NeuralPDR: neural differential equations as surrogate models for photodissociation regions by Gijs Vermariën, Thomas G Bisbas, Serena Viti, Yue Zhao, Xuefei Tang, Rahul Ravichandran

“…We train these surrogate architectures on three datasets of increasing physical complexity, with the last dataset derived directly from a three-dimensional simulation of a molecular cloud using a photodissociation region (PDR) code, 3D-PDR . …”
Get full text

Community health fairs as experiential learning: a qualitative exploration of benefits and challenges by Martha Rojo, Scott Wright, Jing Jin, Erickson Feliciano, Margaret Love, Sharon Stevenson

“…Participants also recommended pre-training of healthcare volunteers and incorporating technology for teaching patients. …”
Get full text

ORANSight-2.0: Foundational LLMs for O-RAN by Pranshav Gajjar, Vijay K. Shah

“…The generated dataset is then used to fine-tune the 18 pre-trained open-source LLMs via QLoRA. To evaluate ORANSight-2.0, we introduce srsRANBench, a novel benchmark designed for code generation and codebase understanding in the context of srsRAN, a widely used 5G O-RAN stack. …”
Get full text

The utilisation of scientific crime investigation methods and forensic evidence in the criminal investigation process in Indonesia by Handar Subhandi Bakhtiar, Amir Ilyas, Abdul Kholiq, Handina Sulastrina Bakhtiar

“…Investigator interviews confirm that forensic evidence strengthens legal cases and reduces wrongful convictions, but obstacles such as insufficient training, outdated technology, and weak regulatory enforcement remain. …”
Get full text

A benchmark for computational analysis of animal behavior, using animal-borne tags by Benjamin Hoffman, Maddie Cusimano, Vittorio Baglione, Daniela Canestrari, Damien Chevallier, Dominic L. DeSantis, Lorène Jeantet, Monique A. Ladds, Takuya Maekawa, Vicente Mata-Silva, Víctor Moreno-González, Anthony M. Pagano, Eva Trapote, Outi Vainio, Antti Vehkaoja, Ken Yoda, Katherine Zacarian, Ari Friedlaender

“…Datasets, models, and evaluation code are made publicly available at https://github.com/earthspecies/BEBE , to enable community use of BEBE.…”
Get full text

A New and Tested Ionospheric TEC Prediction Method Based on SegED-ConvLSTM by Yuanhang Liu, Yingkui Gong, Hao Zhang, Ziyue Hu, Guang Yang, Hong Yuan

“…Furthermore, we analyzed the influence of different batch sizes on model training accuracy to find the best performance of each model. …”
Get full text

Evaluation of the feasibility, appropriateness, and acceptability of an environmental cleaning program improvement toolkit at a tertiary care hospital in Nigeria by Cori Dennison, Matthew Hudson, Damilola Adeniyi, Folasade Ogunsola, Hanako Osuka, Lisa P. Oakley, Paul Malpiedi, Amber Vasquez, Molly Patrick

“…Additional codes and sub-themes that emerged during analysis followed an inductive process. …”
Get full text

Pregnant Women’s Views on the Type of Delivery: Determinants and Relationships by Nooshin Jalali, Shahrzad Hadavand, Farhad Jafari, Maryam Rabiee, Kobra Khajavi Shojaie

Get full text

Presence of Campylobacter spp in raw chicken meat. According to its origin and sold in markets in the city of La Paz, Bolivia by Marcelina Condori Ticona, Angélica María Espada Silva, María del Pilar Donado Godoy

Get full text

Prediction of biological evolution following blood product transfusion during liver transplantation: the contribution of machine learning to decision-making by Jacques Creteur, Thibault Martinez, Valerio Lucidi, Turgay Tuna, Florian Blanchard, Olivier Duranteau, Benjamin Popoff, Axel Abels, Eric Savier, Patrizia Loi, Desislava Germanova, Anne Demulder

“…Despite these limitations, this study provides a reproducible framework for evaluating transfusion efficacy, supported by openly shared Python code and the application of Taylor diagrams for model evaluation.Conclusion While our models are unsuitable for routine clinical use, they highlight the potential of machine learning in transfusion medicine. …”
Get full text

GEDTM30: global ensemble digital terrain model at 30 m and derived multiscale terrain variables by Yu-Feng Ho, Carlos H. Grohmann, John Lindsay, Hannes I. Reuter, Leandro Parente, Martijn Witjes, Tomislav Hengl

