skip to main content

Search for: All records

Creators/Authors contains: "Subbian, Vignesh"

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. Free, publicly-accessible full text available July 1, 2024
  2. To better support engineering students and to create an inclusive and welcoming educational context, it is necessary to reimagine instructional methods and approaches. In contrast to deficit educational models that focus on perceptions of what students lack, asset-based practices focus on how students’ lived experiences can be used to enrich and strengthen their educational experiences. There is a need to support faculty in adopting existing techniques or developing new techniques in undergraduate courses, as most existing literature related to asset-based practices is focused on K-12 settings. Engineering design courses provide an ideal context for asset-based practices because the design process requires a diverse set of knowledge, experiences, and skills. Guided by self-determination theory, an understanding of implicit bias and stereotype threat, and the large existing body of research on asset-based pedagogy, we seek to support engineering student outcomes by empowering faculty with tools and strategies to incorporate asset-based practices in their courses. We are engaged in a three-year project focused on assessing the impact of asset-based practices in engineering design courses a large, public, land-grant, Hispanic-serving institution in the southwestern United States, funded by the NSF IUSE:EDU program. Here, we will summarize the design and results from our professional developmentmore »for faculty, including theoretical frameworks and evidence guiding our work. We share content from our professional development, summarizing learning objectives, presentation content, and activities. Additionally, we present comments shared by instructors related to our professional development, including common barriers to implementing educational innovations in their courses. Our work will provide insights to practitioners interested in promoting inclusive classroom practices in engineering education and researchers who are translating research to practice, especially through professional development.« less
    Free, publicly-accessible full text available January 1, 2024
  3. Deep learning algorithms have been moderately successful in diagnoses of diseases by analyzing medical images especially through neuroimaging that is rich in annotated data. Transfer learning methods have demonstrated strong performance in tackling annotated data. It utilizes and transfers knowledge learned from a source domain to target domain even when the dataset is small. There are multiple approaches to transfer learning that result in a range of performance estimates in diagnosis, detection, and classification of clinical problems. Therefore, in this paper, we reviewed transfer learning approaches, their design attributes, and their applications to neuroimaging problems. We reviewed two main literature databases and included the most relevant studies using predefined inclusion criteria. Among 50 reviewed studies, more than half of them are on transfer learning for Alzheimer's disease. Brain mapping and brain tumor detection were second and third most discussed research problems, respectively. The most common source dataset for transfer learning was ImageNet, which is not a neuroimaging dataset. This suggests that the majority of studies preferred pre-trained models instead of training their own model on a neuroimaging dataset. Although, about one third of studies designed their own architecture, most studies used existing Convolutional Neural Network architectures. Magnetic Resonance Imaging wasmore »the most common imaging modality. In almost all studies, transfer learning contributed to better performance in diagnosis, classification, segmentation of different neuroimaging diseases and problems, than methods without transfer learning. Among different transfer learning approaches, fine-tuning all convolutional and fully-connected layers approach and freezing convolutional layers and fine-tuning fully-connected layers approach demonstrated superior performance in terms of accuracy. These recent transfer learning approaches not only show great performance but also require less computational resources and time.« less
  4. Abstract Background

    Retaining women and racially minoritized individuals in engineering programs has been a subject of widespread discussion and investigation. While the sense of belonging and its link to retention have been studied based on student characteristics, there is an absence of studies investigating the importance of students' social identities to their sense of belonging in engineering.


    This study examines differences in race/ethnic identity centrality, gender identity centrality, and sense of belonging in engineering by subgroups of undergraduate engineering students at Hispanic‐Serving Institutions (HSIs). Subsequently, it examines the extent to which these identity centralities predict a sense of belonging in engineering for each subgroup.


    Survey data was collected from 903 Latinx and 452 White undergraduate engineering students from seven HSIs across the continental United States. Multivariate analysis of variance and sequential multivariate linear regression were used to evaluate the research questions.


    Latinx students had higher identity centralities but a similar sense of belonging in the engineering community as White students. Latinos and Latinas had an equivalent sense of belonging in engineering, whereas White women were higher than White men. In the full models, race/ethnic identity centrality significantly, and positively predicted a sense of belonging in engineering for Latinos and White women.more »Gender identity centrality was not a significant predictor of a sense of belonging in engineering for either Latinx or White students.


    Race/ethnic and gender identity centrality are differentially important to the sense of belonging in engineering for students at Hispanic‐Serving Institutions based on their group membership at the intersection of race and gender.

    « less
  5. Background With advances in digital health technologies and proliferation of biomedical data in recent years, applications of machine learning in health care and medicine have gained considerable attention. While inpatient settings are equipped to generate rich clinical data from patients, there is a dearth of actionable information that can be used for pursuing secondary research for specific clinical conditions. Objective This study focused on applying unsupervised machine learning techniques for traumatic brain injury (TBI), which is the leading cause of death and disability among children and adults aged less than 44 years. Specifically, we present a case study to demonstrate the feasibility and applicability of subspace clustering techniques for extracting patterns from data collected from TBI patients. Methods Data for this study were obtained from the Progesterone for Traumatic Brain Injury, Experimental Clinical Treatment–Phase III (PROTECT III) trial, which included a cohort of 882 TBI patients. We applied subspace-clustering methods (density-based, cell-based, and clustering-oriented methods) to this data set and compared the performance of the different clustering methods. Results The analyses showed the following three clusters of laboratory physiological data: (1) international normalized ratio (INR), (2) INR, chloride, and creatinine, and (3) hemoglobin and hematocrit. While all subclustering algorithms hadmore »a reasonable accuracy in classifying patients by mortality status, the density-based algorithm had a higher F1 score and coverage. Conclusions Clustering approaches serve as an important step for phenotype definition and validation in clinical domains such as TBI, where patient and injury heterogeneity are among the major reasons for failure of clinical trials. The results from this study provide a foundation to develop scalable clustering algorithms for further research and validation.« less