myUMassD is our web portal, a central location for email, notifications, services, and COIN: Corsairs Online Information.
Log in
Topic: Hyperparameter Optimization in Convolutional Neural Network Using Genetic Algorithm with Stopping Criterion ZOOM Teleconference: https://umassd.zoom.us/j/98584029023 Abstract: Hyperparameter optimization is the maximization of a neural network's accuracy using a set of input hyperparameters. With much research going into neural networks, in this case convolutional neural networks (CNNs), most research uses manually chosen hyperparameters instead of choosing optimal hyperparameters. Much work has gone into optimizing hyperparameters as they greatly affect the accuracy of CNNs and enable automated machine learning. Choosing the optimal hyperparameters requires applying an algorithm, in this case the genetic algorithm, to search for them. Each search operation requires a full training using a set of hyperparameters which is computationally expensive. New research has shown advantages to applying a stopping criterion to improve the neural network accuracy while reducing the computational cost. The goal of this research project is to use the genetic algorithm with adapted stopping criterion to reduce the computational cost of optimizing hyperparameters in CNNs. NOTE: All ECE Graduate Students are ENCOURAGED to join the zoom teleconference. All interested parties are invited to join. Advisor: Dr. Ruolin Zhou Committee Members: Dr. Honggang Wang, and Dr. Liudong Xing, Department of Electrical & Computer Engineering, University of Massachusetts Dartmouth *For further information, please contact Dr. Ruolin Zhou via email at rzhou1@umassd
UMass Dartmouth 2021 MFA Thesis Exhibition Exhibition dates: March 30-May 7, 2021 Exhibiting Artists: Ryan Cooley Paulina Fuenzalida-Guzman Taylor Hickey Shabnam Jannesari Sung Ji Lee Madison Moreno Danielle O'Malley Valleri Rami Cynthia Bryndis Schilling Tran Duc Binh Vu Emma Young The UMass Dartmouth 2021 MFA Thesis Exhibition is a much anticipated and celebrated annual event showcasing the artwork of graduating students from the College of Visual and Performing Arts. The creative work of graduating students ranges from traditional media such as painting, sculpture, ceramics, textile, to digital media or site-specific installation. Free timed ticket to see the exhibition for the visitors outside of the UMassD community will be available on the website https://umassdartmouthgalleries.eventbrite.com UMassD students and faculty can visit the exhibition without a ticket. Gallery Hours: Monday - Friday 9 am to 6 pm Exhibition also viewable during CVPA Star Series Finale, Thursdays April 29th from 6 to 8 pm Contact: Viera Levitt, Gallery Director and exhibition curator, gallery@umassd.edu www.umassd.edu/cvpa/galleries
A virtual information session on the graduate business programs at UMass Dartmouth. This event will include information on the following programs: - MBA - MS Accounting - MS Finance - MS Healthcare Management - MS Technology Management This is a virtual zoom event designed to answer questions you may have about the various degree and certificate programs.
Senior Design Projects, or Capstones, represent the culmination of UMass Dartmouth's talented engineering students' academic journey. Small teams of faculty-supervised undergraduates team up with industry partners to apply their skills in real-world applications to address engineering issues. These partnerships offer organizations a preview of potential talent and help in solving engineering-related problems. The University is excited to offer the opportunity for the regional community to learn more about this program from the faculty sponsors in a variety of disciplines to see if it might be a fit for you and your organization. Free, registration required. http://bit.ly/mecapstones For questions, please contact ben.jones@umassd.edu
Senior Design Projects, or Capstones, represent the culmination of UMass Dartmouth's talented engineering students' academic journey. Small teams of faculty-supervised undergraduates team up with industry partners to apply their skills in real-world applications to address engineering issues. These partnerships offer organizations a preview of potential talent and help in solving engineering-related problems. The University is excited to offer the opportunity for the regional community to learn more about this program from the faculty sponsors in a variety of disciplines to see if it might be a fit for you and your organization. Free. Registration required here - https://bit.ly/ececapstones For questions, please contact ben.jones@umassd.edu
Senior Design Projects, or Capstones, represent the culmination of UMass Dartmouth's talented engineering students' academic journey. Small teams of faculty-supervised undergraduates team up with industry partners to apply their skills in real-world applications to address engineering issues. These partnerships offer organizations a preview of potential talent and help in solving engineering-related problems. The University is excited to offer the opportunity for the regional community to learn more about this program from the faculty sponsors in a variety of disciplines to see if it might be a fit for you and your organization. Free. Registration required here - https://bit.ly/becapstones For questions, contact ben.jones@umassd.edu
