Research

• 2025

• Large Language Model Assisted Human Activity Recognition

  Zhuoran Liu (2025)

  Advised by: Karan Ahuja

  Recognizing human activities from IMU sensor data underpins health monitoring, smart environments and HCI. Conventional HAR methods hinge on complex feature engineering or deep learning, demanding extensive labels and compute. We investigate repurposing LLMs for IMU‑based HAR by encoding statistical and spectral features into text prompts, enabling zero‑ and few‑shot classification. We also explore hybrid models where LLMs enrich classical classifiers with metadata and high‑level semantics. Preliminary experiments show LLMs rival traditional methods in interpretability and adaptability—especially in low‑data or personalized scenarios—paving the way for more transparent, generalizable and interactive HAR systems.

• Human-AI Tools for Contextualizing Differences: Bridging Data-Driven Insights with Real-World Interpretability

  Zhuoran Liu, Medini Chopra (2025)

  Advised by: Haoqi Zhang

  Comparing human experiences across locations is a core challenge in computational social science, HCI, and information retrieval. Although Yelp reviews provide abundant data, TF‑IDF’s document‑length bias, coarse category granularity, and ranking inconsistencies impede reliable cross‑location insights. We introduce a human–AI system that applies BM25 scoring with a threshold‑based relevance model to adjust term weights and surface conceptual shifts. Interactive visualizations make results accessible to both technical and non‑technical audiences. Evaluated on cross‑location review datasets, our approach delivers robust rankings and accurate detection of contextual differences, advancing human‑centered AI, scalable comparative analytics, and interpretability in information retrieval.

  PDF Link

• Cultural Underpinnings of Stress Relief: Exploring Cross-Cultural Coping Strategies

  Zhuoran Liu, Siren Wang, Talia Ben-Naim, Yilin Zhang (2025)

  Advised by: Nabil I Alshurafa

  Stress management varies with culture. While most research examines individual or social coping, few compare methods—exercise, meditation, rituals, leisure—across groups. We surveyed diverse college students on stressors, coping preferences, perceived effectiveness, cultural upbringing and personality. Results will inform culturally adaptive, personalized mental‑health interventions tailored to different cultural contexts.

  Link
• 2024

• Mapping the Role of Wearable and mHealth Technologies in Stress: A Scoping Review

  Zhuoran Liu (2024)

  Advised by: Nabil I Alshurafa

  Stress in its various forms—including acute, physical, cognitive, socio‑evaluative and perceived—undermines mental and cardiovascular health. Wearable devices, mHealth and telemedicine offer real‑time stress monitoring, yet evidence is limited by small samples, short durations and heterogeneous outcomes. In this scoping review of 42 PubMed and IEEE Xplore studies (to September 10, 2024), heart rate variability dominated, while cortisol and telemedicine interventions were under‑utilized. We call for standardized protocols, long‑term effectiveness trials and scalable solutions across diverse populations.

• 2023

• Explainable AI–Driven Integration of Health and Sleep Metrics for Enhanced Cardiovascular Risk Prediction

  Zhuoran Liu — ICS Honor Program (UCI) (2023)

  Advised by: Dr. Mohammad Moshirpour

  Cardiovascular disease remains the world’s leading cause of death, yet routine risk assessments typically emphasize cholesterol and blood pressure while overlooking sleep. We present an explainable machine‑learning framework that jointly evaluates traditional health metrics and sleep characteristics—quality, duration and efficiency—using rigorous feature‑selection to surface their relative importance. By exposing model decisions in human‑readable form, clinicians can see how sleep parameters influence predicted CVD risk. In our experiments, adding sleep data boosted the model’s ability to identify high‑risk cases, suggesting that standard screening should expand to include sleep evaluation. This transparent AI approach not only improves predictive accuracy but also builds clinical trust, laying the groundwork for earlier interventions that could materially reduce cardiovascular mortality.