Ai-Driven Methodologies for Real-Time Data Processing in IOT Networks

Farooqi, Shaista Ashraf and Essarani, Bharat Kumar and Khan, Arish and Khan, Wahab and Mehmood, Sajid and Rehman, Muhammad Abdul (2025) Ai-Driven Methodologies for Real-Time Data Processing in IOT Networks. Dialogue Social Science Review (DSSR), 3 (6). pp. 303-319.

Text Shaista+F.pdf Download (521kB)

Abstract

Integrating intelligent units known as Artificial intelligence with IoT networks becomes crucial for improving real-time data analysis. This research aims to investigate the implications of using AI approaches in IoT systems, paying special attention to the efficiency of using AI methods to enhance the real-time processing speed, scalability, and security performances in IoT networks. The main aim of this study is to assess the extent to which AI-based approaches can be used to analyze the processing of big operational data in a real-time fashion in IoT systems. The goal of the work is to measure the extent of improvement that these AI methodologies bring to the performance, accuracy, and scalability of these systems. To collect the data, quantitative research was applied, and structured questionnaires were developed and distributed to IoT specialists and the users of AI technologies. A total of 250 participants across different sectors were used in this study. The statistical tests used in the study include the Shapiro–Wilk test to check the normality of data, Cronbach’s alpha to determine the reliability of the instrument, regression analysis test, and descriptive analysis test. Specifically, the Shapiro-Wilk test revealed that the real-time processing speed data were not normally distributed. In the quantitative analysis measuring internal consistency, using Cronbach’s Alpha on the Likert-scale questions, it was discovered that there was poor internal consistency therefore the need to improve on the survey instrument. For AI Technique 1, it can be seen that the value for R squared was nearly zero, this indicates that it did very little to improve the speed of processing. Also, the distribution of the processing speed was right-skewed, thus suggesting that there might be some standardization of the provision of these features in IoT applications. The key findings of the three AI Techniques applied include AI Technique 1 offers negligible enhancements of real-time data processing in IoT networks from the gathered data. This low reliability, therefore, calls for better instruments to be used in data collection. More research needs to be conducted to assess additional AI approaches and characteristics that would likely account for the changes in the IoT systems’ performance.

Item Type:	Journal
Uncontrolled Keywords:	AI approach, IoT structure, big data technological processing, artificial intelligence techniques, the ability to grow, stability, efficiency, and assessment methodologies
Divisions:	School of Graduate Studies
Depositing User:	Muhamad Aizat Nazmi Mohd Nor Hamin
Date Deposited:	26 Aug 2026 01:50
Last Modified:	26 Aug 2026 01:50
URI:	http://ur.aeu.edu.my/id/eprint/1514

Actions (login required)

View Item