1. AIoT-Related Healthcare Projects

Edge Intelligence and Real-Time Health Monitoring

Our AIoT (Artificial Intelligence of Things) research focuses on bringing intelligence closer to the body and environment through TinyML-enabled wearables and edge computing. We design energy-efficient, privacy-preserving, and adaptive sensing networks that can analyze biosignals and behaviors in real time—without relying solely on the cloud.

Key directions include:

• TinyML for physiological monitoring — on-device models for ECG, respiration, motion, and stress detection.

• Edge-cloud hybrid architectures — integrating local analytics with cloud-based LLM reasoning for continuous care.

• Adaptive routing and sensor collaboration — intelligent data pathways that reduce latency, conserve energy, and prioritize urgent medical events.

Our goal is to create autonomous, always-on healthcare ecosystems—smart environments that sense, learn, and respond instantly to individual health changes while safeguarding data privacy.

2. Intelligent Networks and AI Systems

Scalable AI System Architectures

Our research advances intelligent networked systems that coordinate perception, computation, and decision-making across distributed environments. We examine how AI agents, IoT devices, edge nodes, and cloud services can operate as a coherent system rather than as isolated components.

Rather than optimizing individual models in isolation, we design architectural frameworks that enable structured interaction among data pipelines, state management mechanisms, reasoning modules, and governance layers.

Key directions include:

• Distributed Coordinated Systems — We investigate architectural principles in which shared system state serves as the organizing substrate for coordination, adaptation, and resilience across distributed computational entities, shifting emphasis from device-level control to system-level structural coherence.

• Adaptive Intelligence Orchestration Across Boundaries — We study how intelligence is partitioned and reorganized across edge, network, and cloud layers, focusing on dynamic reallocation of computational roles, representational abstraction, and operational responsibilities under evolving environmental constraints.

• Governed Infrastructure for Scalable Learning — We design foundational frameworks for organizing and governing data flows, enabling controlled persistence, access regulation, and long-term structural learning while preserving transparency, accountability, and architectural integrity.

Our goal is to establish principled foundations for intelligent networked systems that are modular, verifiable, and scalable, systems in which intelligence emerges from structured coordination rather than from isolated models or centralized control.

3. Blockchain-Based Healthcare Data Protection

Privacy, Data Sovereignty, and Verifiable Trust in Digital Health

Our research focuses on designing privacy-preserving digital health infrastructures where data protection is treated as a foundational architectural principle rather than an afterthought. We investigate how blockchain and distributed ledger technologies can enforce data integrity, access accountability, and identity protection in AI-driven healthcare ecosystems.

In environments characterized by large-scale data exchange, federated analytics, and multimodal patient monitoring, safeguarding personal identity and preventing unauthorized data exposure are critical. Our work emphasizes architectural mechanisms that minimize data leakage while maintaining verifiability and system transparency.

Key directions include:

• Blockchain-secured data provenance — verifying the origin and authenticity of health data from IoT devices and clinical systems.

• Privacy-preserving federated learning — enabling collaborative AI training across hospitals without sharing raw data.

• Smart-contract-based consent and access control — empowering patients to manage who uses their data and for what purpose.

Our vision is to build a privacy-first digital health ecosystem in which individuals retain meaningful control over their data, and healthcare innovation advances through secure, accountable, and verifiable collaboration.