Zhuocheng Jiang NEC Labs America

Zhuocheng Jiang

Research Assistant

Optical Networking & Sensing

Posts

Utility Pole Localization by Learning From Ambient Traces on Distributed Acoustic Sensing

Utility pole localization by learning from ambient traces on distributed acoustic sensing Utility pole detection and localization is the most fundamental application in aerial-optic cables using distributed acoustic sensing (DAS). The existing pole localization method recognizes the hammer knock signal on DAS traces by learning from knocking vibration patterns. However, it requires many efforts for data collection such as knocking every pole and manually labeling the poles’ locations, making this labor-intensive solution expensive, inefficient, and highly error prone. In this paper, we propose a pole localization solution by learning the ambient data collected from a DAS system, which are vibration patterns excited by random ambient events, such as wind and nearby traffic. In detail, we investigate a universal framework for learning representations of ambient data in the frequency domain by contrastive learning of the similarity of low and high-frequency series. A Gaussian-based data reweighting kernel is employed for eliminating the effect of the label noise. Experimental results demonstrate the proposed methods outperform the existing contrastive learning methods on the real-world DAS ambient dataset.

A Multi-sensor Feature Fusion Network Model for Bearings Grease Life Assessment in Accelerated Experiments

A Multi-sensor Feature Fusion Network Model for Bearings Grease Life Assessment in Accelerated Experiments This paper presents a multi-sensor feature fusion (MSFF) neural network comprised of two inception layer-type multiple channel feature fusion (MCFF) networks for both inner-sensor and cross-sensor feature fusion in conjunction with a deep residual neural network (ResNet) for accurate grease life assessment and bearings health monitoring. The single MCFF network is designed for low-level feature extraction and fusion of either vibration or acoustic emission signals at multi-scales. The concatenation of MCFF networks serves as a cross-sensor feature fusion layer to combine extracted features from both vibration and acoustic emission sources. A ResNet is developed for high-level feature extraction from the fused feature maps and prediction. Besides, to handle the large volume of collected data, original time-series data are transformed to the frequency domain with different sampling intervals and targeted ranges. The proposed MSFF network outperforms other models based on different fusion methods, fully connected network predictors and/or a single sensor source.

Field Trials of Vibration Detection, Localization and Classification over Deployed Telecom Fiber Cables

Field Trials of Vibration Detection, Localization and Classification over Deployed Telecom Fiber Cables We review sensing fusion results of integrating fiber sensing with video for machine-learning-based localization and classification of impulsive acoustic event detection. Classification accuracy >97% was achieved on aerial coils, and >99% using fiber-based signal enhancers.

A Deep Learning Framework for Detecting and Localizing Abnormal Pedestrian Behaviors at Grade Crossings

A Deep Learning Framework for Detecting and Localizing Abnormal Pedestrian Behaviors at Grade Crossings This paper presents a deep learning-based framework to detect and localize the pedestrians’ anomaly behaviors in videos captured at the grade crossing. A skeleton detection and tracking algorithm are employed to capture the key point trajectories of body movements of the pedestrians. A deep recurrent neural network is applied to learn the normal patterns of pedestrians’ movements using dynamics skeleton trajectories features. An anomaly behaviors detection and localization algorithm are developed by analyzing each pedestrian’s reconstructed trajectories. In the experiments, a video dataset involving normal pedestrian behaviors is established by collecting data at multiple grade crossing spots with different camera angles. Then the proposed framework is trained on the dataset to learn the regularity patterns of normal pedestrians and localize the anomaly behaviors during the testing phase. To the best of our knowledge, it is the first attempt to analyze pedestrians’ behavior at a grade crossing. The experimental results show that the proposed framework can detect and localize the anomaly behaviors, such as squatting down, lingering, and other behaviors that may cause safety issues at the grade crossing. Our study also points out the direction for further improvement of the present development to meet the need for real-world applications.

Rain Intensity Detection and Classification with Pre-existing Telecom Fiber Cables

Rain Intensity Detection and Classification with Pre-existing Telecom Fiber Cables For the first time, we demonstrate detection and classification of rain intensity using Distributed Acoustic Sensing (DAS). An artificial neural network was applied for rain intensity classification and high precision of over 96% was achieved.

Field Tests of Impulsive Acoustic Event Detection, Localization, and Classification Over Telecom Fiber Networks

Field Tests of Impulsive Acoustic Event Detection, Localization, and Classification Over Telecom Fiber Networks We report distributed-fiber-optic-sensing results on impulsive acoustic events localization/classification over telecom networks. A deep-learning-based model was trained to classify starter-gun and fireworks signatures with high accuracy of > 99% using fiber-based-signal-enhancer and >97% using aerial coils.