Self-healing FBG sensor network fault-detection based on a multi-class SVM algorithm.

We propose a three-layer ring architecture with enhanced reconfigurable capabilities for fiber Bragg grating (FBG) sensor networks. The proposed network is capable of self-healing when three fiber links fail. In addition to self-healing, soft faults in the FBG sensors can be detected using a multi-classification support vector machine (multi-class SVM) algorithm. The detection accuracy reached 99%. Additionally, we used an artificial neural network (ANN) reliability estimation model to estimate the reliability of the FBG self-healing network. The results show that the ANN reliability analysis model can accurately estimate the reliability of the architecture at a reasonable cost.

High-performance gas sensor with symmetry-protected quasi-bound states in the continuum.

A high-performance optical sensor with a vertical cavity structure comprising high-contrast gratings (HCGs) and a distributed Bragg reflector was designed. The structure has two peaks with different mechanisms, among which the first peak is formed by breaking the symmetry of the structure and coupling between the incident wave and the symmetric protection mode. The joint action of the HCG resonance and Fabry-Perot resonance formed a second peak. Moreover, changing the structural parameters, such as the grating width, period, and cavity length, can tune the spectral reflection dips. The sensitivity of the designed structure was as high as 674 nm/RIU, and the corresponding figure of merit was approximately 34741. The presented gas sensor provides a method for applying a vertical cavity structure to the sensing domain.

Recognition and localization of asymmetric spectra in FBG sensing networks.

We propose a deep learning demodulation method based on a long short-term memory (LSTM) neural network for fiber Bragg grating (FBG) sensing networks. Interestingly, we find that both low demodulation error and distorted spectrum recognition are realized using the proposed LSTM-based method. Compared with conventional demodulation methods, including Gaussian-fitting, convolutional neural network, and the gated recurrent unit, the proposed method improves the demodulation accuracy being close to 1 pm and achieves a demodulation time of 0.1s for 128-FBG sensors. Furthermore, our approach can realize 100% accuracy of distorted spectra recognition and complete the location of spectra with spectrally encoded FBG sensors.

Joint Cross-Consistency Learning and Multi-Feature Fusion for Person Re-Identification.

To solve the problem of inadequate feature extraction by the model due to factors such as occlusion and illumination in person re-identification tasks, this paper proposed a model with a joint cross-consistency learning and multi-feature fusion person re-identification. The attention mechanism and the mixed pooling module were first embedded in the residual network so that the model adaptively focuses on the more valid information in the person images. Secondly, the dataset was randomly divided into two categories according to the camera perspective, and a feature classifier was trained for the two types of datasets respectively. Then, two classifiers with specific knowledge were used to guide the model to extract features unrelated to the camera perspective for the two types of datasets so that the obtained image features were endowed with domain invariance by the model, and the differences in the perspective, attitude, background, and other related information of different images were alleviated. Then, the multi-level features were fused through the feature pyramid to concern the more critical information of the image. Finally, a combination of Cosine Softmax loss, triplet loss, and cluster center loss was proposed to train the model to address the differences of multiple losses in the optimization space. The first accuracy of the proposed model reached 95.9% and 89.7% on the datasets Market-1501 and DukeMTMC-reID, respectively. The results indicated that the proposed model has good feature extraction capability.

Multi-Level Cycle-Consistent Adversarial Networks with Attention Mechanism for Face Sketch-Photo Synthesis.

The synthesis between face sketches and face photos has important application values in law enforcement and digital entertainment. In cases of a lack of paired sketch-photo data, this paper proposes an unsupervised model to solve the problems of missing key facial details and a lack of realism in the synthesized images of existing methods. The model is built on the CycleGAN architecture. To retain more semantic information in the target domain, a multi-scale feature extraction module is inserted before the generator. In addition, the convolutional block attention module is introduced into the generator to enhance the ability of the model to extract important feature information. Via CBAM, the model improves the quality of the converted image and reduces the artifacts caused by image background interference. Next, in order to preserve more identity information in the generated photo, this paper constructs the multi-level cycle consistency loss function. Qualitative experiments on CUFS and CUFSF public datasets show that the facial details and edge structures synthesized by our model are clearer and more realistic. Meanwhile the performance indexes of structural similarity and peak signal-to-noise ratio in quantitative experiments are also significantly improved compared with other methods.