Ci-STEM Journal of
Advanced Materials and Computing

Title: Self-Evolving Multi-Modal Digital Twin System Using Reinforcement-Driven Physics-Informed Neural Networks (R-PINN) for Sustainable Advanced Manufacturing
Author: Prabhakar Rao. B, Shraddha Prasad
Pages: 01-08
DOI: https://doi.org/10.55306/CJAMC.2026.010101
Abstract:

The need to optimize manufacturing and ensure its sustainability has increased the pace of implementing digital twins in real-time monitoring, optimization, and control of manufacturing processes. Nevertheless, the majority of the current digital twins are built on a fixed data-driven model, which lacks flexibility, has difficulties with multimodal data integration, and does not provide physical consistency with changing operating conditions. Physics-informed neural networks (PINNs) are partially satisfying to physical fidelity but are constrained by their fixed training schemes and inability to adapt to changing process dynamics. To fill this gap, this paper suggests a self-evolving multi-mode digital twin solution, which is based on reinforcement-based physics-informed neural networks (R-PINN) in sustainable high-end manufacturing. The suggested system is based on multimodal sensor data, physical laws, and reinforcement learning that will allow the digital twin to self-adapt continuously when production conditions alter. Reinforcement learning is a set of dynamically optimizing the parameters of PINN and control policies to reduce the consumption of energy, the error in prediction, and the deviations in processes. The framework is tested on benchmark manufacturing data and simulated industrial conditions with different operational loads. The outcome of the experiment shows a prediction accuracy of 98.1, a 27 percent decrease in energy consumption and quicker convergence in comparison to traditional PINN and deep learning-based models of a digital twin. These findings support the usefulness of the developed R-PINN structure in leading to precise, adaptive and sustainable manufacturing wisdom.
Key Words: Digital Twin, Physics-Informed Neural Networks, Reinforcement Learning, Sustainable Manufacturing, Multimodal Data
Citation: P. R. Barre et al,, “Self-Evolving Multi-Modal Digital Twin System Using Reinforcement-Driven Physics-Informed Neural Networks (R-PINN) for Sustainable Advanced Manufacturing” Ci-STEM Journal of Advanced Materials and Computing, Vol. 1(1), pp. 1-8, 2026.

Title: Bio-Inspired Swarm-Transformer Hybrid Algorithm for High-Precision Nanomaterial Design and Experimental Validation in Biomedical Applications
Author: Naveed Farhana
Pages: 09-16
DOI: https://doi.org/10.55306/CJAMC.2026.010102
Abstract:

Rational design of nanomaterials with tightly defined physicochemical characteristics is essential to the development of biomedical uses of nanomaterials including targeted delivery of drugs, biosensing, and therapeutic imaging. The current methods of computational design, however, cannot effectively search high dimensional design spaces and remain predictively accurate and experimentally viable. Mainstream optimization methods tend to reach a solution at an early stage, but deep learning models need massive labelled datasets and do not support any form of exploration. This poses a very important gap between the computer prediction and experimentally achievable nanomaterial designs. To cope with this difficulty, this article presents a bio-inspired swarm-Transformer hybrid algorithm, which may be applied to design nanomaterial with a high degree of precision and biomedical implementation. The structure combines the global exploration through swarm intelligence with a Transformer-based attention mechanism to understand long-range interactions of nanomaterial descriptors. The swarm module intelligently directs the search to likely areas of designs, whereas the Transformer narrows candidate representations used in predicting and optimizing the desired properties. Making use of publicly available nanomaterial property datasets, the model is assessed and experimental synthesis and characterization of the biomedical performance metrics are validated. The experimental outcomes indicate that on average, it has been able to improve the prediction accuracy of deep learning baselines by 6.8% and also achieves 23 reduction in convergence time. In vitro tests also conclude reaching improved biocompatibility and functional effectiveness of the optimized nanomaterials. These findings demonstrate the usefulness of the suggested hybrid methodology in the gap between computational intelligence and experimental nanomedicine.
Key Words: Nanomaterial Design, Swarm Intelligence, Transformer Models, Biomedical Nanotechnology, Hybrid Optimization
Citation: Farhana. N et al, “Next-Generation Adaptive AI Framework for Smart Healthcare Big Data Analytics,” Ci-STEM Journal of Advanced Materials and Computing, Vol. 1(1), pp. 9-16, 2026.

Title: Secure Post-Quantum Cryptographic Framework Using Hybrid Lattice-Based KEM and Adaptive Federated Learning for Smart City Cyber-Infrastructure
Authors: Sayamuddin Ahmed Jilani, Soumitra Kumar Mandal
Pages: 17-25
DOI: https://doi.org/10.55306/CJAMC.2026.010103
Abstract:

