arXiv subjects

Zhaonan Sun

Publications and source records attributed to Zhaonan Sun.

9 recordsLinked to original sources

arXiv2025

Advanced Assistance for Traffic Crash Analysis: An AI-Driven Multi-Agent Approach to Pre-Crash Reconstruction

Traffic collision reconstruction traditionally relies on human expertise and can be accurate, but pre-crash reconstruction is more challenging. This study develops a multi-agent AI framework that reconstructs pre-crash scenarios and infers vehicle behaviors from fragmented collision data. We propose a two-phase collaborative framework with reconstruction and reasoning stages. The system processes 277 rear-end lead vehicle deceleration (LVD) crashes from the Crash Investigation Sampling System (CISS, 2017 to 2022), integrating narrative reports, structured tabular variables, and scene diagrams. Phase I generates natural-language crash reconstructions from multimodal inputs. Phase II combines these reconstructions with Event Data Recorder (EDR) signals to (1) identify striking and struck vehicles and (2) isolate the EDR records most relevant to the collision moment, enabling inference of key pre-crash behaviors. For validation, we evaluated all LVD cases and emphasized 39 complex crashes where multiple EDR records per crash created ambiguity due to missing or conflicting data. Ground truth was set by consensus of two independent manual annotators, with a separate language model used only to flag potential conflicts for re-checking. The framework achieved 100% accuracy across 4,155 trials; three reasoning models produced identical outputs, indicating that performance is driven by the structured prompts rather than model choice. Research analysts without reconstruction training achieved 92.31% accuracy on the same 39 complex cases. Ablation tests showed that removing structured reasoning anchors reduced case-level accuracy from 99.7% to 96.5% and increased errors across multiple output dimensions. The system remained robust under incomplete inputs. This zero-shot evaluation, without domain-specific training or fine-tuning, suggests a scalable approach for AI-assisted pre-crash analysis.

cs.AI↗

arXiv2025

From Narratives to Probabilistic Reasoning: Predicting and Interpreting Drivers' Hazardous Actions in Crashes Using Large Language Model

Vehicle crashes involve complex interactions between road users, split-second decisions, and challenging environmental conditions. Among these, two-vehicle crashes are the most prevalent, accounting for approximately 70% of roadway crashes and posing a significant challenge to traffic safety. Identifying Driver Hazardous Action (DHA) is essential for understanding crash causation, yet the reliability of DHA data in large-scale databases is limited by inconsistent and labor-intensive manual coding practices. Here, we present an innovative framework that leverages a fine-tuned large language model to automatically infer DHAs from textual crash narratives, thereby improving the validity and interpretability of DHA classifications. Using five years of two-vehicle crash data from MTCF, we fine-tuned the Llama 3.2 1B model on detailed crash narratives and benchmarked its performance against conventional machine learning classifiers, including Random Forest, XGBoost, CatBoost, and a neural network. The fine-tuned LLM achieved an overall accuracy of 80%, surpassing all baseline models and demonstrating pronounced improvements in scenarios with imbalanced data. To increase interpretability, we developed a probabilistic reasoning approach, analyzing model output shifts across original test sets and three targeted counterfactual scenarios: variations in driver distraction and age. Our analysis revealed that introducing distraction for one driver substantially increased the likelihood of "General Unsafe Driving"; distraction for both drivers maximized the probability of "Both Drivers Took Hazardous Actions"; and assigning a teen driver markedly elevated the probability of "Speed and Stopping Violations." Our framework and analytical methods provide a robust and interpretable solution for large-scale automated DHA detection, offering new opportunities for traffic safety analysis and intervention.

cs.AI↗

arXiv2020

New approaches in modeling belt-flesh-pelvis interaction using obese GHBMC models

Obesity is associated with higher fatality risk and altered distribution of occupant injuries in automotive collisions partially because of the increased depth of abdominal soft tissue, which results in limited or delayed engagement of the lap belt with the pelvis and increases the risk of pelvis submarining under the lap belt exposing occupant abdomen to belt loading. Previous modeling studies have shown that pelvis submarining could not be replicated using existing human body models. The goal of this study is to perform model modifications and investigate whether they could lead to model submarining. By detaching the connections between the pelvis and surrounding flesh, submarining like belt kinematics were observed. By remeshing the flesh parts of the model, similar belt kinematics was observed but the pelvic wings were fractured. Finally, large shear deformation on the flesh together with submarining like kinematics were observed in the model with its flesh modeled using the meshless Smooth Particle Galerkin Method SPG method. The results of this study showed that SPG method has potential to simulate large deformations in soft tissue which may be necessary to improve the biofidelity of belt/pelvis interaction.

q-bio.TO↗

arXiv2020

Determination of strain rate in modelling belt-flesh-pelvis interaction during frontal crashes

Obesity is associated with higher fatality risk and altered distribution of occupant injuries in motor vehicle crashes partially because of the increased depth of abdominal soft tissue, which results in limited and delayed engagement of the lap belt with the pelvis and increases the risk of pelvis submarining under the lap belt exposing occupant abdomen to belt loading.

physics.app-ph↗

arXiv2020

DPVis: Visual Analytics with Hidden Markov Models for Disease Progression Pathways

