Professor Chen-Nee Chuah explores novel network architectures, protocols, and algorithms that ensure reliable, secure, and efficient operation of large-scale computer networks. Her approach is driven by analysis of real Internet traffic, network structures, and control-plane dynamics using massive sets of measurement data obtained from various sources (e.g., IP backbone, enterprise networks, and end hosts) and across different protocol layers. She received an NSF CAREER award to study failure characteristics and stability for wide-area Internet routing (both intra- and inter-domain) and to design new fault restoration and traffic engineering solutions. She is also interested in studying interactions between different network entities and/or across multiple protocol layers. This includes work on modeling the race conditions between overlay- and IP-layer route control mechanisms, and validating the configurations of distributed firewalls.
One major theme of her research is the pursuit of a versatile, programmable, and scalable measurement architecture that is equipped with a sufficient set of primitives to meet the diverse needs of future network services and applications. Such built-in measurement capabilities are important for supporting a wide range of network management tasks, from resource provisioning to anomaly detection. Her research leverages recent advances in sampling theory, signal processing, data streaming, and reconfigurable hardware platforms. For example, she led an NSF project on improving sampling and streaming methods to accurately track traffic footprints critical for detecting network-wide anomalies.
As more social interaction shifts to the Internet via mobile phones and online social networks (OSNs), new opportunities as well as challenges/problems emerge. For instance, malicious activities involving Android applications are rising rapidly. Spurious user accounts on OSNs can be leveraged to launch a variety of malicious activities (e.g., spam, social engineering). Her research team spear-headed the first large-scale measurement studies of user interactions over online social platforms such as Facebook. By integrating multi-dimensional data coming from different genre of networks and contexts (from raw network traces to user profiles or online behavior), her team leveraged data mining, learning & prediction, anomaly detection, and static/code analysis to uncover new, potentially malicious activities.
Professor Chuah is also active in collaborative, interdisciplinary research targeting the interface between networking technologies and emerging societal-scale applications. This includes using leveraging vehicle-to-vehicle and vehicle-to-roadside communications to support intelligent transportation system (ITS) and enable autonomous driving. She and her collaborators have demonstrated how connected vehicles and intelligent roadside units can enhance safety (e.g., via automated incident or pedestrian detection) and improve efficiency (e.g., via collaborative driving, platooning, and actuated signal light control).
In the recent years, Prof. Chuah has also established collaboration with the UC Davis Medical School to explore the application of data analytics and statistical/machine learning techniques to complex classification problems in healthcare. In one of the projects, she and her collaborators applied supervised learning techniques to raw waveform data from mechanical ventilator machines to detect anomalous episodes due to patient-ventilator asynchrony that can result in serious lung injuries for patients in the intensive care units (ICUs). The ICU is a highly complex and fast-paced environment where clinicians need to make life-saving decisions using large amounts of diverse and often complex data from multiple patient monitoring and management devices. The ability to quickly detect acute patient conditions will be key to improve the management and care of patients.