cd /news/artificial-intelligence/samsung-verizon-turn-mobile-network-… · home topics artificial-intelligence article
[ARTICLE · art-129886] src=koreaherald.com ↗ pub= topic=artificial-intelligence verified=true sentiment=↑ positive

Samsung, Verizon turn mobile network into AI crowd sensor

Samsung Electronics and Verizon completed what Samsung called the industry's first AI-based integrated sensing and communication (ISAC) field trial over a virtualized radio access network, deploying the technology at a major international soccer fan event in Dallas in July. A radio unit on Verizon's portable Cell-On-Wheels network captured signal variations from a commercial 5G device, and Samsung's edge-AI platform, Network in a Server (NIS), estimated crowd density and rendered near-real-time heat maps to help operators manage crowd movement and detect dangerous overcrowding. Samsung positioned ISAC as a key 6G component that adds sensing to communications infrastructure without separate cameras or dedicated sensing equipment.

by read2 min views1 publishedSep 15, 2026
Samsung, Verizon turn mobile network into AI crowd sensor
Image: Koreaherald (auto-discovered)

Samsung Electronics and Verizon have tested technology that turns mobile networks into real-time crowd sensors, demonstrating a potential 6G application in a live environment.

The companies deployed artificial intelligence-powered integrated sensing and communication, or ISAC, at a major international soccer fan event in Dallas in July. Samsung said it was the industry’s first AI-based ISAC field trial conducted over a virtualized radio access network.

ISAC is being developed as a key component of 6G, the next generation of mobile communications. The technology allows network infrastructure not only to transmit data, but also to detect movement and changes in its surroundings.

During the trial, a radio unit installed on Verizon’s portable Cell-On-Wheels network captured variations in signals transmitted by a commercial 5G device. Samsung’s edge-AI platform analyzed the data to estimate crowd density and visualize changes on a near-real-time heat map.

By identifying congested areas through wireless signals, the system could help event operators manage crowd movement, guide visitors toward less crowded facilities and deploy personnel and other resources more efficiently. Samsung said it could also detect potentially dangerous overcrowding and support public safety.

Because ISAC uses variations in existing wireless signals, it can add sensing capabilities to communications infrastructure without requiring separate cameras or dedicated sensing equipment.

Samsung carried out the trial using its commercial AI-powered virtualized radio access network and virtualized core network. These were integrated with an ISAC application through Network in a Server, the company’s edge-AI platform.

Known as NIS, the platform combines network functions with computing resources, including CPUs and graphics processing units, on a single server. This allows telecom operators to introduce new services without replacing existing network equipment or installing dedicated hardware.

“This successful ISAC trial underscores how Verizon’s early adoption of a software-driven, AI-powered vRAN laid a solid foundation and positioned the company at the forefront of the 6G journey,” said Seol Ji-yun, executive vice president and head of product strategy at Samsung Electronics’ Networks Business.

yejinlim@heraldcorp.com

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @samsung electronics 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/samsung-verizon-turn…] indexed:0 read:2min 2026-09-15 ·