Call for Papers -- Lightweight AI Algorithms for Real-Time Data Mining in Edge Computing Environments

2025-03-11

A real-time streaming controlled clustering edge computing method (SCCEC) is presented with the aim of addressing the low efficiency, poor performance, weak stability, and poor responsiveness to the processing of huge data in real-time. AI edge computing allows AI applications to execute directly on field devices, allowing ML and DL algorithms to be applied while processing field data. In the cloud, data processing occurs in a few seconds. On the other hand, processing data at the edge can happen in milliseconds or less. Technologies such as wearables, security cameras, smart home appliances, and self-driving cars use edge AI capabilities to provide users with real-time information quickly when needed. The application of artificial intelligence (AI) in practical devices is known as AI at the edge. The term "edge AI" describes the technique of performing AI calculations close to users at the edge of the network, as opposed to in a centralized place like the data center of a cloud service provider. Even in rural areas with spotty network connectivity, edge computing reduces the cost of deploying IoT equipment.

Retail edge computing
Huge data sets are frequently gathered by major retailers from each of their individual stores. These algorithms can operate right at the edge of a network, on an IoT device or a machine that has an edge computing device installed, near to the source of the data and information required to run the system. By enabling local data processing on devices at the network's edge, edge AI speeds up computing, enhances data security and privacy, and permits real-time decision-making without requiring Internet access or centralized cloud servers. The success of AI at the edge depends on innovations in system and device performance in addition to smaller, more cost-effective, and more efficient models. Predictive maintenance based on the edge boosts operational effectiveness and decreases downtime.

Individualization
AI at the edge technology can be used by retail establishments and smart homes to customize user experiences. For the most part, edge AI systems process data locally. As a result, a lot less data is transferred to the cloud and other external destinations. By doing this, sensitive data is never exposed to cyber-criminals. Scalability: Edge AI frequently handles massive data processing volumes. These technologies are altering the way we handle, analyze, and use data; they are not just trends. Rather, they are catalysts for innovation. Real-time insights are made possible by edge computing, which moves processing capacity closer to the source. Meanwhile, the Internet of Things links objects to form a network of intelligent systems.

An edge case is an issue or scenario that lies outside of standard operating procedures and on the edge of your operational framework in software development and testing. A digital mobile phone technique termed Enhanced Data rates for GSM Evolution (EDGE) permits faster data transfer speeds. It is an improvement to the most extensively used mobile phone standard in the world, the GSM (Global System for Mobile Communications) cellular network.

We welcome contributions from a variety of fields and viewpoints, such as but not limited to: Lightweight AI Algorithms for Real-Time Data Mining in Edge Computing Environments.

 

List of Topics:

  • Special issue on edge computing enabled by artificial intelligence for the Internet of Things.
  • An overview of the latest developments in artificial intelligence driven by edge computing.
  • A simulation-based approach utilizing edge computing for Internet of Things data mining.
  • The intersection of artificial intelligence and edge computing.
  • Innovative artificial intelligence defense strategies implemented in edge computing environments.
  • An intelligent coal mining system using a unique edge computing architecture.
  • An edge service for automated surveillance that uses a hybrid lightweight tracking algorithm.
  • Convolution neural networks with low weight for mobile edge computing in cyber-physical transportation systems.
  • Applying edge computing to pave the final mile of artificial intelligence.
  • An overview of edge and cloud computing's use of computational intelligence techniques.
  • Internet of things edge computing that is intelligent and cooperative.
  • Real-time automotive event logging through near-crash monitoring enabled by inexpensive edge computing.

 

Guest Editors:
Dr. Jawad Khan, Gachon University, Seongnam, South Korea
Dr. Muhammad Hameed Siddiqi, Jouf University, Sakaka, Aljouf, Saudi Arabia
Dr. Tariq Rahim, Kingston University, Kingston, England
Dr. Shah Khalid, National University of Sciences & Technology, Islamabad, Pakistan

 

Tentative Timeline:
Manuscript Submissions Due:   May 15, 2025
First Round of Reviews Completed:   July 20, 2025
Revised Manuscripts Due:   September 18, 2025
Second Round of Reviews Completed:   November 22, 2025
Final Manuscripts Due:   January 10, 2026