Forthcoming and Online First Articles

International Journal of Network Science

International Journal of Network Science (IJNS)

Forthcoming articles have been peer-reviewed and accepted for publication but are pending final changes, are not yet published and may not appear here in their final order of publication until they are assigned to issues. Therefore, the content conforms to our standards but the presentation (e.g. typesetting and proof-reading) is not necessarily up to the Inderscience standard. Additionally, titles, authors, abstracts and keywords may change before publication. Articles will not be published until the final proofs are validated by their authors.

Forthcoming articles must be purchased for the purposes of research, teaching and private study only. These articles can be cited using the expression "in press". For example: Smith, J. (in press). Article Title. Journal Title.

Articles marked with this shopping trolley icon are available for purchase - click on the icon to send an email request to purchase.

Online First articles are published online here, before they appear in a journal issue. Online First articles are fully citeable, complete with a DOI. They can be cited, read, and downloaded. Online First articles are published as Open Access (OA) articles to make the latest research available as early as possible.

Open AccessArticles marked with this Open Access icon are Online First articles. They are freely available and openly accessible to all without any restriction except the ones stated in their respective CC licenses.

Register for our alerting service, which notifies you by email when new issues are published online.

We also offer which provide timely updates of tables of contents, newly published articles and calls for papers.

International Journal of Network Science (2 papers in press)

Regular Issues

  • Ensemble model for network representation learning   Order a copy of this article
    by Pranav Nerurkar, Madhav Chandane, Sunil Bhirud 
    Abstract: Multiple LSR techniques are available in the literature that could scale to networks with more than $10^3$ nodes. However, these techniques preserved one of the three key proximity measures. Hence, Ensemble models were proposed to preserve the three main proximity measures in a network simultaneously. The proposed ensemble models were applied to six network datasets with more than $10^3$ nodes. The computation complexity of proposed ensemble models was better than SBM and LVM. A key drawback observed was that the proposed ensemble models required all nodes in the network to be present during training. This feature meant that proposed models were transductive. They would not generalize to unseen nodes (non-inductive). The proposed models discarded attribute data associated with the network nodes. Alternatively, "deep encoder" based techniques could be investigated for situations where all network nodes cannot be available at the time of training. Such models could also be used where network nodes were associated with attributes.
    Keywords: Representation learning; network embedding; latent space; clustering; ensemble models.

  • Statistical-based Approach for Outlier Detection in Wireless Sensor Networks   Order a copy of this article
    by Chafiq Titouna, Farid Naït-Abdesselam, Ashfaq Khokhar 
    Abstract: Wireless Sensor Networks (WSNs) are sets of autonomous sensors dedicated to capture physical conditions of an area of interest. The collected data is converted to numerical data and transmitted to a central station for further processing. WSNs are also subject to several constraints, such as energy depletion, communication errors, and malicious attacks that impact negatively the quality of the transmitted data. Therefore, and in order to ensure a reliable and accurate data in this type of networks, it is crucial to endow them with mechanisms for detecting and cleaning erroneous and outlier instances of the collected data. To address this ever-increasing problem, we propose in this article a new algorithm called Outlier Detection Algorithm based on Mahalanobis Distance (ODA-MD). In this case, the Mahalanobis metric is used to calculate and compare the collected data in a fully distributed manner. The efficiency of the algorithm for detecting outliers lies also in its ability to perform this task online and in the presence of multivariate data among the data collected. Its functionalities have been evaluated through simulations using realistic datasets obtained from the Intel-Berkeley Research Laboratory (IBRL). The obtained results demonstrate the high effectiveness of the proposed algorithm in comparison to the literature in terms of several metrics.
    Keywords: Wireless sensor networks; outlier detection; Mahalanobis distance.