DDN uses network measurement and user behavior data, based on machine learning techniques, and control/optimization mechanisms, to solve network control and management challenges. We investigate both the practical and theoretical aspects of DDN.
CNS Core: Medium: Collaborative: Exploring and Exploiting Learning for Efficient Network Control: Non-Stationarity, Inter-Dependence, and Domain-Knowledge Oct. 2019 -Sept. 2022.
NeTS: Small: Learning-Guided Network Resource Allocation: A Closed-Loop Approach Sept. 2017 - Aug. 2020.
The Power of Online Learning in Stochastic System Optimization, 2014-2017.
WiFiUS: Collaborative Research: Data-Guided Resource Management for Dense Heterogeneous Networks. 2015-2018.
Machine Learning in Animal Health
This is a collaborative project with Prof. Beatriz Martinez Lopes from UC Davis Veterinarian Medicine. We use machine learning methods to develop effective surveillance and control mechanisms for infectious disease in the swine industry. The work is currently supported by NSF through BIGDATA.
Machine Learning in Healthcare
This project is a collaborative project with Prof. Katherine Kim from UC Davis Nursing school. We use both epidemiologic and machine learning methods to study risks and mortality among adult patients with Acute Lymphoblastic Leukemia, a rare type of cancer.
Past Projects
- Resource Management on Mobile Platforms
- Cognitive Wireless Networks and Opportunistic Spectrum Utilization
- Green ICT
- Enterprise Wireless Mesh Network (SWiM)
- Cellular Network Security
Industrial Collaborators
- AT&T - Data-driving Networking; Cellular Traffic Scheduling
- Fujitsu Laboratories of America, Inc. - Hetnet
- Intel - Mesh Networks