ABSTRACT
Monitoring vital signs is a key part of standard medical care for cancer patients. However, the traditional methods have instability especially when big fluctuations of signals happen, while the deep-learning-based methods lack pertinence to the sensors. A dual-path micro-bend optical fiber sensor and a targeted model based on the Divided-Frequency-CNN (DFC) are developed in this paper to measure the heart rate (HR) and respiratory rate (RR). For each path, features of frequency division based on the mechanism of signal periodicity cooperate with the operation of stable phase extraction to reduce the interference of body movements for monitoring. Then, the DFC model is designed to learn the inner information from the features robustly. Lastly, a weighted strategy is used to estimate the HR and RR via dual paths to increase the anti-interference for errors from one source. The experiments were carried out on the actual clinical data of cancer patients by a hospital. The results show that the proposed method has good performance in error (3.51 (4.51 %) and 2.53 (3.28 %) beats per minute (bpm) for cancer patients with pain and without pain respectively), relevance, and consistency with the values from hospital equipment. Besides, the proposed method significantly improved the ability in the report time interval (30 to 9 min), and mean / confidential interval (3.60/[-22.61,29.81] to -0.64 / [-9.21,7.92] for patients with pain and 1.87 / [-5.49,9.23] to -0.16 / [-6.21,5.89] for patients without pain) compared with our previous work.
Subject(s)
Heart Rate , Neoplasms , Respiratory Rate , Signal Processing, Computer-Assisted , Vital Signs , Humans , Neoplasms/physiopathology , Monitoring, Physiologic/methods , Monitoring, Physiologic/instrumentation , Vital Signs/physiology , Heart Rate/physiology , Respiratory Rate/physiology , Neural Networks, Computer , Male , Deep Learning , Female , Middle Aged , AdultABSTRACT
A highly sensitive Mach-Zehnder interferometer based on a twisted structure in seven-core fiber (SCF) for curvature measurement is investigated both theoretically and experimentally. The device is fabricated by splicing a segment of a twisted SCF with single-mode fibers by the over fusion method. An interference pattern of the straight sensor appears in the transmission spectra. When the sensor is bent, the wavelength shift of the interference pattern is induced, which may be used for curvature measurement through wavelength shift. In the experiment, SCFs with and without the twisted structure are tested, and the results are compared with wavelength-based sensitivities. The proposed twisted-SCF sensor offers a maximum curvature sensitivity of $ - {25.16}\,\,{{\rm nm/m}^{ - 1}}$-25.16nm/m-1 within the measurement range of ${0.5201 - 1.0071}\,\,{{\rm m}^{ - 1}}$0.5201-1.0071m-1, which is a 37-fold improvement compared with the previous works. The results also indicate that this highly sensitive all-fiber sensor offers great potential for realization of curvature measurement in the field of structural health monitoring.
