Soft Computing, Volume 30, Issue 5, May 2026

· Source: Computational Intelligence · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Data Science & Analytics, Emerging Technologies & Innovation · Depth: Expert, medium

Summary

Soft Computing, Volume 30, Issue 5, published in May 2026, presents 41 research articles spanning diverse computational intelligence topics. Key contributions include a novel data normalization technique using a piecewise continuous, symmetric function with tanh-transformation (pages 3099-3141), and an AI-integrated hardware prototype for battery management systems in electric vehicles (pages 3451-3471). Other notable works cover quantum-like imprecise probabilities (pages 2991-3007), APV-based digital forensics with cloud storage using GMNPR-QBNN (pages 3023-3038), and ANFIS-based output power estimation in photovoltaic cells (pages 3069-3086). The volume also features advancements in fuzzy graphs for nutrition analysis in India (pages 3039-3067), optimization using Simulated Annealing and ANFIS for drilling GFRP (pages 3181-3193), and a multi-objective black widow spider algorithm for flexible job shop problems (pages 3503-3523).

Key takeaway

For AI Scientists and Research Scientists exploring advanced computational methods, this volume offers a rich collection of novel techniques and applications. You should review the specific articles on fuzzy-enhanced graph neural networks for drug-disease association or the AI-integrated hardware prototype for battery management systems to identify potential synergies or direct applications in your current projects. Consider how the presented data normalization or optimization algorithms could refine your existing models.

Key insights

The volume showcases diverse soft computing applications, from theoretical advancements to practical engineering solutions.

Principles

Method

Several papers propose novel algorithms, including a piecewise continuous normalization function, a multi-objective black widow spider algorithm, and a fuzzy-enhanced graph neural network.

In practice

Topics

Best for: AI Scientist, Research Scientist

Related on AIssential

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Computational Intelligence.