Searcharxiv⌕ Search

arXiv subjects

Nikhil Raj

Publications and source records attributed to Nikhil Raj.

3 recordsLinked to original sources

PhysXAI: A Theoretical Framework for Diagnosing Physical Hallucinations in Weather Foundation Models

Modern machine learning models for global weather forecasting achieve remarkable predictive accuracy, yet they frequently produce states that violate fundamental physical laws, including conservation of mass, hydrostatic balance, or spectral energy scaling. We term these outputs physical hallucinations and propose PhysXAI, a rigorous diagnostic framework that detects, localises, and attributes such inconsistencies. Unlike existing post-hoc metric suites, PhysXAI is a learnable system that explicitly decouples forecast error from physical plausibility. We formalise the problem through a novel joint condition on numerical and physical residuals, and introduce a multi-branch encoder that extracts representations from conservation, dynamical, spectral, cross-variable, and spatiotemporal residuals. A key innovation is a physics-consistency contrastive learning objective, which we theoretically show the latent representation to be approximately isometric to the physical residual space, ensuring that diagnostic decisions remain grounded in physically meaningful deviations. We further derive an adaptive multi-objective loss with gradient-based weighting to balance competing diagnostic objectives. The framework produces spatially resolved hallucination maps, violation-type classifications, and calibrated Bayesian uncertainty, enabling both detection and interpretable attribution of physical inconsistencies. We conduct a comprehensive comparative evaluation of PhysXAI across ERA5, WeatherBench 2, and MERRA-2, using forecasts from GraphCast, Pangu-Weather, and NeuralGCM, with Python-written code and a fully reproducible experimental protocol. Our theoretical analysis and empirical evaluation establish PhysXAI as a principled framework for diagnosing physical hallucinations and advancing trustworthy AI for weather forecasting.

cs.LG↗

EEG-based Image Feature Extraction for Visual Classification using Deep Learning

While capable of segregating visual data, humans take time to examine a single piece, let alone thousands or millions of samples. The deep learning models efficiently process sizeable information with the help of modern-day computing. However, their questionable decision-making process has raised considerable concerns. Recent studies have identified a new approach to extract image features from EEG signals and combine them with standard image features. These approaches make deep learning models more interpretable and also enables faster converging of models with fewer samples. Inspired by recent studies, we developed an efficient way of encoding EEG signals as images to facilitate a more subtle understanding of brain signals with deep learning models. Using two variations in such encoding methods, we classified the encoded EEG signals corresponding to 39 image classes with a benchmark accuracy of 70% on the layered dataset of six subjects, which is significantly higher than the existing work. Our image classification approach with combined EEG features achieved an accuracy of 82% compared to the slightly better accuracy of a pure deep learning approach; nevertheless, it demonstrates the viability of the theory.

cs.CV↗

Modelling of Human Glottis in VLSI for Low Power Architectures

The Glottal Source is an important component of voice as it can be considered as the excitation signal to the voice apparatus. Nowadays, new techniques of speech processing such as speech recognition and speech synthesis use the glottal closure and opening instants. Current models of the glottal waves derive their shape from approximate information rather than from exactly measured data. General method concentrate on assessment of the glottis opening using optical, acoustical methods, or on visualization of the larynx position using ultrasound, computer tomography or magnetic resonance imaging techniques. In this work, circuit model of Human Glottis using MOS is designed by exploiting fluid volume velocity to current, fluid pressure to voltage, and linear and nonlinear mechanical impedances to linear and nonlinear electrical impedances. The glottis modeled as current source includes linear, non-linear impedances to represent laminar and turbulent flow respectively, in vocal tract. The MOS modelling and simulation results of glottal circuit has been carried out on BSIM 3v3 model in TSMC 0.18 micrometer technology using ELDO simulator.

cs.OH↗