Detection of Welding Defects Using the YOLOv8-ELA Algorithm by Yunxia Chen, Yangkai He, Lei Wu

“…To address the issue of the low precision in detecting defects in aluminum alloy weld seam digital radiography (DR) images using the current target detection algorithms, a modified algorithm named YOLOv8-ELA based on YOLOv8 is proposed. The model integrates a novel HS-FPN feature fusion module, which optimizes the parameter efficiency and enhances the detection performance. …”
Get full text

A Novel Metaheuristic Jellyfish Optimization Algorithm for Parameter Extraction of Solar Module by Dilip Yadav, Nidhi Singh, Vikas Singh Bhadoria, Nimay Chandra Giri, Murthy Cherukuri

“…Accurate parameter identification plays an integral role in the modeling of an optimized solar module which in turn helps in the error-free prediction of its output. …”
Get full text

Automated recognition of deep-sea benthic megafauna in polymetallic nodule mining areas based on deep learning by Guofan Long, Wei Song, Xiangchun Liu, Ziyao Fang, Jinqi An, Kun Liu, Yaqin Huang, Xuebao He

“…Deep learning has emerged as an promising approach in biological identification, offering significantly improved efficiency and reduced reliance on taxonomic expertise. …”
Get full text

Geospatial Segmentation and Vision AI for Rapid Detection and Classification of Faults in Rooftop Solar Panels by Tientanopajai Kitt, Khuanmar Kulyakorn, Kanarkard Wanida

“…Our study focuses on rapidly segmenting rooftop PV systems across various buildings within a university campus, achieving high processing speed and accuracy. The Vision AI model has been trained to identify and classify common faults, such as microcracks and dirt, that impact solar panel efficiency and lifespan. …”
Get full text

Machine Learning Ship Classifiers for Signals from Passive Sonars by Allyson A. da Silva, Lisandro Lovisolo, Tadeu N. Ferreira

“…The dataset encompassed 12 distinct ship classes and was processed in two ways—full-resolution and downsampled inputs—to assess the impacts of preprocessing on the model accuracy and computational efficiency. The classifiers included standard Support Vector Machines, K-Nearest Neighbors, Random Forests, Neural Networks and two less conventional approaches in this context: Linear Discriminant Analysis (LDA) and the XGBoost ensemble method. …”
Get full text

Automatic pine wilt disease detection based on improved YOLOv8 UAV multispectral imagery by Shaoxiong Xu, Wenjiang Huang, Dacheng Wang, Biyao Zhang, Hong Sun, Jiayu Yan, Jianli Ding, Jinjie Wang, Qiuli Yang, Tiecheng Huang, Xu Ma, Longlong Zhao, Zhuoqun Du

“…A dataset of optimal spectral combinations from visible light and multispectral images was constructed, along with an improved YOLOv8 deep learning model for rapid and accurate identification of PWD-infected trees. …”
Get full text

Towards Automated Cadastral Map Improvement: A Clustering Approach for Error Pattern Recognition by Konstantinos Vantas, Vasiliki Mirkopoulou

“…We compare Fuzzy c-means (FCM), Density-Based Spatial Clustering of Applications with Noise (DBSCAN), and Gaussian Mixture Models (GMMs) in clustering error vectors using two different case studies from Greece, each with different error origins. …”
Get full text

The Involvement of MicroRNAs in Modulation of Innate and Adaptive Immunity in Systemic Lupus Erythematosus and Lupus Nephritis by Mohsen Honarpisheh, Paulina Köhler, Ekaterina von Rauchhaupt, Maciej Lech

“…Recently, significant findings have been made in understanding SLE through the use of genetic variant identification and expression pattern analysis and mouse models, as well as epigenetic analyses. …”
Get full text

Smart In-Process Inspection in Human–Cyber–Physical Manufacturing Systems: A Research Proposal on Human–Automation Symbiosis and Its Prospects by Shu Wang, Roger J. Jiao

