Browse Articles

Optimized decomposition and deep learning with bias correction for reliable runoff point-interval prediction

Abstract Accurate runoff prediction is critical for flood risk management and water resources regulation. This study proposes a probabilistic runoff forecasting framework that integrates optimized signal decomposition, deep learning, bias correction, and uncertainty quantification. Variational Mode Decomposition optimized by the Whale Optimization Algorithm (WVMD) is first applied to decompose non-stationary runoff series into stable intrinsic mode functions, which are then modeled using a hybrid Temporal Convolutional Network and Bidirectional Gated Recurrent Unit (TCN-BiGRU) with optimized hyperparameters. A Bias Correction (BC) strategy is further incorporated to improve point prediction accuracy. Based on the runoff point prediction residuals generated by the WVMD-TCN-BiGRU-BC model, Kernel Density Estimation (KDE) is applied to characterize the error distribution and construct probabilistic prediction intervals, with the Normal and Gumbel distributions adopted as parametric benchmarks. Experimental results at the Yangtze River Basin demonstrate that the proposed framework significantly improves both deterministic and probabilistic forecasting performance. The BC strategy reduces RMSE by 68.0% at Yichang and 73.2% at Jianli station compared with the WVMD-TCN-BiGRU model, while the KDE based interval prediction yields an approximately 5% improvement in the F score at the 90% confidence level, confirming the reliability of the proposed runoff probabilistic forecasting framework.

Publisher Correction: Physiology and immunology of a pig-to-human decedent kidney xenotransplant

Synthesis and characterization of NIR-sensitive curcumin-gelatin nanoparticles for targeted drug delivery in 3D colon cancer

Abstract Curcumin (CUR) exhibits potent anti-cancer effects; however, its poor water solubility limits its clinical use. This study explores gelatin nanoparticles (GelNPs) as nanocarriers to improve curcumin delivery. We aimed to enhance the release and efficacy of photosensitive curcumin-loaded GelNPs (Cur-GelNPs) using infrared (IR) light-induced localized hyperthermia in a 3D co-culture cancer model. Cur-GelNPs were synthesized and characterized via DLS, FTIR, STEM, Raman, HPLC, and DSC. Cytotoxicity, migration, invasion, apoptosis, and drug resistance were assessed using MTT, Transwell, Hoechst/PI staining, and Rho123 assays, respectively. Optimal results were achieved by IR treatment at 38 °C for 30 s. Cur-GelNPs localized in the cytoplasm due to curcumin’s natural fluorescence. At 25 µg/ml, Cur-GelNPs significantly reduced the viability, invasion, and migration of colon cancer cells, while promoting apoptosis and mitochondrial damage—more effectively when combined with IR. Importantly, minimal toxicity was observed in healthy cells, suggesting selective cancer targeting. This method enables spontaneous drug-macromolecule binding, reducing time, cost, and labor. Overall, IR-activated Cur-GelNPs represent a promising approach for targeted colon cancer therapy and may offer broader contributions to nanomedicine and drug delivery systems.

Structures of Ostα/β reveal a unique fold and bile acid transport mechanism

A copula based supervised filter for feature selection in machine learning driven diabetes risk prediction

Abstract Effective feature selection is critical for building robust and interpretable predictive models, particularly in medical applications where identifying risk factors in the most extreme patient strata is essential. Traditional methods often focus on average associations, potentially overlooking predictors whose importance is concentrated in the tails of the data distribution. In this study, we introduce a novel, computationally efficient supervised filter that leverages a Gumbel copula implied upper-tail concordance score ( $$\lambda _U$$ , a monotone transformation of Kendall’s $$\tau$$ ) to rank features by their tendency to be simultaneously extreme with the positive class. We evaluated this method against four standard baselines (Mutual Information, mRMR, ReliefF, and L1/Elastic-Net) across four classifiers on two diabetes datasets: a large-scale public health survey (CDC, $$N=253,680$$ ) and a classic clinical benchmark (PIMA, $$N=768$$ ). Our analysis included comprehensive statistical tests, permutation importance, and robustness checks. On the CDC dataset, our method was the fastest selector and reduced the feature space by $$\approx$$ 52%. While this resulted in a minimal but statistically significant performance trade-off compared to using all 21 features, our filter significantly outperformed standard filters (Mutual Information, mRMR) and was statistically indistinguishable from the strong ReliefF baseline. On the PIMA dataset (8 predictors), our method’s ranking produced the numerically highest ROC–AUC, despite paired DeLong tests showing no statistically significant differences versus strong baselines. PIMA thus serves as a ranking-only sanity check that our upper-tail criterion behaves sensibly in a low-dimensional clinical setting. Across both datasets, the Gumbel- $$\lambda _U$$ selector consistently identified clinically coherent and impactful predictors. We conclude that feature selection via upper-tail dependence is an efficient and interpretable screening approach that can complement standard feature-selection baselines in public health and clinical risk prediction.

