Analytical work across data science, statistical modeling, machine learning, graph analysis, and scientific computing. Much of this work involves transforming complex biological and tabular data into interpretable structures and computational outputs.
Large-scale computational analysis of Drosophila connectome data: neuron skeleton processing, synaptic adjacency matrices, connectivity graphs, clustering, and feature extraction using Python and NetworkX.
Statistical analysis of experimental data including hypothesis testing, ANOVA, regression modeling, simulations, and bootstrapping to evaluate patterns in biological and tabular datasets.
Machine learning and deep learning for classification and prediction tasks, including WiFi signal fingerprinting for GPS-supervised geopositioning using TensorFlow/Keras and scikit-learn.
Graph-based analysis of biological structures using NetworkX: tree representations, adjacency matrices, graph features, clustering, and neuron skeleton analysis for connectome research.