arXiv subjects

Rowan Hussein

Publications and source records attributed to Rowan Hussein.

4 recordsLinked to original sources

arXiv2026

Where the Cost Falls: A Deployment-Aware Adoption Order for Stability Enhancements to Cycle-Consistent Adversarial Networks

Teams that adopt cycle-consistent adversarial networks for unpaired image-to-image translation meet the same obstacles: adversarial training oscillates or collapses, cycle consistency preserves coarse layout while finer texture drifts, and a single discriminator judging global realism misses local artifacts. Four enhancements address these failures, and they are usually compared on output quality alone. We show that they also divide sharply by where their cost falls, and that this division, which follows from the architecture and not from any particular run, yields an adoption order for teams under a compute or latency budget. A Wasserstein objective with gradient penalty, a VGG19 perceptual loss on the cycle reconstruction, and multi-scale discriminators change training only, so a team can adopt or drop them without altering what ships. Self-attention alone persists into the deployed generator, with memory growing as the square of the feature-map size, which makes it the one component a resource-constrained team should defer. We integrate all four onto a lightly tuned baseline for horse-to-zebra translation, introduced one at a time on a fixed control and then combined, and for each we give the failure mode it targets and how it integrates. We document the collapse and reconstruction-artifact modes the baseline produced, report what visual inspection of saved samples showed for each variant, and report Fr\'echet Inception Distance and Kernel Inception Distance for the combined model. We specify the protocol still needed, covering the individual variants, perceptual similarity, and downstream segmentation, to rank these enhancements on measured evidence.

cs.CV↗

arXiv2026

FocusBuddy: Encouraging Healthy Desk-Work Habits by Caring for a Virtual Pet on a Water Bottle

People who study or work at a desk sit for long uninterrupted periods and drink less water than they intend to. Software reminders address both problems but are easy to dismiss and easy to resent. We present FocusBuddy, a proof-of-concept fabric case that wraps a standard water bottle and houses a microcontroller, environmental sensors, and a small display showing a virtual pet. The pet's condition mirrors the user's self-care: drinking water feeds the pet, standing up to move plays with it, and refilling an empty bottle cleans it. Twenty undergraduate students used FocusBuddy for two weeks during their regular coursework and completed a written interview. Self-reported water intake rose from a median of 3 to 4 cups per day, movement episodes rose from 2 to 4 per day, and interviews surfaced two tensions: that wellness prompts must respect focused work, and that pet neglect can convert a wellness prompt into a source of guilt. We contribute the prototype, first-deployment evidence of healthy-direction shifts in self-reported habits, and design implications for emotionally framed wellness devices.

cs.HC↗

arXiv2026

Open Source Is Not One Thing: A Typology of Open-Source Software Sub-Genres

Open source software (OSS) is not homogeneous. A project's purpose, governance, and funding shape how its community forms, who contributes, and how the software is maintained, yet empirical research often samples OSS broadly and reports findings as if they held for open source as a whole. We argue that OSS comprises distinguishable sub-genres, and that the sub-genre a study samples bounds how far its findings generalize. Using a light, multi-source review that screens 3,925 unique papers, we synthesize a typology of fourteen OSS sub-genres, from well-studied ones such as community-driven, company-backed, foundation-governed, research and scientific, and open source for social good (OSS4SG), to under-studied ones such as multi-company co-opetition, protestware, and open-source appropriate technology. We place the sub-genres in a framework that records each one's primary driver, governance, and funding, with its maturity in the literature and representative projects, and we present a research agenda whose central question is whether findings established on one sub-genre transfer to others. The contribution is the typology and the agenda rather than a complete census, and we mark the sub-genres whose empirical support is thin.

cs.CY↗

arXiv2026

Single-Channel EEG-Based Cognitive Load Assessment in Online Learning: A Hybrid Deep Learning Approach

Monitoring cognitive load during online learning could help instructors identify content that learners find difficult, but remote settings remove the visual cues that support this judgement in a classroom. We study whether a single-channel, consumer-grade EEG device (the NeuroSky MindWave Mobile 2) can distinguish easy from difficult educational-video content, using the publicly available dataset of Wang et al. [24] (ten learners, one excluded for excessive noise, leaving nine). We implement a hybrid CNN+LSTM+Attention model that combines the raw waveform with band-power features. In a within-subject setting, the model reaches up to 78.5% accuracy, compared with 55% for conventional feature-based classifiers; regularization (dropout and L2) closes the large gap between training and validation accuracy that we observe without it, keeping validation accuracy stable at roughly 68-73%. We are deliberately cautious about these numbers: with only nine subjects, within-subject evaluation is optimistic, and we argue that subject-independent evaluation -- in which no learner appears in both training and test data -- should be the standard for this task. To that end we release a reproducible evaluation pipeline. We frame the work as a feasibility study rather than a deployable system, and pair it with an open, notebook-based tool that records EEG, runs inference, and visualizes estimated cognitive load as a heatmap over the video timeline to help educators locate potentially challenging segments.

cs.LG↗