Search

In view of the high frequency resonance generated by Yu side connected to the AC grid in the Yu to E voltage source converter based high voltage direct current transmission (VSC-HVDC) south channel project, the characteristics of VSC-HVDC converter affecting the system stability were analyzed with the impedance analysis method. Mathematical model of the converter and AC line equivalent impedance was established by using the parameters of the converter and AC lines in Yu to E VSC-HVDC project . The impedance amplitude-frequency characteristics and phase-frequency characteristics of the converter and AC lines were obtained by applying MATLAB simulation calculation. The twice cases of high-frequency resonance in Yu side of the Yu to E back-to-back (BTB) VSC-HVDC south channel project were carried out in-depth analysis, and the cause of high frequency resonance was found by the analysis result. Finally, the high frequency resonance suppression strategy was put forward in Yu to E BTB VSC-HVDC project, and was verified by PSCAD simulation calculation.

Complex dynamic network data, such as social networks, protein interaction networks, and infectious disease transmission networks, are prevalent in the real world, consisting of numerous nodes and edges. Effective mining and utilization of such data for accurate prediction have become a key task. Dynamic graph neural network link prediction is an important branch of deep learning research, which aims to analyze the intrinsic laws of network evolution over time and predict potential future linkages, providing valuable information and basis for decision-making in various fields. This paper first reviews the development of dynamic graph neural networks, then introduces the modeling methods and training processes of dynamic graphs. Based on this, the paper categorizes dynamic graph neural network link prediction models into two main types according to the granularity of time: discrete dynamic graph models and continuous dynamic graph models, and provides an overview of the modeling methods used by current mainstream models in each category. In addition, it also introduces commonly used data sets, evaluation indicators and some application scenarios in dynamic graph link prediction research. Finally, the future development trends in this field are discussed prospectively. [ABSTRACT FROM AUTHOR]

Graph data is commonly used to represent complex relationships between different individuals, such as social networks, financial networks, and microservice networks. Graph neural network (GNN) is a deep learning model used for processing graph data, which can effectively capture structural and feature information in graph data. Anomaly detection refers to identifying unexpected data from a massive amount of data. Traditional anomaly detection methods usually do not consider the relationships between data when detecting graph data, while models that use GNN for anomaly detection can learn from graph structures and features, thereby improving the accuracy and robustness of anomaly detection. This paper reviews the application of GNN in anomaly detection from three aspects. Firstly, the basic framework of GNN is introduced. Secondly, the latest research progress of GNN in static graph anomaly detection, dynamic graph anomaly detection, and time series data anomaly detection is discussed separately. Finally, an in-depth analysis is conducted on the future research directions in this field. [ABSTRACT FROM AUTHOR]

The application of artificial neural network algorithm in pathological diagnosis of gastrointestinal malignant tumors has become a research hotspot. In the previous studies, the algorithm research mainly focused on the model development based on convolutional neural networks, while only a few studies used the combination of convolutional neural networks and recurrent neural networks. The research contents included classical histopathological diagnosis and molecular typing of malignant tumors, and the prediction of patient prognosis by utilizing artificial neural networks. This article reviews the research progress on artificial neural network algorithm in the pathological diagnosis and prognosis prediction of digestive tract malignant tumors.

Objective: To investigate the effects of icariin (ICA) on serum bone turnover markers expressions and histological changes of cartilage and subchondral bone in mouse osteoarthritis (OA) model., Methods: Eighty 8-week-old male C57BL/6J mouse were randomly divided into 8 groups ( n =10). The OA model was established by anterior cruciate ligament transaction (ACLT). Group A: sham operation/early-stage normal saline administration; group B: sham operation/early-stage ICA administration; group C: ACLT/early-stage normal saline administration; group D: ACLT/early-stage ICA administration; group E: sham operation/late-stage normal saline administration; group F: sham operation/late-stage ICA administration; group G: ACLT/late-stage normal saline administration; group H: ACLT/late-stage ICA administration. Each animal received either ACLT or simply opening joint capsule, respectively. For groups B and D, ICA was given by gavage [10 mg/(kg·day)] on the first day after ACLT. For groups F and H, ICA was given with the same volume at 4 weeks after operation. The blood serum of the mouse was collected and prepared at 8 weeks after operation. Serum bone turnover markers and cytokines, including C-telopeptide of type I collagen (CTX), osteocalcin (OC), interleukin 6 (IL-6), tumor necrosis factor α (TNF-α), and IL-1β, were measured by ELISA. Tissue samples from the knee were stained by alcian blue/hematoxylin & orange G (AB/H&OG). Histological changes of cartilage and subchondral bone were observed and evaluated by Osteoarthritis Research Society International (OARSI) scoring system., Results: Comparison between each group with early-stage administration (groups A, B, C, and D): Compared with groups A and B, the levels of CTX and OC in group C were significantly reduced ( P <0.05); the levels of IL-6, TNF-α, and IL-1β and OARSI score was significantly increased ( P <0.05). Compared with group C, the levels of CTX and OC in group D were significantly increased ( P <0.05); the level of IL-6 was significantly reduced ( P <0.05); the levels of TNF-α and IL-1β were not changed ( P >0.05), and OARSI score was significantly reduced ( P <0.05). Histological observation showed that the tibial cartilage loss was significantly improved. Comparison between each group with late-stage administration (groups E, F, G, and H): Compared with groups E and F, the levels of CTX and OC in group G were significantly reduced ( P <0.05); the levels of IL-6, TNF-α, and IL-1β and OARSI score were significantly increased ( P <0.05). Compared with group G, the level of CTX in group H were increased ( P <0.05); the levels of OC, IL-6, TNF-α, and IL-1β and OARSI score were not changed ( P >0.05). Histological observation showed that the tibial cartilage loss had no changes after late-stage ICA administration., Conclusion: ICA plays protective effects on subchondral bone, hyaline, and calcified cartilage. Meanwhile, ICA can improve bone remodeling in subchondral bone of OA to some extent. The consistent changes of serum bone markers and pathological morphology suggest that early intervention of ICA on OA is more effective.