Abstract:  Accurate and efficient modeling of urban mobility, along with the prediction of vehicle and human trajectories and object detection in traffic, are crucial for ensuring the safety and resilience of intelligent transportation systems and smart cities. However, the dynamic nature of external environments (such as weather conditions, road networks, neighboring vehicles, and passenger behaviors) or intrinsic changes in target data can lead to significant shifts in data distribution. These shifts can invalidate the trained deep learning models and foster overconfidence in model outputs. In this thesis, we introduce both the learning-based and statistical-based methods to address these issues.First, we design an attention based method for the citywide anomaly event prediction. This method effectively models the spatio-temporal characteristics of urban anomaly events and quantifies the varying impacts of urban mobility on the occurrence of anomaly events. Second, we present an extreme-aware framework to predict the citywide urban mobility under anomalous situations. The proposed framework decomposes the regional urban mobility into spatio-temporally varying regular and extreme dynamics. It minimizes the citywide urban mobility prediction loss under distribution shift. Third, we introduce a conformal prediction based and Gaussian process regression based framework to quantify the output uncertainty of existing trajectory prediction models (base models). This framework aims to improve the prediction accuracy of the base models and reduce the uncertainty of the predicted trajectories under distribution shift. Finally, we introduce an uncertainty-aware adversarial training framework that enhance the resiliency of existing collaborative object detection models for autonomous driving against adversarial attacks. More specifically, this framework alleviates the impacts of adversarial attacks by providing output uncertainty estimation through learning-based module and conformal prediction-based calibration.

Stop by South Campus to connect with Student Health and Wellness's Sexperts & chat about sex and relationships! Sexpert Peer Health Educator Peer Support Drop-In Hours are a free service offered on the UConn Storrs campus. Peer Support Drop-In Hours are a great option for students who have questions about sex and sexual health, are looking for a non-judgmental, laid-back environment to discuss a sex related concern or issue, or are interested in improving their sexual health and personal well-being. The Sexperts are trained to provide education, support, and connection to resources on and off-campus on a wide variety of topics pertaining to sex, sexual health, and relationships.  Fall 2025 Drop In Hours: September 15th – December 5thMonday: 12pm-4pm Tuesday: 9am-6:30pm Wednesday: 11:15am-6pm Thursday: 11am-5:30pm Friday: 10:30am-5:30pm Sexperts (and supervising staff) are designated confidential employees under UConn's Title IX Reporting Obligations. Peer support sessions are for educational and support purposes only. Peer support visits are not on-call or emergency services, and are not for individualized medical advice, nor are they counseling or therapy. If you can't make the times listed, or would prefer to schedule an appointment with a staff sex educator, please reach out to Program Manager for Sexual Health and Peer Education Initiatives, Cassy Setzler, at cassy@uconn.edu (mailto:cassy@uconn.edu) For more information, visit: studenthealth.uconn.edu/sexperts (https://studenthealth.uconn.edu/sexperts) or email cassy@uconn.edu (mailto:cassy@uconn.edu)

For the full class schedule, descriptions, and to register, please visit the UConn Recreation website (https://recreation.uconn.edu/group-fitness-schedule/).

GI Grand Rounds conferences take place weekly on Wednesdays at noon via Webex. Please contact Amy Pallotti to be added to detailed conference announcement emails.

Discover exciting opportunities in healthcare at the UConn Waterbury Healthcare Involvement Fair. Explore jobs, volunteer roles, research, and internships with local organizations. Open to all students interested in health fields. Refreshments will be served. Register here (https://uconn.12twenty.com/events/30006101314802)

As you consider the MS in Accounting program (https://msaccounting.uconn.edu/) at UConn, it is extremely important that that you make an informed choice, and attending a virtual information session is a valuable way to gather the missing pieces. The MSA Virtual Infosessions are an ideal opportunity to learn first-hand about our highly regarded program from admissions representatives.