Big Data and Cognitive Computing

Open AccessArticle

Semantic Ontology-Based Approach to Enhance Arabic Text Classification

by

Big Data Cogn. Comput. 2019, 3(4), 53; https://doi.org/10.3390/bdcc3040053 - 25 Nov 2019

Cited by 9 | Viewed by 4853

Text classification is a process of classifying textual contents to a set of predefined classes and categories. As enormous numbers of documents and contextual contents are introduced every day on the Internet, it becomes essential to use text classification techniques for different purposes [...] Read more.

Text classification is a process of classifying textual contents to a set of predefined classes and categories. As enormous numbers of documents and contextual contents are introduced every day on the Internet, it becomes essential to use text classification techniques for different purposes such as enhancing search retrieval and recommendation systems. A lot of work has been done to study different aspects of English text classification techniques. However, little attention has been devoted to study Arabic text classification due to the difficulty of processing Arabic language. Consequently, in this paper, we propose an enhanced Arabic topic-discovery architecture (EATA) that can use ontology to provide an effective Arabic topic classification mechanism. We have introduced a semantic enhancement model to improve Arabic text classification and the topic discovery technique by utilizing the rich semantic information in Arabic ontology. We rely in this study on the vector space model (term frequency-inverse document frequency (TF-IDF)) as well as the cosine similarity approach to classify new Arabic textual documents. Full article

► Show Figures

Figure 1

Open AccessArticle

Human-Error Prevention for Autonomous Edge Software Using Minimalistic Modern C++

by

Ryo Fukano

and

Masato Ishikawa

Big Data Cogn. Comput. 2019, 3(4), 52; https://doi.org/10.3390/bdcc3040052 - 04 Nov 2019

Viewed by 4436

Abstract

In science and engineering using edge-embedded software, it is necessary to demonstrate the validity of results; therefore, the software responsible for operating an edge system is required to guarantee its own validity. The aim of this study is to guarantee the validity of [...] Read more.

In science and engineering using edge-embedded software, it is necessary to demonstrate the validity of results; therefore, the software responsible for operating an edge system is required to guarantee its own validity. The aim of this study is to guarantee the validity of the sampled-time filter and time domain as fundamental elements of autonomous edge software. This requires the update law of a sampled-time filter to be invoked once per every control cycle, which we guaranteed by using the proposed domain specific language implemented by a metaprogramming design pattern in modern C++ (C++11 and later). The time-domain elements were extracted from the software, after which they were able to be injected into the extracted software independent from the execution environment of the software. The proposed approach was shown to be superior to conventional approaches that only rely on the attention of programmers to detect design defects. This shows that it is possible to guarantee the validity of edge software by using only a general embedded programming language such as modern C++ without auxiliary verification and validation toolchains. Full article

► Show Figures

Figure 1

Open AccessArticle

Replacing Rules by Neural Networks A Framework for Agent-Based Modelling

by

Georg Jäger

Big Data Cogn. Comput. 2019, 3(4), 51; https://doi.org/10.3390/bdcc3040051 - 09 Oct 2019

Cited by 14 | Viewed by 6344

Abstract

Agent-based modelling is a successful technique in many different fields of science. As a bottom-up method, it is able to simulate complex behaviour based on simple rules and show results at both micro and macro scales. However, developing agent-based models is not always [...] Read more.

Agent-based modelling is a successful technique in many different fields of science. As a bottom-up method, it is able to simulate complex behaviour based on simple rules and show results at both micro and macro scales. However, developing agent-based models is not always straightforward. The most difficult step is defining the rules for the agent behaviour, since one often has to rely on many simplifications and assumptions in order to describe the complicated decision making processes. In this paper, we investigate the idea of building a framework for agent-based modelling that relies on an artificial neural network to depict the decision process of the agents. As a proof of principle, we use this framework to reproduce Schelling’s segregation model. We show that it is possible to use the presented framework to derive an agent-based model without the need of manually defining rules for agent behaviour. Beyond reproducing Schelling’s model, we show expansions that are possible due to the framework, such as training the agents in a different environment, which leads to different agent behaviour. Full article

► Show Figures

Figure 1

Open AccessArticle

Big Data and Energy Poverty Alleviation

by

Hossein Hassani

,

Mohammad Reza Yeganegi

,

Christina Beneki

,

Stephan Unger

and

Mohammad Moradghaffari

Big Data Cogn. Comput. 2019, 3(4), 50; https://doi.org/10.3390/bdcc3040050 - 24 Sep 2019

Cited by 26 | Viewed by 7479

Abstract

The focus of this paper is to bring to light the vital issue of energy poverty alleviation and how big data could improve the data collection quality and mechanism. It also explains the vicious circle of low productivity, health risk, environmental pollution and [...] Read more.

The focus of this paper is to bring to light the vital issue of energy poverty alleviation and how big data could improve the data collection quality and mechanism. It also explains the vicious circle of low productivity, health risk, environmental pollution and energy poverty and presents currently used energy poverty measures and alleviation policies and stresses the associated problems in application due to the underlying dynamics. Full article

► Show Figures

Figure 1

Journal Menu

Journal Browser

Big Data Cogn. Comput., Volume 3, Issue 4 (December 2019) – 4 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI