SIGBITS March 2022
A WPI Computer Science Department summary of short notes on happenings involving faculty and students.
Agu, Korkin and Ruiz awarded Jurist Dean's Professorships
Emmanuel Agu, Dmitry Korkin and Carolina Ruiz were awarded the Harold L. Jurist '61 and Heather E. Jurist Dean's Professorship. This award recognizes cutting-edge research in one of WPI's multidisciplinary concentrations focused on the smart world. In the School of Arts and Sciences, it recognizes the leading researchers in artificial intelligence, machine learning, and biomedical data analytics.
Heffernan Publications and Grant Awards
Neil Heffernan's recent publications include:
"Improving Automated Scoring of Student Open Responses in Mathematics." Sami Baral, Anthony F Botelho, John A Erickson, Priyanka Benachamardi, Neil T Heffernan. Educational Data Mining Conference 2021.
Toward Personalizing Students' Education with Crowdsourced Tutoring. Ethan Prihar, Thanaporn Patikorn, Anthony Botelho, Adam Sales, Neil Heffernan. L@S'21, June 22-25, 2021, Virtual Event, Germany.
"Classifying Math Knowledge Components via Task-Adaptive Pre-Trained BERT" Jia Tracy Shen, Michiharu Yamashita, Ethan Prihar, Neil Heffernan, Xintao Wu, Sean McGrew, Dongwon Lee. Journal of Artificial Intelligence in Education.
He received four funding awards for a WPI total over $3.2 million. The awarded grants are as follows:
(2022) Recovering from COVID-Learning-Loss with a Platform to Support Human Tutoring. Cristina Heffernan wrote a grant to allow us to study human tutors, and to try to assist them with an AI agent that uses ASSISTments data from their classwork/ homework to suggest which problem the tutor should give to the student. Total $8 million over 5 years. EIR (S411B210024).
(2021) Revisions to the ASSISTments Digital Learning Platform to Expand Its Support for Rigorous Education Research. $2 million over 3 years. This is a grant to allow us to add extra research infrastructure to the ASSISTments platform. R305N210049.
(2021) Collaborative Research: Common Error Diagnostics and Support in Short-answer Math Questions, $849,775 for three years. With Professor Andrew Lan at UMASS (#2118706) and Stacy Shaw @ WPI as well as Cristina Heffernan at The ASSISTments Foundation (#2118904) to work on learning how best to respond to student common mistakes (WPI portion is $239,307). WPI NSF (#2118725).
(2021) Fully Latent Principal Stratification: A New Framework for Big, Complex Implementation Data from Education RCTs. $891,895 over 3 years. Professor Adam Sales is PI. IES #R305D210036.
WPI and The ASSISTments Foundation will be competing in the XPRIZE/IES Digital Learning Challenge for a $500,000 cash prize to show that ASSISTments is the best platform in the world to run experiments on student learning.
Rundensteiner Work on AI and Fairness
Elke Rundensteiner and her students are developing a way to address AI-based algorithms that help ensure fairness in aggregated rankings that impact people in profound ways. The work has been supported by a grant of nearly $500,000 from the National Science Foundation.
Guo Award and Publications
Tian Guo received the 2022 Outstanding Achievement by a Young Alum Award from the Manning College of Information and Computer Sciences, UMass Amherst. This award recognizes Guo's outstanding achievement in deep learning research at an early stage of her career.
Read announcement on cics.umass.edu
She has a number of recent publications in resource efficient mobile deep learning and multi-objective optimization.
The paper "FiShNet: Fine-Grained Filter Sharing for Resource-Efficient Multi-Task Learning" by Xin Dai, Xiangnan Kong, Tian Guo, and Xinlu He was published at the ACM International Conference on Information and Knowledge Management (CIKMâ€™21). This work was led by Kong and Guoâ€™s co-advised Ph.D. student Xin Dai who has successfully defended his thesis and graduated in January 2022. Dr. Dai is currently a Research Scientist at VISA Research.
The poster paper "FusedAR: Adaptive Environment Lighting Reconstruction for Visually Coherent Mobile AR Rendering" by Yiqin Zhao and Tian Guo will appear at the IEEE Conference on Virtual Reality and 3D User Interfaces (IEEE VRâ€™22). This work was led by Guoâ€™s Ph.D. student Yiqin Zhao who is interning at Kuaishou's Y-tech Graphics AI team and will intern at Google Research in Summer 2022 to continue their Augmented Reality work.
The paper "Multi-objective Optimization by Learning Space Partitions" by Yiyang Zhao, Linnan Wang, Kevin Yang, Tianjun Zhang, Tian Guo,, and Yuandong Tian will appear at the 10th International Conference on Learning Representations( ICLRâ€™22). This work was led by Guoâ€™s Ph.D. student Yiyang Zhao and was in collaboration with researchers from Facebook AI Research, UC Berkeley, and Brown University.
Neamtu Grants and Publications
Rodica Neamtu received a number of new grants:
She will lead the introduction of the AI4ALL program at WPI in collaboration with the non- profit organization College Pathways. This program aims to foster a diverse community of AI leaders, spark inter-disciplinary interest in AI and contribute to a more inclusive curriculum that approaches AI from a social impact and ethics lens.
She and colleagues received and NSF Grant: Data-driven Model Formulation and Analysis of Powder Feedstock Flowability, Rheology, and Additive Manufacturing Processability.
