Inversion of Water Quality Parameters from UAV Hyperspectral Data Based on Intelligent Algorithm Optimized Backpropagation Neural Networks of a Small Rural River by Manqi Wang, Caili Zhou, Jiaqi Shi, Fei Lin, Yucheng Li, Yimin Hu, Xuesheng Zhang

“…Meanwhile, the model also demonstrated good robustness and generalization ability for data from different periods. …”
Get full text

Virus adaptation to heparan sulfate comes with capsid stability tradeoff by Han Kang Tee, Simon Crouzet, Arunima Muliyil, Gregory Mathez, Valeria Cagno, Matteo Dal Peraro, Aleksandar Antanasijevic, Sophie Clément, Caroline Tapparel

“…Not only are these viruses hindered in tissues rich in HS due to viral trapping, as generally accepted, but our research reveals that their diminished capsid stability further contributes to attenuation in vivo. …”
Get full text

Trimodal organ‑preserving treatment of muscle‑invasive bladder cancer by A. V. Troianov, I. O. Dementev, I. N. Zaborsky, V. S. Chaykov, O. B. Karyakin, Yu. V. Gumenetskaya

“…Purpose of the study. Generalization of the world experience of organ‑preserving treatment in muscle‑invasive bladder cancerMaterials and methods. …”
Get full text

Characterization of Complex Image Spatial Structures Based on Symmetrical Weibull Distribution Model for Texture Pattern Classification by Jinping Liu, Jiezhou He, Zhaohui Tang, Pengfei Xu, Wuxia Zhang, Weihua Gui

“…Visually, the visual appearance of the complex spatial structure (CSS) of texture pattern (TP) generally depends on the random organization (or layout) of local homogeneous fragments (LHFs) in the imaged surface. …”
Get full text

Can urban compactness improve ecosystem services: Evidence from Chinese urban agglomerations by Xuewei Zhang, Jiahui Wu, Jintao Yuan, Wanxu Chen

“…Our findings revealed that the urban compactness of UAs in China generally increased from 2010 to 2020, with the most significant increases observed in the Yangtze River Delta, Mid-Yangtze River, and Central Plains UAs. …”
Get full text

Factors Influencing Hospitalization Expenses Among Patients with Lung Cancer in China by Tingting Xu, Nan Jiang, He Chen, Jun Feng, Qiming Feng, Xianjing Qin, Jinmin Zhao, Hongda Gao

“…Degree of structure variation (DSV) was used to explore internal factors. Generalized linear model (GLM) was used to explore external factor. …”
Get full text

Smell-ML: A Machine Learning Framework for Detecting Rarely Studied Code Smells by Esraa Hamouda, Abeer El-Korany, Soha Makady

“…This paper proposes a novel approach, called Smell-ML, for detecting five rarely studied code smells: Middle Man (MM), Class Data Should Be Private (CDSBP), Inappropriate Intimacy (II), Refused Bequest (RB), and Speculative Generality (SG). The novelty of this approach stems from the improvement in both the data preparation and classification phases. …”
Get full text

Cold temperature-related attributable risk for emergency circulatory hospitalizations, length of stay, and healthcare costs in Hong Kong by Eliza Lai-Yi Wong, Hong Qiu

“…Methods: This ecologic time series analysis linked the daily circulatory EHA count and LOS from the Hong Kong Hospital Authority with the environmental exposures from the fixed monitoring stations from 2004 to 2019. The generalized linear quasi-Poisson model integrated with a distributed lag nonlinear model was applied to examine ambient temperatures' relative and attributable risks on EHA counts and LOS while adjusting the time-varying confounders. …”
Get full text

A Novel Network for Choroidal Segmentation Based on Enhanced Boundary Information by Wenbo Huang, Chaofan Qu, Yang Yan

“…The boundary enhancement module effectively improves the accuracy of choroidal segmentation, while the custom loss function optimizes network performance, increasing both stability and generalization capabilities. Moreover, the modular design of the boundary enhancement module ensures its portability across different segmentation tasks, making it a versatile component for integration into existing frameworks.…”
Get full text

Tracking pygmy blue whale diving behaviour and validation of foraging areas defined from horizontal movement data by Michele Thums, Luciana C. Ferreira, Andrew Davenport, Micheline Jenner, Luciana Möller, Grace Russell, Robert D. McCauley, Curt Jenner

“…Despite a weak temporal relationship between putative (inferred from a movement model) and actual foraging, there was generally good spatial overlap detected, predominantly in high use areas, while more opportunistic foraging areas with lower use were less likely to be detected by the model. …”
Get full text

Chitosan based coating enriched with Spirulina platensis and moringa leaf extracts preserved the postharvest quality of Mexican Lime (Citrus aurantifolia) by Soheila Aghaei Dargiri, Somayeh Rastegar, Mahbobeh Mohammadi

