Search Results (339)

Diabetic retinopathy is a prevalent condition and a major public health concern due to its detrimental impact on eyesight. Diabetes is a root cause of its development and damages small blood vessels caused by prolonged high blood sugar levels. The degenerative consequences of diabetic retinopathy are irrevocable if not diagnosed in the early stages of its progression. This ailment triggers the development of retinal lesions, which can be identified for diagnosis and prognosis. However, lesion detection is challenging due to their similarity in intensity profiles to other retinal features, inconsistent sizes, and random locations. This research evaluates a custom deep learning network for classifying retinal images and compares it with the state-of-the-art classifiers. The novel preprocessing method is introduced to reduce the complexity of the diagnostic process and to enhance classification performance by adaptively enhancing images. Despite being a shallow network, the proposed model yields competitive results with an accuracy of 87.66% and an F1-score of 0.78. The evaluation metrics indicate that class imbalance affects the performance of the proposed model despite using the weighted cross-entropy loss. The future contribution will be the inclusion of generative adversarial networks for generating synthetic images to balance the dataset. This research aims to develop a robust computer-aided diagnostic system as a second interpreter for ophthalmologists during the diagnosis and prognosis stages. Full article

With the widespread adoption of various types of Unmanned Aerial Vehicles (UAVs), their non-compliant operations pose a severe challenge to public safety, necessitating the urgent identification and detection of UAV targets. However, in complex backgrounds, UAV targets exhibit small-scale dimensions and low contrast, coupled with extremely low signal-to-noise ratios. This forces conventional target detection methods to confront issues such as feature convergence, missed detections, and false alarms. To address these challenges, we propose a Multi-View Feature Fusion Network (MVFF) that achieves precise identification of small, low-contrast UAV targets by leveraging complementary multi-view information. First, we design a collaborative view alignment fusion module. This module employs a cross-map feature fusion attention mechanism to establish pixel-level mapping relationships and perform deep fusion, effectively resolving geometric distortion and semantic overlap caused by imaging angle differences. Furthermore, we introduce a view feature smoothing module that employs displacement operators to construct a lightweight long-range modeling mechanism. This overcomes the limitations of traditional convolutional local receptive fields, effectively eliminating ghosting artifacts and response discontinuities arising from multi-view fusion. Additionally, we developed a small object binary cross-entropy loss function. By incorporating scale-adaptive gain factors and confidence-aware weights, this function enhances the learning capability of edge features in small objects, significantly reducing prediction uncertainty caused by background noise. Comparative experiments conducted on a multi-perspective UAV dataset demonstrate that our approach consistently outperforms existing state-of-the-art methods across multiple performance metrics. Specifically, it achieves a Structure-measure of 91.50% and an F-measure of 85.14%, validating the effectiveness and superiority of the proposed method. Full article

Human Activity Recognition (HAR) in resource-constrained settings has been studied mainly through architecture design, compression, and deployment, while the role of the training objective has received less attention. This paper introduces Top-Confidence Gapped Cross-Entropy (TCG-CE), a lightweight modification of categorical cross-entropy in which each sample is weighted by the gap between the two most probable predicted classes. TCG-CE adds no trainable parameters and can be used as a drop-in replacement for standard cross-entropy. The method is evaluated on the UCI-HAR and WISDM benchmarks using compact recurrent models, namely TinyRNN, TinyGRU, and TinyLSTM. The evaluation focuses on macro-averaged predictive performance and also reports empirical runtime and memory observations under a fixed execution environment. Across datasets and models, TCG-CE improves balanced classification metrics, with the clearest gains observed on WISDM and in more capacity-limited settings. These results indicate that top-1/top-2 confidence-gap modulation is a practical loss-design strategy for improving macro-level predictive performance in compact HAR classification. Full article

