Search Results (5,976)

We seek to identify the most relevant benefits offered by Medicare Advantage Health Plans that are attractive to members and that drive membership and market share. We explore plans operating in a single county in New Jersey between 2018 and 2023. A dataset of benefits from publicly available data sources was created and the variance inflation factor was applied to identify the correlation between the extracted features, avoiding multicollinearity and overparameterization problems. We categorized the variable market share and used it as a multinomial response variable with three categories: less than 0.3%, 0.3% to 1.5%, and over 1.5%. Categories were chosen to achieve approximately uniform distribution of plans (47, 60 and 65, respectively). A multinomial Lasso model using 5-fold cross validation tunes the penalty parameter and reduces overfitting by dropping some features from the model, thus increasing interpretability. For each category, important variables vary. Certain brands drive market share, as do PPO plans and prescription drug coverage. Benefits, particularly ancillary benefits that are not part of CMS’s required benefits, appear to have little influence, while financial terms such as deductibles, copays and out-of-pocket limits are associated with higher market share. Finally, we evaluated the multinomial Lasso model on a held-out test set. The model achieved an overall classification accuracy of 0.76, meaning that 76% of plans were correctly classified into the low, medium or high market share categories. Full article

Cross-view geo-localization (CVGL) between unmanned aerial vehicle (UAV) imagery and satellite imagery is a key technique for autonomous UAV navigation in Global Navigation Satellite System (GNSS)-denied environments. However, most existing methods rely on energy-intensive Artificial Neural Networks (ANNs), making them difficult to deploy on resource-constrained edge computing platforms. Spiking Neural Networks (SNNs) provide a promising alternative for energy-efficient inference, but their application to CVGL still faces two challenges that remain insufficiently addressed. First, the isotropic computation used by existing SNN backbones is mismatched with the directional characteristics of spike activations. Spike activations tend to form oriented aggregation patterns along elongated geographic structures, and isotropic computation can therefore dilute directional signals. Second, the limited representational capacity of SNNs further increases the sensitivity during training optimization. However, the standard triplet loss adopts a static weighting strategy and assigns the same weight to all triplets that violate the margin constraint, which is unfavorable for learning from hard negatives. To address these challenges, we propose a framework with two core contributions. At the feature extraction level, the Directional Adaptive Convolution Module (DACM) processes spike feature maps by sequentially performing horizontal strip convolution and vertical strip convolution, thereby capturing a more complete geometric structure of directional spike clusters. At the training supervision level, we propose a Dual-dimensional Progressive Reweighting (DPR) loss, which jointly characterizes sample difficulty from pairwise difficulty and positive-pair quality difficulty. A learnable fusion parameter is used to adaptively balance these two types of difficulty information. Experimental results on the University-1652 and SUES-200 benchmarks show that the proposed framework, when equipped with the same representation learning head as its ANN counterparts, achieves competitive and, in many settings, superior performance. In terms of energy efficiency, its estimated theoretical energy consumption is over $8.8\times$ lower than that of published ANN methods under their original configurations. Under a more rigorous matched ANN control that shares the identical architecture, the estimated energy is reduced from 29.84 mJ to 6.36 mJ, an approximately $4.7\times$ reduction obtained at a cost of only 2.29 percentage points in R@1. Full article

Polymer-based three-dimensional (3D) printing has evolved from a prototyping approach toward a manufacturing strategy with emerging clinical relevance for individualized dosage forms, local drug depots, microneedle systems, microfluidic cartridges, biosensor housings and integrated theranostic platforms. Its value arises from the simultaneous control of polymer chemistry, device architecture and process history: infill, porosity, shell thickness, crosslink density, swelling, degradation and surface chemistry can be used as design variables rather than incidental manufacturing outcomes. This review critically synthesizes recent progress in polymer-enabled additive manufacturing for drug delivery and diagnostic applications, with emphasis on thermoplastic and biodegradable polymers, hydrogels, photopolymers, elastomers, conductive composites, stimuli-responsive networks and bioinks. Fused deposition modelling, hot-melt extrusion, semi-solid extrusion, vat photopolymerization, two-photon polymerization, selective laser sintering, binder jetting and inkjet/aerosol jet approaches are compared in relation to drug stability, diagnostic compatibility, feature resolution, scalability and regulatory risk. Particular attention is given to geometry-controlled release, multi-drug printlets, microneedles, implants, scaffold-based local therapy, microfluidic diagnostics, electrochemical biosensors and wearable or closed-loop systems. Translation is discussed through quality-by-design, critical material attributes, critical process parameters, process analytical technology, extractables/leachables, sterilization, point-of-care manufacturing, data integrity and clinical evidence requirements. Future advances should connect polymer–process–property relationships with clinically meaningful use cases, verified quality attributes and realistic regulatory pathways. Full article

