Generative AI and Signal-Image-Control Applications in Image Analysis
Scope and Purpose:
Signal and image analysis benefit significantly from generative AI, which produces new data similar to the original inputs. In fields like medical diagnostics, signal and image data play a crucial role in disease tracking, decision support, and therapeutic planning. Responsible use of technology in these areas requires attention to interpretability and ethical standards. Generative systems are also highly effective in forecasting using sequential data, including signal predictions for engineering applications, as well as captioning, audio classification, and natural language translation tasks. Legal considerations tied to AI continue to emerge. Key issues include liability, intellectual property, and compliance with standards. When AI-driven decisions result in failures or unsafe systems, accountability becomes a central concern. Generative AI aims to synthesize new data that mimics the structure and characteristics of its training input producing content such as images, signals, audio, and text that are nearly indistinguishable from human-made outputs. This evolving field is moving toward seamless integration of multimodal data sources uniting signal, image, and text analysis.
This convergence marks a leap forward, supporting the development of intelligent systems that generate interactive, cross-domain content. Engineers can apply generative AI to simulate signal behaviors, modify visual features, and even develop control models. It also streamlines tasks like code generation and vulnerability analysis, accelerating development and debugging. Through neural networks, deep learning, and algorithmic learning, generative AI enables systems to identify complex patterns in signal and image data, producing accurate and meaningful outputs. These models can also map one form of image or signal data into another, adapting styles or correcting distortions. Training generative models relies on extensive datasets of structured signals, images, and annotated data, allowing the system to identify latent structures and transformations.
Generative AI draws from a suite of intelligent technologies capable of interpreting, simulating, and producing diverse forms of data supporting applications such as speech recognition, image synthesis, pattern analysis, and autonomous control. The success of these models is tied directly to the quality and relevance of the data used during training. Poor-quality data can lead to incorrect or biased outcomes due to overfitting or noise. Creative domains like digital art and audio synthesis benefit as well, where generative AI replicates artistic styles and soundscapes. This AI approach enables systems to generate novel content that matches user-defined requirements by leveraging learned knowledge from vast datasets. This special issue invites submissions from researchers across disciplines, focusing on Generative AI and Signal-Image-Control Applications in Image Analysis.
List of Topics:
• Generation and Enhancement of Images Using Generative Adversarial Networks (GANs)
• Self-Supervised Signal and Image Representation Learning Techniques
• Bridging Low-Fidelity and Enhanced Image Domains with Generative AI
• Transformer-Based Architectures for Signal and Image Understanding
• Generative Models for Semantic Signal and Image Analysis
• Data Augmentation and Enhancement Through Diffusion-Based Models
• Medical Signal and Image Interpretation Using Generative AI
• Reconstruction, Denoising, and Correction of Imaging and Signal Artifacts
• Signal and Image Mapping in Remote Sensing with Generative Models
• Adversarial Attacks and Defenses in Image and Signal Synthesis
• Efficient Architectures for Signal-Control-Based Generative AI Applications
• Generative AI for Artistic Design and Style Transfer in Images
• Applications of Generative AI in Remote Sensing and Geospatial Signal Analysis
Guest Editors:
Dr. Mustafa Bin Man
Professor,
Faculty of Ocean Engineering Technology and Informatics,
Universiti Malaysia Terengganu, Terengganu, Malaysia.
Email: mustafaman@umt.edu.my, mustafabinman@outlook.com
Google Scholar: https://scholar.google.com.my/citations?user=L4VqciUAAAAJ&hl=en
Prof. Dr. Henderi
Professor,
Informatics Engineering,
University of Raharja, Tangerang, Indonesia.
Email: henderi@raharja.info
Google Scholar: https://scholar.google.co.id/citations?user=mOe2HxcAAAAJ&hl=en
Prof. Bishwajeet Kumar Pandey,
Professor,
Department of Intelligent System and Cyber Security,
Astana IT University, Astana, Kazakhstan.
Email: bk.pandey@astanait.edu.kz
Google Scholar: https://scholar.google.co.in/citations?user=UZ_8yAMAAAAJ&hl=en
Important Dates:
• Manuscript submissions due (5.11.2025)
• First round of reviews completed (20.1.2026)
• Revised manuscripts due (25.2.2026)
• Second round of reviews completed (25.3.2026)
• Final manuscripts due (15.5.2026)