Research output: Contribution to journal › Article › peer-review
Intelligent Distributed Optical Fiber Pressure Sensing for Dental Bite-Force Analysis. / Katrenova, Zhanerke; Kussaiyn, Dauren; Alisherov, Shakhrizat et al.
In: Biosensors, Vol. 16, No. 9, 528, 21.09.2026.Research output: Contribution to journal › Article › peer-review
}
TY - JOUR
T1 - Intelligent Distributed Optical Fiber Pressure Sensing for Dental Bite-Force Analysis
AU - Katrenova, Zhanerke
AU - Kussaiyn, Dauren
AU - Alisherov, Shakhrizat
AU - Blanc, Wilfried
AU - Dostavalov, Alexandr
AU - Zollanvari, Amin
AU - Molardi, Carlo
N1 - Katrenova, Z.; Kussaiyn, D.; Alisherov, S.; Blanc, W.; Dostovalov, A.; Zollanvari, A.; Molardi, C. Intelligent Distributed Optical Fiber Pressure Sensing for Dental Bite-Force Analysis. Biosensors 2026, 16, 528. https://doi.org/10.3390/bios16090528 This research was funded by the Science Committee of the Ministry of Education and Science of the Republic of Kazakhstan (Grants No. AP25795995). This work was supported by the Russian Science Foundation under Grant 21-72-30024-P.
PY - 2026/9/21
Y1 - 2026/9/21
N2 - Measuring bite force is essential for assessing the masticatory system and diagnosing oral disease. Existing measurement devices have low spatial resolution and susceptibility to electromagnetic interference. This paper presents a machine learning (ML)-assisted distributed fiber optic sensing system based on Scattering Level Multiplexing (SLMux) for high-resolution bite force analysis. Enhanced backscattered data were acquired through optical backscattered reflectometry from 88 sensing points along the dental arch. Measured data were reconstructed into a two-dimensional map of bite force and analyzed through an ML pipeline. Sector classification across 4 regions and weight prediction were processed by an end-to-end fine-tuned ResNet-18 Convolutional Neural Network (CNN) and classical ML approaches. ResNet-18 is compared with Logistic Regression, Support Vector Machine (SVM), Random Forest, XGBoost (Extreme Gradient Boosting), Extra Trees, and k-Nearest Neighbors (kNN) trained on handcrafted features. On sector classification, Logistic Regression achieved the best performance (98.71% accuracy). On the weight prediction task, formulated as a 12-class problem, the end-to-end ResNet-18 CNN substantially outperformed all classical models, reaching 51.28% accuracy and a mean absolute error of 78 g, versus 124 g for the best classical model. A regression-based ResNet-18 variant was also trained on the wavelength-shift and weight data, resulting in a mean absolute error of 62.6 g. The results indicate that integrating ML with distributed fiber-optic sensing has the potential to enhance dental diagnostics and treatment planning.
AB - Measuring bite force is essential for assessing the masticatory system and diagnosing oral disease. Existing measurement devices have low spatial resolution and susceptibility to electromagnetic interference. This paper presents a machine learning (ML)-assisted distributed fiber optic sensing system based on Scattering Level Multiplexing (SLMux) for high-resolution bite force analysis. Enhanced backscattered data were acquired through optical backscattered reflectometry from 88 sensing points along the dental arch. Measured data were reconstructed into a two-dimensional map of bite force and analyzed through an ML pipeline. Sector classification across 4 regions and weight prediction were processed by an end-to-end fine-tuned ResNet-18 Convolutional Neural Network (CNN) and classical ML approaches. ResNet-18 is compared with Logistic Regression, Support Vector Machine (SVM), Random Forest, XGBoost (Extreme Gradient Boosting), Extra Trees, and k-Nearest Neighbors (kNN) trained on handcrafted features. On sector classification, Logistic Regression achieved the best performance (98.71% accuracy). On the weight prediction task, formulated as a 12-class problem, the end-to-end ResNet-18 CNN substantially outperformed all classical models, reaching 51.28% accuracy and a mean absolute error of 78 g, versus 124 g for the best classical model. A regression-based ResNet-18 variant was also trained on the wavelength-shift and weight data, resulting in a mean absolute error of 62.6 g. The results indicate that integrating ML with distributed fiber-optic sensing has the potential to enhance dental diagnostics and treatment planning.
KW - SLMux
KW - dentistry
KW - distributed sensing
KW - intelligent intraoral device
KW - machine learning
KW - mouthguard
KW - optical sensor
KW - оптический датчик
KW - распределенное измерение
KW - SLMux
KW - интеллектуальное внутриротовое устройство
KW - капа
KW - машинное обучение
KW - стоматология
UR - https://www.mendeley.com/catalogue/fc785049-f85d-3a5a-8ce3-88583368260b/
UR - https://www.scopus.com/pages/publications/105051615683
U2 - 10.3390/bios16090528
DO - 10.3390/bios16090528
M3 - Article
C2 - 42783195
VL - 16
JO - Biosensors
JF - Biosensors
SN - 2079-6374
IS - 9
M1 - 528
ER -
ID: 85470579