@article{srougi_spencer_cartwright_mckeown_potts_jhala_2024, title={Development and Evaluation of an Immersive and Interactive Virtual Cell Culture Training for Accessible Biotechnology}, volume={300}, ISSN={["1083-351X"]}, DOI={10.1016/j.jbc.2024.105919}, abstractNote={This study explores the design and assessment of an interactive and immersive 3D browser-based virtual mammalian cell culture simulation created to replace or supplement traditional in-person laboratories. Unique to the virtual labs, users are afforded the ability to make independent decisions that drive laboratory outcomes within the virtual environment, thus closely recapitulating the in-person experience while also providing technical feedback. In the fall and spring of 2022, four sections of an upper-level, dual enrollment undergraduate/graduate course in biotechnology tested the simulation that supplemented existing face-to-face cell culture labs focused on sterile mammalian cell culture techniques. Using a qualitative study design, consenting students were surveyed on their perceptions of the simulation and user experience immediately after the virtual lab (n=87 fall, n=96 spring) as well as at the conclusion of the course (n=73 fall, n=74 spring). Seventy-three percent of students surveyed felt the virtual simulation had clear connections to real-world applications and 57% of students agreed that it aided in their understanding of cell culture experiments. Moreover, by the end of the course more than half of students agreed that the virtual experience was realistic and required critical thinking, drawing connections between their existing and new knowledge. These data suggest that the interactive and immersive cell culture simulation may serve as a useful tool in courses such as biochemistry or chemical biology laboratories where expertise in mammalian cell culture techniques is required. Additionally, the virtual experience lowers accessibility barriers to skills training for students who may not be able to participate in traditional labs or at institutions where cost, infrastructure and expertise are prohibitive. This work was funded by BioMADE and an NC State University DELTA grant.}, number={3}, journal={JOURNAL OF BIOLOGICAL CHEMISTRY}, author={Srougi, Melissa and Spencer, Dan and Cartwright, Emily and McKeown, Caitlin and Potts, Colin and Jhala, Arnav}, year={2024}, month={Mar}, pages={S79–S79} }
 @article{spencer_mckeown_tredwell_huckaby_wiedner_dums_cartwright_potts_sudduth_brown_et al._2024, title={Student experiences with a molecular biotechnology course containing an interactive 3D immersive simulation and its impact on motivational beliefs}, volume={19}, ISSN={["1932-6203"]}, DOI={10.1371/journal.pone.0306224}, abstractNote={The development and use of virtual laboratories to augment traditional in-person skills training continues to grow. Virtual labs have been implemented in a number of diverse educational settings, which have many purported benefits including their adaptability, accessibility, and repeatability. However, few studies have evaluated the impact of virtual laboratories outside of academic achievement and skills competencies, especially in biotechnology. In this study, an interdisciplinary team of content experts, video game researchers, instructional designers, and assessment experts developed a 3D immersive simulation designed to teach novice scientists the technical skills necessary to perform sterile mammalian cell culture technique. Unique to the simulation development process is the recreation of an immersive experience through the capture of details in the real-world lab where participants have the freedom of choice in their actions, while receiving immediate feedback on their technical skills as well as procedural execution. However, unlike an in-person laboratory course, students are able to iterate and practice their skills outside of class time and learn from their mistakes. Over the course of two semesters, we used a mixed-methods study design to evaluate student attitudes towards the simulation and their science motivational beliefs. Students' self-efficacy and science identity were assessed after engaging with the simulation prior to the physical laboratory. Our results show that students' science identity remained unchanged while their science self-efficacy increased. Furthermore, students had positive perceptions of the benefits of the virtual simulation. These data suggest that the virtual cell culture simulation can be a useful pedagogical training tool to support students' motivational beliefs that is both accessible and easy to implement.}, number={7}, journal={PLOS ONE}, author={Spencer, Dan and Mckeown, Caitlin and Tredwell, David and Huckaby, Benjamin and Wiedner, Andrew and Dums, Jacob T. and Cartwright, Emily L. and Potts, Colin M. and Sudduth, Nathan and Brown, Evan and et al.}, year={2024}, month={Jul} }
