New statistical features for the design of fiber optic statistical mode sensors

Efendioglu, Hasan Seckin; Yıldırım, Tülay; Toker, O.; Fidanboylu, Kemal

doi:10.1016/j.yofte.2013.02.009

Cited by 15 publications

(7 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A good sensor required a linearity correlation between variable control and variable response [10]. As implied by equation (1) and (2), the changes of transmission coefficient for the sensor should be linear to load.…”

Section: Resultsmentioning

confidence: 99%

Design of micro bending deformer for optical fiber weight sensor

Ula

Hanto

Waluyo

et al. 2017

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

idAbstract. The road damage due to excessive load is one of the causes of accidents on the road. A device to measure weight of the passing vehicles needs to be planted in the road structure. Thus, a weight sensor for the passing vehicles is required. In this study, we designed a weight sensor for a static load based on a power loss due to a micro bending on the optical fiber flanked on a board. The following main components are used i.e. LED 1310 nm as a light source, a multimode fiber optic as a transmission media and a power meter for measuring power loss. This works focuses on obtaining a suitable deformer design for weight sensor. Experimental results show that deformer design with 1.5 mm single side has level of accuracy as 4.32% while the design with 1.5 mm double side has level of accuracy as 98.77%. Increasing deformer length to 2.5 mm gives 71.18% level of accuracy for single side, and 76.94% level of accuracy for double side. Micro bending design with 1.5 mm double side has a high sensitivity and it is also capable of measuring load up to 100 kg. The sensor designed has been tested for measuring the weight of motor cycle, and it can be upgraded for measuring heavy vehicles.

show abstract

Section: Resultsmentioning

confidence: 99%

Design of micro bending deformer for optical fiber weight sensor

Ula

Hanto

Waluyo

et al. 2017

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

“…The variations in I(x,y) of the specklegram are due to the perturbation-induced phase change such as the applied weight on the MMF 18 . The applied weight on the MMF alters the optical path length of each propagating mode of the fiber, thereby causing the change in the intensity distribution of the specklegram.…”

Section: Basic Conceptsmentioning

confidence: 99%

“…This indicates that the specklegrams are capable of encapsulating the fiber status at different applied weights. Due to the stochastic nature of intensity changes in specklegrams, these specklegram images are analyzed by statistical features 18 or by employing machine and deep learning methodologies 24 , 24 , 25 , 28 – 35 …”

Section: Basic Conceptsmentioning

confidence: 99%

“…Specifically, the specklegram undergoes spatial reconfiguration by the movement of certain bright regions (speckles), changes in their shapes, and intensity levels 10 . This capability of the specklegram to encode the perturbation status of the fiber has been previously employed as fiber specklegram sensors (FSSs) 10 – 18 for varied purposes. FSSs offer advantages, such as ease of designing, light coupling, and cost-effectiveness, in comparison with other sensing techniques 19 …”

Section: Introductionmentioning

confidence: 99%

“…This limitation was previously addressed in Ref. 18, in which the authors applied transverse weights (in kg) to the MMF and correlated the new statistical features, namely moments estimated from fiber specklegrams with the weights applied. Also there has been recent rapid progress in sensing and different measurement systems based on plastic optical fibers (POFs) 23 …”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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