• Feb 07, 2023 News!JACN will adopt Article-by-Article Work Flow. The benefit of article-by-article workflow is that a delay with one article may not delay the entire issue. Once a paper steps into production, it will be published online soon.   [Click]
  • May 30, 2022 News!JACN Vol.10, No.1 has been published with online version.   [Click]
  • Dec 24, 2021 News!Volume 9 No 1 has been indexed by EI (inspec)!   [Click]
General Information
    • ISSN: 1793-8244 (Print)
    • Abbreviated Title:  J. Adv. Comput. Netw.
    • Frequency: Semiyearly
    • DOI: 10.18178/JACN
    • Editor-in-Chief: Professor Haklin Kimm
    • Executive Editor: Ms. Cherry Chan
    • Abstracting/ Indexing: EBSCO, ProQuest, and Google Scholar.
    • E-mail: jacn@ejournal.net
    • APC: 500USD
Professor Haklin Kimm
East Stroudsburg University, USA
I'm happy to take on the position of editor in chief of JACN. We encourage authors to submit papers on all aspects of computer networks.

JACN 2020 Vol.8(1): 26-30 ISSN: 1793-8244
DOI: 10.18178/JACN.2020.8.1.276

Fine-Tuning Semantic Information for Optimized Classification of the Internet of Things Patterns Using Neural Word Embeddings

Vusi Sithole and Linda Marshall

Abstract—Word embeddings is a natural language processing modelling technique used to map semantically related words and phrases in proximity vectors. Such embeddings generally reflect semantic similarities between words taken from natural contexts in large corpora. Nonetheless, most natural contexts tend to also have numerous words which do not bear any particular close relationship with regard to their meaning. This results in a lot of noisy data, which also makes the training of word embedding models much more expensive. In this paper, we show that fine-tuning semantic information provide additional benefits for training optimized neural word embeddings. In particular, we use explicit semantic extractions of the Internet of Things patterns attributes as our input data into the model. We propose extracting specific sentences from a large number of the IoT-related documents. These sentences describe the attributes for different IoT patterns. To make our corpora semantically rich, we further extract synonymous words from a thesaurus for some individual words taken from the extracted sentences. This also makes the context of the data more natural. We then embed several IoT pattern names in vector spaces and surround each pattern name with core word units taken from its attributes. In this way, each IoT pattern is classified in close vector spaces with words that represent its core attributes. Furthermore, the IoT patterns belonging in the same family are also classified in close vector spaces based on their attributes. The word vectors obtained from such strict supervised training show improved results on intelligent classification tasks, suggesting that they can be useful in machine learning efforts for building applications used in the categorization of items into both distinct and indistinct classes.

Index Terms—Internet of things, word embeddings, classification, neural networks, patterns.

The authors are with the Department of Computer Science, University of Pretoria, South Africa, Pretoria, South Africa (e-mail: u04409477@tuks.co.za, Lmarshall@cs.up.ac.za).


Cite:Vusi Sithole and Linda Marshall, "Fine-Tuning Semantic Information for Optimized Classification of the Internet of Things Patterns Using Neural Word Embeddings," Journal of Advances in Computer Networks vol. 8, no. 1, pp. 26-30, 2020.

Copyright © 2020 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
Copyright © 2008-2024. Journal of Advances in Computer Networks.  All rights reserved.
E-mail: jacn@ejournal.net