She also has new journal publications:
Stephen Price, Matthew Gleason, Bryer Sousa, Danielle Cote, Rodica Neamtu. Automated and Refined Application of Convolutional Neural Network Modeling to Metallic Powder Particle Satellite Detection. In Proceedings of Journal Integrating Materials and Manufacturing Innovation by Springer.
Bryer Sousa, Christopher Vieira, Rodica Neamtu, Danielle Cote. Clustering Algorithms for Nanomechanical Property Mapping and Resultant Microstructural Constituent and Phase Quantification. In Proceedings of Algorithm Development in Materials Science and Engineering, 2022 TMS Annual Meeting & Exhibition.
Bryer Sousa, Richard Valente, Aaron Krueger, Eric Schmid, Danielle Cote, Rodica Neamtu. Investigating the Suitability of Tableau Dashboards and Decision Trees for Particulate Materials Science and Engineering Data Analysis. In Proceedings of AI/Data Informatics: Computational Model Development, Validation, and Uncertainty Quantification, 2022 TMS Annual Meeting & Exhibition.
Solovey Publications and Summer Program Host
Erin Solovey had a number of recent publications.
She and Lorenzo De Carli co-authored a paper with Indrakshi Ray at Colorado State University and it was presented at the European Symposium on Usable Security in October. The paper was given an Honorable Mention for Best Paper Award, indicating it is in the top two papers at the conference.
De Carli, L., Ray, I., Solovey, E.T. (2021). Vision: Stewardship of Smart Devices Security for the Aging Population, 2021 European Symposium on Usable Security (EuroUSEC 2021). 9 Pages.
Along with Hugo Placido da Silva and Nuno Garcia, she was the Guest Editor for a special issue on Biomedical Signals for Human-Computer Interaction in the Frontiers in Computer Science Journal. Along with the issue, she published an editorial in the journal.
Placido da Silva, H., Garcia N.M. and Solovey E.T. (2021). Editorial: Biomedical Signals for Human- Computer Interaction. Frontiers in Computer Science 3:799952. 2 pages.
Putze, F., Putze, S., Sagehorn, M., Micek, C., Solovey, E.T. (2022) Understanding HCI Practices and Challenges of Experiment Reporting with Brain Signals: Towards Reproducibility and Reuse. ACM Transactions on Computer-Human Interaction (TOCHI) 41 pages. In Press.
She is part of a summer program for WPI to Host Hands-On Research Experiences for Worcester-Area Teachers to Support K-12 STEM Education.
Shue Publications and Recognition
Craig Shue has had many recent publications.
Yu Liu, Craig A. Shue, "Avoiding VPN Bottlenecks: Exploring Network-Level Client Identity Validation Options," EAI Conference on Heterogeneous Networking for Quality, Reliability, Security and Robustness, November 2021.
Zorigtbaatar Chuluundorj, Curtis R. Taylor, Robert J. Walls, Craig A. Shue, "Can the User Help? Leveraging User Actions for Network Profiling," IEEE Conference on Software Defined Systems (SDS), December 2021.
Matthew A. Puentes, Yunsen Lei, Noelle Rakotondravony, Lane T. Harrison, Craig A. Shue, "Visualizing Web Application Execution Logs to Improve Software Security Defect Localization," IEEE Conference on Software Analysis, Evolution and Reengineering (SANER) Workshop on Validation, Analysis and Evolution of Software Tests, March 2022.
He was also recognized by the Association for Computing Machinery as a Senior Member.
Yousefi Nature BME Paper and Book Chapter
Ali Yousefi published a recent Nature BME Paper and a book chapter.
Basu, Ishita, Ali Yousefi, Britni Crocker, Rina Zelmann, Angelique C. Paulk, Noam Peled, Kristen K. Ellard et al. "Closed-loop enhancement and neural decoding of cognitive control in humans." Nature Biomedical Engineering (2021): 1-13.
Book Chapter, Handbook of Neuroengineering
Leitschuh Inaugural Dan Kaminsky Fellow
Alumnus Jonathan Leitschuh received the inaugural Dan Kaminsky Fellow. This fellowship was created to celebrate Dan Kaminsky's memory by funding a Fellow for a year to work on open-source projects that make the world a better (and more secure) place. Jonathan was selected based on his passion for open source and for finding and fixing security issues in open source projects.
Diamond Recipient of Upsilon Pi Epsilon Scholarship
The Executive Council of the national Upsilon Pi Epsilon, the Computer Science Honor Society, awarded a scholarship for academic excellence to Benjamin (N'yoma) Diamond, an undergraduate major in the department.
Gennert Organizes Workshop
Michael Gennert organized a workshop on Unified Curriculum and Course Design for Mechatronics and Robotics Engineering Jan 5-7, 2022, funded by the National Science Foundation. This hands-on workshop gave over 40 university faculty nationwide the skills, knowledge, and materials to teach mechatronics and robotics at their institutions. Originally planned for on-campus, it was reconfigured and moved to a virtual format due to covid, with over 200 robot kits shipped to participants.
He was also interviewed by the Boston Globe on recent changes in the robotics industry.
Vartak's Founded Verta to Help Companies Build AI-Enabled Products Faster
Alumnus Manasi Vartak '10 founded Verta to help companies build AI-enabled products faster than ever. She received her PhD at MIT, but her start at WPI was a critical piece. She credits Prof. Elke Rundensteiner for inspiring her curiosity and Prof. Heffernan's Assistments project for helping her believe. Her startup Verta just got $10 million in VC series A funding.
An archive of previous SIGBITS editions is also available. Feel free to review past editions.