Link Prediction Approach for Opportunistic Networks Based on Recurrent Neural Network

Cai, Xulin; Shu, Jian; Al-Kali, Manar

doi:10.1109/access.2018.2886360

Cited by 19 publications

(13 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then they applied it to the linear regression model and neural machine to predict the link. Cai et al [22] divided the network into a series of time-series snapshots based on the time-varying characteristics of the opportunistic network and defined a set of vectors based on the attributes of the edge, such as the endpoint ID and the start time of the edge. They also constructed a predictive model (RNN-LP) based on a recurrent neural network to extract the features of the edge attribute vector over time to predict the link.…”

Section: Machine Learning-based Prediction Methodsmentioning

confidence: 99%

“…The optimal model (on the ITC and MIT dataset) is determined based on the optimal number of hidden layers, the optimal slice time and the optimal input data length, which are determined by the previous experiments. In this section, the effectiveness and rationality of the IRWR-DBN model (under the optimal parameters) are verified by comparison experiments based on the methods of CN, AA, RA, RWR [27], Katz, RNN-LP [22] and CNN [23]. We consider that these methods are used in different scenarios.…”

Section: ) Experiments 3: Comparison Of Different Prediction Methodsmentioning

confidence: 99%

“…We also need to explain that in experiment 2, according to the research on the slice time on the ITC dataset in [22] and [32] (180s, 240s, 300s and 320s), we extended the length of the slice time on the ITC dataset to [100s, 360s], with a step size of 20s. According to the research on the slice time in [23] and [32] (300s and 600s) and the duration of the MIT dataset, we extend the length of the slice time on the MIT dataset to [100s, 1000s], with a step size of 100s.…”

Section: ) Experimental Configurationmentioning

confidence: 99%

See 2 more Smart Citations

A Novel Link Prediction Method for Opportunistic Networks Based on Random Walk and a Deep Belief Network

2020

View full text Add to dashboard Cite

Link prediction is to estimate the possibility of future links among nodes by utilizing known information such as network topology and node attributes. According to the characteristics of opportunistic networks (topological time-variation, node mobility and intermittent connections), this paper proposes a novel link prediction approach (IRWR-DBN) for opportunistic networks that is based on random walk and a deep belief network. First, we reconstruct the Markov probability transition matrix and define a similarity index-improved random walk with restart (IRWR). Second, we divide the opportunistic network into network snapshots. Then, the similarity matrix of each snapshot is calculated by using the IRWR index to construct a sample set. Finally, a predictive model is constructed based on a deep belief network which extracts the time-domain characteristics in the process of dynamic evolution of the opportunistic network. The experimental results on the ITC and MIT Reality datasets show that compared with methods, such as the similarity-based index (CN, AA, Katz, RA, RWR), convolutional neural network, and recurrent neural network, the proposed method is more accurate and stable. INDEX TERMS Opportunistic network, link prediction, random walk with restart, deep belief network, similarity index.

show abstract

Section: Machine Learning-based Prediction Methodsmentioning

confidence: 99%

Section: ) Experiments 3: Comparison Of Different Prediction Methodsmentioning

confidence: 99%

Section: ) Experimental Configurationmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Link Prediction Method for Opportunistic Networks Based on Random Walk and a Deep Belief Network

2020

View full text Add to dashboard Cite

show abstract

“…Using convolutional neural networks (CNNs), [37] extracted ON's structural features from the evolutionary process of the state diagram, and predicted the links between multiple nodes. Considering the historical connection information, [38] constructed a sequence vector, and extracted the features of the changes of the historical information using a recurrent neural network (RNN). Then, link prediction is performed.…”

Section: Machine Learning and Time Series-based Prediction Methodsmentioning

confidence: 99%

“…, G N }, where G t = (V t , E t ), G t represents the network snapshot at t − th moment, and V t and E t respectively represent the sets of nodes and edges in the network snapshot at t − th moment. The link prediction in ON is to predict connection state in the (t + 1) − th network snapshot according to the historical link information of the node pairs in the previous t network snapshots [38].…”

Section: Problem Descriptionmentioning

confidence: 99%

Opportunistic Networks Link Prediction Method Based on Bayesian Recurrent Neural Network

Shu

2019

IEEE Access

Self Cite

View full text Add to dashboard Cite

The goal of link prediction is to estimate the possibility of future links among nodes using known network information and the attributes of the nodes. According to the time-varying characteristics and the node's mobility of opportunistic networks, this paper proposes a novel link prediction method based on the Bayesian recurrent neural network (BRNN-LP) framework. The time series data of a dynamic opportunistic networks is sliced into snapshots in which there exist the correlation information and spatial location information. A vector of a snapshot is constructed based on such information, which represents the link information. Then, the vectors of multiple network snapshots constitute a spatiotemporal vector sequence. Benefiting from the BRNN's ability of extracting the features of time series data, the correlation between spatiotemporal vector sequence and node connection states is learned, and the law of the link evolution is captured to predict future links. The results on the MIT Reality dataset show that compared with methods such as the similarity-based indices, the support vector classifier, linear discriminant analysis and recurrent neural network, the proposed prediction method is more accurate and stable.INDEX TERMS Link prediction, opportunistic networks, Bayesian recurrent neural network.

show abstract

Review of opportunistic network: Assessing past, present, and future

Sachdeva

Dev

2021

Int J Communication

View full text Add to dashboard Cite

Opportunistic networks aim to deal with the unpredictable environment for data communication. Messages in opportunistic networks need to be stored with the node in the absence of any suitable forwarder. With such a storecarry-forward paradigm, it aims to eliminate challenges of no pre-determined/ fixed connectivity, absence of direct/in-direct routes from source to destination, and high error rate and delay in the network. Node carrying message roams in the network to find a suitable forwarding node. In this study, the survey for various routing protocols and mobility models for opportunistic networks is discussed along with tools available for simulations of opportunistic networks. Further, various challenges in opportunistic networks such as storage management, congestion management, and energy constraints are discussed. Many applications for the opportunistic network, along with real-time case study, are presented in the paper. The objective of the study is to provide future direction to the researchers, along with the systematic review. Hence, future objectives are discussed to mitigate the challenges faced in the current scenario. Also, based upon the study, it is observed that most researchers have taken epidemic, ProPHET, and spray and wait routing protocols as their base of study. Performance analysis for these protocols is done using opportunistic network environment (ONE) simulator.

show abstract

Link Prediction Approach for Opportunistic Networks Based on Recurrent Neural Network

Cited by 19 publications

References 16 publications

A Novel Link Prediction Method for Opportunistic Networks Based on Random Walk and a Deep Belief Network

A Novel Link Prediction Method for Opportunistic Networks Based on Random Walk and a Deep Belief Network

Opportunistic Networks Link Prediction Method Based on Bayesian Recurrent Neural Network

Review of opportunistic network: Assessing past, present, and future

Contact Info

Product

Resources

About