PROJECTSResearch projects
Covers 13 research and applied topics spanning wireless sensor networks, cellular and satellite communications, visual computing, medical and aging studies, and power-equipment inspection.
RESEARCH DIRECTION
Addressing monitoring and data acquisition demands in forest pest and wildfire surveillance, tea-garden disease recognition, and complex under-canopy environments through aerial and near-ground visual sensing alongside low-power wireless sensor networks.
Investigates quality-of-service assurance theory for multi-dimensional, high-precision sensing in forest wireless sensor networks.
Examines quality-of-service (QoS) assurance theory in energy-harvesting cognitive sensor networks, focusing on resource management and service reliability under energy constraints.
Studies quality-of-service (QoS) assurance techniques for cognitive sensor networks operating under dynamic energy conditions, addressing how energy fluctuations affect network service capability.
RESEARCH DIRECTION
Targeting 5G/6G ultra-dense heterogeneous cellular networks and low-Earth-orbit satellite IoT scenarios, this direction studies low-overhead high-dimensional channel acquisition, multi-cell cooperative interference management, and reliable multiple access across dynamic satellite-terrestrial links.
Studies the transmission mechanisms and performance of low-overhead interference alignment assisted by reconfigurable intelligent surfaces for efficient cooperative transmission in ultra-dense heterogeneous networks.
Investigates physical-layer synchronization acquisition and random access techniques for space-based massive wireless IoT systems under long propagation delays, large frequency offsets, and concurrent massive terminal access.
Covers industry-academia research with Huawei on channel acquisition and modelling, cooperative interference management, and metasurface-assisted communication.
RESEARCH DIRECTION
Utilizing radio-frequency signals to simultaneously transmit data and sense environmental and target states, with a focus on WiFi human-action sensing complexity, full-duplex communication security, and energy efficiency in metasurface-assisted wireless systems.
RESEARCH DIRECTION
Combining general deep visual network construction theory with targeted medical image analysis, this direction refines feature extraction operators via signal modulation, wavelet analysis, and multi-channel algebraic structures; scattering networks are studied for medical image segmentation, and multimodal fusion for thyroid-cancer lymph-node metastasis prediction.
Explores construction methods and applications of convolutional neural networks in complex and quaternion domains as a foundational methodology study in visual representation and machine learning.
Focuses on intelligent prediction and interpretability methods for thyroid cancer lymph node metastasis based on multimodal fusion.
Investigates the construction of scattering networks and their application to medical image segmentation.
RESEARCH DIRECTION
Addressing geriatric health evaluation and frailty risk identification requirements through algorithmic and applied research centered on physiological function evaluation, multi-organ aging quantification, and personalized health management.
Participates in a key research initiative with Jiangsu Province Hospital for National Medical Center construction, focusing on AI-enabled early aging warning and personalized anti-aging management frameworks.
Scheduled for 2027-01-01 to 2029-12-31, the research focus is on key technologies for early frailty warning and smart health management based on organ-level aging assessment.
RESEARCH DIRECTION
Serving field operation and maintenance needs in power distribution and metering scenarios, this direction studies equipment localization and defect review workflows in field imagery alongside joint analysis of transformer operating audio and synchronous monitoring parameters.
Studies two-stage equipment localization, defect detection, and manual review mapping for power field imagery, targeting inspection scenarios such as metering boxes, energy meters, data collectors, instrument transformers, enclosure cracks, missing inspection windows, exposed wiring, and work compliance, supported by image-inference demonstration code and Android edge-inference candidate modules.
Focuses on data preparation and joint analysis methodology for the Power Grid Acoustic-and-Parameter Large Model, combining equipment operating audio recordings with synchronous operational parameters and status records from the same equipment and time window.