Senior Design Projects, or Capstones, represent the culmination of UMass Dartmouth's talented engineering students' academic journey. Small teams of faculty-supervised undergraduates team up with industry partners to apply their skills in real-world applications to address engineering issues. These partnerships offer organizations a preview of potential talent and help in solving engineering-related problems. The University is excited to offer the opportunity for the regional community to learn more about this program from the faculty sponsors in a variety of disciplines to see if it might be a fit for you and your organization. Free. Registration required - https://bit.ly/cscaptones For questions, please contact ben.jones@umassd.edu
Mechanical Engineering MS Thesis Defense by Mr. Cory Hoi DATE: May 26, 2021 TIME: 2:00 p.m. to 3:00 p.m. ZOOM LOCATION: https://umassd.zoom.us/j/94137625522? pwd=eW5Jb0pGb0g0U2s2REVsUGl6SXNXZz09 TOPIC: Using computational simulations to develop a fundamental understanding of the governing fluid dynamics of surfactant replacement therapy in treating preterm infants with respiratory distress syndrome ABSTRACT: The aim of this research is to improve the effectiveness of surfactant replacement therapy (SRT) in treating preterm infants with respiratory distress syndrome (RDS) through computational simulations. RDS is caused by a pulmonary surfactant deficiency within the lung, a surface-active molecule necessary for normal breathing operation. Infants born prior to this stage of development (37 weeks) are susceptible to breathing difficulties, and atelectasis, which unfortunately, is the leading cause of mortality in preterm infants. The most common treatment procedure SRT, seeks to replace the missing surfactant in the infant's lung, with the ultimate goal of achieving uniform film distribution and reaching the alveoli at the terminating branches of the airway. Although, relatively effective, SRT has a 35% non-response rate. The low response rate is attributed to the complexity of the human lung, spanning 15 continuously-branching airway tubes which successively become narrower, shorter and more numerous. With the delivery mechanism of surfactant relying on the fluid dynamics in each airway, the consistently changing geometry of the lung makes it extremely difficult for medical practitioners to effectively deliver surfactant plugs uniformly through the airway tree. We seek to better understand the fluid dynamics of surfactant plug transport which contribute to the non-uniform film distribution in the lung. The key principles include: the effect of gravity on plug transport in straight tubes and the relationship between Capillary number and gravity on plug splitting in bifurcating airway models of two- and three-generations. Furthermore, a novel method of surfactant delivery is proposed to overcome the effects which lead to asymmetric film distribution in the airway. The method, muilti-plug aliquot delivery shows improvement in the overall homogeneity of surfactant delivered into the lung, when compared to the traditional method of single dose instillations ADVISOR: Dr. Mehdi Raessi, Associate Professor of Mechanical Engineering, College of Engineering, UMassD COMMITTEE MEMBERS: -Dr. Sankha Bhowmick, Professor of Mechanical Engineering, UMassD -Dr. Banafsheh Seyedaghazadeh, Assistant Professor of Mechanical Engineering, College of Engineering, UMassD Open to the public. All MNE students are encouraged to attend. For more information, please contact Dr. Mehdi Raessi (mraessi@umassd.edu). Thank you, Sue Cunha, Administrative Assistant Mechanical Engineering Department scunha@umassd.edu 508-999-8492
Topic: Reliability Analysis of Storage Area Networks with Cascading Failures ZOOM Teleconference: https://umassd.zoom.us/j/98720525649 Abstract: During the coronavirus pandemic, telecommuting is widely required, making remote data access grow significantly. This requires highly reliable data storage solutions. Storage area networks (SANs) are one of such solutions. To guarantee that SANs can deliver the desired quality of service, reliability modeling and analysis are crucial. A challenge to analyze the reliability of SANs is to address cascading failures that occur when a single initial incident (e.g., the malfunction of one device, overload, extreme weather) triggers a cascade of unexpected failures of other devices. The existing works of considering cascading failures have been mostly centered around traditional power systems and smart grids. In this work, we model the effects of cascading failures triggered by the data overload of devices in SANs. The proportional hazards model and accelerated failure time model are used to describe the relationship between the load and failure behavior of an SAN device. A detailed case study of a mesh SAN system is performed to illustrate the proposed method for the SAN reliability analysis considering cascading failures. Note: All ECE Graduate Students are ENCOURAGED to join the zoom teleconference. All interested parties are invited to join. Advsior: Dr. Liudong Xing Committee Members: Dr. Hong Liu and Dr. Honggang Wang, Department of Electrical & Computer Engineering, University of Massachusetts Dartmouth *For further information, please contact Dr. Liudong Xing via email at lxing@umassd.edu.
Save the date! More details on how the UMass system will honor this holiday that celebrates the emancipation of those who were enslaved in the U.S. to follow Contact: David Gomes, david.gomes.eeo@umassd.edu Sponsored by the Office of the Chief Diversity Officer & BH4S
Visit us from anywhere, at any time. Take a virtual tour of the UMass Dartmouth campus.