Tingfeng Li is a Researcher in the Optical Sensing & Solutions Department at NEC Laboratories America. She received her PhD in Computer Science from Rutgers University, her MS in Automation Engineering from Shanghai Jiao Tong University, and her BE in Automation Engineering from the University of Electronic Science and Technology of China. Her academic research has centered on representation learning, generative models, zero- and few-shot learning, and domain adaptation—areas that equip her with the tools to address complex sensing and signal interpretation challenges.
At NEC Labs, Tingfeng applies advanced machine learning and signal processing techniques to the development of next-generation distributed fiber-optic sensing (DFOS) systems. Her recent contributions include AI-driven road deformation detection using ambient noise–based distributed acoustic sensing (DAS), presented at OFC 2025, which demonstrated new possibilities for large-scale, non-intrusive infrastructure monitoring. She has also developed deep learning methods for intrusion and impulsive event detection, published in the IEEE Journal of Lightwave Technology, expanding the accuracy and reliability of DFOS in security applications. Her earlier work includes reinforcement learning–based localization methods for DFOS systems, presented at ICLR 2022, which explored adaptive approaches to improve event positioning in complex environments.
In addition to her publications, Tingfeng is a co-inventor on a patent for long-distance DFOS and WDM transmission using Raman amplification, a technology that enhances sensing range while maintaining high signal quality. By integrating expertise in AI, photonics, and large-scale sensing, Tingfeng’s work advances NEC Labs’ mission to create high-performance, scalable, and intelligent optical sensing systems with transformative potential for industries such as transportation, infrastructure management, and security.
NEC Laboratories America has formed two new departments from its Optical Networking and Sensing group. Optical Communications and Computing, led by Yue-Kai Huang, and Optical Sensing and Solutions, led by Yue Tian, will carry the lab’s photonics research into new territory.
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.
Real-world deployment requires sound event and acoustic scene classification systems to remain reliable in noisy, diverse environments on resource-constrained devices. Although contrastive language-audio pretraining (CLAP) models with Transformer-based audio encoders achieve strong zero-shot performance, their computational cost hinders deployment. In this paper, we propose Mix-CLAP, a computationally efficient, noise-aware CLAP model with knowledge-distilled audio encoders. Our method includes: (1) a two-stage knowledge distillation from teacher embeddings to two lightweight student encoders?one on clean audio, the other on noisy audio, and (2) adaptive inference that combines their embeddings together with a fusion parameter and minimizes the parameterized entropy at test time. Experiments show that Mix-CLAP with MobileNetV3-based audio encoders greatly improves computational efficiency, while achieving a comparable average accuracy of 52.58% to the Transformer-based CLAP model at 52.83% on the recorded ESC50 datasets with different devices including microphones and fiber-optic distributed acoustic sensors under diverse conditions, making it suitable for real-world, resource-constrained applications.
NEC Laboratories America celebrates Women’s History Month and International Women’s Day by recognizing the women researchers, engineers, and interns whose work in artificial intelligence, optical networking, cybersecurity, and data science is helping shape the future of technology.
We present methods and field trial results demonstrating an integrated distributed acoustic sensing (DAS) and distributed temperature sensing (DTS) system for manhole localization, condition diagnostics, and anomaly detection in pre-deployed telecommunication fiber networks. The proposed system leverages ambient environmental signals, such as vibrational patterns from traffic and day-night temperature fluctuations, and machine learning techniques for automated detection. By combining DAS waterfall traces with temperature measurements from DTS, we achieve improved classification accuracy. Experimental results from three real-world testbeds in Texas and New Jersey show a significant improvement in classification accuracyfrom 78.9% and 89.5% using DAS and DTS alone, respectively, to 94.7% via cross-referenced analysis. We propose a structured prediction formulation for manhole localization based on a U-Net architecture with a gated attention mechanism, where the label of each fiber location in the waterfall image is predicted using both its neighboring context and within-patch discriminative features. The method also supports cross-route generalization for manhole localization and enables condition diagnostics, identifying issues such as cable exposure and water ingress. These results highlight the potential for scalable deployment of fiber sensing solutions for real-time, continuous monitoring of telecom infrastructure.
Transformer-based methods have demonstrated strong potential in hyperspectral pansharpening by modeling long-range dependencies. However, their effectiveness is often limited by redundant token representations and a lack of multiscale feature modeling. Hyperspectral images exhibit intrinsic spectral priors (e.g., abundance sparsity) and spatial priors(e.g., non-local similarity), which are critical for accurate reconstruction. From a spectralspatial perspective, Vision Transformers (ViTs) face two major limitations: they struggle to preserve high-frequency componentssuch as material edges and texture transitions, and suffer from attention dispersion across redundant tokens. These issues stem from the global self-attention mechanism, which tends to dilute high-frequency signals and overlook localized details. To address these challenges, we propose the Token-wise High-frequency AugmentationTransformer (THAT), a novel framework designed to enhance hyperspectral pansharpening through improved high-frequency feature representation and token selection. Specifically, THAT introduces: (1) Pivotal Token Selective Attention (PTSA) to prioritize informative tokens and suppress redundancy; (2) a Multi-level Variance-aware Feed-forward Network (MVFN) to enhance high-frequency detail learning. Experiments on standard benchmarks show that THAT achieves state-of-the-art performance with improved reconstruction quality and efficiency.
Distributed fiber-optic sensing combined with machine learning enables continuous monitoring of telecom infrastructure. We employ generative modeling for event classification, supporting semi supervised learning, uncertainty calibration, and noise resilience. Our approach offers a scalable, data-efficient solution for real-world deployment in complex environments.
We demonstrate real-time fiber risk assessment and dynamic network routing in live metro networks using deployed DASs, satellite imagery, and large-scale AI, achieving the first significantreduction in fiber failures in four years
This study demonstrates an AI-driven method for detecting road deformations using Distributed Acoustic Sensing (DAS) over existing telecom fiber networks. Utilizingambient traffic noise, it enables real-time, long-term, and scalable monitoring for road safety.
Field trials of ambient noise-based automated methods for manhole localization and condition diagnostics using a real-time DAS/DTS integrated system were conducted. Crossreferencingmultiple sensing data resulted in a 94.7% detection rate and enhanced anomaly identification.