Open-world specific emitter identification (SEI) is a practical but challenging task, because it requires accurate identification of both known and unknown emitters in open environments with channel variations. However, traditional closed-set SEI methods suffer from severe performance degradation in open-world environments since 1) closed-set SEI models would misclassify unknown specific emitters (SEs) as known ones, and 2) channel variations would lead to distribution shifts in the radio frequency (RF) fingerprint of known SEs. It is challenging to address both issues, as they coexist and interact with each other. In this paper, we propose a novel prototype matching with domain alignment framework for open-world SEI, which designed to simultaneously address the challenges of unknown SE identification and channel variation. The proposed framework first pretrains a feature extractor and then trains the pretrained feature extractor and an extended open-set classifier via the self-training paradigm. Towards the former, a partial domain alignment strategy is introduced to mitigate the impact of channel variations. Towards the latter, a prototype matching-based pseudo-labeling strategy is proposed to generate reliable pseudo-labels, facilitating subsequent fine-grained identification of unknown SEs. An open-set classification loss is introduced later to help the classifier avoid classifying unknown SEs as known ones. Experiments conducted on a public WiFi dataset demonstrate the superiority and robustness of the proposed method, illustrating its potential application prospects in open-world environments.

Facial expression recognition (FER) is a challenging task due to pervasive occlusion and dataset biases. Especially when facial information is partially occluded, existing FER models struggle to extract effective facial features, leading to inaccurate classifications. In response, we present ORSANet, which introduces the following three key contributions: First, we introduce auxiliary multi-modal semantic guidance to disambiguate facial occlusion and learn high-level semantic knowledge, which is two-fold: 1) we introduce semantic segmentation maps as dense semantics prior to generate semantics-enhanced facial representations; 2) we introduce facial landmarks as sparse geometric prior to mitigate intrinsic noises in FER, such as identity and gender biases. Second, to facilitate the effective incorporation of these two multi-modal priors, we customize a Multi-scale Cross-interaction Module (MCM) to adaptively fuse the landmark feature and semantics-enhanced representations within different scales. Third, we design a Dynamic Adversarial Repulsion Enhancement Loss (DARELoss) that dynamically adjusts the margins of ambiguous classes, further enhancing the model's ability to distinguish similar expressions. We further construct the first occlusion-oriented FER dataset to facilitate specialized robustness analysis on various real-world occlusion conditions, dubbed Occlu-FER. Extensive experiments on both public benchmarks and Occlu-FER demonstrate that our proposed ORSANet achieves SOTA recognition performance. Code is publicly available at https://github.com/Wenyuzhy/ORSANet-master.

Graph learning is widely applied to process various complex data structures (e.g., time series) in different domains. Due to multidimensional observations and the requirement for accurate data representation, time series are usually represented in the form of multilabels. Accurately classifying multilabel time series can provide support for personalized predictions and risk assessments. It requires effectively capturing complex label relevance and overcoming imbalanced label distributions of multilabel time series. However, the existing methods are unable to model label relevance for multilabel time series or fail to fully exploit it. In addition, the existing multilabel classification balancing strategies suffer from limitations, such as disregarding label relevance, information loss, and sampling bias. This article proposes a dynamic graph attention autoencoder-based multitask (DGAAE-MT) learning framework for multilabel time series classification. It can fully and accurately model label relevance for each instance by using a dynamic graph attention-based graph autoencoder to improve multilabel classification accuracy. DGAAE-MT employs a dual-sampling strategy and cooperative training approach to improve the classification accuracy of low-frequency classes while maintaining the classification accuracy of high-frequency and mid-frequency classes. It avoids information loss and sampling bias. DGAAE-MT achieves a mean average precision (mAP) of 0.955 and an F1 score of 0.978 on a mixed medical time series dataset. It outperforms state-of-the-art works in the past two years.

Digital Twins for Mobile Networks (DTMN) can enhance mobile health (mHealth) by increasing diagnostic and monitoring capabilities. Classifying multi-label time series mHealth data in DTMN is challenging due to complex class relevance and feature extraction difficulties. This paper proposes a Class-Driven Graph Attention network learning framework (C-DGAM) for Multi-label classification of mHealth data in DTMN. C-DGAM captures the complex class relationships by constructing a unique class relevance graph for each time series. It uses a temporal context attention module to generates class representation vectors by fusing multi-dimensional features of time and class. Then, it dynamically models different relevance among the class representation vectors through a dynamic graph attention module which improves the performance of multi-label time series classification while maintaining a smaller parameter size and lower computational complexity. The mean Average Precision achieved by C-DGAM on two different multi-label time series datasets are 0.955 and 0.776, respectively, with corresponding F1 scores of 0.867 and 0.80. It demonstrates leading performance compared to existing state-of-art works. It provides more accurate and generalized algorithmic support for DMTN systems.