 @article{banerjee_potts_jhala_jaselskis_2023, title={Developing a Construction Domain-Specific Artificial Intelligence Language Model for NCDOT's CLEAR Program to Promote Organizational Innovation and Institutional Knowledge}, volume={37}, ISSN={["1943-5487"]}, DOI={10.1061/JCCEE5.CPENG-4868}, abstractNote={Transportation agency personnel gain valuable knowledge through their work, but such knowledge is lost if it is not documented properly after the worker leaves the organization. The risk of losing institutional knowledge is a current problem at state departments of transportation, including the North Carolina Department of Transportation (NCDOT), due to high personnel turnover. State transportation agencies have implemented knowledge repositories in the form of lessons learned/best practices databases to address this problem. However, motivating end-users to use such databases is challenging. This paper addresses this challenge through novel artificial intelligence technology whereby a neural network–based language model is implemented as part of the NCDOT's new knowledge management program: Communicate Lessons, Exchange Advice, Record (CLEAR). The CLEAR program encompasses a database of lessons learned/best practices and a website to access and search the database. The developed methodology involves training a language model on transportation construction texts and using that trained model in a novel algorithm enabling users to search the CLEAR database easily. The developed language-processing model provides an easily accessible interface to suggest the most relevant CLEAR data based on the end-user's searched keywords. The model learns an inference model of construction domain–specific vocabulary extracted from various sources, such as contract documents, textbooks, and specifications, to make meaningful connections between lessons learned/best practices in the CLEAR database and project-specific knowledge. The developed model has been validated by project managers for projects at various life cycle stages. The automation of information retrieval is intended to encourage NCDOT personnel to use and embrace the CLEAR program as part of their routine work to improve project workflow. In the long run, the NCDOT will benefit from consistent usage of the CLEAR program and its high quality content, thereby leading to enhanced institutional knowledge and organizational innovation.}, number={3}, journal={JOURNAL OF COMPUTING IN CIVIL ENGINEERING}, author={Banerjee, Siddharth and Potts, Colin M. and Jhala, Arnav H. and Jaselskis, Edward J.}, year={2023}, month={May} }
 @article{potts_savaliya_jhala_2022, title={Leveraging Multiple Representations of Topic Models for Knowledge Discovery}, volume={10}, ISSN={["2169-3536"]}, url={https://doi.org/10.1109/ACCESS.2022.3210529}, DOI={10.1109/ACCESS.2022.3210529}, abstractNote={Topic models are often useful in categorization of related documents in information retrieval and knowledge discovery systems, especially for large datasets. Interpreting the output of these models remains an ongoing challenge for the research community. The typical practice in the application of topic models is to tune the parameters of a chosen model for a target dataset and select the model with the best output based on a given metric. We present a novel perspective on topic analysis by presenting a process for combining output from multiple models with different theoretical underpinnings. We show that this results in our ability to tackle novel tasks such as semantic characterization of content that cannot be carried out by using single models. One example task is to characterize the differences between topics or documents in terms of their purpose and also importance with respect to the underlying output of the discovery algorithm. To show the potential benefit of leveraging multiple models we present an algorithm to map the term-space of Latent Dirichlet Allocation (LDA) to the neural document-embedding space of doc2vec. We also show that by utilizing both models in parallel and analyzing the resulting document distributions using the Normalized Pointwise Mutual Information (NPMI) metric we can gain insight into the purpose and importance of topics across models. This approach moves beyond topic identification to a richer characterization of the information and provides a better understanding of the complex relationships between these typically competing techniques.}, journal={IEEE ACCESS}, author={Potts, Colin M. and Savaliya, Akshat and Jhala, Arnav}, year={2022}, pages={104696–104705} }