A study on expression recognition based on improved mobilenetV2 network.

This paper proposes an improved strategy for the MobileNetV2 neural network(I-MobileNetV2) in response to problems such as large parameter quantities in existing deep convolutional neural networks and the shortcomings of the lightweight neural network MobileNetV2 such as easy loss of feature information, poor real-time performance, and low accuracy rate in facial emotion recognition tasks. The network inherits the characteristics of MobilenetV2 depthwise separated convolution, signifying a reduction in computational load while maintaining a lightweight profile. It utilizes a reverse fusion mechanism to retain negative features, which makes the information less likely to be lost. The SELU activation function is used to replace the RELU6 activation function to avoid gradient vanishing. Meanwhile, to improve the feature recognition capability, the channel attention mechanism (Squeeze-and-Excitation Networks (SE-Net)) is integrated into the MobilenetV2 network. Experiments conducted on the facial expression datasets FER2013 and CK + showed that the proposed network model achieved facial expression recognition accuracies of 68.62% and 95.96%, improving upon the MobileNetV2 model by 0.72% and 6.14% respectively, and the parameter count decreased by 83.8%. These results empirically verify the effectiveness of the improvements made to the network model.

Preparation of Hybrid Nanoparticle Nucleating Agents and Their Effects on the Crystallization Behavior of Poly(ethylene terephthalate).

In this research contribution, the primary objective was to enhance the crystallization behavior of poly(ethylene terephthalate) (PET). To accomplish this tack, three kinds of new nucleating agents SiO2-diethylene glycol-LMPET (PET-3), SiO2-triethylene glycol-LMPET(PET-4) and SiO2-tetraethylene glycol-LMPET (PET-5) nucleating agents were prepared via grafting different oligomers (diethylene glycol; triethylene glycol and tetraethylene glycol) to the surface of nano-SiO2 and then linking to the low molecular weight poly(ethylene terephthalate) (LMPET). These nano-particle nucleating agents facilitated the crystallization of PET. Differential scanning calorimetry (DSC) studies of the composites that pure PET blended with PET-3, PET-4 and PET-5 indicated that the longer ethoxy segment in the nucleating agents exhibited (i) higher degrees of crystallinity; (ii) faster rates of crystallization; and (iii) higher crystallization temperatures. The Jeziorny method was employed to analyze the non-isothermal crystallization kinetics of the composites. These works demonstrated that the PET-3, PET-4 and PET-5 were attractive nucleating agents for poly(ethylene terephthalate), and the longer the chain length of the ethoxy segment in the nucleating agents, the more efficient the nucleation effect.