Clinical researchers use disease progression models to understand patient status and characterize progression patterns from longitudinal health records. One approach for disease progression modeling is to describe patient status using a small number of states that represent distinctive distributions over a set of observed measures. Hidden Markov models (HMMs) and its variants are a class of models that both discover these states and make inferences of health states for patients. Despite the advantages of using the algorithms for discovering interesting patterns, it still remains challenging for medical experts to interpret model outputs, understand complex modeling parameters, and clinically make sense of the patterns. To tackle these problems, we conducted a design study with clinical scientists, statisticians, and visualization experts, with the goal to investigate disease progression pathways of chronic diseases, namely type 1 diabetes (T1D), Huntington's disease, Parkinson's disease, and chronic obstructive pulmonary disease (COPD). As a result, we introduce DPVis which seamlessly integrates model parameters and outcomes of HMMs into interpretable and interactive visualizations. In this study, we demonstrate that DPVis is successful in evaluating disease progression models, visually summarizing disease states, interactively exploring disease progression patterns, and building, analyzing, and comparing clinically relevant patient subgroups.

cs.LG↗

arXiv2018

Simultaneous Modeling of Multiple Complications for Risk Profiling in Diabetes Care

Type 2 diabetes mellitus (T2DM) is a chronic disease that often results in multiple complications. Risk prediction and profiling of T2DM complications is critical for healthcare professionals to design personalized treatment plans for patients in diabetes care for improved outcomes. In this paper, we study the risk of developing complications after the initial T2DM diagnosis from longitudinal patient records. We propose a novel multi-task learning approach to simultaneously model multiple complications where each task corresponds to the risk modeling of one complication. Specifically, the proposed method strategically captures the relationships (1) between the risks of multiple T2DM complications, (2) between the different risk factors, and (3) between the risk factor selection patterns. The method uses coefficient shrinkage to identify an informative subset of risk factors from high-dimensional data, and uses a hierarchical Bayesian framework to allow domain knowledge to be incorporated as priors. The proposed method is favorable for healthcare applications because in additional to improved prediction performance, relationships among the different risks and risk factors are also identified. Extensive experimental results on a large electronic medical claims database show that the proposed method outperforms state-of-the-art models by a significant margin. Furthermore, we show that the risk associations learned and the risk factors identified lead to meaningful clinical insights.

cs.LG↗

arXiv2017

Boosting Deep Learning Risk Prediction with Generative Adversarial Networks for Electronic Health Records

The rapid growth of Electronic Health Records (EHRs), as well as the accompanied opportunities in Data-Driven Healthcare (DDH), has been attracting widespread interests and attentions. Recent progress in the design and applications of deep learning methods has shown promising results and is forcing massive changes in healthcare academia and industry, but most of these methods rely on massive labeled data. In this work, we propose a general deep learning framework which is able to boost risk prediction performance with limited EHR data. Our model takes a modified generative adversarial network namely ehrGAN, which can provide plausible labeled EHR data by mimicking real patient records, to augment the training dataset in a semi-supervised learning manner. We use this generative model together with a convolutional neural network (CNN) based prediction model to improve the onset prediction performance. Experiments on two real healthcare datasets demonstrate that our proposed framework produces realistic data samples and achieves significant improvements on classification tasks with the generated data over several stat-of-the-art baselines.

cs.LG↗

arXiv2017

Exploiting Convolutional Neural Network for Risk Prediction with Medical Feature Embedding

The widespread availability of electronic health records (EHRs) promises to usher in the era of personalized medicine. However, the problem of extracting useful clinical representations from longitudinal EHR data remains challenging. In this paper, we explore deep neural network models with learned medical feature embedding to deal with the problems of high dimensionality and temporality. Specifically, we use a multi-layer convolutional neural network (CNN) to parameterize the model and is thus able to capture complex non-linear longitudinal evolution of EHRs. Our model can effectively capture local/short temporal dependency in EHRs, which is beneficial for risk prediction. To account for high dimensionality, we use the embedding medical features in the CNN model which hold the natural medical concepts. Our initial experiments produce promising results and demonstrate the effectiveness of both the medical feature embedding and the proposed convolutional neural network in risk prediction on cohorts of congestive heart failure and diabetes patients compared with several strong baselines.

cs.LG↗

arXiv2014

Statistical calibration of qRT-PCR, microarray and RNA-Seq gene expression data with measurement error models

The accurate quantification of gene expression levels is crucial for transcriptome study. Microarray platforms are commonly used for simultaneously interrogating thousands of genes in the past decade, and recently RNA-Seq has emerged as a promising alternative. The gene expression measurements obtained by microarray and RNA-Seq are, however, subject to various measurement errors. A third platform called qRT-PCR is acknowledged to provide more accurate quantification of gene expression levels than microarray and RNA-Seq, but it has limited throughput capacity. In this article, we propose to use a system of functional measurement error models to model gene expression measurements and calibrate the microarray and RNA-Seq platforms with qRT-PCR. Based on the system, a two-step approach was developed to estimate the biases and error variance components of the three platforms and calculate calibrated estimates of gene expression levels. The estimated biases and variance components shed light on the relative strengths and weaknesses of the three platforms and the calibrated estimates provide a more accurate and consistent quantification of gene expression levels. Theoretical and simulation studies were conducted to establish the properties of those estimates. The system was applied to analyze two gene expression data sets from the Microarray Quality Control (MAQC) and Sequencing Quality Control (SEQC) projects.

stat.AP↗