More about HKUST
Towards Ubiquitous IoT Sensing: From Low-Cost Devices to Highly- Generalizable Models
The Hong Kong University of Science and Technology
Department of Computer Science and Engineering
PhD Thesis Defence
Title: "Towards Ubiquitous IoT Sensing: From Low-Cost Devices to Highly-
Generalizable Models"
By
Mr. Yinan ZHU
Abstract:
Internet of Things (IoT) sensing has enabled numerous smart applications,
yet still fails to reach full ubiquity, due to two core challenges: (i)
Cost: precise sensing always relies on expensive professional devices,
impeding large-scale deployment, while commercial low-cost devices have
limited sensing granularity; (ii) Generalizability: cross-domain
adaptability is severely hindered by complex domain shifts, such as device
deployment and environmental gaps. This thesis addresses these two
challenges on five typical applications, with innovative research attempts.
The first two attempts develop algorithms to enhance the resolutions of
low-cost sensors: layout features utilization for radio-frequency
identification tag groups and task-oriented spectral reconstruction for
multispectral cameras, thus succeeding high-cost sensors. The next two
attempts explore feature-wise optimization for dataset-level domain
generalization: feature distribution alignment with source-resemble
target-domain data selection and domain- invariant semantic-related feature
extraction with large multimodal models. The last work performs cross-domain
feature alignment for low-cost multispectral data, synergizing two prongs.
Overall, our attempts advance IoT sensing ubiquity with notable cost
reduction and generalizability gain.
Date: Thursday, 8 January 2026
Time: 10:00am - 12:00noon
Venue: Room 3494
Lifts 25/26
Chairman: Prof. Jianzhen YU (CHEM)
Committee Members: Prof. Qian ZHANG (Supervisor)
Prof. Song GUO
Prof. Mo LI
Dr. Qijia SHAO (ISD)
Dr. Yuanqing ZHENG (PolyU)