Deadline Verification for Web Services Using Timed Automata

Abstract

Many computation tasks are made today on remote cloud platforms using web services. Beyond the advantages provided by such services, many new challenges arise. One of the challenging problems is ensuring that web services respect critical deadlines. This is a critical issue, especially for real-time systems that use remote web services. This paper aims to propose a framework for deadline verification using Timed Automata (TA).

Feature Imputation using Neutrosophic Set Theory in Machine Learning Regression Context

“…In the field of machine learning [1], specifically in the context of regression models [2], the correctness of data characteristics is of utmost importance. The efficacy of a regression model depends on its ability to identify patterns and correlations within the input data, therefore establishing the accuracy of these attributes crucial in the overall prediction process [3][4][5][6]. Flawed or untrustworthy data characteristics might add interference and hinder the model's ability to make generalizations, resulting in unreliable predictions and impaired effectiveness.…”