arXiv subjects

Mia Naeini

Publications and source records attributed to Mia Naeini.

6 recordsLinked to original sources

arXiv2024

Embedding-based Multimodal Learning on Pan-Squamous Cell Carcinomas for Improved Survival Outcomes

Cancer clinics capture disease data at various scales, from genetic to organ level. Current bioinformatic methods struggle to handle the heterogeneous nature of this data, especially with missing modalities. We propose PARADIGM, a Graph Neural Network (GNN) framework that learns from multimodal, heterogeneous datasets to improve clinical outcome prediction. PARADIGM generates embeddings from multi-resolution data using foundation models, aggregates them into patient-level representations, fuses them into a unified graph, and enhances performance for tasks like survival analysis. We train GNNs on pan-Squamous Cell Carcinomas and validate our approach on Moffitt Cancer Center lung SCC data. Multimodal GNN outperforms other models in patient survival prediction. Converging individual data modalities across varying scales provides a more insightful disease view. Our solution aims to understand the patient's circumstances comprehensively, offering insights on heterogeneous data integration and the benefits of converging maximum data views.

q-bio.CB↗

arXiv2024

Self-Normalizing Foundation Model for Enhanced Multi-Omics Data Analysis in Oncology

Multi-omics research has enhanced our understanding of cancer heterogeneity and progression. Investigating molecular data through multi-omics approaches is crucial for unraveling the complex biological mechanisms underlying cancer, thereby enabling more effective diagnosis, treatment, and prevention strategies. However, predicting patient outcomes through the integration of all available multi-omics data is still an under-study research direction. Here, we present SeNMo, a foundation model that has been trained on multi-omics data across 33 cancer types. SeNMo is particularly efficient in handling multi-omics data characterized by high-width and low-length attributes. We trained SeNMo for the task of overall survival of patients using pan-cancer multi-omics data involving 33 cancer sites from the GDC. The training multi-omics data includes gene expression, DNA methylation, miRNA expression, DNA mutations, protein expression modalities, and clinical data. SeNMo was validated on two independent cohorts: Moffitt Cancer Center and CPTAC lung squamous cell carcinoma. We evaluated the model's performance in predicting patient's overall survival using the C-Index. SeNMo performed consistently well in the training regime, reflected by the validation C-Index of 0.76 on GDC's public data. In the testing regime, SeNMo performed with a C-Index of 0.758 on a held-out test set. The model showed an average accuracy of 99.8% on the task of classifying the primary cancer type on the pan-cancer test cohort. SeNMo demonstrated robust performance on the classification task of predicting the primary cancer type of patients. SeNMo further demonstrated significant performance in predicting tertiary lymph structures from multi-omics data, showing generalizability across cancer types, molecular data types, and clinical endpoints.

cs.LG↗

arXiv2024

Resilient Temporal GCN for Smart Grid State Estimation Under Topology Inaccuracies

State Estimation is a crucial task in power systems. Graph Neural Networks have demonstrated significant potential in state estimation for power systems by effectively analyzing measurement data and capturing the complex interactions and interrelations among the measurements through the system's graph structure. However, the information about the system's graph structure may be inaccurate due to noise, attack or lack of accurate information about the topology of the system. This paper studies these scenarios under topology uncertainties and evaluates the impact of the topology uncertainties on the performance of a Temporal Graph Convolutional Network (TGCN) for state estimation in power systems. In order to make the model resilient to topology uncertainties, modifications in the TGCN model are proposed to incorporate a knowledge graph, generated based on the measurement data. This knowledge graph supports the assumed uncertain system graph. Two variations of the TGCN architecture are introduced to integrate the knowledge graph, and their performances are evaluated and compared to demonstrate improved resilience against topology uncertainties. The evaluation results indicate that while the two proposed architecture show different performance, they both improve the performance of the TGCN state estimation under topology uncertainties.

eess.SP↗

arXiv2023

Characterizing the Effects of Single Bus Perturbation on Power Systems Graph Signals

This article explores the effects of a single bus perturbation in the electrical grid using a Graph Signal Processing (GSP) perspective. The perturbation is characterized by a sudden change in real-power load demand or generation. The study focuses on analyzing the spread of the perturbation throughout the grid and proposes a measure of spreadability based on GSP. Moreover, the global and local smoothness properties of the difference bus voltage angle graph signals are evaluated for understanding their embedded patterns of spreadability property. It is demonstrated that the global smoothness of the bus voltage angle graph signal follows a quadratic relationship with the perturbation strength, which helps in characterizing the critical perturbation strength after which the power flow diverges indicating a stressed system. The impact of a single bus perturbation on power system graph signals has been investigated through both analytical derivations using the DC power flow model and simulation using the AC power flow model. The results reveal that the proposed measure of spreadability as well as local and global smoothness properties of the graph signals are independent of the perturbation strength and instead mainly depend on the perturbation's location.

eess.SY↗

arXiv2023

Machine Learning Applications in Cascading Failure Analysis in Power Systems: A Review

Cascading failures pose a significant threat to power grids and have garnered considerable research interest in the power system domain. The inherent uncertainty and severe impact associated with cascading failures have raised concerns, prompting the development of various techniques to study these complex phenomena. In recent years, advancements in monitoring technologies and the availability of large volumes of data from power systems, coupled with the emergence of intelligent algorithms, have made machine learning (ML) techniques increasingly attractive for addressing cascading failure problems. This survey provides a comprehensive overview of ML-based techniques for analyzing cascading failures in power systems. The survey categorizes these techniques based on the evolutionary phases of the cascade process in power systems, as well as studies focusing on cascade resiliency before the occurrence of cascades and problems related to cascades after their termination. By organizing and presenting these works into relevant categories, this survey aims to offer insights and a systematic understanding the role of ML in mitigating cascading failures in power systems.

eess.SY↗

arXiv2022

A Temporal Graph Neural Network for Cyber Attack Detection and Localization in Smart Grids

This paper presents a Temporal Graph Neural Network (TGNN) framework for detection and localization of false data injection and ramp attacks on the system state in smart grids. Capturing the topological information of the system through the GNN framework along with the state measurements can improve the performance of the detection mechanism. The problem is formulated as a classification problem through a GNN with message passing mechanism to identify abnormal measurements. The residual block used in the aggregation process of message passing and the gated recurrent unit can lead to improved computational time and performance. The performance of the proposed model has been evaluated through extensive simulations of power system states and attack scenarios showing promising performance. The sensitivity of the model to intensity and location of the attacks and model's detection delay versus detection accuracy have also been evaluated.

cs.LG↗