In ecologically fragile and geomorphologically complex mountainous regions, ensuring a smooth transition from poverty alleviation to multidimensional sustainable rural development remains a key issue in regional governance. Focusing on the Qinba Mountains, a typical former contiguous poverty-stricken region in China covering 18 prefecture-level cities in six provinces, this study uses 2009–2023 prefecture-level panel data to examine the spatiotemporal evolution and driving mechanisms of coordinated rural revitalization. An integrated framework of “multi-dimensional evaluation–spatiotemporal tracking–attribution diagnosis” is developed by combining the improved AHP–entropy-weight TOPSIS method, the Coupling Coordination Degree (CCD) model, spatial Markov chains, spatial autocorrelation, and the Geodetector. The results show pronounced subsystem asynchrony. Livelihood and Well-being Security (U5) improves steadily, while Level of Industrial Development (U1), Civic Virtues and Cultural Vibrancy (U3), and Rural Governance (U4) also rise but with clear spatial differentiation; by contrast, Quality of Human Settlements (U2) fluctuates in stages under ecological fragility. Overall, the coupling coordination level advances from the Verge of Imbalance to Intermediate Coordination, yet the regional pattern remains uneven, with eastern basin cities leading and western deep mountainous cities lagging. State transitions display both policy responsiveness and path dependence: the probability of retaining the original state ranges from 50.0% to 90.5%; low-level neighborhoods reduce the upward transition probability to 25%, whereas medium-to-high-level neighborhoods raise the upward transition probability of low-level cities from 36.36% to 53.33%. Spatial dependence is also evident, with Global Moran’s I increasing, with fluctuations, from 0.331 in 2009 to 0.536 in 2023; high-value clusters extend along the Guanzhong Plain–Han River Valley corridor, while low-value clusters remain relatively locked in mountainous border areas. Driving mechanisms show clear stage-wise succession. At the single-factor level, the explanatory power of Road Network Density (F6) declines from 0.639 to 0.287, whereas Terrain Relief Amplitude (F1) becomes the dominant background constraint in the later stage (q = 0.772). Multi-factor interactions are generally enhanced. In particular, the traditional infrastructure-led pathway weakens markedly, with F1 ∩ F6 = 0.055 in 2023, while the interaction between terrain and consumer market vitality becomes dominant, with F1 ∩ F7 = 0.987 in 2023. On this basis, three major pathways are identified: government fiscal intervention and transportation accessibility improvement, capital agglomeration and market demand stimulation, and human–earth system adaptation and ecological value realization. These findings provide quantitative evidence for breaking spatial lock-in and improving cross-regional resource allocation in ecologically constrained mountainous regions. Full article

Non-destructive and automated detection of bacterial contamination is a critical prerequisite for ensuring high efficiency production and quality control in plant tissue culture. In this study, we developed a multispectral image acquisition system for Alocasia explants and proposed a novel image fusion model, termed Intensity-Texture enhanced Swin Fusion (ITSF). The ITSF framework employs convolutional neural networks to extract texture and intensity features from visible and near-infrared channels. Subsequently, a Swin Transformer-based module is integrated to model long-range spatial dependencies, ensuring cross-domain integration between the texture and intensity features. We formulated a composite loss function to guide the fusion process toward optimal results. This objective function integrates texture loss, entropy weighted structural similarity index (SSIM) and intensity aware dynamic gain guided loss. Experimental results demonstrate that the proposed method significantly enhances the visual saliency of bacteria and achieves superior quantitative performance across a comprehensive range of objective image fusion metrics. The detection performance reached a mean Average Precision (mAP50) of 0.949 with the fused images, satisfying industrial requirements for high-precision inspection, which provides a critical technical solution for the industrialization of automated micropropagation. Full article