Maritime ship detection remains challenging because of large scale variations, high inter-class visual similarity, weak target boundaries, and complex maritime backgrounds. This study proposes MCSwin-YOLOv8, an enhanced YOLOv8-based detector that combines three complementary architectural designs. First, a re-parameterizable multi-scale convolutional backbone, named RepMCSwin, is introduced to extract scale-aware semantic information and fine-grained boundary cues. Unlike the standard Swin Transformer, the MCSwin block does not use window-based self-attention but adopts cascaded multi-scale convolutions and residual feature transformation. Second, a Multi-Feature Parallel Convolutional Block Attention Module (MFPCBAM) is developed to compute channel and spatial attention in parallel, thereby preserving weak ship features while suppressing irrelevant background responses. Third, a Modified Generalized Feature Pyramid Network (MGFPN) is constructed to improve cross-level feature interaction and retain high-resolution spatial information through an additional 160 × 160 prediction branch. Experiments were conducted on the public SeaShips dataset and a private infrared maritime ship dataset. MCSwin-YOLOv8 achieved an F1-score of 94.4%, mAP@0.5 of 97.4%, and mAP@0.5:0.95 of 75.1% on SeaShips. On the infrared dataset, the corresponding results were 91.2%, 94.1%, and 66.9%, respectively. Compared with the YOLOv8 baseline, mAP@0.5 increased by 1.4 and 3.0 percentage points on the two datasets. These accuracy gains were accompanied by an increase in model complexity from 11.12 M to 19.29 M parameters and from 28.5 G to 56.7 G FLOPs, indicating an accuracy–complexity trade-off that requires further runtime evaluation. Full article

This article investigates offline recognition of handwritten Kazakh text in the Latin script using a convolutional recurrent neural network. The relevance of the study is determined by the transition of the Kazakh language to the Latin alphabet and the need to automate the processing of handwritten documents. The proposed model consists of a convolutional neural network feature extractor, two bidirectional long short-term memory layers, and a Connectionist Temporal Classification decoder. The convolutional layers extract visual features from word images, the bidirectional recurrent layers model the sequential relationships between characters, and CTC enables end-to-end training without explicit character-level segmentation. A specialized dataset named KazEsim, containing 20,000 handwritten Kazakh name images, was created and divided into writer-independent training, validation, and test subsets. Experimental results showed a character accuracy rate of 96.5% and a word accuracy rate of 92.3%. Compared with a conventional CNN baseline, the proposed CRNN model improved character accuracy by 6.1 percentage points and word accuracy by 9.2 percentage points. The proposed model also outperformed the fine-tuned TrOCR-small comparative baseline while requiring fewer parameters and lower inference latency. These findings demonstrate the effectiveness of CNN–BiLSTM–CTC sequence modeling for offline recognition of handwritten Kazakh words in the Latin script. Full article

To address the problems of enhanced non-stationarity, significant feature distribution shift, and insufficient cross-condition generalization capability of traditional fault diagnosis methods under variable operating conditions such as varying speed and load, a rolling bearing fault diagnosis method integrating group sparse reconstruction and a multi-strategy improved quantum particle swarm optimization-based relevance vector machine (RVM) is proposed. First, group sparse representation learning is employed to reconstruct the original vibration signals, thereby suppressing background noise and enhancing fault-related impulsive components to improve signal separability and stability. Subsequently, a modal component selection criterion combining kurtosis and correlation coefficients is introduced to optimize and reconstruct the decomposed modal components, enabling the reconstructed signals to retain more fault-sensitive information. On this basis, multiple information entropy features are extracted from the reconstructed signals to construct high-dimensional state feature vectors for comprehensively characterizing the dynamic operating states of rolling bearings. To further enhance the parameter optimization capability, Chebyshev chaotic mapping is incorporated into the quantum particle swarm optimization (QPSO) algorithm to improve the uniformity of population initialization. Meanwhile, a Cauchy mutation strategy is introduced to strengthen the global search capability and avoid premature convergence, thereby forming a multi-strategy improved QPSO algorithm. Finally, the improved optimization algorithm is utilized to adaptively optimize the key hyperparameters of the RVM, resulting in a fault diagnosis model with high accuracy, strong generalization capability, and sparse characteristics. Experimental validation on the HUST and XJTU-SY bearing datasets demonstrates that the proposed MIQPSO-RVM framework achieves diagnostic accuracies of 96.70% and 94.83%, respectively. Compared with several representative intelligent diagnosis methods and deep learning models, the proposed method exhibits superior diagnostic performance, robustness, and generalization capability under complex operating conditions. Full article