“…Research limitations: There was no limitation. Originality/value: Generally, the utilization of chitosan edible coatings, specifically chitosan combined with spirulina algae, has shown promising results in preserving the quality and extending the shelf life of Mexican lime fruit stored at 20 ± 2 °C.…”
Get full text

LFN-YOLO: precision underwater small object detection via a lightweight reparameterized approach by Mingxin Liu, Mingxin Liu, Yujie Wu, Ruixin Li, Cong Lin, Cong Lin

“…Furthermore, We employed the Generalized Feature Pyramid Network (GFPN) for feature fusion in the network's neck, enhancing the network's adaptability to features of varying scales. …”
Get full text

Implication of tumor morphology and MRI characteristics on the accuracy of automated versus human segmentation of GBM areas by Valeria Cerina, Chiara Benedetta Rui, Andrea Di Cristofori, Davide Ferlito, Giorgio Carrabba, Carlo Giussani, Gianpaolo Basso, Elisabetta De Bernardi

“…Brats-Toolkit and DeepBraTumIA generally provide accurate segmentations, particularly for the most common round-shaped or well-demarked tumors, where: (1) gross tumor segmentation correctly includes necrosis and contrast enhanced tumor in 100% and 97.06% of cases (vs. 73.68% for manual segmentation) and wrongly includes healthy or non-tumor related tissues in 2.94% and 20.59% of cases (vs. 10.53% for manual segmentations); (2) T2-FLAIR hyper-intensity segmentations completely includes edema in 88.24% of cases for both software. …”
Get full text

Factores bioquímicos asociados a la adherencia a la dieta mediterránea by Víctor Juan Vera Ponce, Silva Mariana, Mario Valladares Garrido, Luis Zapata Castro, Helena Domínguez Troncos, Jenny Raquel Torres Malca, Jesús Enrique Talavera, Jhony Alberto De La Cruz Vargas

“…Se utilizaron modelos lineales generales. Resultados: De 209 participantes, la mayoría fueron hombres (79,9 %) y la mediana de edad fue de 31 años. …”
Get full text

Do land models miss key soil hydrological processes controlling soil moisture memory? by M. A. Farmani, A. Behrangi, A. Behrangi, A. Gupta, A. Tavakoly, A. Tavakoly, M. Geheran, G.-Y. Niu

“…We test the effects of these processes, which are generally missed by most LSMs in SMM. We compare SMMs computed from various Noah-MP configurations against that derived from the Soil Moisture Active Passive (SMAP) L3 soil moisture and in situ measurements from the International Soil Moisture Network (ISMN) from the years 2015 to 2019 over the contiguous United States (CONUS). …”
Get full text

Directions for the development of the criminal procedure science by S. O. Shatrava, О. V. Dzhafarova, D. Ye. Denyschuk, О. V. Pohorilets

“…In addition to playing the role of a moral and ethical component of public life, it acts as a lever in the international political arena, and also touches upon some matters of financial income and tax revenue. EU legislation generally regards pornography as a phenomenon that does not pose a social or moral and ethical danger. …”
Get full text

Improving drug repositioning with negative data labeling using large language models by Milan Picard, Mickael Leclercq, Antoine Bodein, Marie Pier Scott-Boyer, Olivier Perin, Arnaud Droit

“…Supervised machine learning is commonly used to score drug candidates but is hindered by the lack of reliable negative data—drugs that fail due to inefficacy or toxicity— which is difficult to access, lowering their prediction accuracy and generalization. Positive-Unlabeled (PU) learning has been used to overcome this issue by either randomly sampling unlabeled drugs or identifying probable negatives but still suffers from misclassification or oversimplified decision boundaries. …”
Get full text

Multiple Influences of Paleogeography, Sequence Stratigraphy, and Fold Structure on Coalbed Methane Accumulation in the Lopingian (Late Permian) of Junlian Coalfield, SW China by Xiangdong Gao, Wuzhong Li, Yiming Yang, Kaigui Yin, Shihao Zhou

“…Closely related to coal seam thickness, gas contents of Lopingian coal seams are generally higher than 8 m3/t, except the low level in northwest and partial denudation areas. …”
Get full text

Research on Traffic Accident Severity Level Prediction Model Based on Improved Machine Learning by Jiming Tang, Yao Huang, Dingli Liu, Liuyuan Xiong, Rongwei Bu

“…In the prediction of different traffic accident severity levels (minor, moderate, and severe), the improved machine learning model also generally shows better performance and stability. The research results of this study have broad prospects in the field of intelligent driving. …”
Get full text

Effect of regular thicknesses on the microstructural and quantitative analysis for a hypo-eutectic ductile iron alloyed with Ni and V by Colin-García E., Sánchez-Alvarado R.G., Cruz-Ramírez A., Suarez-Rosales M.A., Portuguez-Pardo L., Jiménez-Lugos J.C.

“…Ductile iron contains free graphite nodules within the metallic matrix, which generally consists of ferrite and pearlite in the as-cast condition. …”
Get full text