Northeastern Selects First Cohort of Impact Engines
Northeastern University has selected its first cohort of Impact Engines to ignite measurable change in problem-solving, three of the five of which are led by engineering faculty. In support of Northeastern University’s Academic Plan, Impact Engines emphasize seamless collaboration across multi-expertise, inclusive networks. Innovation emerges organically wherever challenges and research partnerships intersect. Each Impact Engine focuses on a specific problem in the world and seeks to “move the needle” with respect to that problem.
- Healthier Air and People: Intelligent Solutions to Urban Pollution for Equity and Resilience (iSUPER)
Hyperlocal data is critically needed to make sound policy decisions and recommendations for air pollution control, environmental justice, and urban infrastructure improvement at the city level.
The Intelligent Solutions to Urban Pollution for Equity and Resilience (iSUPER) Impact Engine will pair low-cost, adaptable sensing technologies with novel pollution prediction models to accurately identify hyperlocal pollution hot spots in real-time. This innovative use of these technologies will generate neighborhood-level data that will help guide decision-makers towards effective governance and policymaking. The pilot program will measure data in two Boston neighborhoods representing communities with different socioeconomic characteristics.
Lead PI: CEE Professor Yang Zhang
Crossdisciplinary Team: CEE Professor Haris N. Koutsopoulos, Associate Professor Qi “Ryan” Wang, Associate Professor Matthew J. Eckelman, Assistant Professor Amy Mueller, Professor Ming Wang, Assistant Professor Julia Varshavsky, ECE Professor Jennifer Dy, Assistant Professor Stratis Ioannidis, Professor David Kaeli, CSSH Sara Wylie, Daniel T. O’Brien, and Becca Berkey
- Healthcare Enabled by AI in Real-Time—HEA(RT)
HEA(RT) will focus on the recovery lifecycle of heart surgery patients. Data confirms both poor patient outcomes while in acute care for cardiac surgery and high readmission rates once they are discharged.
By leveraging internal and external partnerships and expertise, HEA(RT) will develop and validate predictive machine-learning algorithms applied to real-time Electronic Health Records (EHRs), vital-signs, physiological waveform, and wearable mobility data from patients in the Maine Medical Center Cardio-Thoracic ICU (CT-ICU). This Impact Engine will perform the first full study that includes algorithms as part of the healthcare team and patient recovery lifecycle.
Lead PIs – BioE/Bouve Professor Rai Winslow and ECE Affiliated Faculty Gene Tunik
- Advanced Design Augmentation (ADA) Through AI for Socially-Aware Product Design
There are several underlying issues with integrating social sustainability and product design. 1. Existing methods to elicit the needs of users are mostly based on human interaction and assessment activities, which are limited in the scope of the data collected and rely on human assessment, experience, and intuition to develop unique insights. 2. Bias, a lack of diversity, and limited inclusion are challenges designers must overcome as they design new products for the global community. 3. The Internet, digital platforms, social media, and mobile devices have enabled users to interact, share opinions, and discuss the products and services they use at scale. However, existing sentiment analysis methods are mostly limited to extracting general favorability metrics from user reviews, leaving the fundamental “latent” needs of individuals/society unknown. 4. There is a lack of computational methods to translate these insights into new, explorative ways to increase the quantity, quality, and diversity of new design knowledge and concepts.
We envision a substantial opportunity to devise an AI framework to fundamentally enhance designers’ ability to innovate “socially-aware” products by identifying pressing and latent societal needs from social media and e-commerce platforms and automatically generating design concept recommendations for designers informed by those needs.
Lead PI(s) – DMSB/MIE Associate Professor Tucker Marion, MIE Assistant Professor Mohsen Moghaddam, CAMD Paolo Ciuccarelli