Proceedings of the National Academy of Sciences (PNAS)

Identifying variation in dinosaur footprints and classifying problematic specimens via unbiased unsupervised machine learning

Machine learning holds great promise for classifying and identifying fossils, and has recently been marshaled to identify trackmakers of dinosaur ...
Ecommerce Fastlane

What Are AI Algorithms? Types of AI Algorithms + Use Cases

The line between human and artificial intelligence is growing ever more blurry. Since 2021, AI has deciphered ancient texts ...
Bulletin of the Atomic Scientists

Division begets division in the age of algorithmic classification

Social media and algorithmic recommendations aren’t just reflecting our divisions — they’re driving them. According to a poll conducted by Siena University and The New York Times, “most voters think ...
Frontiers

3D colored point cloud classification of a deep-sea cold-water coral and sponge habitat using geometric features and machine learning algorithms

Classification of benthic habitats in the deep sea is instrumental in managing and monitoring marine ecosystems as it provides distinct units for which changes can be quantified over time. These ...
Frontiers

Technical classification of professional cycling stages using unsupervised learning: implications for performance variability

Introduction: In professional cycling, the technical characteristics of race stages significantly influence group dynamics and performance variability among competitors. However, stage classifications ...
Scientific Research Publishing

Land Cover Classification through GIS-Based Clustering of Morphometric Terrain Features: The Chepelarska River Basin (Western Rhodopes, Bulgaria) ()

This paper proposes a GIS-based approach to classifying land cover using key morphometric indicators—slope, aspect, and elevation. The study focuses on the Chepelarska River basin in the Western ...
IEEE

Unsupervised Band Selection for Hyperspectral Images Classification: Particle Swarm Optimization via Cross-Domain Knowledge Transfer

Abstract: Band selection (BS) is a key method in Hyperspectral image (HSI) classification that helps to reduce the computational burden and improve the class separability. However, with the emerging ...
Scientific Research Publishing

An Evaluation of Machine Learning Models for Threat Classification in IoT Devices ()

1 Center for Cyberspace Studies, Nasarawa State University, Keffi, Nigeria. 2 Department of Computer Engineering, Nile University of Nigeria, Abuja, Nigeria. 3 Department of Public and International ...
UroToday

Combined unsupervised-supervised classification of multiparametric PET/MRI data: application to prostate cancer

Multiparametric medical imaging data can be large and are often complex. Machine learning algorithms can assist in image interpretation when reliable training data exist. In most cases, however, ...