Research

Professor Corey E. Bakerdirects the Network Reconnaissance (NetRecon) Lab at USC. The NetRecon Lab investigates full stack systems for distributing, protecting, and authenticating data in opportunistic networking scenarios for remote patient monitoring, smart cities, and natural disasters to improve the livelihood of people. I evaluate real-world applications of opportunistic delay tolerant networks (DTNs) and human centered computing to empower device-to-device (D2D) social networks for crowd sourcing information. Leveraging opportunistic communication provides complementary solutions to traditional networks which are typically dependent upon centralized infrastructures such as the Internet. The goal of my research is to make critical  data accessible to vulnerable communities in the midst of intermittent and poor connectivity while minimizing delay.

Resilient networking technology that facilitates the flow of information can be deployed in resource-deprived environments and play an instrumental role in disseminating data that can save lives. Reliance on Internet connectivity is detrimental when modern networking technology is unavailable, power outages are frequent, or network connectivity is sparse or non-existent (i.e., rural environments, natural disasters, and developing countries). My current research provides systems and frameworks for building domain specific mobile applications for routing information in vivo to dynamically create delay tolerant online/offline networks.

 

Sponsorships

Affiliations

Ongoing Projects

2024

Designing Usable Symptom Monitoring Apps for Post Surgery Cancer Patients

Routing solutions do not solely address all of the issues with respect to providing access to underserved communities. There is still the issue of current distress screening measures not being designed in a patient-centric manner. For example, patients may misinterpret how to complete a distress questionnaire or symptom report. Involving patients in the design process of a distress screening intervention could allow for an increased perception of benefits by patients, since the design took patient values into consideration. My research lab designs usable mobile apps for cancer patients and physicians in the Markey Cancer Center. In particular, the NetRecon developed, Assuage, a medical research platform that hosts multiple user interfaces (UIs) for capturing quality of life survey information for patients. For example, Assuage has four UIs that serve as digital representations of the National Comprehensive Cancer Network (NCCN) Distress Thermometer for use as a screening tool for recognizing distress in cancer patients. Assuage allows the aforementioned UIs to be assessed in medical IRB approved pilot studies and for objective and subjective (sensor data) to be delivered to physicians in a distributed HIPAA compliant fashion. Assuage enables physicians and researchers to explore what parts of user interfaces designed with Apple's ResearchKit, CareKit, and HealthKit provide suitable usability without the need of patient-centered design as well as what components have severe limitations that need to be overhauled and codesigned.

Reference Paper
2023

Routing for Remote Patient Care

Rural communities are often plagued with higher rates of chronic disease prevalence and lower access to clinical providers. As a result, rural residents have less access to health services than their urban counterparts. A promising solution to health disparity in rural areas is through the use of mobile health (mHealth) solutions which has been shown to improve the timeliness of clinical decision making, decrease the length of hospital stays, and reduce mortality rates. Despite these promising results, and national efforts to accelerate broadband deployment in underserved areas of the US, rural patients do not benefit to the same extent as their non-rural counterparts due to geographical and financial barriers that result in limited or nonexistent access to broadband connectivity. Additionally, the prevalent design of mHealth solutions are best suited for areas with high speed Internet, as such applications are designed based on the premise that broadband is available and accessible to the users. To address rural remote patient monitoring, the NetRecon Lab investigates hybrid architectures that leverages minimal Internet infrastructure along with node mobility for the dispersal of non-emergency PHI for RRPM real-world rural communities.

Reference Paper
2022

Low Cost Smart Cities

Rapid urbanization burdens city infrastructure and creates the need for local governments to maximize the usage of resources to serve its citizens. Smart city projects aim to alleviate the urbanization problem by deploying a vast amount of Internet-of-things (IoT) devices to monitor and manage environmental conditions and infrastructure. However, smart city projects can be extremely expensive to deploy and manage. A significant portion of the expense is a result of providing Internet connectivity via 5G or WiFi to IoT devices. We propose the use of delay tolerant networks (DTNs) as a backbone in combination with edge computing for smart city communication; enabling developing communities to become smart cities at a fraction of the cost. In collaboration with the City of Louisville, KY, we investigate models to aid policy makers in designing and evaluating the expected performance of such networks. To demonstrate the utility of DTNs we develop a distributed privacy-conscious people counter over existing city infrastructure.

Intellectual Merit

Research in delay tolerant networks (DTNs) and opportunistic communication has been conducted for almost for almost 20 years, yet real-world evaluations and deployments are inadequate or limited to simulation environments. Simulations tend to lead to unexpected real-world performance due to the complexity of characterizing node discovery, mobility, message delivery, and power consumption. This project enables real-world smart city deploy- ments and will assist policy makers will making strategic financial communication decisions based on quality of service (QoS) requirements of smart city data instead of depending on cellular infrastructure that may be underutilized.

Broader Impacts

The research and technology developed in this proposal enables developing communities, rural areas, and developed cities to become smart cities at a reduced cost. Because of the proposed situations, it is a valuable tool in scenarios where government budgets are limited, centralized communications have been temporarily disabled or congested (such as in bad weather events and natural disasters). The potential impact of the proposed innovations can provide important connectivity to citizens, hospitals, and safety personnel in rural areas where infrastructure is limited and to low-income users who would benefit from smart city applications, but cannot afford the costs of standard Internet service. In addition, widespread adoption of low-cost smart cities could relieve congestion on overburdened networks in heavily populated areas without the need to build expensive new infrastructure, allowing municipal leaders to maximize smart city potential without incurring excessive costs.

NSF Presentation & Poster

Interested in Joining the Lab?

The NetReconLab is always looking for motivated students