arXiv subjects

Mostafa Karami

Publications and source records attributed to Mostafa Karami.

8 recordsLinked to original sources

arXiv2026

GIF: A Conditional Multimodal Generative Framework for IR Drop Imaging in Chip Layouts

IR drop analysis is essential in physical chip design to ensure the power integrity of on-chip power delivery networks. Traditional Electronic Design Automation (EDA) tools have become slow and expensive as transistor density scales. Recent works have introduced machine learning (ML)-based methods that formulate IR drop analysis as an image prediction problem. These existing ML approaches fail to capture both local and long-range dependencies and ignore crucial geometrical and topological information from physical layouts and logical connectivity. To address these limitations, we propose GIF, a Generative IR drop Framework that uses both geometrical and topological information to generate IR drop images. GIF fuses image and graph features to guide a conditional diffusion process, producing high-quality IR drop images. For instance, On the CircuitNet-N28 dataset, GIF achieves 0.78 SSIM, 0.95 Pearson correlation, 21.77 PSNR, and 0.026 NMAE, outperforming prior methods. These results demonstrate that our framework, using diffusion based multimodal conditioning, reliably generates high quality IR drop images. This shows that IR drop analysis can effectively leverage recent advances in generative modeling when geometric layout features and logical circuit topology are jointly modeled. By combining geometry aware spatial features with logical graph representations, GIF enables IR drop analysis to benefit from recent advances in generative modeling for structured image generation.

cs.CV↗

arXiv2025

Robust Training with Data Augmentation for Medical Imaging Classification

Deep neural networks are increasingly being used to detect and diagnose medical conditions using medical imaging. Despite their utility, these models are highly vulnerable to adversarial attacks and distribution shifts, which can affect diagnostic reliability and undermine trust among healthcare professionals. In this study, we propose a robust training algorithm with data augmentation (RTDA) to mitigate these vulnerabilities in medical image classification. We benchmark classifier robustness against adversarial perturbations and natural variations of RTDA and six competing baseline techniques, including adversarial training and data augmentation approaches in isolation and combination, using experimental data sets with three different imaging technologies (mammograms, X-rays, and ultrasound). We demonstrate that RTDA achieves superior robustness against adversarial attacks and improved generalization performance in the presence of distribution shift in each image classification task while maintaining high clean accuracy.

eess.IV↗

arXiv2025

Enhanced LSTM by Attention Mechanism for Early Detection of Parkinson's Disease through Voice Signals

Parkinson's disease (PD) is a neurodegenerative condition characterized by notable motor and non-motor manifestations. The assessment tool known as the Unified Parkinson's Disease Rating Scale (UPDRS) plays a crucial role in evaluating the extent of symptomatology associated with Parkinson's Disease (PD). This research presents a complete approach for predicting UPDRS scores using sophisticated Long Short-Term Memory (LSTM) networks that are improved using attention mechanisms, data augmentation techniques, and robust feature selection. The data utilized in this work was obtained from the UC Irvine Machine Learning repository. It encompasses a range of speech metrics collected from patients in the early stages of Parkinson's disease. Recursive Feature Elimination (RFE) was utilized to achieve efficient feature selection, while the application of jittering enhanced the dataset. The Long Short-Term Memory (LSTM) network was carefully crafted to capture temporal fluctuations within the dataset effectively. Additionally, it was enhanced by integrating an attention mechanism, which enhances the network's ability to recognize sequence importance. The methodology that has been described presents a potentially practical approach for conducting a more precise and individualized analysis of medical data related to Parkinson's disease.

cs.SD↗

arXiv2024

Multi-modal Spatial Clustering for Spatial Transcriptomics Utilizing High-resolution Histology Images

Understanding the intricate cellular environment within biological tissues is crucial for uncovering insights into complex biological functions. While single-cell RNA sequencing has significantly enhanced our understanding of cellular states, it lacks the spatial context necessary to fully comprehend the cellular environment. Spatial transcriptomics (ST) addresses this limitation by enabling transcriptome-wide gene expression profiling while preserving spatial context. One of the principal challenges in ST data analysis is spatial clustering, which reveals spatial domains based on the spots within a tissue. Modern ST sequencing procedures typically include a high-resolution histology image, which has been shown in previous studies to be closely connected to gene expression profiles. However, current spatial clustering methods often fail to fully integrate high-resolution histology image features with gene expression data, limiting their ability to capture critical spatial and cellular interactions. In this study, we propose the spatial transcriptomics multi-modal clustering (stMMC) model, a novel contrastive learning-based deep learning approach that integrates gene expression data with histology image features through a multi-modal parallel graph autoencoder. We tested stMMC against four state-of-the-art baseline models: Leiden, GraphST, SpaGCN, and stLearn on two public ST datasets with 13 sample slices in total. The experiments demonstrated that stMMC outperforms all the baseline models in terms of ARI and NMI. An ablation study further validated the contributions of contrastive learning and the incorporation of histology image features.

