Events
Winter 2025 grades are due, 72 hours from final exam day.
Martin Luther King, Jr. Day, no classes.
Spring 2025 First 7-week session classes begin.
Spring 2025 Accelerated Nursing Session 1 classes begin.
Spring 2025 First 5-week session classes begin.
Spring 2025 14-week full session classes begin.
Spring classes begin today.
Date: Tuesday, January 21, 2025 Time: 10am Topic: Statistical and Machine Learning Models for System Reliability and Resilience Location: TXT 105 (CSCDR) Abstract: Software reliability and resilience are essential for ensuring dependable system performance, particularly in the face of evolving demands and unexpected disruptions. Traditional reliability models, such as the Non-Homogeneous Poisson Process (NHPP), have been widely used to predict defect occurrence based on testing time or effort. However, these models often fall short of capturing the complexities of real-world systems. Resilience engineering, which focuses on a system's ability to respond to and recover from shocks, has gained significant attention as a complementary approach to reliability. While statistical models provide foundational insights, their rigid assumptions limit flexibility and fail to account for dynamic patterns in defect occurrence and recovery processes. On the other hand, machine learning methods, such as neural networks, offer the potential to model intricate dependencies and non-linear trends. However, these models often require extensive data, which is not always available in resilience engineering contexts, and may lack robustness in long-term predictions. This gap highlights the need for integrated approaches that effectively address the challenges of modeling resilience in systems experiencing varying types and intensities of shocks. In order to address these challenges, this dissertation proposes hybrid approaches including: (i) For defect prediction, we use recurrent neural networks (RNNs) and long short-term memory (LSTM) networks that incorporate covariates to improve predictive accuracy by reflecting key factors driving defect discovery, (ii) To enhance defect classification, we apply Locally Linear Embedding (LLE) as a preprocessing step, which simplifies complex data, allowing classifiers to better interpret defect patterns, and (iii) For resilience assessment, we introduce a transfer function model, a flexible time series approach that considers multiple stressors and recovery patterns. This model captures the dynamic response of a system under varied shocks, allowing for a more accurate resilience evaluation without needing extensive data. By combining machine learning and statistical methods, this dissertation aims to advance both reliability and resilience assessment in software systems, providing robust, adaptable models capable of predicting defects and tracking recovery under complex conditions. These contributions support the development of systems that not only maintain performance but also adapt to future challenges with resilience. ADVISOR(S): Dr. Lance Fiondella, Department of Electrical & Computer Engineering (lfiondella@umassd.edu) COMMITTEE MEMBERS: Dr. Alfa Heryudono, Department of Mathematics Dr. Ruolin Zhou, Department of Electrical & Computer Engineering Dr. Hong Liu, Department of Electrical & Computer Engineering NOTE: All EAS Students are ENCOURAGED to attend.
Spring 2025 Add period and Drop period (for a 100% refund) end for the First 7-week session.
Spring 2025 Add period and Drop period end for the First 5-week session MLT-MLS Program classes.
Handshake is your lifeline to internships, jobs, employers, and events! Join us to activate and complete your account, giving you access to this powerful resource.
Location: ROOM 397D, LARTS, College of Arts & Sciences If you prefer to attend via zoom: Join Zoom Meeting https://umassd.zoom.us/j/92666487596?pwd=NYjSDnGl4BVIibQQEz7ZGM7I5hOTyk.1 Meeting ID: 926 6648 7596 Passcode: 655154 Title: Examining the Associations between Children's Context-Incongruent Fear, Emotion Knowledge, Picture-book Narratives, and Internalizing Outcomes Abstract: Children with less knowledge of emotions, more fearful behaviors, and more negative narratives during storytelling have more internalizing behaviors. However, further research is essential to clarify the complex interplay among these affective factors of early development. This includes pinpointing the contexts in which children's fearfulness is enacted and exploring specific types of emotion knowledge deficits that might be at play. A sample of 74 preschoolers participated in this study on emotion and internalizing behaviors. The study introduced a novel measure of children's fear expressed during non-fearful contexts (context-incongruent fear), and an unexplored assessment of sad and fearful narratives to a picture book. To clarify the contribution of children's processing of emotional contexts, knowledge of negative emotional situations was also assessed. Parents and teachers reported on children's internalizing behavior. Hypotheses predicted context-incongruent fear would be associated with less knowledge of negative emotions, more fearful and sad narratives, and greater internalizing behaviors. Hypotheses also predicted that less knowledge of negative emotion and more fearful and sad narratives would be associated with internalizing behaviors. It was also expected that context-incongruent fear would moderate the association between emotion knowledge and internalizing behavior, such that context-incongruent fear would strengthen the association. Likewise, I expected that context-incongruent fear would moderate the association between sad and fearful narratives and internalizing behavior, but context-incongruent fear would strengthen the association. Finally, a model that incorporated all study factors proposed that the association between emotion knowledge and internalizing behavior would be mediated by fearful and sad narratives, but that this mediation would be more likely in children who showed higher levels of context-incongruent fear. As expected, children's context-incongruent fear and understanding of negative emotion contexts were predictive of internalizing behavior. Additionally, although children who made fearful and sad narratives to the picture-book had greater internalizing behaviors, this was more likely for children who had greater knowledge of negative emotional situations. These findings suggest understanding of negative situations may transpire into negative expressions in everyday situations that promote internalizing behaviors. Additionally, they highlight the interplay between children's understanding of emotional context and the narratives they project onto them with relevance to their emotional well-being. Advisor: Dr. Robin Arkerson Committee Members: Dr. Judith Sims-Knight, Dr. Mary Kayyal For additional information, please contact Verna Drayton at vdrayton@umassd.edu or 508-999-8380