Rapid development in the functionalities and innovations of Internet of Things (IoT) have made more openings of IoT applications in various sectors like transportation, healthcare, buildings, infrastructure and logistics field. Considering the pervasive and context dependent nature of IoT, the applicability in multiple domains generates a lot of urgent issues, and one of these problems is missing data imputation, due to that fact some experimental data are incomplete. The IoT research carried out with such an experimental data results in significant decrease in accuracy and reliability of data analysis performed. Most of the big data analytics algorithms applied for data collected through sensors and actuators assume that the data is complete such that each property of the instances are filled with appropriate value. These data has temporal and spatial correlation between them. Most of the research carried out in the context of missing value imputation did not consider the characteristics of IoT data itself. The planned work bases its development using an aspect oriented software development approach and addresses the issues involved in the estimation of missing data point during the service discovery. The proposal analyses the situation of missing data completely at random and appropriately weaves the aspect and the application together thereby decreasing the complexity in handling the missing data issues. The woven aspect estimates the missing data using context and linear mean technique and updates the information. The observation on experimental results reveals significant improvement in response time compared to deriving the missing data in a conventional manner. © 2018 Elsevier Inc. All rights reserved.