Search Results
Evolutionary design of explainable algorithms for biomedical image segmentation
An unresolved issue in contemporary biomedicine is the overwhelming number and diversity of complex images that require annotation, analysis and interpretation. Recent advances in Deep Learning have revolutionized the field of computer vision, creating algorithms that compete with human experts in image segmentation tasks. However, these frameworks require large human-annotated datasets for training and the resulting “black box” models are difficult to interpret. In this study, we introduce Kartezio, a modular Cartesian Genetic Programming-based computational strategy that generates fully transparent and easily interpretable image processing pipelines by iteratively assembling and parameterizing computer vision functions. The pipelines thus generated exhibit comparable precision to state-of-the-art Deep Learning approaches on instance segmentation tasks, while requiring drastically smaller training datasets. This Few-Shot Learning method confers tremendous flexibility, speed, and functionality to this approach. We then deploy Kartezio to solve a series of semantic and instance segmentation problems, and demonstrate its utility across diverse images ranging from multiplexed tissue histopathology images to high resolution microscopy images. While the flexibility, robustness and practical utility of Kartezio make this fully explicable evolutionary designer a potential game-changer in the field of biomedical image processing, Kartezio remains complementary and potentially auxiliary to mainstream Deep Learning approaches.
Decay radius of climate decision for solar panels in the city of Fresno, USA
To design incentives towards achieving climate mitigation targets, it is important to understand the mechanisms that affect individual climate decisions such as solar panel installation. It has been shown that peer effects are important in determining the uptake and spread of household photovoltaic installations. Due to coarse geographical data, it remains unclear whether this effect is generated through geographical proximity or within groups exhibiting similar characteristics. Here we show that geographical proximity is the most important predictor of solar panel implementation, and that peer effects diminish with distance. Using satellite imagery, we build a unique geo-located dataset for the city of Fresno to specify the importance of small distances. Employing machine learning techniques, we find the density of solar panels within the shortest measured radius of an address is the most important factor in determining the likelihood of that address having a solar panel. The importance of geographical proximity decreases with distance following an exponential curve with a decay radius of 210 meters. The dependence is slightly more pronounced in low-income groups. These findings support the model of distance-related social diffusion, and suggest priority should be given to seeding panels in areas where few exist.
Research data management in agricultural sciences in Germany: We are not yet where we want to be
To meet the future challenges and foster integrated and holistic research approaches in agricultural sciences, new and sustainable methods in research data management (RDM) are needed. The involvement of scientific users is a critical success factor for their development. We conducted an online survey in 2020 among different user groups in agricultural sciences about their RDM practices and needs. In total, the questionnaire contained 52 questions on information about produced and (re-)used data, data quality aspects, information about the use of standards, publication practices and legal aspects of agricultural research data, the current situation in RDM in regards to awareness, consulting and curricula as well as needs of the agricultural community in respect to future developments. We received 196 (partially) completed questionnaires from data providers, data users, infrastructure and information service providers. In addition to the diversity in the research data landscape of agricultural sciences in Germany, the study reveals challenges, deficits and uncertainties in handling research data in agricultural sciences standing in the way of access and efficient reuse of valuable research data. However, the study also suggests and discusses potential solutions to enhance data publications, facilitate and secure data re-use, ensure data quality and develop services (i.e. training, support and bundling services). Therefore, our research article provides the basis for the development of common RDM, future infrastructures and services needed to foster the cultural change in handling research data across agricultural sciences in Germany and beyond.