Search

This study aimed to explore the underlying role and mechanism of LINC00313 in osteoarthritis (OA) progression. CHON-001 chondrocytes were treated with interleukin (IL)-1β to induce OA in vitro, and then transfected with LINC00313 overexpression plasmids (pcDNA-LINC00313) or small interfering RNA against tumor necrosis factor (TNF) receptor-associated factor 1 (si-TRAF1). Cell viability, apoptosis, levels of inflammatory cytokines tumor necrosis factor-α (TNF-α), IL-6 and IL-8, and expression of extracellular matrix (ECM) degradation related proteins in CHON-001 cells were determined. TRAF1 promoter methylation were was detected with methylation‐specific polymerase chain reaction (MSP) assay. Furthermore, a c-Jun N-terminal kinase (JNK) signaling activator was used to confirm whether the apoptosis signal-regulating kinase 1 (ASK1)/JNK signaling pathway was involved in the function of LINC00313/TRAF1 axis in chondrocytes. In addition, an OA mouse model was established and lentivirus LINC00313 overexpression vector (Lv-LINC00313) was injected, and then inflammatory cytokine levels, ECM protein expression, and pathological changes in cartilage tissues were detected. LINC00313 was downregulated and TRAF1 was upregulated in OA cartilage tissues. LINC00313 overexpression or TRAF1 silencing attenuated IL-1β-induced viability inhibition, apoptosis, inflammation and ECM degradation in CHON-001 cells. Moreover, LINC00313 inhibited TRAF1 expression through promoting DNA methyltransferase 1 (DNMT1) mediated promoter methylation. TRAF1 overexpression reversed the effects of LINC00313 on IL-1β-induced chondrocyte injury. LINC00313 overexpression inhibited the ASK1/JNK signaling pathway, and JNK activator reversed the effect. In addition, Lv-LINC00313 treatment alleviated cartilage tissue damage and cartilage matrix degradation in OA mice. LINC00313 alleviated OA progression through inhibiting TRAF1 expression and the ASK1/JNK signaling pathway.

FER(Face expression recognition) plays an important role in human-computer interaction, but it is also one of the hot problems that artificial intelligence is difficult to solve. In recent years, as researchers have intensively studied the field of FER, the number of network models applied to FER has also increased. Relying on their strong feature extraction ability, CNN(Convolutional neural networks) have gradually become the main model in the field of FER. However, the excessive amount of parameters of CNN limits its application scenarios, and the lightweight technique for CNN brings about the degradation of face expression feature extraction ability. To address the above problems, this paper proposes an improved MobileNeXt-based expression recognition network. Based on the MobileNext lightweight network , the model improves its feature extraction capability. Firstly, the SandGlass block in the network can enhance the transmission of feature information in the network and reduce the loss of expression features during transmission. Secondly, the Ghost module is used to replace the 1×1 convolution kernel in the network to reduce the number of parameters in the feature extraction layer. Then use Drop-Activation layer instead of ReLU layer in Sandglass block to enhance the generalization ability and accuracy of the network. Finally, the Spatial Group-wise Enhance attention mechanism is introduced to enhance the network's ability to refine the expression features. The experimental results show that the network model improves the expression recognition accuracy by 2.6%, 6.5% and 7.15% in FER2013, RAF-DB and CK+ datasets, respectively, while the parameter and floating-point operations only increase 0.85M and 2.93M compared with MobileNet V2.

Proton exchange membrane fuel cell has become the most widely used fuel cell type in fuel cell vehicles. Estimation of fuel cell operating conditions can ensure the safety of the system, determine whether the system is faulty, and provide help for controller design. Aiming at the air supply system of PEMFC, considering the non-linearity and coupling of the system, a condition estimation algorithm based on the TrAdaboost algorithm is proposed to estimate whether the membrane thickness of the proton exchange membrane inside the stack is normal or not. Through the analysis of the model, the key variables affecting the membrane thickness of the stack are written into the system measurement values, and the working conditions of the stack are estimated by using the proposed algorithm. Finally, the proposed hybrid algorithm is verified on the Matlab simulation platform, and the results show that the proposed method can accurately track the real-time working conditions of the fuel cell stack.