Integration of spatiotemporal features into machine learning assessment of open surgical skills.

Machine learning classification of PAH exposure in the Antarctic limpet Nacella concinna.

Artificial intelligence in the diagnosis of Hirschsprung disease: A scoping review and rationale for a multicentric approach.

Soybean (Glycine max L.) performs an important position as a main resource of protein in Indonesia. Its quality and productivity can be assessed based on the characteristics of its seed. Accordingly, the identification process through the observation of soybean seed traits is a crucial step in plant breeding and quality assurance. Manual approaches rely on manual observation, which is subjective, prone to human error and time-consuming. With the improvement of artificial intelligence, automated seed identification has appeared as a potential solution. However, progress is constrained by the lack of open and standardized image datasets, especially for locally bred varieties in developing countries. To address this gap, we propose an open image dataset of Indonesian soybean seeds from three widely cultivated and plant-bred varieties: Anjasmoro, Grobogan, and DEGA-1. The dataset consists of high-resolution seed images captured with an Epson L360 flatbed scanner, with the optical resolution fixed at 800 dots per inch, yielding images of 6800 × 9359 pixels. All raw images are saved in JPG format. No manually segmentation masks are released in this version, instead of using Deeplab V3+ with MobileNet as backbone to enable the automated seed image segmentation. The curated dataset is intended to support a broad range of applications, including computer vision tasks such as image classification and segmentation, as well as research in plant breeding, seed quality assessment, and agricultural informatics. By providing a standardized and publicly accessible resource, this dataset contributes to the advancement of interdisciplinary studies at the intersection of agriculture and artificial intelligence.

This study employed an HY-6010-S hyperspectral imaging system, covering a spectral range of 400-1000 nm, combined with an RGB industrial camera to acquire multimodal data. The dataset simulates phenotypic analysis scenarios of maize seeds under controlled laboratory conditions, with the ambient temperature maintained at 20-25°C. Comprehensive testing was conducted using 12 different maize varieties. Approximately 200 seed samples were collected per variety, resulting in a total sample size of about 2400, each subjected to hyperspectral and RGB image acquisition. Preprocessing steps included noise reduction, background removal, band selection, and modality alignment. To ensure the accuracy and reliability of the experimental data, HHIT software and Python were utilized for data processing. This dataset plays a significant role in seed variety classification, phenotypic analysis, precision agriculture, and machine learning applications.

Machine learning application and evaluation of CO2 emissions for sustainable biofuels production from pyrolysis of cotton stalks

Advancing international business research through artificial intelligence and machine learning applications

Application of data-driven machine learning in performance prediction and multi-objective optimization of green sustainable steam-cured concrete

This article presents the Knowledge Graph for Agricultural Prices (KGAP), which is a knowledge graph (KG) that integrates agricultural commodity prices data from three major Brazilian institutions: Cepea, Conab, and Ipea. The datasets, originally published in heterogeneous formats, were harmonized and converted into RDF/Turtle using the Almes Core metadata schema as the data model. Agricultural products were classified with the Agricultural Product Types Ontology (APTO), and geographic references were aligned with GeoNames identifiers, ensuring semantic consistency and adherence to the FAIR data principles. KGAP is archived on Zenodo and GitHub, and hosted on the Platform Linked Data Nederland (PLDN) with a public SPARQL endpoint. It contains metadata, price observations, product types, and location entities, allowing users to query and compare agricultural prices across institutions, regions, and time periods. The knowledge graph can potentially support applications in agricultural economics, policy analysis, journalism, data science, and machine learning. By explicitly modeling metadata such as reference quantities, KGAP enables semantically-aware queries that prevent common analytical errors and reveal insights previously obscured by data heterogeneity.

Cancer arises and is resistant to therapy via intricate molecular networks that are poorly characterised. While individually, Cullin-3 (CUL3) and circular RNAs (circRNAs) have been reported to modulate cancer, their synergistic effect in the modulation of tyrosine kinase inhibitor (TKI) resistance is yet to be studied. An emerging circRNA-CUL3-TKI regulatory framework is highlighted as a potential contributor to oncogenesis and drug sensitivity in this review. We discuss how circRNA-associated networks may influence CUL3-dependent pathways implicated in tumour resistance to therapy by modulating autophagy, ferroptosis, stress-responses, and redox signalling. Exosomal circRNAs and circRNAs of the CUL3 gene itself are highlighted as dynamic mediators of resistance as well as biomarkers. How they interact with Kelch-like ECH-associated protein 1- Nuclear factor erythroid 2-related factor 2 (KEAP1-NRF2) signalling reveals that they enhance tumour survival under therapy pressure. By highlighting key processes of carcinogenesis and resistance, the circRNA-CUL3-TKI axis represents a testable therapeutic framework. Modeling circRNA networks, predicting TKI response, finding biomarkers, and developing personalised treatment plans are all made possible by applications of artificial intelligence and machine learning (AI/ML), as explored in this review. Antisense oligonucleotides, Clustered Regularly Interspaced Short Palindromic Repeats (CRISPR)-based molecules, neddylation inhibitors or PROteolysis TArgeting Chimera (PROTACs) are examples of potential interventions that, when combined with AI/ML techniques, improve therapeutic efficacy and may inform future desensitisation strategies. These collectively emphasize the emerging applications for AI/ML in understanding the circRNA-CUL3-TKI crosstalk and developing methods to resensitize cancers that are resistant to therapy.

From green routes to digital design: Two-dimensional photocatalysts at the interface of machine learning and environmental applications

Application of machine learning to rechargeable aqueous zinc-ion batteries: Advancements and prospects

Artificial intelligence in animal anatomy: Exploring the technologies, applications, benefits, and challenges.

Predicting psychological risk among college students using the Freshman Entrance Psychological Survey: A machine learning model based on LASSO-logistic regression.

Applying machine learning for precipitation forecasting in uneven rainfall regions of Taiwan

Predicting carbohydrate productivity in continuous microalgae cultivation systems remains a significant technical challenge due to the non-linear nature of metabolic pathways under multiple stresses. This study applied Machine Learning (ML) models to predict biomass and carbohydrate productivity in Chlorella vulgaris grown in continuous culture, utilizing 145 independents experimental sets. Linear (Multiple Linear Regression, Ridge, and LASSO) and non-linear (Random Forest, Artificial Neural Networks, and Support Vector Regression) models were evaluated, integrating nutritional (N and P), environmental (light intensity and optical density), and operational (residence time) variables. Model optimization was carried out via grid search with 5-fold cross-validation and an 80/20 data split to ensure robustness and prevent overfitting. Results showed that non-linear models significantly outperformed traditional methods. Random Forest emerged as the most effective algorithm, achieving an R2 of 0.9072 and RMSE of 0.0518 for biomass productivity, and an R2 of 0.9304 and RMSE of 0.0187 for carbohydrate productivity. These findings demonstrate the potential of ML as a "virtual sensor" for real-time control and optimization of large-scale industrial bioprocesses, enabling immediate operational adjustments without reliance on time-consuming laboratory analyses.

ICMP-Flood-SDN: A Python based machine learning application for ICMP flood DDoS attack detection in software defined networks

Implementing a declarative query language for high level machine learning application design

A multimodal imaging dataset for quality grading of Canadian wild rice kernels using RGB and VNIR hyperspectral data.

Application of Machine learning in predicting cancer complications using longitudinal Data: A systematic review and Meta-Analysis.