The intensive development of smart city cyber-infrastructure has aggravated the security issues because of the heterogeneity of devices, the volume of constantly changing data, and the lack of confidentiality in the long term. Traditional public-key cryptographic systems like RSA and ECC are becoming susceptible to quantum-powered attacks, and are inappropriate to use in smart city applications in the future. Despite their quantum resistance, post-quantum cryptographic (PQC) schemes are not widely used in practice due to high computational cost, difficulty in key management, and inflexibility to dynamic cyber-threats. Furthermore, the current security systems do not tend to be decentralized, but the sources of intelligence are usually centralized which creates issues of privacy and scalability. This paper mitigates these shortages by suggesting a safe post-quantum architecture that incorporates an adjustable federated learning architecture and a hybridized lattice-based Key Encapsulation Mechanism to smart city cyber-infrastructure. The KEM based on lattice provides resistant to quantum key exchange, whereas federated learning provides decentralized threat intelligence without sensitive local information disclosure. An adaptive aggregation approach dynamically scales model updates based on node reliability and threat intensity, improving resilience to poisoning and inference attacks. Benchmark post-quantum parameters and public intrusion datasets, such as UNSW-NB15 and CICIDS2017 are tested in the framework in a simulated smart city setting. The experimental findings indicate a maximum common exchange latency reduction of 21 percent, versus standalone lattice schemes, and a threat detection rate of 97.8 percent with stable convergence. The results have shown the efficiency of integrating post-quantum cryptography with adaptive federated intelligence in ensuring the security of the next generation smart city infrastructures.
Key Words: Post-Quantum Cryptography, Lattice-Based KEM, Federated Learning, Smart City Security, Quantum-Resistant Cyber-Infrastructure
Citation: S.A. Jilani et al., “Secure Post-Quantum Cryptographic Framework Using Hybrid Lattice-Based KEM and Adaptive Federated Learning for Smart City Cyber-Infrastructure” Ci-STEM Journal of Advanced Materials and Computing, Vol. 1(1), pp. 17-25, 2026.

Title: Quantum-Informed Predictive Deep Graph Neural Network for Microstructure-Property Optimization in Next-Generation Energy Materials
Author: Roshan.K, Ramesh Babu. N
Pages: 26-35
DOI: https://doi.org/10.55306/CJAMC.2026.010104
Abstract:

The development of high-performance materials based on the accurate optimization of microstructure and property is needed to meet the rapid development of energy storage systems and conversion systems. Traditional methods of computation, including density functional theory (DFT) and molecular dynamics (MD), give essential accuracy and can be computationally demanding, and scale-limited when large-scale exploration of materials is required. To overcome these limitations, this research paper suggests a Quantum-Informed Predictive Deep Graph Neural Network (QD-GNN) model that combines quantum-mechanical simulated capabilities with graph-based deep learning to predict and optimize microstructural performance features, including conductivity, mechanical stability, and thermal resiliency. The model uses DFT-based descriptors and graph-based atomic connectivity representations to learn complex structure-property correlations which allows one to predict properties rapidly without the use of expensive repeated high-cost simulation. Also a reinforcement-based optimization tool repeatedly optimizes microstructural configurations to yield desired thresholds in properties. Significant improvements in currently state of art GNN, CGCNN, MEGNet, and SchNet frameworks, in terms of smaller prediction errors, faster screening speed, and better generalization have been verified experimentally through benchmark energy-material datasets. The proposed QD-GNN is a scalable route to AI-intensified discovery of next-generation battery, fuel-cell, and solid-state electrolyte materials.
Key Words: Quantum mechanical simulation, Deep Graph Neural Network, Microstructure-property mapping, Energy materials, Predictive modeling, DFT descriptors, Material informatics, Reinforcement optimization, Materials discovery
Citation: Roshan. K. et al, “Next-Generation Adaptive AI Framework for Smart Healthcare Big Data Analytics,” Ci-STEM Journal of Intelligent Engineering Systems and Networks, Vol. 1(1), pp. 26-35, 2026.

Title: Interpretable Quantum-Enhanced Generative AI Model for Predictive Simulation of Electronic and Thermal Transport in 2D Functional Materials
Author: Rajani D, Ravindranadh. J, Rao. C. R.
Pages: 36-44
DOI: https://doi.org/10.55306/CJAMC.2026.010105
Abstract:

The availability of precise prediction of electronic and thermal transport properties in multidimensional (2D) functional materials is a key to the next-generation nanoelectronics, thermoelectric devices, and energy-efficient system. The conventional first-principles and numerical simulation methods though physically accurate, are computationally complex and not very scalable due to the large size of material design spaces that can be investigated. New deep learning and generative AI designs have made predictions more efficient but are limited by data dependency, poor physical interpretability and lack of generalization between material families. Additionally, a majority of current methods fail to utilize new quantum-enhanced learning state-of-the-art that has the potential to learn the electromagnetic scale interactions of 2D materials which are complex. In response to these issues, this paper will present an interpretable quantum-enhanced generative artificial intelligence to predictive simulation of electronic and thermal transport in 2D functional materials. The proposed model combines a quantum-inspired generative architecture with physics-aware feature encoding and explainability mechanisms to guarantee physically meaningful predictions. The framework is assessed on benchmark 2D material datasets that ushers in first-principles simulations, such as electronic band structure and thermal conductivity measurements. The results of the experiment indicate accuracy in prediction of 98.4 percent of electronic transport and a 24 percent smaller error in simulation of thermal transport as opposed to the state-of-the-art deep learning models. The findings affirm the existence of quantum-enhanced generative intelligence that facilitates precise, interpretable, and scalable simulation of transport phenomena in new 2D materials.
Key Words: Quantum-Enhanced AI, Generative Models, 2D Materials, Electronic Transport, Thermal Transport, Explainable AI
Citation: Rajini. D. et. al, “Next-Generation Adaptive AI Framework for Smart Healthcare Big Data Analytics,” Ci-STEM Journal of Intelligent Engineering Systems and Networks, Vol. 1(1), pp. 36-44, 2026.