With the continuous advancement of industrialization in China, industrial wastewater discharge has become a critical factor influencing water environmental quality, public health, and the long-term sustainability of regional development. This study systematically examines both the direct and spatial spillover effects of industrial wastewater on disease incidence. Based on panel data from 30 provincial-level regions in China over the period 2011–2020, a composite incidence index of four waterborne infectious diseases is constructed using the entropy weight method, and the Spatial Durbin Model (SDM) is employed to capture both local and cross-regional effects. The results show that industrial wastewater discharge significantly increases disease incidence and exhibits clear spatial spillover effects, suggesting that the associated health risks may extend beyond local boundaries. Moreover, the analysis suggests that the “Water Ten Plan” reduced both local effects and regional spillovers, highlighting the value of stricter discharge control and coordinated basin-level governance for sustainable regional development. Overall, this study uncovers the spatial health externalities of industrial pollution and provides empirical support for integrated policy approaches linking environmental governance with public health protection. Full article

Due to the rapid process of urbanization and the threat of environmental hazards, the need to enhance the intelligence and resilience of urban infrastructure has emerged as a pre-eminent demand of sustainable urban development. This paper evaluates the smart-resilience of urban infrastructure in Kunming by creating a well-developed evaluation framework with reference to the DPSIR (Driving Force–Pressure–State–Impact–Response) model and using the Entropy Weight TOPSIS technique to measure infrastructure performance during the years 2020–2024. The study fills an existing gap in the literature regarding the integration of intelligence and resilience evaluation, as well as the dynamic obstacle diagnosis based on causal logic. It provides a transferable analytical framework and empirical evidence for the “smart-resilience” development of similar cities. The findings suggest that there is steady progress in infrastructure smart-resilience in Kunming, whereby the composite index grew from 0.330 to 0.597, which is equivalent to an average growth rate of about 16.0 per annum. In spite of this favorable tendency, there are a number of structural issues that remain unsolved. The driving force dimension is unstable with regard to long-term mechanisms of investment, and the responding dimension is lagging behind, indicating weaknesses in the governance capacity and inter-departmental coordination. Moreover, extreme weather events have become the major threat to infrastructure systems in the city, superseding traditional social and operational risks; consequently, the city has changed its risk profile. Obstacle factor analysis shows that state and response dimensions make up almost 60% of the total constraint level, which shows the significance of enhancing the effectiveness of management. The research findings are based on the proposal of specific policy actions, such as the creation of special infrastructure resilience funds, the enhancement of mechanisms relating to cross-departmental emergency responses, the implementation of risk-based engineering standards, and the creation of an integrated infrastructure data platform to facilitate efficient, resilient, and sustainable urban governance. Full article

Cities are increasingly expected to address digital transformation and sustainability challenges at the same time. However, existing urban indices generally approach smart city and sustainable city perspectives separately, which limits their ability to capture the integrated nature of contemporary urban development. In addition, many index-based studies rely on similar methodological choices. This study develops a composite Sustainable Smart City (SSC) index supported by a systematic scoring framework that brings smartness and sustainability together. The proposed framework follows a step-by-step procedure covering data preparation, normalization, weighting, aggregation, and final scoring. To address information overlap among indicators, a Redundancy-Penalized Entropy Weighting (RPEW) approach is applied. Then, overall SSC scores are calculated using a soft non-compensatory aggregation to emphasize balanced performance across dimensions. The framework is empirically illustrated through a cross-country case study including 38 OECD (Organization for Economic Co-Operation and Development) countries. A machine-learning-based polynomial forecasting approach is used for a limited number of indicators to deal with data gaps allowing the assessment to reflect more up-to-date conditions. The results highlight clear differences in SSC performance and show that strong outcomes in a single dimension are not sufficient to achieve high overall SSC scores. Instead, balanced progress across economic, digital, environmental, governance, mobility, and social dimensions plays an important role. In addition, the proposed framework provides a practical basis for comparative analysis, benchmarking, and policy-oriented evaluation of smart and sustainable urban development. Full article

