Measuring country sustainability performance using ensembles of neuro-fuzzy technique

• Main Authors: Nilashi, M., Cavallaro, F., Mardani, A., Zavadskas, E. K., Samad, S., Ibrahim, O.
• Format: Article
• Language: English
• Published: MDPI AG 2018
• Subjects: QA75 Electronic computers. Computer science
• Online Access: http://eprints.utm.my/id/eprint/79688/1/AbbasMardani2018_MeasuringCountrySustainabilityPerformance.pdf; http://eprints.utm.my/id/eprint/79688/; http://dx.doi.org/10.3390/su10082707
• Institution: Universiti Teknologi Malaysia

Global warming is one of the most important challenges nowadays. Sustainability practices and technologies have been proven to significantly reduce the amount of energy consumed and incur economic savings. Sustainability assessment tools and methods have been developed to support decision makers in evaluating the developments in sustainable technology. Several sustainability assessment tools and methods have been developed by fuzzy logic and neural network machine learning techniques. However, a combination of neural network and fuzzy logic, neuro-fuzzy, and the ensemble learning of this technique has been rarely explored when developing sustainability assessment methods. In addition, most of the methods developed in the literature solely rely on fuzzy logic. The main shortcoming of solely using the fuzzy logic rule-based technique is that it cannot automatically learn from the data. This problem of fuzzy logic has been solved by the use of neural networks in many real-world problems. The combination of these two techniques will take the advantages of both to precisely predict the output of a system. In addition, combining the outputs of several predictors can result in an improved accuracy in complex systems. This study accordingly aims to propose an accurate method for measuring countries' sustainability performance using a set of real-world data of the sustainability indicators. The adaptive neuro-fuzzy inference system (ANFIS) technique was used for discovering the fuzzy rules from data from 128 countries, and ensemble learning was used for measuring the countries' sustainability performance. The proposed method aims to provide the country rankings in term of sustainability. The results of this research show that the method has potential to be effectively implemented as a decision-making tool for measuring countries' sustainability performance.