According to the current development situation, the application of chipless radio frequency identification (RFID) sensors in structural health monitoring has the disadvantages of difficult detection, poor effect, and single design function, limiting the further development of this technology. Therefore, a new type of RFID strain sensor that realizes the compact structure and separated function of miniaturized chipless RFID coded tags is proposed. The integrated disk monopole antennas make wireless measurement possible. Through the single-parameter strain simulation analysis, six characteristic parameters with good linearity are determined. The time sequences data enhancement algorithm and the background noise data enhancement algorithm are used to expand the training dataset. Then, the BP neural network is utilized for data fusion, and the training error finally converges to 0.0005. A comparison experiment between wired and wireless is designed, and the wireless experiment is optimized through wired experimentation. The results of wireless measurement experiments show that, combined with multiparameter information fusion technology, the average error between the proposed sensor and the actual strain is 6.04%, and the minimum error is 0.25%. The multiparameter fusion monitoring method of the strain sensor corrects the error of single-parameter measurement, and its accuracy and robustness are improved.

A new structural health monitoring (SHM) program using spectrum sensing and radio-frequency identification technology is presented to measure structural strain. The proposed program involving universal software radio peripheral (USRP) provides an economical alternative to these type of measurements as compared to high-end equipment while this method can achieve more flexible data processing. The overall system for strain detection consists of three main parts: 1) a patch antenna as the sensor for strain; 2) an USRP as a measuring instrument; 3) a computer for data processing. The patch antenna can be used to measure structural strain by interrogating resonant frequency shift due to changes in antenna length. In this article we use the optimized energy detection algorithm applied on USRP to detect the spectrum of the patch antenna, the final measurement results show that the patch antenna sensor has a strain sensitivity 1.7678 kHz/ μ ε while the error between the measured value and the true value of the stress is 2.443% after corrected by machine learning.

In the field of structural health detection, since the sensor needs to be directly bonded to the measured object, it is difficult to stably transmit the RFID information and realize the passive wireless structure strain detection. To circumvent these difficulties, this paper innovatively proposes a dual-resonant circular microstrip patch antenna (CMPA) sensor with chipless RFID tag. The information of the RFID tag can be changed that allows the sensor to be deployed on a large scale. The separating sensor includes chipless RFID tag layer and dual-resonant CMPA layer, which can simultaneously reflect RFID tag information and strain information.The design of separated layers can minimize the resonant frequency shift of ID tags when stress is implemented on CMPA strain part. Current distribution analysis and equivalent circuit are used to study the strain size and direction. Experiments show that the offset of the resonant frequency of the sensor antenna has linear relationship with the lateral and longitudinal strains. The correlation coefficients are 0.9284 and 0.9235 respectively, and the sensitivity coefficient of the lateral and longitudinal strain is 528 MHz ϵ ⁻¹ and 384 MHz ϵ ⁻¹ . At the same time, the readability of the RFID tag information is maintained.

Partially defective fingerprint image (PDFI) with poor performance poses challenges to the automated fingerprint identification system (AFIS). To improve the quality and the performance rate of PDFI, it is essential to use accurate segmentation. Currently, most fingerprint image segmentations use methods with ridge orientation, ridge frequency, coherence, variance, local gradient, etc. This paper proposes a method of XFinger-Net for segmenting PDFIs. Based on U-Net, XFinger-Net inherits its characteristics. The attention gate with fewer parameters is used to replace the cascaded network, which can suppress uncorrelated regions of PDFIs. Moreover, the XFinger-Net implements a pixel-level segmentation and takes non-blocking fingerprint images as an input to preserve the global characteristics of PDFIs. The XFinger-Net can achieve a very good segmentation effect as demonstrated in the self-made fingerprint segmentation test.

A compact microstrip rectangular patch antenna with defeated ground structures (DGSs) is proposed. The DGS with a better performance is chosen so that the reduction in the size of antenna can be achieved. In order to eliminate the negative impact of DGS, a small portion of this patch is truncated so as to acquire a better gain and return loss. This paper elaborate on the mechanism of miniaturization in mathematics and physics respectively and the mathematical model of a single C-shaped ring is obtained. By optimizing these parameters, the size of the antenna can be reduced to 55.58% of the original size while the return loss of the antenna can reach to 37.10 dB. The measurement results indicate that the performance of the antenna can match well with the simulation results.

This is a reply to the Comments proposed by Mahmoud Wagih on our published paper entitled “A Passive and Wireless Sensor Based on RFID Antenna for Detecting Mechanical Deformation”. His concerns about Fig. 6 in the paper are clarified and his good suggestion is appreciated.