Chao Chen

An offline, position-indexed channel-direction database can support location-aware unmanned aerial vehicle (UAV) beamforming, but sparse measurements leave intervals with different directional consistency. We propose Sampling-Adaptive Gauge-Projective Channel-Direction Reconstruction (SAGP-CDR). It treats normalized channel vectors that differ only by a common phase as the same array direction. Each anchor interval selects one of three reconstruction methods: anchor-calibrated line of sight (LOS), an aligned along-track chord, or a three-dimensional spatial affine fit. Four anchor-observable descriptors describe physical gap, endpoint agreement, spatial-neighbor agreement and directional turn. The LOS method additionally uses the station position and an assumed array geometry. Retrospective nested leave-one-flight-out evaluation uses five measured massive-MIMO UAV flights from one campaign, with 64 antennas and 100 subcarriers. The primary loss takes a median over query positions at each subcarrier, then a median across subcarriers. Across 450 matched masks, SAGP-CDR lowers mean primary direction loss by 30.25% relative to anchor-tuned aligned Gaussian interpolation. Reductions relative to the strongest fixed comparator are 14.24%, 18.84% and 3.27% at 2%, 5% and 10% retention. At 2%, loss is 0.1705 versus 0.2682 for three-dimensional nearest-anchor reuse. Relative to a global rate control calibrated on the primary metric with identical candidates, the aggregate reduction is 14.87%. These results support observable local selection for sparse channel-direction reconstruction within the evaluated campaign.

Background: Predicting respiratory trajectory and prognosis of high-risk preterm infants could better support targeted interventions and parental counselling. Current models are static, limiting their utility. They provide single day predictions at 36 weeks postmenstrual age, bounded by fixed timepoints, without incorporating clinical trajectory. We aimed to develop and validate a dynamic model for predicting respiratory state trajectory and demonstrate utility in predicting successful extubation and postnatal corticosteroids use. Methods: A dynamic model based on a Markov chain modelling framework was developed and validated in a retrospective population-based National Neonatal Research Database cohort before external validation in a prospective PRemature Infant Outcome Risk cohort. Both cohorts consist of infants born <32 weeks’ gestation in participating units in England and Wales from 2010-2022 (n=93,342) and 2023-2024 (n=1,420), respectively. Fourteen static once only and six daily predictors were used. Missing data was addressed using mean and model-based imputation, respectively. The dynamic model predicted daily respiratory states (no support, supplemental oxygen only, non-invasive or invasive ventilation) or death. Discrimination (area under the receiver operating characteristic curve (AUROC)), calibration, and utility performance were assessed. Findings: The developed online dynamic model (https://premoutcome.shinyapps.io/Respiratory/) showed strong discrimination (AUROCs 0·82–0·84), calibration and utility performance, demonstrating superior net benefit across probabilities of 30%-80%, in predicting bronchopulmonary dysplasia or death during external validation. The dynamic model had excellent performance in predicting non-invasive/invasive ventilation or death within the next 7 or 14 days (AUROCs 0·89-0·96). Infants with predicted risk of poorer respiratory outcomes were more likely to remain intubated and receive postnatal dexamethasone (p<0·001). Interpretation: The dynamic model demonstrated strong performance in predicting the complex task of daily respiratory trajectory and clinical utility in predicting likelihood of extubation timing. Further external validation and impact analysis are needed to establish personalised prediction utility.

Image Aesthetic Assessment (IAA) has developed rapidly in recent years, but most existing studies focus on predicting the absolute quality of individual images. In contrast, intra-group relative assessment under a unified evaluation context in art exam scenarios remains insufficiently explored. To fill this gap, we construct the Art Exam Dataset (AED), which contains 3360 art exam works from 93 exam themes, covering three major categories: sketch, quick sketch, and color painting. Based on AED, we propose the Dual-path Reference Encoder with Adaptive Routing Network (DPAR-Net), which provides a preliminary group-conditioned assessment framework for art exam works. DPAR-Net consists of a Dual-path Reference Encoder and an Adaptive Routing Fusion module. The Dual-path Reference Encoder models both a context-aware representation with respect to the group reference and a residual-relative representation that emphasizes sample-wise deviation from the group context. The Adaptive Routing Fusion module dynamically integrates the single-image baseline prediction with two correction candidates according to the sample state. Experiments on AED show that DPAR-Net outperforms representative general aesthetic assessment methods, validating the effectiveness of group-context correction and adaptive routing fusion. This work provides a data foundation and methodological reference for fine-grained ranking assessment of art exam works, and also offers a new experimental scenario for group-conditional aesthetic assessment.