“…In addition, to maintain high product quality and enable the in-time feedback of process issues for advanced manufacturing, in-process inspection is an efficient strategy that manufacturers adopt. In this regard, this paper outlines a research framework combining smart in-process inspection and human–automation symbiosis, enabling real-time defect identification and process optimization with cognitive intelligence. …”
Get full text

An Explainable Deep Learning Network With Transformer and Custom CNN for Bean Leaf Disease Classification by R. Karthik, R. Aswin, K. S. Geetha, K. Suganthi

“…Importantly, the model’s computational efficiency makes it well-suited for practical application in real-world agricultural scenarios.…”
Get full text

Advancing Pediatric Growth Assessment with Machine Learning: Overcoming Challenges in Early Diagnosis and Monitoring by Mauro Rodriguez-Marin, Luis Gustavo Orozco-Alatorre

“…Unlike complex machine learning models, it offers parsimony in transparency, efficiency, and reproducibility, making it ideal for clinical settings where explainable, data-driven decisions are essential. …”
Get full text

Ecological networks construction and optimization in the Longdong Loess Plateau: The advantages of self-organizing map and complex networks by Xueyu Huang, Lina Xiu, Zhixiang Lu, Jiahui Wang

“…Additionally, it is vulnerable to interference from artificially assigned weights, which hinders the accurate identification of ecological sources. In this study, a self-organizing map (SOM) model was utilized to optimize the ecological sources identification in the Longdong Loess Plateau. …”
Get full text

Study on the Compressive Strength Predicting of Steel Fiber Reinforced Concrete Based on an Interpretable Deep Learning Method by Huiming Wang, Jie Lin, Shengpin Guo

“…In order to predict the compressive strength of SFRC efficiently and accurately, this study proposes a deep learning-based prediction model, trained and tested on a large set of experimental data. …”
Get full text

Cross-sensor data reconstruction for optical remote sensing gap-filling with attention-enhanced multi-scale fusion network by Xi Wang, Songchao Chen, Chang Zhou, Si-Bo Duan, Zhou Shi

Get full text

Extraction of Garlic in the North China Plain Using Multi-Feature Combinations from Active and Passive Time Series Data by Chuang Peng, Binglong Gao, Wei Wang, Wenji Zhu, Yongqi Chen, Chao Dong

“…A key factor influencing garlic prices is the planted area, which can be accurately and efficiently determined using remote sensing technology. …”
Get full text

MLinvitroTox reloaded for high-throughput hazard-based prioritization of high-resolution mass spectrometry data by Katarzyna Arturi, Eliza J. Harris, Lilian Gasser, Beate I. Escher, Georg Braun, Robin Bosshard, Juliane Hollender

“…For each analyzed HRMS feature, MLinvitroTox generates a 490-bit bioactivity fingerprint used as a basis for prioritization, focusing the time-consuming molecular identification efforts on features most likely to cause adverse effects. …”
Get full text

Transdisciplinary Approach in Palliative Care MDT Meetings – A Way Forward by Annum Ishtiaq

“…These meetings yield evidence-based care plans developed by a diverse group of specialists, minimizing variations in practice patterns, and efficiently utilizing healthcare resources. The outcome of MDT meetings is time-efficient, cost-effective, and quality care that enhances patient satisfaction [4]. …”
Get full text

Adaptive weight optimization with large pretraining for pest detection by Kejian Yu, Wenwen Xu, Fuqin Geng, Yunzhi Wu

“…These results highlight the significant practical value of multimodal pest detection methods in enhancing the efficiency and accuracy of agricultural pest identification. …”
Get full text

Dictyostelium discoideum transformation by oscillating electric field electroporation by Laeticia Alibaud, Pierre Cosson, Mohammed Benghezal

“…High-efficiency transformation is a prerequisite for successful genetic screens such as mutant complementation, identification of suppressor genes, or insertional mutagenesis. …”
Get full text

SAG-YOLO: A Lightweight Real-Time One-Day-Old Chick Gender Detection Method by Yulong Chang, Rongqian Sun, Zheng Yang, Shijun Li, Qiaohua Wang

“…Feather sexing, based on wing feather growth rate, is a widely used method for chick sex identification. However, it still relies on manual sorting, necessitating automation. …”
Get full text