Given less than five years remaining until the target year for the first phase of China’s dual carbon goals, this paper studies carbon allowance allocation with an in-depth study of Jiangsu Province due to its significant role in driving the Yangtze River Delta’s pioneering achievement of the dual carbon goals. This study considered 2017 (the intermediate target year) as the base year and incorporated socio-economic data such as population, GDP, and the urbanization rate. Then, methods including the entropy weight method, gravity model and social network analysis were applied to classify Jiangsu’s 95 counties. From a regional coordination perspective, carbon governance clusters were constructed with the Shapley value, based on which spatial heterogeneity patterns were analyzed, and a carbon quota allocation was proposed. The findings reveal that: (1) The dominant factors influencing cross-scale carbon reduction capacity at the county level are natural carbon sink capacity (indicator weight: 0.180) and urbanization rate (indicator weight: 0.145). (2) The correlation between carbon reduction factors among different districts and counties exhibits an uneven spatial pattern. And the spatial configuration exhibits a multi-tiered, network-like distribution. (3) Through conducting spatial analysis and spatial grouping, Jiangsu could be divided into 14 county-level carbon governance alliances, with the number of member counties ranging from 4 to 10 within each alliance. (4) The allocation of carbon quotas in Jiangsu exhibits a distinct descending gradient from the southern to the northern regions, which is coupled with the regional economic geography. This is exemplified by the highest quota in Jiangyin (496.46 Mt) in the south and the lowest in Lianyun (34.90 Mt) in the north. It is concluded that two carbon emission reduction pathways should be established as a priority: (a) Tongshan-Gulou (Xuzhou)-Yunlong-Quanshan-Jiawang and (b) Tianning-Jiangyin-Zhangjiagang-Changshu-Taicang-Kunshan. Full article

Wafer map defect pattern recognition is a key task for ensuring yield in integrated circuit manufacturing. However, in real production lines it commonly suffers from scarce labeled data, long-tailed class distributions, and limited feature representations, which cause existing deep learning models to degrade in performance, particularly for minority defect classes and complex defect morphologies. To address these challenges, we propose a semi-supervised classification method for wafer maps based on a multimodal Wasserstein autoencoder (MM-WAE). The framework constructs three parallel feature branches in the spatial, frequency, and texture domains, using a multi-head attention mechanism and gating mechanism for adaptive multimodal fusion. This allows defect patterns to be comprehensively characterized by macroscopic geometric distributions, spectral periodic structures, and microscopic texture details. The Wasserstein autoencoder is introduced, with the latent space distribution regularized by a maximum mean discrepancy (MMD) loss using an inverse multiquadratic kernel. Additionally, an inverse class-frequency weighted cross-entropy loss and a modality consistency loss between the encoder and classifier jointly optimize the reconstruction and classification paths while leveraging large amounts of unlabeled wafer maps for semi-supervised learning. Experimental results show that MM-WAE mitigates performance limitations caused by insufficient labels and class imbalance, significantly improving the accuracy and robustness of wafer defect classification, with promising potential for industrial application and further development. Full article

Multimodal epileptic seizure detection using physiological biosignals remains challenging due to signal noise, inter-subject variability, weak cross-modal alignment, and the limited interpretability of many machine learning models. To address these challenges, this study proposes a parameterized multimodal feature-fusion framework that unifies normalization, modality weighting, and nonlinear cross-modal interaction within a single mathematical representation. Four fusion parameters, the fusion exponent $\rho$, interaction weight $\left(\delta \right)$, normalization factor $\left(\lambda \right),$ and the cross-modal interaction term $\left(\eta \right)$, are introduced at the feature-fusion level, while all classifiers retain their original learning mechanisms. The framework is evaluated using synchronized EEG, ECG, EMG, and accelerometer signals from 120 subjects, segmented into 2 s windows at 512 Hz and analyzed using twelve classical and deep learning classifiers. Principal Component Analysis (PCA) applied to the fused feature space reveals improved class separability compared to unimodal representations, with EEG exhibiting the strongest intrinsic discrimination and peripheral modalities contributing complementary structure when fused. SHapley Additive exPlanations (SHAP) further identify entropy as the most influential feature across all modalities, followed by RMS and energy, yielding physiologically coherent attributions. Quantitative performance evaluation and ablation analysis confirm that the observed improvements arise from the proposed representation design rather than classifier-specific modifications. Unlike existing architecture-dependent fusion strategies, the proposed method introduces a mathematically parameterized feature-space formulation that enhances separability and interpretability without modifying classifier architectures, thereby establishing a representation-driven paradigm for explainable multimodal seizure detection. These results demonstrate that mathematically principled feature-space modeling can simultaneously enhance predictive performance and interpretability, providing a transparent and robust foundation for explainable multimodal seizure detection. Full article

