Applications

Applications show where the methods are used. The order reflects current research direction first, while preserving prior work as evidence of transferable capability.

Biomedical Sensing

Status: ongoing

Radar-based physiological sensing is the primary adaptive sensing testbed. It combines physical measurement models, challenging inverse problems, real-time constraints, and health-relevant signals such as respiration and cardiac motion.

Research themes

• Adaptive waveform design — selecting radar measurement configurations that maximize expected information gain about the underlying physiological state, framed as a sequential decision problem under uncertainty.
• Uncertainty-aware state estimation — reconstructing continuous physiological signals (respiration rate, cardiac motion patterns) from sparse, noisy radar measurements with calibrated Bayesian uncertainty intervals.
• Mechanistic measurement models — encoding electromagnetic propagation physics and sensor geometry into the inference pipeline, rather than treating the radar as a black-box signal source.

Platform

This work is conducted as part of the guest researcher appointment at Hangzhou Institute of Technology, Xidian University. The sensing platform combines radar hardware with real-time signal processing and inference software.

→ Project case study: Adaptive Radar-Based Physiological Sensing

Methodological connection

The sequential-decision framework — choose the next measurement to maximize information gain under constraints — is the same framework that drove target-adjusted MPC for microgrid frequency control (published). The shift is from controlling physical energy systems to measuring physiological systems, but the underlying decision-under-uncertainty architecture is shared.

Closed-loop Discovery

Status: ongoing (manuscript under review)

AntiSyn-AI and related biomedical collaborations motivate expert-reviewed closed-loop experimentation: choosing informative combinations, concentrations, or experimental conditions under assay cost, feasibility, and safety constraints.

Research themes

• Active experiment selection — prioritizing experimental conditions that are expected to be most informative, given current evidence and uncertainty, under safety and cost constraints.
• Uncertainty-aware screening — using calibrated uncertainty to distinguish well-established findings from exploratory results, avoiding premature conclusions from sparse data.
• Human-supervised autonomy — connecting automated selection, execution, and inference into a feedback loop where expert review gates actions that require safety judgment.

Current status

The first manuscript describing the AntiSyn-AI platform for antibacterial combination discovery is currently under review (submitted to npj Antimicrobials and Resistance). A related manuscript on virus-host entity mining is also under review (submitted to Genomics, Proteomics & Bioinformatics). Neither is counted as a published output.

See: AntiSyn-AI for antibacterial discovery, Mining virus-host interaction entities.

→ Project case study: Closed-Loop Discovery with AntiSyn-AI

Methodological connection

The closed-loop experimentation cycle — measure, infer, decide, act — with an expert review gate is the same architecture validated in hardware-in-the-loop microgrid control (published). The shift is from energy hardware to biomedical hardware, but the closed-loop validation methodology is shared.

Energy And Cyber-Physical Systems

Status: published (prior work)

Earlier work in microgrids, building systems, and automation demonstrates the same methodological base in a mature engineering context: model predictive control, grey-box modeling, optimization under uncertainty, and hierarchical closed-loop control.

Selected projects

• Target-adjusted MPC for microgrid frequency control — predictive control under uncertain renewable generation. Published in IET Renewable Power Generation (2019).
• SINDYc and MCMC for prosumer response estimation — mechanistic identification with Bayesian uncertainty. Published in Energies (2020), with open-source software.
• Three-level hierarchical microgrid control — coordinated control validated on a hardware-in-the-loop platform. Published in Electric Power Systems Research (2020).

Prior work is presented as transferable evidence of methodological capability, not as the dominant research identity. The same toolkit — state estimation, prediction, constrained optimization, hardware validation — is being extended to domains where uncertainty is higher and the stakes are clinical.

Status Summary

See the Research page for the research program overview, the Methods page for the methodological pillars, and the Publications page for the complete output record.