“…The GEDTM30 dataset and code are publicly available as Cloud-Optimized GeoTIFFs via Zenodo and the OpenLandMap STAC. …”
Get full text

Flying Robots Teach Floating Robots—A Machine Learning Approach for Marine Habitat Mapping Based on Combined Datasets by Zacharias Kapelonis, Georgios Chatzigeorgiou, Manolis Ntoumas, Panos Grigoriou, Manos Pettas, Spyros Michelinakis, Ricardo Correia, Catarina Rasquilha Lemos, Luis Menezes Pinheiro, Caio Lomba, João Fortuna, Rui Loureiro, André Santos, Eva Chatzinikolaou

“…In this work, a sea-bottom classification methodology is presented for mapping the protected habitat of Mediterranean seagrass <i>Posidonia oceanica</i> (habitat code 1120) in a coastal subregion of Heraklion (Crete, Greece). …”
Get full text

Lung adenocarcinoma subtype classification based on contrastive learning model with multimodal integration by Changmiao Wang, Lijian Liu, Chenchen Fan, Yongquan Zhang, Zhijun Mai, Li Li, Zhou Liu, Yuan Tian, Jiahang Hu, Ahmed Elazab

“…These results significantly outperform recent multimodal classification approaches. The code is available at https://github.com/fancccc/LungCancerDC .…”
Get full text

Acute Upper Gastrointestinal Bleeding: A Hands-On Simulation Case for Internal Medicine Residents Improves Knowledge and Confidence by Marni H. Wilkoff, Emily S. Seltzer, Nicholas R. Piniella, Harrindra Seepersaud, Priscilla Loanzon, Susannah Kurtz, James Salonia, Daniela Jodorkovsky

“…Introduction Upper gastrointestinal (GI) bleeding leads to approximately 350,000 hospital admissions annually. Simulation-based training enhances medical education by improving quality care, patient safety, and clinical competency. …”
Get full text

Time Series Remote Sensing Image Classification with a Data-Driven Active Deep Learning Approach by Gaoliang Xie, Peng Liu, Zugang Chen, Lajiao Chen, Yan Ma, Lingjun Zhao

“…On the PASTIS dataset, when the initial number of samples was 1000 after our method selected and labeled 2000 samples, an accuracy improvement of 4.89% was achieved. Our code is available in Data Availability Statement.…”
Get full text

TransNN-MHA: A Transformer-Based Model to Distinguish Real and Imaginary Motor Intent for Assistive Robotics by Tipu Sultan, Guangping Liu, Pascal Sikorski, Madi Babaiasl

“…Implementation details and code are available at <uri>http://github.com/madibabaiasl/EEGIntentPaper</uri>…”
Get full text

Quantifying solid volume of stacked eucalypt timber using detection-segmentation and diameter distribution models by Gianmarco Goycochea Casas, Zool Hilmi Ismail, Mathaus Messias Coimbra Limeira, Carlos Pedro Boechat Soares, José Marinaldo Gleriani, Daniel Henrique Brada Binoti, Carlos Alberto Araújo Júnior, Mohd Ibrahim Shapiai, Leonardo Ippolito Rodrigues, Tassius Menezes Araújo, Helio Garcia Leite

Get full text

Reconstruction of the Radiation Belts for Solar Cycles 17–24 (1933–2017) by A. A. Saikin, Y. Y. Shprits, A. Y. Drozdov, D. A. Landis, I. S. Zhelavskaya, S. Cervantes

“…The radiation belt simulations are produced using the Versatile Electron Radiation Belt (VERB)‐3D code. The VERB‐3D code simulations incorporate radial, energy, and pitch angle diffusion to reproduce the radiation belts. …”
Get full text

Mechanical Design and Motion Analysis of a Hybrid Robot for Equine Rehabilitation by YE Zenglin, DAI Zhonghong, ZHANG Liang'an, WEI Liangguo, CHEN Hua

“…Furthermore, challenges related to individual variations and the requirement for specialised therapist training need to be addressed, alongside cost, resource, and training concerns, to ensure wider adoption of equine therapy. …”
Get full text

Study of the Lived Experience of Divorced and Divorced Couples in Ahvaz and Development of a Divorce Prevention Education Package by Nasrin Ardali, Yousefali Attari, Fatemeh Javadzadeh Shahshahani

“…In the selective coding stage, three general training codes including training for acceptance, training for change, and training for cognition were extracted, based on which the final training package was designed.…”
Get full text