Journal of Supercomputing最新文献

The behaviour of individual users in an online social network is a major contributing factor in determining the outcome of multiple network phenomenon. Group formation, growth of the network, information propagation, and rumour blocking are some of the many network behavioural traits that are influenced by the interaction patterns of the users in the network. Network motifs capture one such interaction pattern between users in online social networks (OSNs). For this work, four second-order (two-edged) network motifs have been considered, namely, message receiving pattern, message broadcasting pattern, message passing pattern, and reciprocal message pattern, to analyse user behaviour in online social networks. This work provides and utilizes a node interaction pattern-finding algorithm to identify the frequency of aforementioned second-order network motifs in six real-life online social networks (Facebook, GPlus, GNU, Twitter, Enron Email, and Wiki-vote). The frequency of network motifs participated in by a node is considered for the relative ranking of all nodes in the online social networks. The highest-rated nodes are considered seeds for information propagation. The performance of using network motifs for ranking nodes as seeds for information propagation is validated using statistical metrics Z-score, concentration, and significance profile and compared with baseline ranking methods in-degree centrality, out-degree centrality, closeness centrality, and PageRank. The comparative study shows the performance of centrality measures to be similar or better than second-order network motifs as seed nodes in information diffusion. The experimental results on finding frequencies and importance of different interaction patterns provide insights on the significance and representation of each such interaction pattern and how it varies from network to network.

The study of innate immune-based algorithms is an important research domain in Artificial Immune System (AIS), such as Dendritic Cell Algorithm (DCA), Toll-Like Receptor algorithm (TLRA). The parameters in these algorithms usually require either manually pre-defined usually provided by the immunologists, or empirically derived from the training dataset, and result in poor self-adaptation and self-learning. The fundamental reason is that the original innate immune mechanisms lack adaptive biological theory. To solve this problem, a theory called ‘Trained Immunity™ or Innate Immune Memory (IIM)™ that thinks innate immunity can also build immunological memory to enhance the immune system™s learning and adaptive reactions to the second stimulus is introduced into AIS to improve the innate immune algorithms™ adaptability. In this study, we present an overview of IIM with particular emphasis on analogies in the AIS world, and a modified DCA with an effective automated tuning mechanism based on IIM (IIM-DCA) to optimize migration threshold of DCA. The migration threshold of Dendritic Cells (DCs) determines the lifespan of the antigen collected by DCs, and directly affect the detection speed and accuracy of DCA. Experiments on real datasets show that our proposed IIM-DCA which integrates Innate Immune Memory mechanism delivers more accurate results.

Online social network is one of the most prominent media that holds information about society's epidemic problem. Due to privacy reasons, most of the users will not disclose their location. Detecting the location of the tweet users is required to track the geographic location of the spreading diseases. This work aims to detect the spreading location of the COVID-19 disease from the Twitter users and content discussed in the tweet. COVID-19 is a disease caused by the "novel coronavirus." About 80% of confirmed cases recover from the disease. However, one out of every six people who get COVID-19 can become seriously ill, stated by the World health organization. Inferring the user location for identifying the spreading location for the disease is a very challenging task. This paper proposes a new technique based on a hypergraph model to detect the Twitter user's locations based on the spreading disease. This model uses hypergraph with weighting factor technique to infer the spreading disease's spatial location. The accuracy of prediction can be improved when a massive volume of streaming data is analyzed. The Helly property of the hypergraph was applied to discard less potential words from the text analysis, which claims this work of unique nature. A weighting factor was introduced to calculate the score of each location for a particular user. The location of each user is predicted based on the one that possesses the highest weighting factor. The proposed framework has been evaluated and tested for various measures like precision, recall and F-measure. The promising results obtained have substantiated the claim for this work compared to the state-of-the-art methodologies.

The purposes are to automatically collect information about human sports behavior from massive video data and provide an explicit recognition and analysis of body movements. The analysis of multi-scale input data, the improvement of spatiotemporal Deep Belief Network (DBN), and the different pooling strategies are regarded as the focuses to improve the belief networks in deep learning (DL). Moreover, a human sports behavior recognition model is proposed based on particular spatio-temporal features. Also, video frame data are collected from the Royal Institute of Technology (KTH) and University of Central Florida (UCF) datasets for training. The TensorFlow platform is employed to simulate the built algorithm. Finally, the constructed algorithm model is compared with the DBN proposed by Yang et al. the Convolutional Neural Network (CNN) proposed by Ullah et al. and the DBN-Hidden Markov Model (HMM) algorithm proposed by Xu et al. to analyse its performance. The recognition effects of each algorithm in the two datasets are analyzed. Results demonstrate that CNN developed by Ullah et al. has the worst accuracy on the KTH and UCF datasets, followed by DBN developed by Yang et al. and DBN-HMM developed by Xu et al. The constructed algorithm model can provide the highest accuracy, reaching about 90%, and the recognition accuracy of human sports behaviors of each algorithm on the KTH dataset is lower than that on the UCF dataset. On the KTH dataset, the recognition accuracy for boxing is the highest and running the lowest. Analyzing the model's accuracy in the four scenes (S1, S2, S3, and S4) on the KTH dataset suggests that the recognition accuracy for the indoor scene (S4) is higher than that of the outdoor scenes (S1, S2, and S3). On the UCF dataset, the recognition accuracy for lifting is the highest, reaching 99%, and that for walking is the lowest, reaching 51%. Therefore, the proposed human sports recognition model can provide a higher accuracy than other classic DL algorithms, providing an experimental basis for subsequent human sports recognition research.