Neural Network Based Perturbation-Location Fiber Specklegram Sensing System Towards Applications With Limited Number of Training Samples

Wei, Menglong; Tang, Gang; Liu, Jie; Zhu, Luyang; Liu, Junyi; Cong, Huan; Zhang, Jingxing; Shen, Lei; Yu, Siyuan

doi:10.1109/jlt.2021.3098345

Cited by 33 publications

(12 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It was shown that DNNs were able to reconstruct the input information sent through the fiber when the DNN was given examples of input-output for all positional configurations. Other lines of work use DNNs to characterize perturbed MMFs for sensing applications such as temperature [215] and mechanical sensors [216,217]. In addition to sensing in the linear domain, DNNs have started to be used for the characterization of nonlinear dynamics in MMFs.…”

Section: Current and Future Challengesmentioning

confidence: 99%

Roadmap on wavefront shaping and deep imaging in complex media

et al. 2022

View full text Add to dashboard Cite

The last decade has seen the development of a wide set of tools, such as wavefront shaping, computational or fundamental methods, that allow to understand and control light propagation in a complex medium, such as biological tissues or multimode fibers. A vibrant and diverse community is now working on this field, that has revolutionized the prospect of diffraction-limited imaging at depth in tissues. This roadmap highlights several key aspects of this fast developing field, and some of the challenges and opportunities ahead.

show abstract

Section: Current and Future Challengesmentioning

confidence: 99%

Roadmap on wavefront shaping and deep imaging in complex media

et al. 2022

View full text Add to dashboard Cite

show abstract

“… 30 , 31 The complex and sensitive information provided by the specklegram output of an MMF is a topic of recent interest, particularly when combined with machine learning approaches, where it has been shown that spatial information can be extracted without requiring time or frequency domain interrogation schemes 32 , 33 and can be used to extract measurement signals well below noise levels. 34 While it is possible to extract spatial (multipoint/distributed) sensing information from MMFs using machine learning, this approach fundamentally relies on mode coupling and requires pretraining, with examples including 3000 samples in the case of strong mode coupling in a ring core fiber 33 and ten thousand or more samples for conventional MMF. 32 , 33 These approaches have so far only demonstrated the classification of a perturbation location without providing quantitative information on the degree of perturbation.…”

Section: Introductionmentioning

confidence: 99%

“… 34 While it is possible to extract spatial (multipoint/distributed) sensing information from MMFs using machine learning, this approach fundamentally relies on mode coupling and requires pretraining, with examples including 3000 samples in the case of strong mode coupling in a ring core fiber 33 and ten thousand or more samples for conventional MMF. 32 , 33 These approaches have so far only demonstrated the classification of a perturbation location without providing quantitative information on the degree of perturbation.…”

Section: Introductionmentioning

confidence: 99%

Multimode optical fiber specklegram smart bed sensor array

et al. 2022

View full text Add to dashboard Cite

. Significance: Monitoring the movement and vital signs of patients in hospitals and other healthcare environments is a significant burden on healthcare staff. Early warning systems using smart bed sensors hold promise to relieve this burden and improve patient outcomes. We propose a scalable and cost-effective optical fiber sensor array that can be embedded into a mattress to detect movement, both sensitively and spatially. Aim: Proof-of-concept demonstration that a multimode optical fiber (MMF) specklegram sensor array can be used to detect and image movement on a bed. Approach: Seven MMFs are attached to the upper surface of a mattress such that they cross in a array. The specklegram output is monitored using a single laser and single camera and movement on the fibers is monitored by calculating a rolling zero-normalized cross-correlation. A image is formed by comparing the signal at each crossing point between two fibers. Results: The MMF sensor array can detect and image movement on a bed, including getting on and off the bed, rolling on the bed, and breathing. Conclusions: The sensor array shows a high sensitivity to movement, which can be used for monitoring physiological parameters and patient movement for potential applications in healthcare settings.

show abstract

“…32,33 Furthermore, a paradigm shift has been observed toward the development of neural networks-assisted FSSs in the recent past for various purposes. [34][35][36][37][38][39][40][41][42][43] Rodríguez-Cuevas et al proposed a convolutional neural network (CNN) model with a classification accuracy of 99% for three locations and 79% for ten locations of vibrations. 34 Razmyar and Mostafavi 35 estimated and classified the deflection direction of the MMF and achieved 96% classification accuracy.…”

Section: Introductionmentioning

confidence: 99%

“…Furthermore, a paradigm shift has been observed toward the development of neural networks-assisted FSSs in the recent past for various purposes 34 – 43 Rodríguez-Cuevas et al. proposed a convolutional neural network (CNN) model with a classification accuracy of 99% for three locations and 79% for ten locations of vibrations 34 .…”

Section: Introductionmentioning

confidence: 99%

Analyzing specklegrams of plastic optical fiber using convolutional neural network for weight recognition

et al. 2022

View full text Add to dashboard Cite

A weight recognition scheme is proposed based on the analysis of plastic optical fiber (POF) specklegrams. A simple experiment is performed for data acquisition comprising specklegram images corresponding to different external applied weights ranging from 0 to 3 kg in steps of 0.5 kg on the POF. These specklegram images are further split into training, validation, and test datasets for employment in the convolutional neural network (CNN). The model is trained and validated with a sufficient number of epochs (iterations) to obtain optimal training and validation accuracies (>90%); it is then used for recognizing (classifying) the unseen test dataset images. A user-defined CNN model is optimized using four different optimizers: Adam, AdaMax, Nadam, and RMSProp. The recognition (or test) accuracy of these optimizers is compared. The Nadam optimizer has the highest recognition accuracy of 93.1% for increasing weights and 91.9% for decreasing weights. Furthermore, we investigate the impact of two parameters, namely temperature effect and information loss of specklegrams, on the model's weight recognition accuracy. The temperature effect is studied for finite temperatures ranging from 29°C to 35°C with 3°C step fluctuations around the ambient temperature of 25°C. We find that the maximum deviation in recognition accuracy is about 1.2%. To quantify the information content (speckles) in each blocked specklegram, Shannon entropy (SE) is estimated. These images are then used in our existing CNN model with the Nadam optimizer to evaluate recognition performance with blocking. With increasing blocking, we observe a decrease in SE and recognition accuracy. This analysis suggests that, even with information loss in the specklegrams at ≤20% blocking, a good representation of weights with high recognition accuracy (>80%) can be obtained. The presence of a small physical obstacle in front of the imaging system can cause information loss in specklegrams to manifest in practical scenarios.

show abstract

Neural Network Based Perturbation-Location Fiber Specklegram Sensing System Towards Applications With Limited Number of Training Samples

Cited by 33 publications

References 27 publications

Roadmap on wavefront shaping and deep imaging in complex media

Roadmap on wavefront shaping and deep imaging in complex media

Multimode optical fiber specklegram smart bed sensor array

Analyzing specklegrams of plastic optical fiber using convolutional neural network for weight recognition

Contact Info

Product

Resources

About