The Internet of Things (IoT) has transformed healthcare via Healthcare-IoT (HIoT) by enabling continuous patient monitoring and efficient data analytics, offering promising solutions for managing the escalating global diabetes burden. The glycated hemoglobin (HbA1c) is an important biomarker for diabetes evaluation and control. Accurate prediction of HbA1c fluctuations remains a critical challenge, as existing models often overlook the interplay between stable patient profiles (demographics, lifestyle, clinical indicators) and dynamic dietary nutrient intake, limiting their ability to model glycemic responses. This study constructs a comprehensive multi-source dataset comprising detailed personal information, lifestyle, medical tests, and multi-day dynamic nutrient intake through the HIoT system. Utilizing this dataset, we propose a novel progressive multimodal adaptive fusion network (PMAFNet) to decode the complex determinants of HbA1c variability. PMAFNet employs two core modules: the multimodal graph feature-level enhancement (MGFE) module processes static and dynamic features to capture structural dependencies and temporal patterns, and the adaptive modality-aware progressive fusion (AMPF) module integrates these representations via the hierarchical attention mechanism. Experimental results demonstrate that PMAFNet achieves 95.24% accuracy. Ablation analysis confirms nutrient intake is a critical driver, with accuracy declining by 19.04% upon its exclusion. Furthermore, the SHapley Additive exPlanations (SHAP) was employed to interpret the PMAFNet and identify key features influencing HbA1c. This study highlights the significance of incorporating multimodal data to unravel the complexity of glycemic regulation and reveals the pivotal influence of nutrient intake in diabetes management.

Currently, there is a growing scholarly and industrial interest in micro-video-centric research. Within these domains, multi-label learning has emerged as a fundamental yet attractive subject. Existing methods primarily place emphasis on feature representations of individual micro-videos, while neglecting latent interdependencies between instance and label domains. To address this problem, in this paper, we propose a novel self-attentive deep consistent matrix factorization (SADCMF) method, which jointly explores dualdomain hierarchical representations and their inherent dependencies for micro-video multi-label classification. Specifically, SADCMF includes three primary characteristics: 1) A dualdomain deep collaborative factorization module is developed to explore the first-stage representations of instance features and the discriminative embeddings of label semantics in a mutually beneficial manner. 2) A correlation-driven selfattentive factorization module is devised to acquire the labelaware attentive outputs, which are further combined with original features through a residual structure to enrich the second-stage feature representations. 3) A dual-stream representation consistency module ensures the unidirectional and bidirectional representation consistency, meanwhile, narrows the discrepancies between the two-stage representations for improving the generalization ability of our method. Extensive experiments conducted on two publicly available micro-video multi-label datasets demonstrate its superior performance in comparison with state-of-the-art methods.

An improved Backus-Gilbert resampling scheme is developed and applied on Advanced Microwave Scanning Radiometer-EOS (AMSR-E) brightness temperature swath data. The new resampling scheme has two improvements over the special sensor microwave imager and AMSR-E resampling schemes currently used to produce standard brightness products. First, the use of a circular Gaussian footprint as the reference footprint achieves near-circular synthesized footprints for all channels. The near-circular synthesized footprints diminish the effect of different orientations of the synthesized elliptical footprints produced by the standard algorithm. Second, a better synthesized footprint spatial resolution for the 6.925- and 10.65-GHz channels in the across scan direction is achieved with a significant reduction in noise level. Oversampling by AMSR-E at these frequencies enables this improvement.

Advanced microwave scanning radiometer - EOS (AMSR-E) brightness temperature observations of the North Slope, Alaska are synthesized using an improved Backus-Gilbert algorithm and compared to the standard brightness temperature product for AMSR-E. This algorithm improves the spatial resolution for the 6 GHz and 10 GHz channels by taking advantage of the oversampling of these two frequencies, which allows a tradeoff between noise and spatial resolution. Nearly circular synthesized footprints for all channels are achieved by using a circular Gaussian reference footprint. Our synthetic observations differed from the standard AMSR-E products at 19 and 37 GHz where the scales of surface heterogeneities become important. The synthesized AMSR-E observations are compared with ground-based data collected during the Tenth Radiobrightness Energy Balance Experiment (REBEX10) conducted from May to June of 2004 near Toolik Lake on the North Slope. Plot-scale and satellite resolution scale observations differed at both 6 and 19 GHz caused by sensitivity to scale- dependent hydrologic processes.