Technology / WORLD

Glasses prototype uses facial motion-powered sensors

A Northwestern prototype classified six activities using glasses sensors powered by facial movement.

Reading sizeSources ↓Share story ↗
Conceptual illustration of technology, processors and connected information.Illustration
Symbolic illustration

Northwestern researchers described GlassTENG, a glasses prototype with three thin triboelectric sensors that harvest energy from facial movement. Signals recorded as 20 participants performed six activities were classified with machine learning at an overall accuracy of 93.8%.

The three sensors together used 4.1 microwatts; signals were streamed to a phone over Bluetooth. The findings come from a small laboratory study and do not establish clinical diagnostic accuracy or a finished all-day health product that needs no battery.

Data

Timeline

Research announcement

A Northwestern prototype classified six activities using glasses sensors powered by facial movement.

  1. · Occurred

    Glasses prototype uses facial motion-powered sensors

    A Northwestern prototype classified six activities using glasses sensors powered by facial movement.

Methodology

The event date follows the source institution’s announcement. Results are limited to the study or institutional report; prospective applications are not presented as completed products or clinical outcomes.

Updated:

Key figures

Source-reported indicators

A Northwestern prototype classified six activities using glasses sensors powered by facial movement.

Laboratory classification accuracy for six activities
93.8 percent
2026-10-12 · Observed
Laboratory-study participants
20 count
2026-10-12 · Observed
Methodology

These are source-announced grants or study indicators; the date is the report day. Grants are not expenditure; classification and chemistry findings retain the reported experiment/model scope.

Updated:

Structured coverage

Subjects and places

Subject proposals

Geographic references

Only source-provided geographic references are shown. Opening an external map is optional. Optional story maps use OpenStreetMap. Opening a map sends your IP address and this site’s address to the map provider; location data remains readable as text without loading the map.

  • United States · Place role: Coverage · Place type: Country or area · Location precision: Regional
    Evidence
Taxonomy version: IPTC Media Topics 2026-Q2

Continue reading

Technology

UTA studies deep learning to reduce radiation in cardiac CT angiography

UTA studies deep learning to reduce radiation in cardiac CT angiography. The University of Texas at Arlington’s three-year, $579,745 NIH project plans to combine deep learning and imaging physics to reconstruct multiphase coronary CT angiography at lower radiation doses.

University of Texas at Arlington1 min read
Data included
Technology

Lithium-ion clusters found in battery electrolytes

A Columbia study identified lithium-ion clusters in common battery electrolytes with experimental validation.

Columbia University Arts & Sciences1 min read
Data included