Lithium-ion batteries are widely used in various energy sectors, and accurately predicting their early remaining useful life (RUL) is crucial for shortening battery evaluation time and accelerating battery commercialization. However, information on degradation during the early cycling stages of batteries is limited, and it is difficult to fully characterize their lifespan. This study proposes a CNN–Transformer–BiGRU-based method for predicting the early RUL of lithium-ion batteries using Grey Wolf Optimization (GWO). First, using only the first 100 cycles of each battery in the MIT dataset, early degradation features are extracted from the dimensions of capacity and internal resistance, and then standardized. Second, a CNN is employed to extract local degradation features, while the Transformer’s self-attention mechanism is used to capture global correlations, and BiGRU is utilized to further extract bidirectional temporal dependency information. Building on this foundation, GWO is introduced to perform joint optimization of the model’s key hyperparameters to obtain optimal network parameters. Finally, the effectiveness of the proposed method is validated through ablation and comparison experiments. The experimental results show that the proposed model achieved an R² of 0.9633, with RMSE, MAE, and MAPE values of 80.5608 cycles, 63.2524 cycles, and 7.29%, respectively, demonstrating overall prediction performance superior to that of the comparison models. This method can effectively mine degradation information related to battery life from limited early-cycle data, providing an effective approach for the accurate prediction of the early RUL of lithium-ion batteries. Full article

Convolutional Neural Networks (CNNs) are fundamental tools for image analysis and recognition in monitoring systems, particularly in photovoltaic (PV) installations, where visual inspection and thermal imaging play crucial roles in anomaly detection and energy optimization. This publication presents a Hybrid Fuzzy Convolutional Neural Network (HFCNN) that integrates a fuzzy dense layer utilizing Ordered Fuzzy Numbers (OFNs) into the CNN architecture. The architecture is additionally validated on the public ELPV benchmark of 2624 electroluminescence images of photovoltaic cells, where the HFCNN with Mean of Maxima defuzzification attains classification quality statistically indistinguishable from a CNN baseline while using a four times smaller dense layer and training two to three times faster. The methodology combines the feature extraction capabilities of traditional CNNs with the uncertainty handling properties of fuzzy logic. Experiments using the MNIST dataset demonstrate that HFCNN with Mean of Maxima (MOM) defuzzification achieves comparable accuracy to standard CNNs while using significantly fewer parameters (75% reduction in the dense layer). This efficiency gain is advantageous for deployment on edge computing devices. This work constitutes a methodological contribution—establishing, for the first time, the feasibility of integrating Ordered Fuzzy Numbers into CNN architectures without requiring expert membership function design. While the current study validates this approach on MNIST, actual photovoltaic applications require dedicated future research on real PV thermal imagery. Nevertheless, the proposed HFCNN framework could potentially support practical photovoltaic energy system applications in detecting panel degradation, performance anomalies, and autonomous decision-making in large-scale PV installations. Full article

Damage identification in instrumented structures is often framed through modal-parameter changes, finite element updating, or supervised classifiers. These approaches are powerful, but they require an explicit structural model, identified modes, labeled damage cases, or expert choices about reference sensors. This paper introduces a new data-driven and training-free approach with limited physical priors, defining a sensor network where each sensor is a node and the edges are defined from the spatial correlation of sensor responses. The idea is to use each sensor time history as the measured structural dynamics feature while damage is localized from the edges, whose correlations change relative to a baseline. The method is demonstrated on a full-scale seven-story reinforced-concrete shear-wall building tested at UC San Diego, considering four progressive earthquake-induced damage states and one brace-modification state. The results are compared with those obtained from a previously published finite element model. The results reveal that this network-based approach localizes the damage states in agreement with previous studies with limited prior requirements and low computational cost. Beyond damage localization, this network representation provides sensor centrality, allowing informative sensors to be selected from data rather than chosen randomly or only from experimental intuitions. For the case study, using this sensor network, we find the most central sensors, those carrying the most information with reduced trial-and-error and reduced expert intervention, and use them to recover the first three natural frequencies as a secondary dynamic check. The results show that spatial correlation networks can screen for damage, localize affected regions, and guide modal parameter extraction without building an FE model. This study opens a research avenue in which network representations of multi-sensor structural dynamics complement traditional modal analysis for structural health monitoring, with dense or heterogeneous sensing systems. Full article

