In complex real-world situations, problems such as illumination changes, facial occlusion, and variant poses make facial expression recognition (FER) a challenging task. To solve the robustness problem, this paper proposes an adaptive multilayer perceptual attention network (AMP-Net) that is inspired by the facial attributes and the facial perception mechanism of the human visual system. AMP-Net extracts global, local, and salient facial emotional features with different fine-grained features to learn the underlying diversity and key information of facial emotions. Different from existing methods, AMP-Net can adaptively guide the network to focus on multiple finer and distinguishable local patches with robustness to occlusion and variant poses, improving the effectiveness of learning potential facial diversity information. In addition, the proposed global perception module can learn different receptive field features in the global perception domain, and AMP-Net also supplements salient facial region features with high emotion correlation based on prior knowledge to capture key texture details and avoid important information loss. Many experiments show that AMP-Net achieves good generalizability and state-of-the-art results on several real-world datasets, including RAF-DB, AffectNet-7, AffectNet-8, SFEW 2.0, FER-2013, and FED-RO, with accuracies of 89.25%, 64.54%, 61.74%, 61.17%, 74.48%, and 71.75%, respectively. All codes and training logs are publicly available at https://github.com/liuhw01/AMP-Net .

Acoustic emission (AE) technology can predict the occurrence of partial discharge (PD) faults, which is used to improve the safe operation level of gas-insulated switchgear (GIS) equipment. However, the strong noise interference from the production site is still the main factor affecting the identification accuracy. In this study, a simplified model is designed to approximate the accumulation of free metal particles on the surface of the GIS internal insulation structure, and white noise of various intensities is added to the collected PD-induced AE signals to simulate the background interference. The results prove that the proposed denoising method can achieve a better denoising effect in various signal-to-noise ratio (SNR) conditions. In particular, in the case of low SNR, the recognition accuracy of the accumulation degree of metal particles has been improved by more than 15%.

In this study, a new type of highly sensitive fiber-optic Fabry–Perot interferometer (FFPI) is proposed with a high sensitivity on a wide refractive index (RI) measurement range based on internal reflection mirrors of micro-cavity. The sensor head consists of a single-mode fiber (SMF) with an open micro-cavity. Since light reflections of gold thin films are not affected by the RI of different measuring mediums, the sensor is designed to improve the fringe visibility of optical interference through sputtering the gold films of various thicknesses on the inner surfaces of the micro-cavity, as a semi-transparent mirror (STM) and a total-reflection mirror (TRM). Experiments have been carried out to verify the feasibility of the sensor’s design. It is shown that the fabricated sensor has strong interference visibility exceeding 15 dB over a wide measurement range of RI, and the sensor sensitivity is higher than 1160 nm/RIU, and RI resolution is better than 1.0 × 10⁻⁶ RIU.

Prediction of building energy consumption using mathematical modeling is crucial for improving the efficiency of building energy utilization, assisting in building energy consumption planning and scheduling, and further achieving the goal of energy conservation and emission reduction. In consideration of the non-linear and non-smooth characteristics of building energy consumption time series data, a short-term, hybrid building energy consumption prediction model combining variational mode decomposition (VMD), a simulated annealing (SA) algorithm, and a deep belief network (DBN) is proposed in this study. In the proposed VMD-SA-DBN model, the VMD algorithm decomposes the time series into different modes to reduce the fluctuation of the data. The SA-DBN prediction model is built for each mode separately, and the DBN network structure parameters are optimized by the SA algorithm. The prediction results of each model are aggregated and reconstructed to obtain the final prediction output. The validity and prediction performance of the proposed model is evaluated on a publicly available dataset, and the results show that the proposed new model significantly improves the accuracy and stability of building energy consumption prediction compared with several typical machine learning methods. The mean absolute percent error (MAPE) of the VMD-SA-DBN model is 63.7%, 65.5%, 46.83%, 64.82%, 44.1%, 36.3%, and 28.3% lower than that of the long short-term memory (LSTM), gated recurrent unit (GRU), VMD-LSTM, VMD-GRU, DBN, SA-DBN, and VMD-DBN models, respectively. The results will help managers formulate more-favorable low-energy emission reduction plans and improve building energy efficiency.