arXiv subjects

Josh Siegel

Publications and source records attributed to Josh Siegel.

2 recordsLinked to original sources

arXiv2026

Driving Accessibility: Shifting the Narrative & Design of Automated Vehicle Systems for Persons With Disabilities Through a Collaborative Scoring System

Automated vehicles present unique opportunities and challenges, with progress and adoption limited, in part, by policy and regulatory barriers. Underrepresented groups, including individuals with mobility impairments, sensory disabilities, and cognitive conditions, who may benefit most from automation, are often overlooked in crucial discussions on system design, implementation, and usability. Despite the high potential benefits of automated vehicles, the needs of Persons with Disabilities are frequently an afterthought, considered only in terms of secondary accommodations rather than foundational design elements. We aim to shift automated vehicle research and discourse away from this reactive model and toward a proactive and inclusive approach. We first present an overview of the current state of automated vehicle systems. Regarding their adoption, we examine social and technical barriers and advantages for Persons with Disabilities. We analyze existing regulations and policies concerning automated vehicles and Persons with Disabilities, identifying gaps that hinder accessibility. To address these deficiencies, we introduce a scoring rubric intended for use by manufacturers and vehicle designers. The rubric fosters direct collaboration throughout the design process, moving beyond an `afterthought` approach and towards intentional, inclusive innovation. This work was created by authors with varying degrees of personal experience within the realm of disability.

cs.CY↗

arXiv2024

Pareto Data Framework: Steps Towards Resource-Efficient Decision Making Using Minimum Viable Data (MVD)

This paper introduces the Pareto Data Framework, an approach for identifying and selecting the Minimum Viable Data (MVD) required for enabling machine learning applications on constrained platforms such as embedded systems, mobile devices, and Internet of Things (IoT) devices. We demonstrate that strategic data reduction can maintain high performance while significantly reducing bandwidth, energy, computation, and storage costs. The framework identifies Minimum Viable Data (MVD) to optimize efficiency across resource-constrained environments without sacrificing performance. It addresses common inefficient practices in an IoT application such as overprovisioning of sensors and overprecision, and oversampling of signals, proposing scalable solutions for optimal sensor selection, signal extraction and transmission, and data representation. An experimental methodology demonstrates effective acoustic data characterization after downsampling, quantization, and truncation to simulate reduced-fidelity sensors and network and storage constraints; results shows that performance can be maintained up to 95\% with sample rates reduced by 75\% and bit depths and clip length reduced by 50\% which translates into substantial cost and resource reduction. These findings have implications on the design and development of constrained systems. The paper also discusses broader implications of the framework, including the potential to democratize advanced AI technologies across IoT applications and sectors such as agriculture, transportation, and manufacturing to improve access and multiply the benefits of data-driven insights.

cs.LG↗