Medical time series are often irregular and face significant missingness, posing challenges for data analysis and clinical decision-making. Existing methods typically adopt a single modeling perspective, either treating series data as sequences or transforming them into image representations for further classification. In this paper, we propose a joint learning framework that incorporates both sequence and image representations. We also design three self-supervised learning strategies to facilitate the fusion of sequence and image representations, capturing a more generalizable joint representation. The results indicate that our approach outperforms seven other state-of-the-art models in three representative real-world clinical datasets. We further validate our approach by simulating two major types of real-world missingness through leave-sensors-out and leave-samples-out techniques. The results demonstrate that our approach is more robust and significantly surpasses other baselines in terms of classification performance.

Text entry in virtual reality (VR) often faces challenges in terms of efficiency and task loads. Prior research has explored various solutions, including specialized keyboard layouts, tracked physical devices, and hands-free interaction. Yet, these efforts often fall short of replicating the efficiency of real-world text entry, or introduce additional spatial and device constraints. This study leverages the extensive capabilities of large language models (LLMs) in context perception and text prediction to enhance text entry efficiency by reducing users’ manual keystrokes. Three LLM-assisted text entry methods - Simplified Spelling, Content Prediction, and Keyword-to-Sentence Generation - are introduced, aligning with user cognition and the contextual predictability of English text at word, grammatical structure, and sentence levels. Through user experiments encompassing various text entry tasks on an Oculus-based VR prototype, these methods demonstrate a 16.4%, 49.9%, 43.7% reduction in manual keystrokes, translating to efficiency gains of 21.4%,74.0%, 76.3%, respectively. Importantly, these methods do not increase manual corrections compared to manual typing, while significantly reducing physical, mental, and temporal loads and enhancing overall usability. Long-term observations further reveal users’ strategies for using these LLM-assisted methods, showing that users’ proficiency with the methods can reinforce their positive effects on text entry efficiency.

In many scenarios, we need to identify an object and then locate it within high precision (centimeter or millimeter level). RFIDs have played a significant role in this field. While many state-of-the-art systems have shown good performance, they require expensive hardware or extra time. Based on a previous work, GLAC, we present PoM, a 3D localization system within millimeter-level precision using only COTS RFID devices. Inspired by the same idea, PoM also draws power from mobility, and makes two key technical improvements. First, to the best of our knowledge, PoM is the first localization system that simultaneously adopts Synthetic Aperture Radar (SAR) and Inverse Synthetic Aperture Radar (ISAR) method. In particular, we employ antenna motion to construct SAR and tag's mobility to construct ISAR. Second, we take actual application scenarios into consideration and apply an extra mechanism so that PoM can gain better performance in special situations. Our simulation experiments show that, in high-speed scenarios and other challenging real-world applications, PoM achieves better performance than the original GLAC system.