Abstract:. Robots are becoming increasingly essential in diverse applications, yet their adoption outside controlled environments is hindered by the need for expert programming. For wider accessibility, robots must be able to learn directly from human interactions, even when those humans are non-experts. Learning from Demonstration (LfD) offers a natural approach, enabling skill acquisition from human-provided examples without requiring coding or technical expertise. However, real-world demonstrations can be complex, imperfect, and variable, creating challenges for traditional LfD methods.

This talk describes novel LfD algorithms that can learn from features implicit in human-provided demonstrations, even from non-experts. It presents methods for segmenting long-horizon tasks into primitive movements that can be effectively encoded through LfD techniques and showcases an approach for learning from both successful and failed demonstrations. Together, these contributions advance the ability of robots to acquire more human-like, adaptive, and generalizable skills through human-guided experiences.

Bio: Reza Azadeh is an Associate Professor with the Miner School of Computer and Information Sciences at the University of Massachusetts Lowell (UML), where he directs the Persistent Autonomy and Robot Learning (PeARL) lab. His research interests encompass robot learning and autonomy. He is the recipient of an NSF CAREER Award and a senior member of IEEE. Before joining UML, he was a Postdoctoral Fellow with the School of Interactive Computing at Georgia Institute of Technology. He holds a Ph.D. in Robotics, Cognition, and Interactive Technologies from the University of Genoa, in collaboration with the Italian Institute of Technology. For more on his research, please visit his profile page.

Abstract:. TBA.

Bio: TBA.

Abstract:. Collecting environmental information with mobile sensors had been one of the focus areas of the mobile computing community for several decades. In the last five years, however, two major developments brought new perspectives to the field. The significant decrease in the cost and wide availability of drones made them the default technology in mobile sensing. At the same time, significant developments in artificial intelligence brought new tools into the toolkit of researchers allowing models that use predictive models to react more dynamically to changes in the environment and real-time results of sensing. 

In this talk, I describe an algorithm that is a good example of the new generation of algorithms enabled by the AI revolution. Confidence Guided Path-planning (CGP) has the goal of increasing the confidence in the accuracy of the estimated model at any time point in the data collection process. The approach employs a local estimator based on a Gaussian process regressor and takes advantage of the uncertainty estimation to guide the sensor to areas of lower confidence. In an experimental study comparing CGP with systematic lawnmower-type exploration and random waypoint movement, we found that CGP achieves better scores than both during most of the exploration process, being outperformed only by a fully completed systematic exploration.

Bio: Damla Turgut is Pegasus Professor and Chair of Computer Science at the University of Central Florida (UCF). She is the co-director of the AI Things Laboratory. She held visiting researcher positions at the University of Rome ``La Sapienza'', Imperial College of London, and KTH Royal Institute of Technology, Sweden. Her research interests include wireless ad hoc, sensor, underwater, vehicular, and social networks, edge/cloud computing, smart cities, smart grids, IoT-enabled healthcare and augmented reality, as well as considerations of privacy in the Internet of Things. Dr. Turgut serves on several editorial boards and program committees of prestigious ACM and IEEE journals and conferences. Her most recent honors include Pegasus Professorship in 2024, NCWIT 2021 Mentoring Award for Undergraduate Research (MAUR), the UCF Research Incentive Award, and the UCF Women of Distinction Award. Since 2019, she serves as the N2Women Board Co-Chair where she co-leads the activities of the N2Women Board in supporting female researchers in the fields of networking and communications. Dr. Turgut is an IEEE ComSoc Distinguished Lecturer, IEEE ComSoC Women in Engineering (WIE) Distinguished Lecturer, ACM and IEEE Senior Member, the Chair of the IEEE Technical Community on Computer Communications (TCCC). She is IEEE Computer Society Board of Governors Member (2025-2027).

Abstract:. TBA.

Bio: Emily is a graduating MS cyber student.

Abstract 1: Solar-flare forecasting is a long-standing challenge in space-weather research. Using the SWAN-SF dataset, we evaluate whether elastic distance measures improve pattern detection compared to Euclidean distance. A simple $k$-medoids clustering framework is applied with extensive optimization across high-dimensional metrics. Our experiments reveal that elastic distances, while effective for univariate time series, do not significantly outperform Euclidean distance on the multivariate and highly stochastic solar-flare data. Thousands of trials, supported by both quantitative and qualitative analyses, consistently show that elastic measures collapse to Euclidean distance, highlighting fundamental limitations for solar-flare forecasting with this approach.

Abstract 2: The vast data from space- and ground-based observatories require advanced algorithms for processing, making data quality crucial for machine learning applications. Hα observations from the GONG network provide continuous solar data since 2010. We present H-Alpha Anomalyzer, a lightweight, non-ML anomaly-detection algorithm that flags anomalies based on user-defined criteria. Unlike black-box approaches, it identifies specific regions responsible for anomalies and quantifies their likelihood. To support evaluation, we also release a balanced dataset of 2,000 labeled observations. Results show our method outperforms existing techniques while offering explainability, enabling domain experts to qualitatively assess anomalies.

Bio: Elaina Rohlfing and Mahsa Khazaei are UMSL graduate students in the ESAIR lab, where their research focuses on the use of AI for space-weather preparedness.

Abstract: Argumentative writing is a critical skill that strengthens students reasoning, communication, and analytical abilities. However maintaining a clear and organized argument structure while writing can be challenging. Argument maps visual diagrams which explicitly show an arguments structure have been shown to improve students writing, but are rarely used outside of the planning stage of an essay due to the time and effort required to create them. Automatically generating argument maps from student essays helps students to evaluate the structure of their argument as they write and makes identifying unsupported claims clearly visible.

Bio: Alex is an MS CS student (graduating this semester)

Abstract: This work focuses on improving the accuracy of state-of-the-art LLM-based AES methods. We began by thoroughly investigating why these methods were performing poorly for certain datasets and certain examples. This led us to identify several limitations. After this, we tested several new prompting strategies to improve the accuracy on these hard cases, while maintaining the accuracy on the others. Our improved prompting strategies improved the state-of-the-art essay scoring accuracy by 11%, with an increase in average QWK agreement scores from 0.53 to 0.60. This significant improvement comes from enriching the context for the LLM, reiterating critical instructions, and walking the LLM through the grading process. Accurate AES methods, if implemented with accuracy and validity concerns addressed, can enable students to receive instant feedback, thus improving their learning.

Bio: Tommy is an MS graduating student. He is pursuing PhD in CS at UMSL starting in the fall.

Abstract: MS students will present their master thesis work on Zero Trust Network Architecture: Dipak Sunar: Zero Trust Network Architecture (ZTNA) - technical challenges, implementation approaches, and practical tools for security; Ajay Krishna: Zero Trust Network Architecture for 6G Networks

Bio: Dipack and Ajay are MS cybersecurity students (graduarting this semester)

Abstract: Keith Barber will provide his insight on how to start a career in the geospatial sector. This is a great talk for anyone interested in getting a job as an entry level geospatial professional.

Bio: Keith Barber is a Director of Strategy and Engagement with BAE Systems. BAE is one of the premiere aerospace and information services corporations.