Trustworthy AI × Cardiac Digital Twins × Real-world Deployment

Building trustworthy AI systems for cardiac digital twins and safety-critical sensing.

I am Sanjian Zhang, a Ph.D. student in Interdisciplinary Engineering at Kennesaw State University, working on trustworthy AI, multimodal learning, and AI-driven spatiotemporal modeling. My current research focuses on developing machine learning frameworks for cardiac dynamics prediction, with the goal of modeling how the heart evolves over time throughout the cardiac cycle. Specifically, I aim to build models that take as input cardiac structures reconstructed from CT/MRI imaging, together with clinical variables such as blood pressure and physiological signals, and predict the temporal evolution of cardiac motion and physiological states. This research integrates spatiotemporal modeling, generative modeling, and structured representations such as meshes and graphs, with the long-term goal of enabling patient-specific cardiac digital twins as efficient, data-driven alternatives to traditional biomechanical simulation.

View Projects Publications Contact Me Google Scholar

Structure + signals → temporal dynamics → digital twin prediction

Research focus

My work is centered on a core question: how can we learn accurate temporal dynamics of the human heart from heterogeneous data sources, including imaging, clinical variables, and simulation signals? I approach this by designing spatiotemporal learning frameworks that bridge machine learning with structured representations such as meshes and graphs, enabling predictive and generative modeling of cardiac motion.

Spatiotemporal modeling for cardiac motion prediction across the full cardiac cycle Patient-specific cardiac digital twin modeling using imaging, clinical variables, and simulation data Machine learning frameworks for reliable prediction under real-world biomedical constraints

News

Recent updates and milestones. Scroll to view earlier items.

Apr 2026

Began research as a Research Assistant at the University of Mississippi.

Feb 2026

Received Ph.D. offer in Interdisciplinary Engineering at Kennesaw State University.

Dec 2025

Received M.S. degree from the University of Washington.

Aug 2025

One paper accepted at Findings of EMNLP 2025.

Jun 2025

Awarded Best Paper Award at CVPR Workshop 2025.

May 2025

Invited Reviewer for ACM Transactions on the Web (TWEB).

Jan 2025

Won 5th Place in the Cell Behavior Video Classification Challenge (CBVCC), Lugano.

Selected Projects / Systems

Research systems that show both scientific direction and engineering depth.

Ongoing Direction

Cardiac Dynamics Modeling for Digital Twins

Developing spatiotemporal models for cardiac dynamics prediction using imaging-derived structures, physiological variables, and machine learning-based prediction.

Focus: cardiac cycle prediction, mesh representation, and displacement-based temporal modeling.
Methods: spatiotemporal transformers, graph neural networks (e.g., GraphSAGE), mesh-based modeling, and diffusion or video-based generative models.
Goal: building AI-driven surrogates for biomechanical simulation to enable efficient, interpretable, and patient-specific cardiac digital twins.

Benchmark System

Safety-by-Design Visual De-identification Benchmark

Built a reproducible benchmark framework for evaluating privacy-preserving visual transformation under realistic adversarial and utility constraints.

Evaluates privacy leakage through face/plate re-identification and OCR text recovery.
Measures utility, perceptual quality, robustness, latency, and deployment trade-offs.
Designed for camera streams in smart sensing, transportation, and safety-critical environments.

Large-scale Modeling

Temporal Graph Modeling for Community Evolution

Constructed and analyzed large-scale dynamic transaction networks to quantify community evolution and decentralization patterns in blockchain games.

Processed 34M+ transactions and 1.3M+ nodes into monthly temporal graphs.
Applied Leiden community detection and overlap-based tracking for merge/split/birth/death patterns.
Produced CSCWD 2025 oral paper on governance tokens and community evolution.

Selected Publications

Publications connecting trustworthy AI, benchmark design, multimodal systems, and large-scale analysis.

Large Language Model Agents in Finance: A Survey Bridging Research, Practice, and Real-World Deployment Sanjian Zhang, et al. · Findings of EMNLP 2025

Paper →

Securing the Skies: A Comprehensive Survey on Anti-UAV Methods, Benchmarking, and Future Directions Co-first Author · CVPR Workshop 2025 · Best Paper Award

Paper →

Decentralization and Community Evolution in Blockchain Games: The Role of Governance Tokens Sanjian Zhang · CSCWD 2025 · Oral Presentation

IEEE Xplore →

Professional Experience

Production engineering experience supporting deployable, reliable, and measurable AI systems.

Feb 2022 – Aug 2024

Shandong Bee Intelligent Manufacturing Software Developer

Shipped microservice dashboards and exposed ML inference as REST APIs.
Scaled data pipelines to process 2.3 million rows; optimized PostgreSQL/MySQL queries to reduce hot-query P95 latency by 42%.
Improved deployment lead time by 46% by introducing Docker and GitHub Actions CI/CD.
Integrated multiple external data sources with idempotent loaders, retry mechanisms, and structured monitoring.

Aug 2021 – Feb 2022

Tencent (Shenzhen) Backend Developer

Designed search and pagination REST APIs for a knowledge system, reducing P95 latency by 41%.
Implemented JWT authentication, RBAC, and rate limiting for secure backend services.
Reduced post-release defects by 35% through unit and integration testing.
Instrumented structured logging to support offline evaluation of ML features.

Technical Skills

Research, backend, ML, and deployment stack.

AI / ML

PyTorchTransformersVLMsCLIPYOLOv8OpenCVCUDA

Systems

FastAPIDockerGitHub ActionsLinuxRedisREST APIsCI/CD

Data / Engineering

PythonJavaC/C++SQLPostgreSQLMongoDBBash

Research Fit for PhD Collaboration

Designed for faculty visitors: what I can contribute and where I want to grow.

What I bring

I bring a combination of research writing, benchmark construction, backend engineering, and reproducible ML system implementation. My experience spans computer vision, multimodal AI, large-scale graph modeling, evaluation pipelines, and production-oriented software systems.

Strong focus on measurable, reproducible research artifacts.
Experience connecting research ideas with deployable software infrastructure.
Background in visual privacy, trustworthy AI, and safety-critical sensing.

Where I am heading

My PhD direction is to develop AI-driven spatiotemporal models for cardiovascular systems, especially cardiac digital twins, temporal prediction, and simulation-based evaluation. I am interested in methods that combine structure, dynamics, clinical variables, and physical constraints.

Cardiac motion and physiological time-series prediction.
Graph, mesh, and spatiotemporal representation learning.
Robust evaluation for healthcare AI and digital twin deployment.

Contact

Let's build trustworthy AI systems for biomedical modeling, cardiac digital twins, and real-world sensing.

Email GitHub Scholar LinkedIn