With the development of semantic social networks, social networks become more complex and their size expands rapidly, which brings significant challenges to social network analysis. Network Embedding can transform the...
详细信息
ISBN:
(数字)9798350362930
ISBN:
(纸本)9798350362947
With the development of semantic social networks, social networks become more complex and their size expands rapidly, which brings significant challenges to social network analysis. Network Embedding can transform the network from a high-dimensional adjacency matrix to a low-dimensional one, which has excellent foreground in link prediction, vertex classification, and graph visualization. Nowadays, most algorithms are proposed for static networks with little consideration of the dynamic changes in the network. However, most real-world networks change over time. Directly applying static network embedding algorithms to dynamic networks will result in poor stability, flexibility, and efficiency. Because of these shortcomings, we propose a graph convolution-based dynamic network representation learning algorithm (GNEA), which combines Graph Convolutional Network (GCN) with Long Short-term Memory (LSTM) to train the time series networks. GCN is applied to extract features in the network, and LSTM is utilized to capture temporal information. GNEA can not only perform characterization learning on the network but also obtain more abundant information during the dynamic evolution of the network. GNEA is compared with several typical algorithms on the datasets Stochastic Block Model (SBM), Autonomous Systems (AS), and Digital Bibliography and Library Project (DBLP). The results prove that GNEA has good performance in MAP and precision@k.
Bio-medical entity recognition extracts significant entities, for instance cells, proteins and genes, which is an arduous task in an automatic system that mine knowledge in bioinformatics texts. In this thesis, we uti...
ISBN:
(纸本)9781538680988;9781538680971
Bio-medical entity recognition extracts significant entities, for instance cells, proteins and genes, which is an arduous task in an automatic system that mine knowledge in bioinformatics texts. In this thesis, we utilized a bidirectional long short-term memory (Bi-LSTM) combined with conditional random fields (CRFs) approach to automatically obtain word representation, obliterated the need for a marvelous number of feature engineering tasks. The consequences of this experiment represent the word representation method can effectually acquire potential semantic information. Without relying on any artificial features, the result on the test dataset obtained 76.81 % F-score. Therefore, the proposed method is expected to advance biomedical text mining in bioinformatics entity recognition.
Directed graph is able to model asymmetric relationships between nodes and research on directed graph embedding is of great significance in downstream graph analysis and inference. Learning source and target embedding...
详细信息
An automatic question answering system is generally composed of the question analysis module, the information retrieval module, the answer selection module, etc. The core component of automatic question answering syst...
详细信息
ISBN:
(纸本)9781538676738;9781538676721
An automatic question answering system is generally composed of the question analysis module, the information retrieval module, the answer selection module, etc. The core component of automatic question answering system is the answer selection module, which focuses on extracting adequate information from the questions and answers and representing them effectively. The performance of answer selection directly determines the quality of the answers submitted to users. In this paper, we studied the answer selection schemes, especially the Attentive LSTM scheme, focusing on the application of the attention mechanism commonly utilized in deep learning models. Meanwhile, a self-attentive LSTM is proposed by combining the Attentive LSTM with self-attention which is capable of extracting the local features and the global features of texts at the same time. In addition, a multi-attentive LSTM is proposed so that multiple parts of information in the question are available for the answer. We performed a series of experiments based on the datasets InsuranceQA and TrecQA, compared and analyzed on the performances of the above schemes.
This paper proposes a point cloud registration method for substations based on an improved SAC-IA algorithm. This method optimizes the SAC-IA algorithm by filtering the randomly selected point pairs to ensure that the...
This paper proposes a point cloud registration method for substations based on an improved SAC-IA algorithm. This method optimizes the SAC-IA algorithm by filtering the randomly selected point pairs to ensure that the triangles formed by the selected points in the model and scene point clouds have certain similarities. Furthermore, the registration error judgment of the SAC-IA algorithm has been improved. In addition to using the Euclidean distance between the registered model and scene point clouds as the judgment standard, this method also considers the SHOT difference and average curvature difference. Successful registration is only considered when all three standards are satisfied. The experimental research shows that the time performance of this method is twice as high as that of the traditional SAC-IA algorithm on average, and the recognition accuracy is improved in the recognition results.
With rising uncertainty in the real world, online Reinforcement Learning (RL) has been receiving increasing attention due to its fast learning capability and improving data efficiency. However, online RL often suffers...
详细信息
Astronomical outliers, such as unusual, rare or unknown types of astronomical objects or phenomena, constantly lead to the discovery of genuinely unforeseen knowledge in astronomy. More unpredictable outliers will be ...
详细信息
Blockchain based applications benefit from decentralization, data privacy, and anonymity. However, they may suffer from inefficiency due to underlying blockchain. In this paper, we aim to address this limitation while...
详细信息
ISBN:
(数字)9781728150895
ISBN:
(纸本)9781728150901
Blockchain based applications benefit from decentralization, data privacy, and anonymity. However, they may suffer from inefficiency due to underlying blockchain. In this paper, we aim to address this limitation while still enjoying the privacy and anonymity. Taking the blockchain based crowdsourcing system as an example, we propose a new smart contract based cyber-insurance framework, which can greatly shorten the delay, and enable the workers to obtain the economic compensation for increased security risk caused by a conflict between the need to provide service quickly and delay in payment. We model the process of determining insurance premium and number of confirmations as a Stackelberg Game and prove the existence of Stackelberg Equilibria, at which the utility of the requester is maximized, and none of the workers can improve its utility by unilaterally deviating from its current strategy. The experimental results show that our framework can definitely improve the time efficiency of crowdsourcing. Particularly, it takes on average only 33% of the time required by the naive blockchain based crowdsouring solution for time-sensitive cases.
The taxonomy of galaxy morphology is critical in astrophysics as the morphological properties are powerful tracers of galaxy evolution. With the upcoming Large-scale Imaging Surveys, billions of galaxy images challeng...
详细信息
With the rapid development of smart cities and the advance of city safety and defense demands, the question that how to accurately discover and retrieve the data that users request from VideoGIS data faces a series of...
详细信息
With the rapid development of smart cities and the advance of city safety and defense demands, the question that how to accurately discover and retrieve the data that users request from VideoGIS data faces a series of bottleneck problems. VideoGIS data retrieval is one of the important ways to solve above problems. In order to accelerate the rate of feature matching and improve the efficiency of the video retrieval, a new method of VideoGIS data retrieval based on multi-feature fusion is proposed in this paper. The method firstly use video frame difference based on Euclidean distance to extract the key frames under the spatial and temporal sampling of the video. On the basis of this, the global features (e.g. color, shape, texture) are fused by different weighted coefficients, then the feature vector, as the video multi-feature fusion representation, can be constructed by fusing the global features and local features. Based on the multi-feature fusion, correlation between video features is made full use. Compared with the method of single feature and two-feature fusion, the experimental results indicate that the proposed retrieval method has better retrieval effect.
暂无评论