Association between early red blood cell transfusion after return of spontaneous circulation and clinical outcomes in cardiac arrest patients

Harnessing machine learning to explore influencing mechanism in the dual pro-environmental intention-behavior gap

Abstract Fostering pro-environmental behaviors (PEBs) is crucial for advancing low-carbon development. A significant obstacle in this endeavor is the intention-behavior gap, where intentions fail to translate into actual behaviors. This study addresses both the commonly discussed negative gap, where high intentions do not lead to corresponding behaviors, and the less explored positive gap, where behaviors exceed intentions. Drawing from 2216 questionnaires, this study compared eight machine learning methods and selected LightGBM as the optimal approach. And the study examined the impact of individual and situational factors on these two types of gaps by LightGBM. The results identify robust predictive associations: for Cooperative-Grey-PEBs, attitude and ascription of responsibility exhibit inverted U-shaped patterns, while high environmental knowledge supports behavior maintenance in no-intention contexts. For Negative-Grey-PEBs, the negative gap narrows when attitude surpasses a critical threshold (4.5). Furthermore, higher levels of ascription of responsibility and self-efficacy are associated with a lower negative gap. Conversely, high infrastructure visibility is characterized by a divergent pattern, where it correlates with an expanded negative gap, consistent with a “responsibility dilution effect”. The study proposes tailored measures for different groups, which would have significant implications for policies aiming to bolster low-carbon development.

Magnetic fluid offers better seal in heart-plugging medical procedure

Addressing the data imbalance issue in machine learning modeling of rare and disruptive outage events

An explainable deep learning framework for few shot crop disease detection in rice and sugarcane using CNN based feature extraction

Abstract Where crop health is essential to global food security. Our focus is on early crop disease detection in the field of agriculture, especially Rice and Sugar cane leaf disease. This prompts researchers to consider quick, automated, cost-effective, precise, and efficient methods of identifying the kinds of diseases utilizing contemporary technologies like image processing, artificial intelligence (AI), and Explainable Artificial Intelligence (XAI). This paper proposes an framework to detect pest infestation for rice and Sugar cane cultivation and suggests an effective framework for rice and Sugar cane disease detection and forecasting that uses image processing to standard, resizing, and normalization rice and Sugar cane images then, using feature extractor using CNN after that we using few-shot learning (FSL) techniques such as like Prototypical Networks and Model-Agnostic Meta-Learning (MAML) learning techniques for superior decision-making in smart farming systems. The experimental findings demonstrated the Accuracy and specificity of the suggested framework in identifying and effectively predicting the kind of disease. According to the results, the suggested framework outperformed the state-of-the-art benchmark algorithms in disease prediction while producing results that were plausible. With Prototypical Networks and MAML for rice leaf disease datasets, it increased by up to 97.6% and 95.27%, respectively. For effective rice disease identification, Prototypical Networks and MAML for Sugar cane leaf disease datasets increased by up to 91.68% and 90.27%, respectively. Interpretable AI-driven insights were further made possible by the combination of proposed system with Grad-CAM Explanation, which improved decision-making transparency.

Optimizing MAF-ENF-CO2 coordination in steel mills: system modeling and emission reduction scenarios

Fuzzy decision support systems for hospital infection management: a circular q-ROF CRADIS method to prevention and control

Cost-effective plant-based medium for enhanced spore production of B. amyloliquefaciens CN12 for biofertilizer application

GoLoCo-Net: global-local guided contextual attention network for medical images segmentation

Abstract Accurate medical image segmentation plays a vital role in assisting diagnosis with quantifiable visual evidence. Due to the complex structure and diverse patterns in medical images, it is crucial to capture both short and long-range pixel relations. While transformers are adept at modeling long-range spatial dependencies in images, they struggle with learning local pixel relationships. To address this, we propose a deep learning network named GoLoCo-Net incorporating a dual decoder structure. More specifically, one decoder entails a Contextual Attention Feature Enhancement (CAFE) module to enhance the features for a broader capture of local and global contexts, whereas the other uses a Global-Guide-Local Feature (GGLF) module that leverages high-level features to enrich low-level features with a global context. The proposed method is evaluated on two dynamic MRI datasets and one multi-organ CT dataset. Experimental results show that the model achieves state-of-the-art performance across all three datasets. The code is available: https://github.com/Yhe9718/GoLoCoNet .

Assessing the effectiveness of the ZICOMP-Shewhart control chart for monitoring zero-inflated processes

Cancer blood tests are everywhere — here's why you should be cautious

Metagenomic analysis reveals rectal microbiota features associated with HIV and behavioral factors in Nigerian men who have sex with men

Large-scale quantum communication networks with integrated photonics

Microstructure and mechanical properties of (Mg, Ce)-modified Al-7.5Si-15Cu-5Zn brazing joints on 5083 aluminum alloy

A dual limb attention based deep learning network for multipath classification of millimetre wave signals in intelligent transportation system

Abstract The presence of line-of-sight (LOS) and non-line-of-sight conditions in an intelligent transportation system (ITS) is critical, as it directly impacts the localisation and overall system performance. Distinguishing LOS, first-order and higher-order multipaths (HOMP) is hindered by the dense multipath (MP) propagation. The computational resource requirement and limited accuracy associated with traditional iterative methods have stimulated the use of deep learning (DL). This work proposes a novel, lightweight, dual limb attention (DLA) based DL network termed as “MOVENetx64”, for robust identification of MPs in ITS. DLA mechanism stacked with convolutional neural networks and long-short-term memory layers forms the prominent feature extractor, which enables feeding raw, unprocessed data into the DL pipeline. A novel alternating loss strategy is designed to nullify the effect of the extreme imbalance associated with the target output classes. Ray-tracing-based vehicular datasets for City, Suburban, and Highway are generated. A combination of time, received power, angular characteristics, and phase spectrum forms the input feature-set. The proposed MOVENetx64 showcases MP classification accuracy of (98.71%,99.41%,96.44%), and achieves the least HOMP prediction error of (0.6%,0.17%,2.28%) on the datasets. These results validate that the proposed MOVENetx64 is scalable and computationally efficient for distinguishing multipaths efficiently and enabling reliable vehicular communication in ITS.