CONNIE experiment installed 12 charge- coupled devices (CCDs) sensors near the Angra II nuclear reactor in Angra dos Reis (Brazil) aiming to detect low energy antineutrinos produced in the core of the reactor. For two years, these sensors recorded particle images catching mainly muons and other particles such as electrons and alphas that will be considered as external radioactive background that must be removed. The images were created from the data taken every 3 hours, generating in this way a vast catalog of detected events on each CCD. In this work we propose an instance segmentation and a classification model in order to study the variation of the muon rate produced by those particles. For this purpose we developed two models: a Convolutional Neural Network (CNN) for event classification, and an instance segmentation model for identifying overlapped events. The classification model demonstrated exceptional efficacy, achieving an impressive accuracy of 0.8. Furthermore, precision and recall values of 0.85 and 0.92, respectively, were achieved for the particles of interest. Within the domain of bounding box detection, our model exhibited remarkable recall and precision rates of 71 % and 69 %, respectively, further underlining its adeptness in accurately localizing objects. Our results not only illuminate the potential of these models but also contribute to a deeper understanding of muon rate variations within the experimental context of the CONNIE setup. Index Terms- muon, deeplarning, yolo V8, yolo, CONNIE, neutrine.

Effective computational tools for shape analysis are needed in many areas of science and engineering. We address this and propose a new fast iterative algorithm to compute the elastic geodesic distance between shapes of closed planar curves. The original algorithm for this has cubic time complexity with respect to the number of nodes per curve. Hence it is not suitable for large shape data sets. We aim for large-scale shape analysis and thus propose an iterative algorithm based on the original one but with quadratic time complexity. In practice, we observe subquadratic, almost linear running times, and that our algorithm scales very well with large numbers of nodes. The key to our algorithm is the decoupling of the optimization for the starting point and rotation from that of the reparametrization, and the development of fast dynamic programming and iterative nonlinear constrained optimization algorithms that work in tandem to compute optimal reparametrizations fast.

Image cytometry has emerged as a valuable in vitro screening tool and advances in automated microscopy have made it possible to readily analyze large cellular populations of image data. The purpose of this paper is to illustrate the viability of using cell shape to test equality of cell populations based on image data. Shape space theory is reviewed, from which differences between shapes can be quantified in terms of geodesic distance. Several multivariate nonparametric statistical hypothesis tests are adapted to test equality of cell populations. It is illustrated that geodesic distance can be a better feature than cell spread area and roundness in distinguishing between cell populations. Tests based on geodesic distance are able to detect natural perturbations of cells, whereas Kolmogorov-Smirnov tests based on area and roundness are not.

Cell segmentation is a critical step in the analysis pipeline for most imaging cytometry experiments and evaluating the performance of segmentation algorithms is important for aiding the selection of segmentation algorithms. Four popular algorithms are evaluated based on their cell segmentation performance. Because segmentation involves the classification of pixels belonging to regions within the cell or belonging to background, these algorithms are evaluated based on their total misclassification error. Misclassification error is particularly relevant in the analysis of quantitative descriptors of cell morphology involving pixel counts, such as projected area, aspect ratio and diameter. Since the cumulative distribution function captures completely the stochastic properties of a population of misclassification errors it is used to compare segmentation performance.