eess.IV↗

arXiv2024

Bimodal Scaling Law and Size Effect In Superelastic Nanopillars

Shape memory alloys that can deform and then spring back to their original shape, have found a wide range of applications in the medical field, from heart valves to stents. As we push the boundaries of technology creating smaller, more precise tools for delicate surgery treatments, the behavior of these alloys at tiny scales becomes increasingly crucial. In this study, we discover that the size effect of critical stress required for stress-induced phase transformation is not universal. We propose an orientation-dependent power decay law, indicating a specific increase in critical stress for pillars smaller than 1 micron meter for the nominally soft [001] and hard [111] orientations. Additionally, we observe high transformability with 11\% recoverable strain under high stress (2 GPa) through lattice frustration at 200nm scale. This research opens new avenues for exploring the superior elastic behavior of shape memory alloys for nanodevices.

cond-mat.mtrl-sci↗

arXiv2020

Impact of Leakage for Electricity Generation by Pyroelectric Converter

Pyroelectric energy converter is a functional capacitor using pyroelectric material as the dielectric layer. Utilizing the first-order phase transformation of the material, the pyroelectric device can generate adequate electricity within small temperature fluctuations. However, most pyroelectric capacitors are leaking during energy conversion. In this paper, we analyze the thermodynamics of pyroelectric energy conversion with consideration of the electric leakage. Our thermodynamic model is verified by experiments using three phase-transforming ferroelectric materials with different pyroelectric properties and leakage behaviors. We demonstrate that the impact of leakage for electric generation is prominent, and sometimes may be confused with the actual power generation by pyroelectricity. We discover an ideal material candidate, (Ba,Ca)(Ti,Zr,Ce)O$_3$, which exhibits large pyroelectric current and extremely low leakage current. The pyroelectric converter made of this material generates 1.95 $\mu$A/cm$^2$ pyroelectric current density and 0.2 J/cm$^3$ pyroelectric work density even after 1389 thermodynamic conversion cycles.

physics.app-ph↗

arXiv2019

Data-driven approach for synchrotron X-ray Laue microdiffraction scan analysis

We propose a novel data-driven approach for analyzing synchrotron Laue X-ray microdiffraction scans based on machine learning algorithms. The basic architecture and major components of the method are formulated mathematically. We demonstrate it through typical examples including polycrystalline BaTiO$_3$, multiphase transforming alloys and finely twinned martensite. The computational pipeline is implemented for beamline 12.3.2 at the Advanced Light Source, Lawrence Berkeley National Lab. The conventional analytical pathway for X-ray diffraction scans is based on a slow pattern by pattern crystal indexing process. This work provides a new way for analyzing X-ray diffraction 2D patterns, independent of the indexing process, and motivates further studies of X-ray diffraction patterns from the machine learning prospective for the development of suitable feature extraction, clustering and labeling algorithms.

cond-mat.mtrl-sci↗

arXiv2019

Derived Crystal Structure of Martensitic Materials by Solid-Solid Phase Transformation

We propose a mathematical description of crystal structure: underlying translational periodicity together with the distinct atomic positions up to the symmetry operations in the unit cell. It is consistent with the international table of crystallography. By the Cauchy-Born hypothesis, such a description can be integrated with the theory of continuum mechanics to calculate a derived crystal structure produced by solid-solid phase transformation. In addition, we generalize the expressions for orientation relationship between the parent lattice and the derived lattice. The derived structure rationalizes the lattice parameters and the general equivalent atomic positions that assist the indexing process of X-ray diffraction analysis for low symmetry martensitic materials undergoing phase transformation. The analysis is demonstrated in a CuAlMn shape memory alloy. From its austenite phase (L2_1 face-centered cubic structure), we identify that the derived martensitic structure has the orthorhombic symmetry Pmmm with derived lattice parameters a_dv = 4.36491 \AA, b_dv = 5.40865 \AA and c_dv = 4.2402 \AA, by which the complicated X-ray Laue diffraction pattern can be well indexed, and the orientation relationship can be verified.

cond-mat.mtrl-sci↗