Supporting Scientific Research Through Machine and Deep Learning: Fluorescence Microscopy and Operational Intelligence Use Cases

Although the debate of what data science is has a long history and has not reached a complete consensus yet, Data Science can be summarized as the process of learning from data. Guided by the above vision, this thesis presents two independent data science projects developed in the scope of multidisciplinary applied research. The first part analyzes fluorescence microscopy images typically produced in life science experiments, where the objective is to count how many marked neuronal cells are present in each image. Aiming to automate the task for supporting research in the area, we propose a neural network architecture tuned specifically for this use case, cell ResUnet (c-ResUnet), and discuss the impact of alternative training strategies in overcoming particular challenges of our data. The approach provides good results in terms of both detection and counting, showing performance comparable to the interpretation of human operators. As a meaningful addition, we release the pre-trained model and the Fluorescent Neuronal Cells dataset collecting pixel-level annotations of where neuronal cells are located. In this way, we hope to help future research in the area and foster innovative methodologies for tackling similar problems. The second part deals with the problem of distributed data management in the context of LHC experiments, with a focus on supporting ATLAS operations concerning data transfer failures. In particular, we analyze error messages produced by failed transfers and propose a Machine Learning pipeline that leverages the word2vec language model and K-means clustering. This provides groups of similar errors that are presented to human operators as suggestions of potential issues to investigate. The approach is demonstrated on one full day of data, showing promising ability in understanding the message content and providing meaningful groupings, in line with previously reported incidents by human operators.

Advanced statistical models for the segregation, identification and measurement of coexisting sound sources

Long-term monitoring of acoustical environments is gaining popularity thanks to the relevant amount of scientific and engineering insights that it provides. The increasing interest is due to the constant growth of storage capacity and computational power to process large amounts of data. In this perspective, machine learning (ML) provides a broad family of data-driven statistical techniques to deal with large databases. Nowadays, the conventional praxis of sound level meter measurements limits the global description of a sound scene to an energetic point of view. The equivalent continuous level Leq represents the main metric to define an acoustic environment, indeed. Finer analyses involve the use of statistical levels. However, acoustic percentiles are based on temporal assumptions, which are not always reliable. A statistical approach, based on the study of the occurrences of sound pressure levels, would bring a different perspective to the analysis of long-term monitoring. Depicting a sound scene through the most probable sound pressure level, rather than portions of energy, brought more specific information about the activity carried out during the measurements. The statistical mode of the occurrences can capture typical behaviors of specific kinds of sound sources. The present work aims to propose an ML-based method to identify, separate and measure coexisting sound sources in real-world scenarios. It is based on long-term monitoring and is addressed to acousticians focused on the analysis of environmental noise in manifold contexts. The presented method is based on clustering analysis. Two algorithms, Gaussian Mixture Model and K-means clustering, represent the main core of a process to investigate different active spaces monitored through sound level meters. The procedure has been applied in two different contexts: university lecture halls and offices. The proposed method shows robust and reliable results in describing the acoustic scenario and it could represent an important analytical tool for acousticians.

Embryo transfer as a tool to disseminate k-casein BB genotype and improve milk clotting properties

Dairy industries are asked to be increasingly competitive and efficient. Despite the increasing trend in milk yield and protein content during the last decade genetic selection, milk coagulation ability has diminished and even if the absolute amount of cheese produced has increased, the relative cheese yield from a set amount of milk, has decreased. As casein content and variants, along with milk clotting properties (MCP) are determined to a large extent at DNA level, genetic selection and embryo transfer can provide efficacious tools to reverse this trend and achieve improvements. The aim of the proposed research was to determine how rapidly and to what extent milk coagulation properties could be improved by using embryo transfer (ET) as a tool to increase the frequency of k-casein BB genotype cattle and reducing A and E variants in an Italian Holstein herd with a low prevalence of the favourable genotype. In the effort to optimize superovulation protocols and results, synchronization of wave emergence was performed through manual transrectal ablation of the largest (dominant) ovarian follicle on days 7 or 8 of the cycle (estrus = day 0); different drugs and dosage for the superstimulation protocol were experimented trying to overcome the negative effects of stress and the perturbance of LH secretion in superovulated highly producing lactating cows and the use of SexedULTRA™ sex-sorted semen, for artificial insemination of superovulated cows was reported for the first time. The selection program carried out in this research, gave evidence and gathered empirical data of feasible genetic improvements in cheesemaking ability of milk by means of k-casein BB selection. In conclusion, in this project, selection of k-casein BB genotype markedly enhanced cheese-making properties of milk, providing an impetus to include milk coagulation traits in genetic selection and breeding programs for dairy cattle.