CNN-based classification model for automated magnetic state identification in spin dynamics simulations

Francesca Albertini, Domenico D’Alessandro

V. Durgadevi, N. Subbulakshmi

Recent breakthroughs in medical computational modelling, particularly in ophthalmology, have produced remarkable achievements in disease identification and classification with the aid of deep learning and hybrid quantum–classical methods. Though the current ensemble CNNs have more than 99% accuracy in diagnosing glaucoma, diabetic retinopathy, and other retinal diseases, scalability and interpretability remain problematic. This paper presents a novel hybrid quantum–classical approach that combines quantum feature encoding with ensemble CNNs optimised to improve diagnostic accuracy and lower computational burden. The new model exhibits higher feature extraction efficiency and noise robustness than traditional architectures. Through the use of quantum state representations, the system enables better decision-making, prediction, and personalised therapy suggestions. Integrated automated analysis of behaviour in this system also supports real-time identification and adaptive treatment planning.In general, the main innovation is the integration of quantum encoding and ensembles of deep learning for the classification of ophthalmic disease, providing a scalable avenue toward intelligent, real-time healthcare analysis.

Elham Taghizadeh, Mohammadtaha Amini, Ali Mohammad-djafari A

R. Rastgarpour, N. Majd

Quantum spin networks represent systems in which quantum spins are arranged on a topological lattice, where the nature of spin interactions and the influence of external magnetic fields can lead to complex collective behaviors. The Hamiltonian governing such systems determines the energy landscape and phase transitions under various thermodynamic conditions. In this paper, we focus on the two-dimensional Ising spin model with periodic boundary conditions subjected to a uniform external magnetic field. Initially, we employ the Metropolis Monte Carlo (MP-MN) algorithm to simulate the system and identify its phase transitions at different magnetic field strengths. The emergence of ordered and disordered phases in response to thermal fluctuations and magnetic interactions is systematically analyzed. Subsequently, we explore the application of convolutional neural networks (CNNs), a powerful class of deep learning models, to detect and classify the phases of the Ising model based on spin configurations generated at a fixed temperature. The CNN is trained using labeled data representing different magnetic field values, and its performance in phase prediction is quantitatively evaluated. The results demonstrate that CNNs can successfully learn complex spin patterns and provide accurate classification of spin phases, highlighting their potential for analyzing phase transitions in statistical physics models.

Elguja Archemashvili

Santiago Acevedo, Carlos Alberto Lamas, Alejo Costa Duran +2 more