A5057585795- Digital Imaging for Blood Diseases
- Cell Image Analysis Techniques
- Smart Agriculture and AI
- Water Quality Monitoring Technologies
- Species Distribution and Climate Change
- Scientific Computing and Data Management
- AI in cancer detection
- Genetics, Bioinformatics, and Biomedical Research
- Radiomics and Machine Learning in Medical Imaging
- Big Data and Business Intelligence
- Research Data Management Practices
Biodiversity Research Institute
2021-2024
Tulane University
2021-2024
Metadata are key descriptors of research data, particularly for researchers seeking to apply machine learning (ML) the vast collections digitized specimens. Unfortunately, available metadata is often sparse and, at times, erroneous. Additionally, it prohibitively expensive address these limitations through traditional, manual means. This paper reports on that applies machine-driven approaches analyzing fish images and extracting various important features from them. The specimens being...
Abstract Image‐based machine learning tools are an ascendant ‘big data’ research avenue. Citizen science platforms, like iNaturalist, and museum‐led initiatives provide researchers with abundance of data knowledge to extract. These include extraction metadata, species identification, phenomic data. Ecological evolutionary biologists increasingly using complex, multi‐step processes on often techniques, built by others, that difficult reuse other members in a collaboration. We present...
Abstract Biodiversity image repositories are crucial sources of training data for machine learning approaches to biological research. Metadata, specifically metadata about object quality, is putatively an important prerequisite selecting sample subsets these experiments. This study demonstrates the importance quality a species classification experiment involving corpus 1935 fish specimen images which were annotated with 22 properties. A small subset high produced F1 accuracy 0.41 compared...
Abstract Metadata are key descriptors of research data, particularly for researchers seeking to apply machine learning (ML) the vast collections digitized specimens. Unfortunately, available metadata is often sparse and, at times, erroneous. Additionally, it prohibitively expensive address these limitations through traditional, manual means. This paper reports on that applies machine-driven approaches analyzing fish images and extracting various important features from them. The specimens...
Artificial Intelligence (AI) becomes more prevalent in data science as well areas of computational science. Commonly used classification methods AI can also be for unorganized databases, if a proper model is trained. Most the work done on image purposes such object detection and face recognition. If an detected from image, may to organize data. In this work, we try identify images Integrated Digitized Biocollections (iDigBio) dataset classify these generate metadata use AI-ready future. The...