Dataset Information

Interactive machine learning for soybean seed and seedling quality classification.

ABSTRACT: New computer vision solutions combined with artificial intelligence algorithms can help recognize patterns in biological images, reducing subjectivity and optimizing the analysis process. The aim of this study was to propose an approach based on interactive and traditional machine learning methods to classify soybean seeds and seedlings according to their appearance and physiological potential. In addition, we correlated the appearance of seeds to their physiological performance. Images of soybean seeds and seedlings were used to develop models using low-cost approaches and free-access software. The models developed showed high performance, with overall accuracy reaching 0.94 for seeds and seedling classification. The high precision of the models that were developed based on interactive and traditional machine learning demonstrated that the method can easily be used to classify soybean seeds according to their appearance, as well as to classify soybean seedling vigor quickly and non-subjectively. The appearance of soybean seeds is strongly correlated with their physiological performance.

SUBMITTER: de Medeiros AD

PROVIDER: S-EPMC7347887 | biostudies-literature | 2020 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Interactive machine learning for soybean seed and seedling quality classification.

de Medeiros André Dantas AD Capobiango Nayara Pereira NP da Silva José Maria JM da Silva Laércio Junio LJ da Silva Clíssia Barboza CB Dos Santos Dias Denise Cunha Fernandes DCF

Scientific reports 20200709 1

New computer vision solutions combined with artificial intelligence algorithms can help recognize patterns in biological images, reducing subjectivity and optimizing the analysis process. The aim of this study was to propose an approach based on interactive and traditional machine learning methods to classify soybean seeds and seedlings according to their appearance and physiological potential. In addition, we correlated the appearance of seeds to their physiological performance. Images of soybe ...[more]

PMID: 32647230

Similar Datasets

Project description:IntroductionEnvironmental conditions play a prime role in the growth and development of plant species, exerting a significant influence on their reproductive capacity. Soybean is sensitive to high temperatures during flowering and seed developmental stages. Little is known about the combined environmental effect of temperature and CO2 on seed yield and quality and its future generation.MethodsA study was conducted to examine the effect of temperature (22/14°C (low), 30/22°C (optimum), and 38/30°C (high)), and CO2 (420 ppm (ambient; aCO2) and 720 ppm (elevated; eCO2)) on seed yield, quality, and transgenerational seedling vigor traits of soybean cultivars (DS25-1 and DS31-243) using Soil-Plant-Atmospheric-Research facility.ResultsA significant temperature effect was recorded among yield and quality attributes. At high-temperature, the 100-seed weights of DS25-1 and DS31-243 declined by 40% and 24%, respectively, over the optimum temperature at aCO2. The harvest index of varieties reduced by 70% when exposed to high temperature under both aCO2 and eCO2, compared to the optimum temperature at aCO2. The seed oil (- 2%) and protein (8%) content altered when developed under high temperature under aCO2. Maximum sucrose (7.5%) and stachyose (3.8%) accumulation in seeds were observed when developed under low temperatures and eCO2. When the growing temperature increased from optimum to high, the seed oleic acids increased (63%), while linoleic and linolenic acids decreased (- 28% and - 43%, respectively). Significant temperature and CO2 effects were observed in progenies with the highest maximum seedling emergence (80%), lesser time to 50% emergence (5.5 days), and higher seedling vigor from parents grown at low-temperature treatment under eCO2.DiscussionExposure of plants to 38/30°C was detrimental to soybean seed yield, and eCO2 levels did not compensate for this yield loss. The high temperature during seed developmental stages altered the chemical composition of the seed, leading to an increased content of monounsaturated fatty acids. The findings suggest that parental stress can significantly impact the development of offspring, indicating that epigenetic regulation or memory repose may be at play.

Dataset Information

Interactive machine learning for soybean seed and seedling quality classification.

Publications

Interactive machine learning for soybean seed and seedling quality classification.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets