Research
-
Do Better Embeddings Lead to Better Judgments? A User Study of PCA and UMAP for Single-Cell Data
· pdf
Dimensionality-reduction visualizations are essential to modern biology, but the same data can yield different embeddings depending on algorithm and hyperparameter choices. Whether these choices influence analyst conclusions, and whether more faithful embeddings yield better conclusions, is unknown. We ran an exploratory within-subject study with 12 participants comparing PCA, UMAP set to default hyperparameters, and a tuned version of UMAP across clustering and trajectory tasks grounded in single-cell analysis workflows. Both UMAP conditions produced higher accuracy and confidence than PCA and were strongly preferred, and completion time did not differ significantly. However, tuning did not improve accuracy over default UMAP and higher confidence did not correspond to higher accuracy. These findings suggest that computational embedding fidelity and perceptual usefulness are related but distinct.
-
FlowNote: Making Bodily Experiences Visible in Music Production
· video
Creative work is deeply embodied, yet creative histories captured by most tools largely center on changes to external artifacts, leaving bodily experience difficult to revisit. We present FlowNote, a system that augments digital music-production histories with physiological data to support retrospective reflection. FlowNote synchronizes FL Studio interaction events, workspace recordings, and physiological signals captured by EmotiBit, then clusters intervals with similar physiological configurations and surfaces repeated occurrences as Pattern Suggestions. Users can inspect these suggestions or select moments themselves, revisit them in context, and annotate them in their own words. Saved annotations remain linked to the underlying session data for cross-session retrieval. FlowNote explores how bodily experiences can become part of creative histories while keeping interpretation in the user’s hands.