The slow evolution and inconspicuous nature of buffer-layer ablation in high-voltage cables pose a significant challenge for early fault diagnosis. To tackle this issue, we propose a hybrid diagnostic approach that integrates frequency-domain impedance measurement with a convolutional neural network (CNN). A cable simulation model is first established using transmission-line theory and a distributed-parameter framework. We examine the impedance and phase responses at the cable’s sending end, revealing a consistent decreasing trend with rising frequency alongside periodic resonant peaks. The simulator generates a diverse set of spectral signatures corresponding to various cable health states. The CNN then extracts discriminative features from these waveforms, and a probabilistic clustering preprocessing step further refines the input data. Experimental results on a test set of 78 samples—comprising 52 experimentally measured normal spectra and 26 experimentally calibrated simulated spectra for mild and severe ablation—demonstrate a classification accuracy of 0.95, confirming that the proposed methodology enables reliable, non-intrusive detection of buffer-layer ablation without cable disassembly. Full article

Background: Accurate preoperative assessment of bone invasion is essential for surgical planning in gingival squamous cell carcinoma (SCC). This study evaluated the diagnostic value of conventional ¹⁸F-FDG PET/CT-derived imaging parameters and PET-based radiomic features for predicting histopathologic bone invasion. Methods: This retrospective study included 68 patients with gingival SCC who underwent preoperative ¹⁸F-FDG PET/CT followed by primary surgical treatment. Bone invasion was confirmed histopathologically. Conventional PET parameters (MTD, SUVmax, SUVmean, MTV, and TLG) and PET-based radiomic features were extracted from the primary tumor. Group comparisons, receiver operating characteristic (ROC) analysis, and univariate logistic regression were performed. Results: Patients with bone invasion showed significantly higher MTD, SUVmax, MTV, and TLG than those without bone invasion (all p < 0.05), whereas SUVmean was not significantly different. Entropy, correlation, and zone entropy were significantly higher in the bone invasion-positive group. MTV showed the numerically highest AUC among conventional PET parameters (AUC = 0.748), whereas correlation (AUC = 0.725) and zone entropy (AUC = 0.714) showed the highest performance among radiomic features. Univariate logistic regression showed significant associations of MTD, MTV, TLG, entropy, correlation, and zone entropy with bone invasion. Conclusions: Conventional PET parameters and PET-based radiomic features were significantly associated with histopathologic bone invasion in gingival SCC. Radiomic features reflecting intratumoral heterogeneity may complement conventional metabolic parameters and improve preoperative assessment of bone invasion. Full article

Manual fruit thinning is labor-intensive and inefficient, making the development of intelligent visual detection systems a crucial approach for improving the quality and production efficiency of the pear industry. However, in natural orchard environments, young pear fruits are small in size with slender fruit stalks, and their texture and color characteristics are highly similar to those of tender branches. Furthermore, variations in illumination and occlusions caused by branches and leaves make it difficult for existing detection models to simultaneously and accurately identify fruits and fruit stalks, limiting their application in automated thinning equipment. In this study, Yuluxiang pear was selected as the research object, and image data were collected under diverse field conditions, including forward-lighting, backlighting, close-range shooting, long-range shooting and fruit overlapping. A dedicated dataset containing 3057 images was established. Based on the RT-DETR-R18 network, a lightweight and high-precision fruit–stalk synchronous detection model was proposed. Specifically, the backbone network was reconstructed by integrating GCConv with C2f modules to enhance global feature extraction for slender fruit stalks. The bottleneck structure was optimized using GCConvC3 to reduce feature degradation under occlusion conditions, and an additional 4× down-sampling P2 detection head was introduced to improve the detection capability for small targets. To fully validate the model performance and stability, three types of experiments were conducted in this study: ablation experiments, repeated experiments with different random seeds, and comparative experiments. Ablation experiments verified the cumulative performance improvements brought by the introduced modules. Repeated experiments with different random seeds were performed to explore training randomness-induced performance fluctuations, and the results demonstrated that the proposed model maintains stable overall detection accuracy with minor metric fluctuations. Comparative experiments demonstrated that the proposed model achieved a compact parameter size of only 15.97 M, with a precision of 95.0% for young pear fruit detection and an mAP50 of 83.0% for fruit stalk detection, outperforming all comparative models in overall mAP50. The training convergence curves and Grad-CAM++ visualization results further confirmed the stable optimization process and enhanced feature attention capability of the proposed model. By achieving a favorable balance between detection accuracy and model lightweightness, this approach provides effective technical support for the development of intelligent fruit thinning equipment and vision-based systems for smart pear orchards. Full article