Purpose This study conducts quantitative and qualitative analyses to investigate the relationship between human-annotated and AI-derived uncertainty in cardiac MRI segmentation, aiming to enhance the reliability of AI-based cardiac MRI segmentation models and foster better human-AI collaboration. Methods The CMRI dataset used in the experiments consists of 483 scans, each with two types of labels: an annotated segmentation mask and an uncertainty score per CMRI slice, both provided by clinicians. First, the AI-derived uncertainty estimated by the fuzzy-based algorithm is utilized to indicate the quality of segmentation. Multiple levels of uncertainties are derived from the method, including class-wise, slice-wise, subject-wise, etc. Subsequently, they are compared to the human-annotated uncertainty scores. Finally, qualitative analyses are conducted with clinicians to investigate all uncertainty measures potentially impacting real clinical applications. Results Experimental results show a strong inverse correlation between AI-derived uncertainty and Dice score, a standard metric for segmentation quality, indicating that lower uncertainty predicts higher segmentation quality. Additionally, it is found that human-annotated uncertainty coincides with AI-derived uncertainty for some anatomical structures (e.g., papillary muscle). However, high human-annotated uncertainty does not necessarily correlate with low AI segmentation quality, and there is no obvious association between human-annotated uncertainty and the size of the segmented structure. Concluded from qualitative analysis with clinicians, humans are better at utilizing prior knowledge (e.g. cardiac structural and contextual information) for uncertainty scoring, while the current AI method lacks this capability and is mainly data-driven for decision-making and uncertainty estimation. Conclusion AI-derived uncertainty could be utilized as quality control for CMRI segmentation. Humans utilize structural and contextual information to formulate uncertainty, while AI models currently lack this capability.

The complex causes and varied visual manifestations of cotton diseases create significant obstacles for accurate disease identification in cotton plants. Under limited computational conditions, it is still challenging to construct lightweight cotton disease detection models that maintain high detection accuracy. To address this issue, we propose LMF-YOLO (Lightweight Multi-scale Feature-enhanced YOLO), aiming to achieve accurate cotton disease detection with reduced computational cost. Specifically, a lightweight multi-scale feature extraction block (LMFEBlock) is introduced to reconstruct the original C2f module, forming the C2f-LMFEB backbone, which enhances fine-grained disease representation while significantly reducing redundant computation. Meanwhile, a dynamic upsampling strategy, DySample, is incorporated into the neck network to adaptively optimize feature reconstruction across scales and alleviate spatial misalignment caused by fixed interpolation. Furthermore, a shared and refined detection head, LMFEB-Detect, is developed to improve feature consistency between classification and regression tasks, strengthen boundary localization, and suppress background interference with lower parameter overhead. Extensive experiments conducted on a publicly available cotton disease dataset demonstrate that LMF-YOLO achieves an mAP of 90.0%, outperforming YOLOv8n by 2.5%, while reducing computational complexity, parameter count, and model size by 50.0%, 40.1%, and 36.1\%, respectively. Additional evaluations on two independent public datasets further confirm its strong generalization capability. These results indicate that LMF-YOLO provides an effective balance between detection accuracy and computational efficiency, making it particularly suitable for real-time cotton disease monitoring in resource-constrained agricultural environments.

Decision-making in perinatal management of extremely preterm infants is challenging. Mortality prediction tools may support decision-making. We used population-based routinely entered electronic patient record data from 25,902 infants born between 23 ⁺⁰ –27 ⁺⁶ weeks’ gestation and admitted to 185 English and Welsh neonatal units from 2010–2020 to develop and internally validate an online tool to predict mortality before neonatal discharge. Comparing nine machine learning approaches, we developed an explainable tool based on stepwise backward logistic regression ( https://premoutcome.shinyapps.io/Death/ ). The tool demonstrated good discrimination (area under the receiver operating characteristics curve (95% confidence interval) of 0.746 (0.729–0.762)) and calibration with superior net benefit across probability thresholds of 10%–70%. Our tool also demonstrated superior calibration and utility performance than previously published models. Acceptable performance was demonstrated in a multinational, external validation cohort of preterm infants. This tool may be useful to support high-risk perinatal decision-making following further evaluation.

