International Journal of Parallel, Emergent and Distributed Systems

Data-Driven Approaches to Improve Sensor Accuracy in IoT-based Automotive Systems

Data-Driven Approaches to Improve Sensor Accuracy in IoT-based Automotive Systems

This special issue focuses on data-driven techniques to enhance sensor accuracy in IoT-based automotive systems. With the growing integration of IoT sensors in modern vehicles, ensuring precise and reliable data collection is crucial for optimizing performance, safety, and decision-making. Advanced methodologies, including big data analytics, machine learning, and AI-driven sensor calibration, play a pivotal role in addressing inaccuracies and improving real-time monitoring. This issue welcomes original research and innovative solutions that enhance sensor performance, predictive maintenance, and system adaptability in automotive environments. Key topics include IoT-based sensor accuracy assessment, AI-driven data refinement, real-time big data processing, digital twins for automotive analytics, and edge computing for adaptive sensor calibration. Contributions that explore novel frameworks, case studies, and interdisciplinary approaches to improving sensor-driven intelligence in connected and autonomous vehicles are highly encouraged.

The topics of the issue include but not limited to the following:

• IoT-based sensor, big data processing, and neural network model performance assessment
• Smart, context-aware, data-driven framework for fogging infrastructures in the Internet of Vehicles
• IoT in agriculture: Data-driven production and precise monitoring in the future
• Creating an IoT and data-driven assessment through an integrated technique
• IoT with artificial intelligence: obstacles and potential paths for data-driven systems
• Digital duplicates and infrastructures developments in industrial data-driven energy-saving
• A technique utilising edge computing for data-driven adaptive sampling
• Design and execution of an algorithm for data-driven projections in safety-critical systems
• Discovering and identifying IoT-enabled load-altering assaults in power grids using data
• Audiovisual interaction via data-driven clustering in the Internet of Automobiles
• Safety detection and prediction using a collection of data-driven techniques