The work presented herein proposes DisasterReliefGPT, a multimodal AI system for automation in the areas of crisis communication and post-disaster assessment. The system integrates three tightly coupled components: a vision module called DisasterOCS for structural damage detection in satellite images, a Large Vision–Language Model (LVLM) for enhanced visual understanding and contextual reasoning, and a Large Language Model (LLM) to produce detailed, clear assessment reports. DisasterOCS relies on a ResNet34-based encoder with partial weight sharing and event-specific decoders, coupled with a custom MultiCrossEntropyDiceLoss function for multi-class segmentation on pre- and post-disaster image pairs. On the benchmark xBD dataset, the developed system reaches a high score of 78.8% in identifying F1-damage, making correct identifications of destroyed buildings with 81.3% precision, while undamaged structures are found with a very high value of 90.7%. From a combination of these components, emergency responders can immediately provide reliable and readable assessments of damage that can be used to directly support urgent decision-making. Full article

Background: Early childhood caries (ECC) affects a substantial proportion of young children worldwide, and timely screening is essential for early intervention and referral. While deep learning has shown promise for automated dental diagnostics, many existing approaches rely on computationally heavy models that limit deployment in community and mobile settings. This study investigates whether compact convolutional neural networks can achieve clinically meaningful performance for screening dental caries from oral photographs. Methods: We curated a dataset of 435 intraoral images from children aged 3–14 years, annotated by licensed dentists, and performed patient-level stratified splitting to prevent data leakage. Three convolutional neural networks (ResNet-18, MobileNetV3-Small, and EfficientNet-B0) were fine-tuned using ImageNet-pretrained weights and comparatively evaluated for the detection of dental caries from oral photographs. Models were trained with class-weighted cross-entropy loss and evaluated on a held-out test set using sensitivity, specificity, balanced accuracy, ROC-AUC, and PR-AUC with bootstrap 95% confidence intervals. Results: ResNet-18 achieved the highest balanced accuracy (0.929), weighted F1-score (0.954), and perfect sensitivity (1.00), while EfficientNet-B0 achieved the strongest threshold-independent discrimination with the highest ROC-AUC (0.978) and PR-AUC (0.990). MobileNetV3-Small maintained competitive performance (ROC-AUC 0.952; PR-AUC 0.976) with substantially lower computational complexity. Conclusions: In addition to performance evaluation, we incorporated an interpretability analysis using Grad-CAM to examine model decision behavior. The resulting attribution maps predominantly highlighted clinically relevant tooth regions associated with caries, providing evidence that the models rely on meaningful dental features rather than background artifacts. These results demonstrate that compact, deployment-friendly architectures can achieve clinically meaningful performance for ECC detection, supporting their suitability for scalable, real-world screening applications. Full article

