Fibre-optic based particle sensing via deep learning

Grant-Jacob, James; Jain, Saurabh; Xie, Yunhui; MacKay, Benita; McDonnell, Michael; Praeger, Matthew; Loxham, Matthew; Richardson, David J.; Eason, R.W.; Mills, B.

doi:10.1088/2515-7647/ab437b

Cited by 17 publications

(7 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors in [123] used CNN to demonstrate the capability for the identification of specific species of pollen from the backscattered light. Thirty-core optical fiber were used to collect the backscattered light.…”

Section: Cnn-based Applicationsmentioning

confidence: 99%

Deep Learning for Optical Sensor Applications: An Insight Review

Al‐Ashwal¹,

Soufy²,

Hamza³

et al. 2023

Preprint

View full text Add to dashboard Cite

Over the past decade, Deep Learning (DL) had been applied in a large number of optical sensors’ applications. DL algorithms can improve the accuracy and reduce the noise level in optical sensors. Optical sensors are considered as promise technology for the modern intelligent sensing platforms. These sensors are widely used to process monitoring, quality prediction, pollution, defense, security and many other applications. However, they suffer major challenges such as the large generated data and low processing speed for that data and moreover the much cost of these sensor. These challenges can be mitigated by integrating deep learning system with the optical sensor technologies. This paper presents recent studies that integrate DL algorithms with optical sensors applications. This paper also highlights several of DL algorithms directions that promise a considerable impact on use for optical sensor applications. Moreover, this study provides new directions for the future related research development.

show abstract

Section: Cnn-based Applicationsmentioning

confidence: 99%

Deep Learning for Optical Sensor Applications: An Insight Review

Al‐Ashwal¹,

Soufy²,

Hamza³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Several researchers proposed various pattern recognition algorithms, such as Jiao et al, [108] who demonstrated a remote fiber coupled method for classifying particles via analysis of their backscattered light. The illumination source is a fiber-coupled laser diode and backscattered light is collected via a 30-core fiber.…”

Section: Anomaly Detection and Event Classification For Pointwise Fosmentioning

confidence: 99%

Recent Advances in Machine Learning for Fiber Optic Sensor Applications

Venketeswaran

Lalam

Wuenschell

et al. 2021

Advanced Intelligent Systems

111

View full text Add to dashboard Cite

The latest digital revolution involves the rise of smart devices composed of sensor hardware and artificial intelligence (AI) software for performing intelligent tasks. Smart sensors have become ubiquitous in our lives with varied applications ranging from voice-enabled home devices (Google Home, Alexa, etc.) to the Industrial Internet of Things (IIoT). This revolution has been fueled by 1) miniaturization of sensing hardware, 2) easy access to cloud and high-performance computing, 3) development of big data storage and analytics technologies, and 4) the latest breakthroughs in machine learning (ML) and AI technologies. The emergence of AI since 2012 and its major breakthroughs can be attributed to the research and development (R&D) in deep learning, a subfield of ML that uses biologically inspired neural networks to perform learning tasks. [1] The performance of conventional ML algorithms depends on the individual selection of specific features, while deep neural networks (DNN) automatically generate features as part of the learning process. Deep learningbased AI technologies are increasingly showing performance

show abstract

“…The deep learning model even predicted the distance the particle was from the end of the fiber through the intensity of scattered light. 7 Hollow core fibers were utilized as an unconventional optical cavity with a confined particle, for sensing fluctuations in the environment for quantities such as temperature or electric field. 8,9 In these instances, the incorporation of freely diffusing particles in the hollow cores has no interference on the monitoring and measurement process.…”

Section: Introduction: Optical Fiber Sensorsmentioning

confidence: 99%

Analyzing the behavior of biological component aggregation in optical fibers

Wynne

2023

Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2023

View full text Add to dashboard Cite

Optical fibers are reliable sensors and can provide accurate measurements in microfluidic systems. Photonic crystal fibers are a variation of the conventional optical fiber, where the difference is the distribution of an array of hollow cores along the length of the fiber. These types of fibers are used as sensors in microfluidic cell cultures and offer the unique accessibility of using the hollow cores as a transport mechanism for biological samples. This type of system can benefit the biomedical and healthcare industry by reducing unnecessary manufacturing costs, while modeling complicated systems such as the interaction between the blood and cancer cells in the circulatory system. This manuscript briefly reviews recent literature on optical fiber sensors exploiting the hollow core technology of these optical fibers in real-time monitoring applications while transporting biological compounds. The significance of using biological samples such as human or animal cells integrated with optical fiber sensors can enhance research and clinical testing in modern industry. The remaining portion of the manuscript is an analysis on an experimental system designed to transport a cell culture through a photonic crystal fiber that is connecting two microfluidic devices. The internal diameter of the hollow core of the fiber is 22 µm, and the diameter of the cell is approximately 15 µm, indicating no extreme limitations in transport. Spectroscopic data confirms the presence of a cellular aggregate impeding the flow rate either within the hollow cores of the fiber, or the region transitioning between the microfluidic device and the fiber. The analysis consists of determining the mechanisms that contribute to cellular aggregation in microfluidic theory, to accurately model this phenomenon.The introduction of the analysis examines the experimental configuration with a class of dimensionless quantities that are often used in microfluidic theory. The Reynold's, Peclet, capillary, Knudsen number, and Transcapillary conductance are dimensionless quantities used in recent literature in describing microfluidic transport. An analysis on these quantities led to the Lattice Boltzmann method for modeling the behavior in the experimental configuration. The Lattice Boltzmann method is a method in computational fluid dynamics that operates by imposing a discrete lattice to stimulate the fluid environment. The system evolves through collision and streaming processes, and along with Brownian dynamics, dictates the behavior of deformable particle mechanics. The combination of these two models is applied to the problem cellular aggregation in the experimental configuration. A simulation depicting the scenario of cellular aggregation in the hollow core fiber under conditions of Poiseuille flow with pressure differential of ∆p = 10 2 P a, fluid velocity U = 10 3 µm/sec, with a particle diameter to constriction diameter of 10/15 measured at the microscale (10 −6 m). This is in comparison with conditions the experimental system operated at under a pr...

show abstract

Fibre-optic based particle sensing via deep learning

Cited by 17 publications

References 63 publications

Deep Learning for Optical Sensor Applications: An Insight Review

Deep Learning for Optical Sensor Applications: An Insight Review

Recent Advances in Machine Learning for Fiber Optic Sensor Applications

Analyzing the behavior of biological component aggregation in optical fibers

Contact Info

Product

Resources

About