Driven by the recent advances in smart, miniaturized, and mass produced sensors, networked systems, and high-speed data communication and computing, the ability to collect and process large volumes of higher veracity real-time data from a variety of modalities is expanding. An ability to fuse these data streams to extract detailed system understanding has the potential to enable more efficient and effective solutions across sectors, particularly if the development cycle can be expedited through tools that can identify a priori the data fusion method best suited for a new, arbitrary application. This points to a critical need for a deeper understanding of the utility and capabilities – as well as the shortcomings and challenges – of existing multimodal data fusion methods across sectors.
This workshop aims to promote the next stage of understanding and discovery – i.e., the development of generalized solutions – by bringing together experts from academia, industry, and government across all domains to drive the needed fundamental advances in the field of multimodal data fusion. This cross-pollination and sharing of lessons will provide a forum for taking initial steps toward the design of a generalized framework for addressing the inherent challenges of fusing multimodal data and outlining a roadmap for critical areas of research in the field, with the goal of working toward domain-independent tools and techniques to facilitate extraction of knowledge from complex data. A highly interactive, facilitated but discussion-driven breakout-and-reconvene format will provide a forum for rapid aggregation of knowledge and learning. Conference discussions and conclusions will be assembled into a comprehensive summary of current state-of-the-art and national roadmap report identifying commonalities, gaps, challenges, and recommending future research directions.
Attendees will benefit by:
- Learning the latest multimodal data fusion success stories from experts across many domains: improving performance, enabling new capabilities, facilitating system cost savings, etc.
- Understanding how MMDF methods and techniques were adapted to various application domains, including highlighting challenges and responses.
- Networking with other professionals who have achieved similar successes, faced comparable challenges, and can share MMDF-related insights.
- Providing critical contributions to the resulting report highlighting the current state of the field and a roadmap for future MMDF research and development.
- Building new cross-disciplinary collaborations to improve competitiveness for upcoming research and funding opportunities.
The MMDF2018 is an expert-driven event organized by a highly interdisciplinary group of faculty utilizing these tools for diverse applications. The complete details of the event, registration, and accommodation for the attendees can be found at the website: www.northeastern.edu/mmdf2018. Organizers can be reached at firstname.lastname@example.org.
Advisory Committee: Akram Alshawabkeh, Lisa Feldman Barrett, Claire Duggan, Deniz Erdoğmuş, Sagar Kamarthi, Haris Koutsopoulos, Stacy Marsella, Mark Patterson, Leonard Polizzotto, Carey Rappaport, Hanumant Singh, Milica Stojanovic, Tommy Thomas.