Search

Diabetics are prone to postoperative cognitive dysfunction (POCD). The occurrence may be related to the damage of the prefrontal lobe. In this study, the prefrontal lobe was segmented based on an improved clustering algorithm in patients with diabetes, in order to evaluate the relationship between prefrontal lobe volume and COPD. In this study, a total of 48 diabetics who underwent selective noncardiac surgery were selected. Preoperative magnetic resonance imaging (MRI) images of the patients were segmented based on the improved clustering algorithm, and their prefrontal volume was measured. The correlation between the volume of the prefrontal lobe and Z -score or blood glucose was analyzed. Qualitative analysis shows that the gray matter, white matter, and cerebrospinal fluid based on the improved clustering algorithm were easy to distinguish. Quantitative evaluation results show that the proposed segmentation algorithm can obtain the optimal Jaccard coefficient and the least average segmentation time. There was a negative correlation between the volume of the prefrontal lobe and the Z -score. The cut-off value of prefrontal lobe volume for predicting POCD was <179.8, with the high specificity. There was a negative correlation between blood glucose and volume of the prefrontal lobe. From the results, we concluded that the segmentation of the prefrontal lobe based on an improved clustering algorithm before operation may predict the occurrence of POCD in diabetics., Competing Interests: All authors declare no conflicts of interest in this paper., (Copyright © 2021 Na Zhao et al.)

Link prediction aims to identify unknown or missing connections in a network. The methods based on network structure similarity, known for their simplicity and effectiveness, have garnered widespread attention. A core metric in these methods is "proximity", which measures the similarity or linking probability between two nodes. These methods generally operate under the assumption that node pairs with higher proximity are more likely to form new connections. However, the accuracy of existing node proximity-based link prediction algorithms requires improvement. To address this, this paper introduces a Link Prediction Algorithm Based on Weighted Local and Global Closeness (LGC). This algorithm integrates the clustering coefficient to enhance prediction accuracy. A significant advantage of LGC is its dual consideration of a network's local and global features, allowing for a more precise assessment of node similarity. In experiments conducted on ten real-world datasets, the proposed LGC algorithm outperformed eight traditional link prediction methods, showing notable improvements in key evaluation metrics, namely precision and AUC. [ABSTRACT FROM AUTHOR]

Relatively important node mining has always been an essential research topic in complex networks. Existing relatively important node mining algorithms suffer from high time complexity and poor accuracy. Therefore, this paper proposes an algorithm for mining relatively important nodes based on the edge importance greedy strategy (EG). This method considers the importance of the edge to represent the degree of association between two connected nodes. Therefore, the greater the value of the connection between a node and a known important node, the more likely it is to be an important node. If the importance of the edges in an undirected network is measured, a greedy strategy can find important nodes. Compared with other relatively important node mining methods on real network data sets, such as SARS and 9/11, the experimental results show that the EG algorithm excels in both accuracy and applicability, which makes it a competitive algorithm in the mining of important nodes in a network. [ABSTRACT FROM AUTHOR]

More and more researches have focused on the use of knowledge graphs (KG) to solve the sparsity problem of traditional collaborative filtering recommendation systems. Most KG based recommendation algorithms focus on independent paths connecting users and items, or iteratively propagate user preferences in KG. However, the current approachs that focus on indedpent paths ignore the association between paths. Therefore, in this study, we propose a knowledge graph recommendation system algorithm for the multiple paths RNN encoder (AGRE), which fully considers the association between paths. Specifically, the paths between the user and the item are coded by a specified RNN (MRNN) to accurately learn the user's preferences. Traditional RNNs can encode multiple paths without considering the association between paths, but our RNN can encode multiple paths with considering the association between paths. We have compared AGRE with other state-of-the-art algorithms on three real-world datasets, and achieved good results in terms of AUC and Precision@K. This indicates that AGRE could solve the problem of sparse interaction between users and items, and could make full use of the knowledge graph for recommendation. • We consider the association between paths when encoding multiple paths. • We design an improved RNN. By this RNN, we can encode multiple paths. • We conduct experiments on three datasets. The experiments prove that our algorithm outperforms the baselines. • Compared with other algorithms, our algorithm can better solve the data sparse problem. [ABSTRACT FROM AUTHOR]

As modern network communication technology rapidly develops in recent years, complex networks have become a hot multidisciplinary research field. In this field, relatively important nodes mining is an emerging research topic with theoretical significance and application value. However, most researchers in the field of complex networks focus on sorting the global information in the network. Existing relatively important nodes mining algorithms commonly focus on the structural characteristics of the network and do not take into account the influence of community information on relatively important nodes mining. This paper addresses these problems by proposing a relatively important nodes mining algorithm based on community detection and biased random walk with restart (CDBRWR). This approach integrates the community information of the network into the mining of relatively important nodes for the first time and recommends a new biased random walk strategy with restart to realize the accurate and efficient mining of relatively important nodes in various networks. The performance of the proposed algorithm is examined through experimental verification and analysis of real network datasets. Results show that the CDBRWR algorithm outperforms other comparative algorithms in precision, recall, and AUC (area under the curve). • CDBRWR makes the best of the network nodes' community information. • CDBRWR adopts a brand-new random walk strategy to acquire global information. • CDBRWR is a superior candidate for quantifying the relative importance of nodes. • A simple yet clear framework about how to identify relatively important nodes. [ABSTRACT FROM AUTHOR]