A grey-scale surveillance image of a shoreline, with a boat in the water outlined by an orange box.

Homeland Sensors and Analytics

The nature of threats to the U.S. homeland is continually evolving, with increasingly sophisticated adversaries and criminal networks targeting our critical infrastructure, land and maritime borders, transportation systems, and public places. Our group develops technologies that use advanced sensors, data analytics, and integrated human-machine decision making to help recognize and disrupt these threats. We specialize in collecting and processing a wide range of data types — including radar, video, imagery, text, point cloud, transactional, and body-worn sensor data — from both commercial and Laboratory-developed sensors. We often apply advanced machine learning methods to convert raw data into actionable insights about the behavior of threat actors and those who intervene to stop them. To help generate requirements for and evaluate our sensing and machine learning technologies, we use systems analysis methods that consider the operators and their environment as part of the system. Our ultimate goal is to field solutions that significantly enhance the decision-making process of analysts and operators who secure the homeland.   

Featured Projects

three people stand on a big dirt pile, outside, with blue sky in the background. One researcher is holding a laptop, which another looks at. The third person is holding a remote, controlling a robotic vehicle also on the dirt pile.
disaster relief
Our see-through-wall sensor is a lightweight, portable technology that peers through rubble and debris of a disaster site to detect survivors.
a photo of boston harbor with several boats on the water; each boat has an orange box drawn around it as a 'detection'
Our video analytics are helping to improve waterway security.
Researchers test the prototype standoff microwave imaging system. The antennas emit radio signals that reflect off the person standing in front of the array; the system processes the reflections to create the image on the monitors in the background.
advanced imaging
The system can rapidly and discreetly detect threat items concealed under clothes or hidden in bags of people in crowded public spaces.
The FOVEA tool is just one of Lincoln Laboratory's efforts to help the Department of Homeland Security Science and Technology Directorate protect public spaces such as subways from attacks.
The tool lets security officials quickly analyze video surveillance footage and track incidents of interest.

Advancing Our Research

Featured Publications

Predicting ankle moment trajectory with adaptive weighted ensemble of LSTM network

Nov 1
2022 IEEE High Perf. Extreme Comp. Conf. (HPEC), 19-23 September 2022, DOI: 10.1109/HPEC55821.2022.9926370.

Utility of inter-subject transfer learning for wearable-sensor-based joint torque prediction models

Oct 31
43rd Annual Intl. Conf. of the IEEE Engineering in Medicine & Biology, 31 October 2021-4 November 2021.