Modelling of the Cloud Service Quality Factors Using ISM

Abstract

In today's world, it is appallingly hard to run a global business, spread over multiple continents without adopting cloud computing technology. Cloud computing makes it easy, saves bucks, reduces IT burden, and helps organisations to focus on customer requirements, market strategy, growth, revenue, and profit, etc. While the organisations are busy planning, selecting, migrating their core business data and applications to the cloud, at the same time it is pertinent to evaluate the service quality of cloud service providers. This will help organisations to adopt the right cloud service provider as per their business requirements. Eleven cloud service quality factors have been explored through an extensive review of the literature and then interpretive structural modelling (ISM) has been used to find out the driving and dependent factors of the cloud service quality and contextual relations among them. This study reveals six driving factors of the cloud service quality namely availability, reliability, scalability, security, service responsiveness, and usability.

Ensemble feature selection for multi‐label text classification: An intelligent order statistics approach

“…where N is the number of data sources used, r i is the rank ratio for ith ranking, and r = 0 0 . Since the complexity of this formula was factorial, Aerts et al 63 proposed a faster alternative formula with complexity O N ( ) 2 :…”

“…Over time and the emergence of new technologies such as cloud 1,2 IoT, 3 and fog computing, many text data have posed many data science challenges. We are beholding their overgrowing every moment.…”

Multiobjective whale optimization algorithm‐based feature selection for intelligent systems

“…Nowadays, research are proposing the use of machine learning to solve the real word problems related to cloud computing, 16,17 cyber security, 18 IoT, 19,20 fog computing, 21 and the healthcare sector. 22 Considering the importance of feature selection for intelligent systems, many different research have been proposed in this field.…”

“…The aforementioned objectives are in different ranges, which definitely affect the performance of the fitness function. Hence, the values are transferred into same range with Equations ( 16), (17), and (18), where Maximum information is the maximum information that can be obtained by selected features. Since the maximum information of each feature can be 1, therefore, the variable Maximum information is equal with the number of selected features.…”

“…Last but not least, the computational time of the proposed approach is analyzed in this section. Computational time is another important factor, which determines how fast an intelligent 20 Monga et al 12 Agarwal and Dhingra 17 Dokeroglu et al 23 Li et al 29 Proposed method…”