Paper Contents
Abstract
The proliferation of smart devices and the Internet of Things (IoT) has led to an exponential increase in data generation, creating new opportunities for understanding human behavior through intelligent Big Data analytics. Traditional data processing techniques are often inadequate for managing the scale and complexity of such data, necessitating the adoption of more robust and scalable solutions. This research explores the use of advanced frameworkssuch as Hadoop, Spark, and Hiveto analyze behavioral patterns within the Social Internet of Things (SIoT). The proposed system architecture incorporates real-time data processing capabilities to derive insights from diverse sources, including social media interactions, wearable sensors, and smart city infrastructure. By integrating machine learning algorithms and data mining methods, the system enhances the accuracy of behavioral predictions, supports informed decision-making, and facilitates intelligent automation. A comparative analysis demonstrates that Spark-based processing significantly outperforms traditional single-threaded methods in both execution speed and analytical precision. Experimental results confirm the effectiveness of the framework in capturing complex human behavior, with potential applications across urban planning, healthcare, security, and personalized recommendation systems. This study underscores the transformative potential of Big Data-driven analytics in advancing human behavior understanding and enabling smarter, data-informed environmentsKeywords Big Data Analytics, Human Behavior Analysis, Internet of Things (IoT), Machine Learning, Smart Cities, Data Mining, Artificial Intelligence, Real-time Processing..
Copyright
Copyright © 2025 Mrs. Helini Kolan. This is an open access article distributed under the Creative Commons Attribution License.
