grouping unlabeled intents. In this work, we propose an effective method (Deep Aligned Clustering) to discover new intents with the aid of limited known intent data. Firstly, we leverage a few labeled known intent samples as prior knowledge to pre-train the model. Then, we perform k-means to produce cluster assignments as pseudo-labels. Moreover, we propose an alignment strategy to tackle the label inconsistency problem during clustering assignments. Finally, we learn the intent representations under the supervision of the aligned pseudo-labels. With an unknown number of new intents, we predict the number of intent categories by eliminating low-confidence intent-wise clusters. Extensive experiments on two benchmark datasets show that our method is more robust and achieves substantial improvements over the state-of-the-art methods.