Conceptual Clustering

Boubacar, Abdoulahi; Niu, Zhendong

doi:10.1007/978-3-642-55038-6_1

Cited by 3 publications

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This classification provides insight into the type of settlements found in the countries based on a functional perspective and for the first time offered a numerical understanding of how they could be categorised (Boubacar & Niu, 2014). However, the categorisation of these entities was not aligned to the constitutional requirements and offers a whole new typology altogether.…”

Section: Literature Reviewmentioning

confidence: 99%

Exploring settlement typologies in Post‐Apartheid South Africa

Jeeva

Cilliers

2020

Journal of Public Affairs

View full text Add to dashboard Cite

Settlement categorisation differs tremendously between countries making their cross‐comparison, globally, close to impossible. In 2012, the United Nations (UN) proposed a manner in which settlements within its member states could be classified. However, the proposed typology is rather broad and does not offer much on how settlements are classified. Consequently, this paper explored how settlements in South Africa (one of the UN member states) have been categorised, as it is believed that at the least settlements should be categorised consistently within a particular country. This paper conducted an explorative literature review in order to uncover how settlements have been classified in South Africa between 1993 and 2016 in order to draw deduction on the typology of settlements in South Africa. Findings were drawn through a comparative analysis of the literature in order to determine if there was consistency in the understanding of how settlements are classified within the country. The paper found that the categorisation of settlements within South Africa has been a rather contentious matter and the method of classification being fickle in its application. The paper calls for a more structured approach to categorising settlements within the country and pose spatial considerations for other countries dealing with similar issues. Future research in this regard should be considered in order to understand the application of settlement typologies in the quest of a uniform classification as envisioned by the UN.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Exploring settlement typologies in Post‐Apartheid South Africa

Jeeva

Cilliers

2020

Journal of Public Affairs

View full text Add to dashboard Cite

show abstract

Augmented Intelligence with Ontology of Semantic Objects

Fong

Hong

Fong

2019

2019 International Conference on Contemporary Computing and Informatics (IC3I)

View full text Add to dashboard Cite

A Tensor Space Model-Based Deep Neural Network for Text Classification

Kim

Lim

2021

Applied Sciences

View full text Add to dashboard Cite

Most text classification systems use machine learning algorithms; among these, naïve Bayes and support vector machine algorithms adapted to handle text data afford reasonable performance. Recently, given developments in deep learning technology, several scholars have used deep neural networks (recurrent and convolutional neural networks) to improve text classification. However, deep learning-based text classification has not greatly improved performance compared to that of conventional algorithms. This is because a textual document is essentially expressed as a vector (only), albeit with word dimensions, which compromises the inherent semantic information, even if the vector is (appropriately) transformed to add conceptual information. To solve this `loss of term senses’ problem, we develop a concept-driven deep neural network based upon our semantic tensor space model. The semantic tensor used for text representation features a dependency between the term and the concept; we use this to develop three deep neural networks for text classification. We perform experiments using three standard document corpora, and we show that our proposed methods are superior to both traditional and more recent learning methods.

show abstract

Conceptual Clustering

Cited by 3 publications

References 8 publications

Exploring settlement typologies in Post‐Apartheid South Africa

Exploring settlement typologies in Post‐Apartheid South Africa

Augmented Intelligence with Ontology of Semantic Objects

A Tensor Space Model-Based Deep Neural Network for Text Classification

Contact Info

Product

Resources

About