Louis Rosenberg

Dr. Louis Rosenberg

orcid

Research Focus & Metrics

Academic Career Length

35Years (1992-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications

18 November 2019 in npj Digital Medicine
Verified
Journal Article
Open access
PDF file
BPBhavik N. Patel
Bhavik N. Patel
Louis RosenbergLouis Rosenberg
Louis Rosenberg
GWGregg Willcox
Gregg Willcox
DBDavid Baltaxe
David Baltaxe
MLMimi Lyons
Mimi Lyons
MLMatthew P. Lungren
Matthew P. Lungren
Human-in-the-loop (HITL) AI may enable an ideal symbiosis of human experts and AI models, harnessing the advantages of both while at the same time overcoming their respective limitations. The purpose of this study was to investigate a novel collective intelligence technology designed to amplify the diagnostic accuracy of networked human groups by forming real-time systems modeled on biological swarms. Using small groups of radiologists, the swarm-based technology was applied to the diagnosis of pneumonia on chest radiographs and compared against human experts alone, as well as two state-of-the-art deep learning AI models. Our work demonstrates that both the swarm-based technology and deep-learning technology achieved superior diagnostic accuracy than the human experts alone. Our work further demonstrates that when used in combination, the swarm-based technology and deep-learning technology outperformed either method alone. The superior diagnostic accuracy of the combined HITL AI solution compared to radiologists and AI alone has broad implications for the surging clinical AI deployment and implementation strategies in future practice.

25 March 2022
Verified
Conference Paper
Open access
Louis RosenbergLouis Rosenberg
Louis Rosenberg
Over the last thirty years, virtual reality (VR) and augmented reality (AR) technologies have steadily advanced, enabling high-fidelity experiences at consumer prices. Over the same period, network speeds have risen dramatically. Combined, such advancements have increased the prospects of widespread adoption of VR and AR worlds. Recently branded “the metaverse” by Facebook (now Meta), major corporations have begun investing billions to deploy immersive worlds aimed at mainstream activities from socializing and shopping to education and business. With the likelihood rising that metaverse platforms greatly impact society over the next decade, it is prudent to consider the societal risks and plan for meaningful regulation. The dangers of the metaverse are outlined herein along with proposals for regulation.

1 January 1993
Verified
Conference Paper
Closed access
Louis RosenbergLouis Rosenberg
Louis Rosenberg
BAB.D. Adelstein
B.D. Adelstein
The analysis and construction of virtual haptic surfaces are considered from a perceptual point of view rather than from the dynamics and controls approach of prior work. The authors developed a perceptual decomposition of surface contact sensation by examining three qualities associated with the different stages of interaction with a haptic wall simulation. These qualities are the crispness of initial contact, the hardness of surface rigidity, and the cleanness of final release from the virtual wall's surface. These qualities, plus an overall rating of wall quality, were employed consistently by seven subjects to evaluate a set of six simple haptic wall simulations. Three of the wall models consisted of single linear springs; the remainder, single viscous dampers. Highest rankings of subjective hardness were associated with the spring models; damper models received the highest crispness rankings. Subjects favored the simple spring models as having, overall, the more wall-like perceptual character.<>

1 November 2018
Verified
Conference Paper
Closed access
Louis RosenbergLouis Rosenberg
Louis Rosenberg
MLMatthew Lungren
Matthew Lungren
SHSafwan Halabi
Safwan Halabi
GWGregg Willcox
Gregg Willcox
DBDavid Baltaxe
David Baltaxe
MLMimi Lyons
Mimi Lyons
Swarm Intelligence (SI) is a biological phenomenon in which groups of organisms amplify their combined brainpower by forming real-time systems. It has been studied for decades in fish schools, bird flocks, and bee swarms. Recent advances in networking and AI technologies have enabled distributed human groups to form closed-loop systems modeled after natural swarms. The process is referred to as Artificial Swarm Intelligence (ASI) and has been shown to significantly amplify group performance. The present research applies ASI technology to the field of medicine, exploring if small groups of networked radiologists can improve their diagnostic accuracy when reviewing chest X-rays for the presence of pneumonia. Performance data was collected for individual radiologists generating diagnoses alone, as well as for small groups of radiologists working together to generate diagnoses as a real-time ASI system. Diagnoses were also collected from a state-of-the-art deep learning system (CheXNet) developed at Stanford University. Results showed that small groups of networked radiologists, when working as a real-time ASI system, were significantly more accurate than the individual radiologists on their own, reducing diagnostic errors by 33%. Results also showed that small groups of networked radiologists, when working as an ASI system, were significantly more accurate (22%) than a state-of-the-art deep learning system (CheXNet).