Partha Sarathi Bishnu

Objective. Reconstructing clean spin configurations from corrupted or partially observed lattice data is an important inverse problem in statistical physics and scientific machine learning. This paper proposes an attention-guided physics -regularized deep learning framework to reconstruct corrupted two-dimensional Ising spin configurations. Approach. The proposed framework receives a degraded spin lattice together with its corresponding observation mask and jointly reconstructs the unknown spin configuration while estimating its global thermodynamic state. A convolutional encoder–decoder with residual connections and spatial attention is employed to recover the underlying clean spin field. Physical consistency is enforced during training through a composite objective combining reconstruction fidelity with constraints on energy ( E ), absolute magnetization ( | M | ), second-neighbor correlation ( C 2 ) at lattice separation r l = 2 , and binary spin consistency, together with temperature regression and phase classification. Main results. Experiments on Monte Carlo generated datasets for lattice sizes L show that the proposed model achieves a high reconstruction accuracy of approximately 0.88 , with an observed-spin accuracy around 0.90 and a missing-spin accuracy around 0.83 . The model also attains a low temperature prediction error, with the mean absolute error decreasing from 0.197 ( L = 32 ) to 0.088 ( L = 128 ), together with strong phase classification performance ranging from 0.985 to 0.999 . Significance. The reconstructed configurations preserve key thermodynamic observables across temperature, including magnetization, energy, correlation, and heat capacity, demonstrating that the framework successfully maintains physical consistency while performing inverse reconstruction from corrupted Ising data.

Clustering high-dimensional data while assuring robustness to noise and outliers remains a significant challenge in unsupervised learning. This paper proposes an adaptive hybrid clustering framework that integrates the Mahalanobis distance in the latent space and iterative noise filtering to enhance outlier resilience. The framework employs an autoencoder to transform raw data into a compact latent representation, where clustering is performed using the Mahalanobis distance for outlier detection. An adaptive re-weighting mechanism iteratively minimizes the impact of noisy data points, refining cluster assignments. A hybrid loss function is proposed that integrates reconstruction accuracy, an outlier penalty, and the novel Davies-Bouldin Index Normalized Silhouette Score (DBNS) ratio. This combined loss optimizes clustering quality by jointly enhancing intra-cluster cohesion and inter-cluster separation. Experimental results on synthetic and real datasets demonstrate the superior robustness and precision of the proposed approach, outperforming the latest clustering methods in noisy environments.

This study presents a temperature-conditioned deep generative approach for efficiently generating spin configurations of the two-dimensional (2D) Ising model. The method employs a convolutional generator network, conditioned on spin states, temperature embeddings, and random noise, to generate thermodynamically accurate spin configurations on a 2D square lattice. Physics-based constraints, derived from magnetization, energy, and nearest-neighbor correlations obtained via Monte Carlo simulations, are integrated as auxiliary loss terms during training to ensure physical consistency. The model accurately captures phase transition behaviors near the critical temperature and supports the scalable generation of synthetic configurations for further analysis. Investigations across lattice sizes L=16, 32, and 64 demonstrate close alignment with Monte Carlo baselines, with generated configurations achieving mean absolute errors as low as 0.0016 for magnetization, 0.0063 for energy, and 0.0016 for correlation in the L=64 case. Phase classification using standard machine learning models further validates the quality of the generated data, with ensemble classifiers yielding F1 scores above 0.99. These findings highlight the proposed framework as a scalable, computationally efficient solution for generating spin configurations in an Ising model.

Mood disorders can significantly interfere with daily life, ranging from mild to severe, impacting relationships, work, and overall well-being. Globally, the scarcity of mental health resources and the stigma attached to mental illness are significant obstacles. Existing approaches for mood disorder detection often rely on static clinical data or other modalities (e.g., imaging or questionnaires), and the potential of continuous motor activity data remains underexplored. Continuous wearable motor activity recordings represent an objective, non-invasive method that tracks an individual’s behavioral patterns relevant to their mood states, while enabling ongoing monitoring in contrast to the episodic clinical assessments. Our primary goal in this paper is to employ a Deep Learning Model utilizing CNN-GRU architecture for analyzing motor activity sequences. Through rigorous experimentation on Depresjon datasets recorded via wrist worn actigraphy, our approach achieves an accuracy of 98.1%, surpassing the accuracy levels achieved by state-of-the-art techniques.

In the competitive landscape of modern product development, prioritizing features that resonate with customers and deliver maximum value is crucial. This chapter explores the application of clustering algorithms in enhancing decision-making processes across various domains. Beginning with an overview of the K-Means clustering algorithm, the chapter delves into its implementation for feature prioritization and advertising item selection. Key topics include the importance of data collection and preprocessing, interpreting clustering results and integrating insights into product development workflows. Practical case studies and examples illustrate the effectiveness of clustering in real-world scenarios, while discussions on challenges and best practices provide essential guidance for maximizing clustering outcomes. The chapter concludes with a proposed approach for leveraging clustering in advertising strategy, highlighting its role in optimizing marketing efforts through customer segmentation. The chapter aims to equip readers with practical insights into leveraging clustering algorithms for strategic decision-making and innovation.