AI/Fiber-Optic Combo Poised To Improve Telecommunications

September 7, 2023 | NEC Labs America | News | Tags: fiber-optics, AI

Distributed fiber optics sense everything everywhere all at once. Paired with artificial intelligence and machine learning, it can act as an interface between the physical and digital worlds. Existing underground fiber-optic telecommunications cable networks that can be accessed through street manholes are helping a team at NEC Labs America improve wireless communications systems and the Internet of Things (IoT).

“Hundreds of millions of fiber-optic cables are already there for communications purposes,” says Shaobo Han, a researcher at NEC Labs America who focuses on the design and development of machine learning and signal-processing techniques for real-world sensing applications. “We’re turning it all into a ‘thinking’ device, using the same cable that’s already there.”

AI Fiber Optic Combo Poised To Improve Telecommunications

Using the existing cable networks, Han’s team can monitor and track the path of almost any object above ground without installing additional sensors or connecting to wireless networks. The fiber sensing system provides optical as well as acoustic information by using thin-film optoelectronics as an integrator that sends out optical power from lasers to the optical fiber. By analyzing its scattering, information about physical parameters such as acoustical aberration and temperatures can be found.

The story was based on a technical paper in Optica on Ambient Noise-Based Weakly Supervised Manhole Localization Methods Over Deployed Fiber Optic Networks.

Check out the full article in Laser Focus World which provides additional details on practical use cases for this technology, including tracking the movements of objects on city streets.

Read Our News Posts

Mix-CLAP Teaching Audio AI to Work in the Noisy Real World

Mix-CLAP: Teaching Audio AI to Work in the Noisy Real World

Mix-CLAP from NEC Laboratories America delivers near-Transformer accuracy for sound event classification at a fraction of the compute cost, using dual lightweight encoders and adaptive, noise-aware inference for real-world edge deployment.
Read more
How AI Can Transform the Way Companies Buy What They Need

How AI Can Transform the Way Companies Buy What They Need

Procurement teams lose time and money to inaccurate demand forecasts and manual supplier negotiations. A new framework from NEC Corporation and NEC Laboratories America combines automated negotiation with multimodal AI forecasting to optimize both sides of the procurement process.
Read more
Open SAT How We Taught AI to Search Satellite Images Like a Search Engine

Open SAT: How We Taught AI to Search Satellite Images Like a Search Engine

Satellite imagery is vast, high-resolution, and rich with information, but finding specific objects within it using natural language has remained a stubborn challenge. Open-SAT, developed by researchers at NEC Laboratories America and North South University, tackles this problem without retraining any models.
Read more
Training Small AI Models Without Blindly Trusting Big Teacher Models

Training Small AI Models Without Blindly Trusting Big Teacher Models

Machine learning is shifting from learning from data alone to learning from both data and teacher models. Beta-KD uses uncertainty-aware Bayesian weighting to train compact multimodal AI without blindly trusting every teacher signal.
Read more
How Rule-Driven Routing Makes Retrieval-Augmented Generation Smarter

How Rule-Driven Routing Makes Retrieval-Augmented Generation Smarter

Most retrieval-augmented generation systems stop at documents, ignoring the relational databases that power finance, healthcare, and research. Our researchers built a rule-driven framework that learns which source to query for each question, delivering better answers at lower computational cost.
Read more
Making Video AI Fast Enough for the Real World

Making Video AI Fast Enough for the Real World

State-of-the-art video models are accurate but too slow for live deployment. This work transfers their knowledge into causal streaming models that process video frames in real time, achieving 4x lower latency with competitive accuracy across action detection and pedestrian intent tasks.
Read more