Multi-label emotion detection (MLED) suffers from long-tailed label distributions and structured inter-label correlations, which jointly suppress rare label recall and yield incoherent predictions. We present Graph Neural Network-Enhanced Transformer with Hybrid Loss Weighting (GTHL-Emo), a unified framework that addresses both challenges without heavy additional machinery. First, an adaptive imbalance-aware training scheme combines binary cross-entropy, asymmetric focal, and pairwise ranking losses under a learned batch-wise controller, emphasizing rare labels while stabilizing thresholding. Second, a lightweight correlation alignment module learns transformer-based label embeddings and aligns their predicted affinities with empirical co-occurrence via Kullback–Leibler (KL) regularization, smoothing rare label predictions through correlated frequent labels. A transformer encoder with learnable attention pooling provides semantic representations, and a dynamic GraphSAGE layer captures inter-instance structural dependencies. Comprehensive evaluation across three Arabic benchmarks—SemEval-2018-Ec-Ar, ExaAEC, and SemEval-2025 (Track A, Arq)—demonstrates competitive or leading performance. On SemEval-2018-Ec-Ar, GTHL-Emo attained a Jaccard accuracy of 58.70%, micro-F1 score of 71.02%, and macro-F1 score of 60.48%. On ExaAEC, it achieved a Jaccard accuracy of 65.99%, micro-F1 score of 70.72%, and macro-F1 score of 68.71%. On SemEval-2025-Arq, it obtained a Jaccard accuracy of 41.47%, micro-F1 score of 56.78%, and macro-F1 score of 56.69%. Ablation studies revealed that the GraphSAGE structure and ranking loss contributed most significantly (1.45% and 1.46% Jaccard accuracy drops, respectively), while label correlation alignment provided consistent improvements across the scales. These findings demonstrate that jointly optimizing imbalance-aware objectives and label dependencies yields robust Arabic MLED with minimal overhead. Full article

Background and Objectives: Diabetes mellitus represents one of the most prevalent chronic metabolic disorders worldwide, necessitating precise insulin dose management to prevent both acute and long-term complications. The optimization of insulin dosing remains a significant clinical challenge, as inappropriate dosing can lead to hypoglycemia or hyperglycemia, each carrying substantial morbidity risks. Machine learning approaches have emerged as promising tools for developing clinical decision support systems; however, their practical implementation requires both high predictive accuracy and model interpretability. This study aimed to develop and evaluate an explainable machine learning framework for predicting insulin dose adjustments in diabetic patients. We sought to compare multiple ensemble learning approaches and identify the optimal model configuration that balances predictive performance with clinical interpretability through comprehensive SHAP and LIME analyses. Materials and Methods: A comprehensive dataset comprising 10,000 patient records with 12 clinical and demographic features was utilized. We implemented and compared nine machine learning models, including gradient boosting variants (XGBoost, LightGBM, CatBoost, GradientBoosting), AdaBoost, and four ensemble strategies (Voting, Stacking, Blending, and Meta-Learning). Model interpretability was achieved through SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) analyses. Performance was evaluated using accuracy, weighted F1-score, area under the receiver operating characteristic curve (AUC-ROC), precision-recall AUC (PR-AUC), sensitivity, specificity, and cross-entropy loss. Results: The Meta-Learning Ensemble achieved superior performance across all evaluation metrics, attaining an accuracy of 81.35%, weighted F1-score of 0.8121, macro-averaged AUC-ROC of 0.9637, and PR-AUC of 0.9317. The model demonstrated exceptional sensitivity (86.61%) and specificity (91.79%), with particularly high performance in detecting dose reduction requirements (100% sensitivity for the ‘down’ class). SHAP analysis revealed insulin sensitivity, previous medications, sleep hours, weight, and body mass index as the most influential predictors across different insulin adjustment categories. The meta-model feature importance analysis indicated that LightGBM probability estimates contributed most significantly to the ensemble predictions. Conclusions: The proposed explainable Meta-Learning Ensemble framework demonstrates robust predictive capability for insulin dose adjustment recommendations while maintaining clinical interpretability. The integration of SHAP-based explanations facilitates clinician understanding of model predictions, supporting transparent and informed decision-making in diabetes management. This approach represents a significant advancement toward the clinical implementation of artificial intelligence in personalized insulin therapy. Full article