The design of membership functions in fuzzy systems often requires satisfying domain, semantic, and relational constraints. Existing methods, while effective at enforcing parameter bounds, often lack flexibility or fail to address complex relational constraints. To overcome these limitations, this paper introduces the Constraints Always Satisfied Parameters (CASPs) framework, which inherently satisfies constraints during optimisation. Three variants of the CASPs are proposed, each balancing design flexibility, performance, and interpretability differently. Experimental evaluations on the Electricity and Laser datasets demonstrate consistent constraint satisfaction across all runs, with CASPs-Single prioritising interpretability, CASPs-Free excelling in RMSE performance, and CASPs-Adapted offering a balanced approach. The results highlight the potential of CASPs to enhance the design and optimisation of fuzzy systems.

Parkinson's disease (PD) is a progressive neurodegenerative disorder characterized by mental abnormalities and motor dysfunction. Its early classification and prediction of clinical scores have been major concerns for researchers. Currently, multi-view data learning has become an essential research area due to the capacity of multiple views to provide complementary insights from various perspectives. However, the discontinuous distribution, data missing complexity, small sample size, and redundant features in multi-view datasets pose a substantial obstacle, and most existing multi-view learning methods are unable to handle these challenges effectively. In this study, we propose a novel incomplete multi-view data learning framework (IMVDL) via dynamic embedding and partial l_2,1 norm constraints for PD diagnosis. Specifically, multi-view dynamic embedding can adapt to any view missing scene, thereby linearly/nonlinearly mapping incomplete multi-view data to low-dimensional manifold spaces and generating complete multi-view data representations. The partial l_2,1 norm constraint can ignore larger feature weight values and perform l_2,1 norm sparse on the remaining weights, thereby avoiding the sparse bias problem caused by larger weight values. An efficient iterative algorithm is derived to find the optimal solution of the IMVDL method. We conduct extensive experiments using multi-modal neuroimage data from the Parkinson's Progression Markers Initiative (PPMI) database. The results demonstrate that the IMVDL method is superior to other comparative methods. The source code for IMVDL is available at https://github.com/a610lab/IMVDL/.

Since their introduction, fuzzy sets and systems have become an important area of research known for its versatility in modelling, knowledge representation and reasoning, and increasingly its potential within the context explainable AI. While the applications of fuzzy systems are diverse, there has been comparatively little advancement in their design from a machine learning perspective. In other words, while representations such as neural networks have benefited from a boom in learning capability driven by an increase in computational performance in combination with advances in their training mechanisms and available tool, in particular gradient descent, the impact on fuzzy system design has been limited. In this paper, we discuss gradient-descent-based optimisation of fuzzy systems, focussing in particular on automatic differentiation -- crucial to neural network learning -- with a view to free fuzzy system designers from intricate derivative computations, allowing for more focus on the functional and explainability aspects of their design. As a starting point, we present a use case in FuzzyR which demonstrates how current fuzzy inference system implementations can be adjusted to leverage powerful features of automatic differentiation tools sets, discussing its potential for the future of fuzzy system design.

Deep learning models have achieved high performance in numerous semantic segmentation tasks. However, when the input data at test time do not resemble the training data, deep learning models can not handle them properly and will probably produce poor results. Therefore, it is important to design algorithms for deep learning models to reliably detect out-of-distribution (OOD) data. In this paper, we propose a novel fuzzy-uncertainty-based method to detect OOD samples for semantic segmentation. Firstly, to capture both data and model uncertainties, test-time augmentation and Monte Carlo dropout are applied to a ready-trained image segmentation model for generating multiple predicted instances of a given test image. Then interval fuzzy sets are generated from these multiple predictions to describe the captured uncertainty via distance transform operators. Finally, an image-level uncertainty score, which is calculated from the generated interval fuzzy sets, is used to indicate if it is an OOD sample. Experiments on testing three OOD test sets on a skin lesion segmentation model show that our proposed method achieved significantly higher classification accuracy in detecting OOD samples than three other state-of-the-art uncertainty-based algorithms.