Tag Archives: Neural networks

Pragmatic Research Design: an Illustration of the Use of the Delphi Technique

The creation of wealth is an important issue in any society, and entrepreneurship is regarded as an important catalyst in the creation of new wealth. This presents a challenge to develop entrepreneurship successfully. An important site for the development of entrepreneurship is higher education. The challenge however, is that there is a lack of a general understanding on how to educate students for entrepreneurship. In addition, current thought and practice on entrepreneurship education is historically biased, implying that graduates are essentially prepared for the past instead of for the future. From the perspective of higher education, the problem is how to develop current students to be entrepreneurial in the future. What is needed is to project into the future and then to develop an understanding of what should be taught as well as how it should be taught today.

A versatile research technique that can assist in achieving this objective is the Delphi technique, as it is used to conduct futures research or research into areas where knowledge is incomplete. The Delphi method is a type of group interview, using the collective opinion of knowledgeable experts. The technique makes use of several rounds of data collection and feedback to create a consensus of opinion.

Making use of the Delphi technique, research is being designed that will formulate expert-based strategic guidelines on entrepreneurial education within the South African higher education sector. The aim of this paper is to illustrate the research design considerations that arise in the use of the Delphi technique for this purpose and how they are addressed.

The main characteristics of the Delphi are presented and arguments for the use of the Delphi within a constructivist paradigm are discussed. Practical issues related to the design of the Delphi, panel-member selection, and the formulation of panel questions, are examined. In illustrating these design considerations, the paper demonstrates a pragmatic approach to research design as well as the importance of creating coherence between the research question, the research paradigm, the research method and its use, encouraging research practitioners to adopt a more systematic, deliberate and philosophically-based approach to research design.

Article originally published in ‘The Electronic Journal of Business Research Methods’, V. 6 (2008), n. 2, pp. 95-102, http://www.ejbrm.com/vol6/v6-i2/v6-i2-art1-abstract.htm

Reprinted with permission

View full Article in PDF

Machine Learning: a crucial tool for sensor design

Sensors have been widely used for disease diagnosis, environmental quality monitoring, food quality control, industrial process analysis and control, and other related fields. As a key tool for sensor data analysis, machine learning is becoming a core part of novel sensor design. Dividing a complete machine learning process into three steps: data pre-treatment, feature extraction and dimension reduction, and system modelling, this paper provides a review of the methods that are widely used for each step. For each method, the principles and the key issues that affect modelling results are discussed. After reviewing the potential problems in machine learning processes, this paper gives a summary of current algorithms in this field and provides some feasible directions for future studies.

Article originally published in ‘Algorithms’, V.1 (2008), n. 2, pp. 130-152, http://www.mdpi.com/1999-4893/1/2/130. ¬© 2008 by the authors; licensee Molecular Diversity Preservation International, Basel, Switzerland. This article is an open-access article distributed under the terms and conditions of the Creative Commons Attribution license (http://creativecommons.org/licenses/by/3.0/).

View full Article in PDF