UAV-based insulator detection is challenging because insulators often occupy small regions of aerial images and appear against complex backgrounds, while subtle local features may be lost during feature extraction and down-sampling. Moreover, practical UAV and edge-device applications require efficient models with limited computational and memory demands. This study proposes an optimized lightweight YOLOv11n model for high-voltage transmission-line insulator detection. The architecture integrates C3k2MBNV2 to reduce model complexity, SCDown to preserve spatial information during down-sampling, and C3k2WTDC to enhance multi-frequency feature representation. A diverse dataset containing 5750 insulator images acquired under different environmental conditions, viewing angles, and backgrounds was used for evaluation. Experimental results show that the proposed model reduces the parameter count from 6.20 M to 3.26 M and computational complexity from 20.5 to 12.7 GFLOPs, corresponding to reductions of 47.4% and 38.0%, respectively. Meanwhile, precision increases from 91.3% to 93.8%, recall from 73.4% to 75.2%, mAP50 from 71.2% to 73.9%, and mAP50–95 from 65.6% to 67.3%. These results demonstrate an improved accuracy–efficiency trade-off, supporting real-time insulator detection in resource-constrained UAV and edge-device applications. Full article

Power line component and insulator defect detection is an important task in intelligent transmission line inspection. However, UAV-based inspection images often contain small, densely distributed targets under complex backgrounds, making it difficult for existing detectors to balance accuracy and model compactness. To address these challenges, this paper proposes a lightweight YOLOv8-based detector named DSCMamba-TAD-YOLOv8. First, depthwise separable convolutions are introduced into the Neck to reduce parameters and computational cost. Second, DSCMambaNet replaces the original C2f module to enhance multi-scale feature representation by combining lightweight local feature extraction and cross-region contextual modeling. An embedded CBAM component is further integrated inside DSCMambaNet to strengthen informative channel responses and spatial regions. Finally, a Task-Aware Dynamic Detection Head, named TADetect, improves head adaptability through scale-aware and task-aware feature modulation. Experiments on the InsPLAD-det dataset show that DSCMamba-TAD-YOLOv8 achieves 91.86% Precision, 88.02% Recall, 91.83% mAP@0.5, and 74.82% mAP@0.5:0.95. Compared with YOLOv8n, the proposed model improves Precision, mAP@0.5, and mAP@0.5:0.95 by 4.09, 2.43, and 4.46 percentage points, respectively, while maintaining a comparable Recall level with a slight increase from 87.04% to 88.02%. Meanwhile, Params decrease from 3.209 M to 2.702 M and GFLOPs from 8.2 to 7.5. On the revised TPL-SOD held-out test subset, the proposed model improves Precision from 86.20% to 88.16%, mAP@0.5 from 87.09% to 88.81%, and mAP@0.5:0.95 from 68.44% to 70.13%, while Recall remains stable and slightly increases from 91.75% to 92.33%. These results demonstrate that DSCMamba-TAD-YOLOv8 improves detection accuracy and localization quality while maintaining a compact structure and stable recall performance. Full article

Although research on lightweight monocular depth estimation models has been actively conducted, achieving real-time deployment on edge devices remains challenging due to limited computational resources and memory capacity. To address these limitations, we propose a lightweight model for self-supervised monocular depth estimation. We cut the iterations of each feature-extracting block nearly in half, while our proposed Asymmetric Dilated Convolution module and a StarNext module compensate for the reduced model capacity. Specifically, the Asymmetric Dilated Convolution module captures horizontal and vertical structural features through asymmetric kernels, and the StarNext module fuses multi-scale features via element-wise multiplication. In model training, random cropping and scaling are applied for inducing the model to focus on localized object features. Additionally, we introduce a Disparity-guided Cutout technique based on the pre-inferred disparity map to randomly mask adjacent pixels. Simulation results on the KITTI dataset demonstrate that the proposed model reduces the number of parameters and GFLOPs by approximately 50% and 58%, respectively, without significant degradation in depth estimation accuracy compared to the baseline Lite-Mono. Furthermore, inference benchmarks on the Jetson Orin Nano platform demonstrate speedups of approximately 46.0%, 46.1%, 46.3%, and 52.0% across the MaxN, 25 W, 15 W, and 7 W power modes, respectively. Full article