Deep Neural Network (DNN) assisted activity monitoring algorithms are investigated, aiming to discriminate three activity states, including presence without movement, nobody in bed, and presence with movement. The signal is collected from a fiber-based Mach-Zehnder Interferometer (MZI) sensor, which is placed under a 20-cm thick mattress. When people are lying on the mattress, cardiopulmonary activities will lead to the change of the phase difference of the MZI optical fiber sensor. In this paper, three kinds of DNNs are developed to investigate the classification performance, including feedforward neural network (FNN), convolutional neural network (CNN), and long short-term memory network (LSTM). The accuracy of FNN, CNN and LSTM is 95.14%, 99.01%, and 99.37% within one second, respectively. Moreover, LSTM has low time and space complexity and better performance. The algorithms constructed can obtain high accuracy and robustness with low computational overhead and storage consumption and have broad application prospects. What’s more, the MZI optical fiber sensor has many advantages such as low cost and anti-electromagnetic interference, which means that the system can be popular in medical treatment and households.
Real-time SAHS events detection system during sleep is proposed and investigated based on contact-free Mach-Zehnder Interferometer ballistocardiograph (MZI-BCG) senor, which is placed under the mattress. The breath activity influences the optical phase difference of the MZI which is demodulated with 3*3 optical coupler. In this paper, three SAHS events are successfully detected, including OSAS (Obstructive sleep apnea syndrome), CSAS (Central sleep apnea syndrome) and MSAS (Mixed sleep apnea syndrome). The proposed system is simple, cost-effective and non-invasive, which has great potential application in home monitoring
A temperature independent microdisplacement sensor based on microbending-induced core-cladding mode coupling loss
via a polarization maintaining photonic-crystal-fiber (PMPCF) is presented. By core-offsetting one splice joint between
the single mode fiber (SMF) and PMPCF in an SMF-PMPCF-SMF structure, one core-cladding modal interferometer
can be constructed. By packaging the interferometer in a carbon-fiber-composite based simple-supported beam,
temperature independent microdisplacement measurement can be achieved by monitoring the extinction ratio variation
of the interference spectrum. This type of sensor exhibits the advantages of temperature independent, high sensitivity and
simple structure.
A novel lateral force sensor based on a core-offset multimode fiber interferometer with intensity-based interrogation
technique is reported. An offset between the cores of the single-mode fiber and multimode fiber is made to produce high
extinction ratio. When a lateral force is applied to a short section of the multimode fiber, the extinction ratio decreases
with the interference phase almost unchanged. In addition to serving as a sensing head, the multimode fiber can also act
as a filter to realize lateral force measurement by determining the power change from a power meter. Experimental
results show that the power ratio change has a linear relationship with respect to the applied lateral force, and the
resolution of the sensor configuration is about 0.01 N.
A novel temperature-independent multi-mode fiber (MMF) lateral strain sensor based on a core-offset interferometer is
presented and demonstrated experimentally. Slightly misaligning a splice between an MMF and a single-mode fiber
(SMF), high extinction ratio of the interferometer based on SMF-MMF-SMF structure can be obtained. When the lateral
strain is applied to a short section of the MMF, the extinction ratio of the interferometer will decrease accordingly while
the interference phase remains almost constant. Temperature variation only leads to shift in the transmission power
spectrum of the interferometer and does not affect the extinction ratio. Experimental results show that there is a good
quadratic relationship between the lateral strain and the extinction ratio. The proposed strain sensor has the advantages of
temperature-independency, high extinction ratio sensitivity, good repeatability, low cost, and simplicity in structure.
A novel electric current sensor based on a high-birefringence fiber loop mirror(HBFLM) and a kind of magnetostrictive material rod(MMR) is demonstrated theoretically and experimentally. Part of the high-birefringence fiber(HBF) is pasted onto the MMR which is placed in the central part of a solenoid. The HBFLM is used as the sensor head and the linear filter simultaneously. Part of the high-birefringence fiber(HBF) is pasted onto the MMR which is placed in the central part of a solenoid. The rod will have elastic lengthening along the direction of the magnetic field when the uniform magnetic field changes, which will lead to a change of transmission intensity of the HBFLM filter, thus the variation of the electric current can be determined via the laser wavelength within the quasi-linear transmission range of the HBFLM filter. The sensitivity reaches 0.0153/100mA, the resolution reaches 10mA. Comparing with the previous fiber-optic electric current sensor, it has nothing with the linear birefringence based on Faraday effects in the previous fiber-optic electric current sensor. Comparing with the expensive and complex FBG electric current, the sensing signal can be directly detected by a photodiode(PD) and complicated demodulation devices are avoidable. The advantages of the electric current include optical power detection, simple and smart structure, high sensitivity, low cost, and good repeatability, etc.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.