Results 141 to 150 of about 17,724 (252)

Passive Water Filtration Enhances the Detection of Endangered Fish Species in Rivers: Anguilla anguilla and Salmo salar Monitoring Using qPCR

Ecology and Evolution, Volume 16, Issue 8, August 2026.
This study assesses the effectiveness of environmental DNA (eDNA) for monitoring the critically endangered Anguilla anguilla and the near‐threatened Salmo salar using quantitative PCR. Active in situ water filtration and passive metaprobe deployment were compared, showing that metaprobes provided greater sensitivity for low‐abundance species, while ...
Irene de Carlos Fernández, Alba Ardura, Sara Fernández   +2 more
wiley   +1 more source

Monitoring and Early Warning of the Cage-Rearing Broiler Farming Environment Based on an Inspection Robot. [PDF]

Animals (Basel)
Luo S, Kong X, Xie X, Zhang W, Zheng P, Zhu H, Hao D, Sun J, Chen C.   +8 more
europepmc   +1 more source

A Lightweight and Erudite Automated BiLSTM‐Based Multi‐Cycle GAN for Retinal Blood Vessel and Optic Disc Segmentation in Fundus Images

Engineering Reports, Volume 8, Issue 8, August 2026.
This graphical abstract presents a lightweight and automated BiLSTM‐based Multi‐Cycle GAN framework for retinal blood vessel and optic disc segmentation in fundus images. Initially, fundus images undergo preprocessing, including green channel extraction, denoising, resizing, and dataset splitting.
Rasmita Kumari Mohanty, Amaravarapu Pramod Kumar, Yuvaraju Macha, Agraharam Siva Kumar, J. Srinivas, G. Shyama Chandra Prasad, Rajesh Kumar Verma, Shashi Kant   +7 more
wiley   +1 more source

LSTM-GRU hybrid model for multi-layer microclimate prediction in solar greenhouse. [PDF]

Sci Rep
Li B, Wang Z, Guo Y, Zhou X, Qiao B, Han L.   +5 more
europepmc   +1 more source

Explainable Machine Learning With Hybrid Feature Selection for Thyroid Disease Classification: A Case Study in Bangladesh

Engineering Reports, Volume 8, Issue 8, August 2026.
Our research establishes a hybrid feature selection and ensemble machine learning pipeline for the classification of euthyroid, hyperthyroid, hypothyroid, and subclinical hypo‐ and hyperthyroid disorders. Variance Threshold with Backward Feature Elimination attained nearly 100% accuracy, while SHAP and LIME clarified the significance of features and ...
Md. Minhajul Abedin, Arka Chakraborty, Sawrav Das, Manoshi Das Turjo, Aditta Chowdhury, Mahdy Rahman Chowdhury   +5 more
wiley   +1 more source

Block‐Wise Data Synthesis to Achieve 1 Km Resolution Monthly Rainfall Forecast for Mainland China With Small Computing Resources

Engineering Reports, Volume 8, Issue 8, August 2026.
This paper proposes a patch‐based data synthesis method to solve the problem of insufficient computing resources due to excessive data and the inability of conventional methods to preserve the spatial autocorrelation in the data. At the same time, this method is used to complete the 1 km monthly rainfall forecast for mainland China. ABSTRACT This study
Kebin Dai, Chong Xu
wiley   +1 more source

A Hybrid CNN-GRU-SE Forecasting Method for Short-Term Photovoltaic Power Considers AFD and Data Aggregation. [PDF]

Entropy (Basel)
Liu K, Jia D, Zhan H, Zhou J, Wang Z, Bao J.   +5 more
europepmc   +1 more source

Daily Residential Natural Gas Demand Forecasting Using Machine Learning Regression: Comparative Evaluation With a Case Study in Qazvin Province, Iran

Energy Science &Engineering, Volume 14, Issue 8, Page 3656-3673, August 2026.
This graphical abstract summarizes the proposed framework for improving short‐term residential natural gas consumption forecasting by integrating a novel socioeconomic indicator, the subscription growth ratio (SGR), with conventional meteorological variables.
Ali Pirzad, Mostafa Khanzadi
wiley   +1 more source

Decentralized Federated Learning for Wind Turbine Bearing Prognostics Under Data Scarcity and Statistical Heterogeneity

Energy Science &Engineering, Volume 14, Issue 8, Page 3674-3696, August 2026.
This paper proposes a decentralized peer‐to‐peer federated learning framework for wind turbine bearing remaining useful life prediction, introducing a virtual client paradigm in which statistical health indicators serve as independent feature‐level clients—enabling privacy‐preserving collaborative prognostics from a single physical asset under ...
Jihene Sidhom, Lotfi Saidi, Eric Bechhoefer   +2 more
wiley   +1 more source

DGrA: Lightweight Modulation Recognition Based on Hybrid Neural Networks. [PDF]

Sensors (Basel)
Chen X, Gao R, Xu D, Zhu H.
europepmc   +1 more source