Join Zoom Meeting

https://sc-edu.zoom.us/j/87569507267

 Meeting ID: 875 6950 7267

Abstract:

Artificial Intelligence (AI) is THE topic of the hour - praised to solve the most pressing problems of humankind while at the same time damned as the end of civilization as we know it. In manufacturing, every company today has been told by service providers, vendors, and the media that they need to invest in AI and other Smart Manufacturing technologies or face certain failure. At the same time, there is a lack of understanding of how Applied AI and other Smart Manufacturing technologies impact the business models, value creation, and sustainability in a manufacturing and digital supply network context. This seminar highlights recent promising efforts to apply AI to improve manufacturing. First, we will be looking at selected advanced, smart, and sustainable manufacturing related projects including i) a recently completed collaborative project on ‘Hybrid modeling for energy efficient CNC grinding’ funded by CESMII which achieved a 37% reduction in energy and 41% in processing time, ii) an ongoing effort funded by NSF on factory to factory communication, digital twins, and time-series analytics, iii) a new DoD funded project on time-series analytics in composites additive manufacturing, and iv) a NSF funded effort combining federated learning and blockchain technology in manufacturing networks. Concluding, we will be venturing out a bit by exploring more visionary ‘tomorrow’s’ opportunities of advanced and smart manufacturing technologies. The seminar content is based on projects funded by CESMII, NSF, DoD, NIST, and the EPA, and partially based on the presenter's book 'Digital Supply Networks' by McGraw-Hill that won the IISE Book of the Year 2021 award - www.digitalsupplynetwork.com

Short Bio:

Dr. Thorsten Wuest is a Full Professor of Mechanical Engineering in the Molinaroli College of Engineering and Computing at the University of South Carolina. His research focusses on Smart and Advanced Manufacturing, AI/ML incl., Hybrid Analytics and Federated Learning, Industry 4.0, Servitization and Product Service Systems, as well as closed-loop, item-level Product Lifecycle Management. Dr. Wuest's research is funded by a variety of federal agencies (incl. NSF, NIST, DoD, EPA, NIH, CESMII/DoE), international agencies (incl. Thomas Jefferson Fund, DFG, EC, BMBF, etc.), and industry. He is a globally recognized Smart Manufacturing thought leader and one of SME's 20 most influential professors in smart manufacturing. In addition to publishing his work in the premier academic outlets of his field, he was featured by Forbes, Futurism, IndustryWeek, the World Economic Forum, CBC Radio, and World Manufacturing Forum, etc. Dr. Wuest gave invited talks in more than 10 countries and published three award-winning books and over 170 peer-reviewed articles in international archival journals and conferences gathering over 11,000 citations to-date, and serves as a reviewer for many. He serves as Vice-Chair Americas for the IFIP WG 5.7, is an Associate Editor for the Robotics & Computer-Integrated Manufacturing (RCIM), ASTM Journal Smart and Sustainable Manufacturing Systems (SSMS), and the International Journal of Manufacturing Research (IJMR), and a member of the Editorial Board for the Journal of Manufacturing Systems (JMSY) and Production & Manufacturing Research (PMR) and several more. He serves on the Advisory Board for multiple companies and startups, including the Knudsen Institute, Maven Machines, Veepio, Sustainment, and SavePlanetEarth. Learn more at www.SmartMfg.info

Details at https://research.cec.sc.edu/aii/roundtable-discussion

AI-athon: Bring your data, research problem, and a potential Machine Learning approach (perhaps developed during AI-ification) for full implementation during a one-day hands-on workshop. The AII will provide space and expertise to guide you through installation, coding, and development of a Machine Learning engine. To remain effective, we aim to offer a low participant-to-instructor ratio, therefore, space is limited. At the end of this one-day workshop, you will walk away with a functional ML engine, the knowledge of how to improve the core engine, and have formed a collaborative research in AI/ML.
Registration form: https://forms.office.com/r/muzySJTtnY

AI-ification: Present your research that can benefit from modern AI approaches to a panel of friendly and knowledgeable AI practitioners during the first hour of this meeting. During the second hour of the meeting, the panel will brainstorm and recommend ways of integrating modern AI techniques into your existing research. Form new collaborations and partnerships during the brainstorming session, take the formed ideas to AI-athon, and embark on your path to Deep AI-ification.
Registration form: https://forms.office.com/r/n5dMWBFCXT

Details at https://research.cec.sc.edu/aii/ai-ification

Roundtable Discussion: Join us in a 2-hour meeting when an AI-related topic (suggested by the USC community) is presented by a panel of experts (during the first hour) and discussed by the broader community of participants and experts (during the second hour). The topics will be suggested by the participants and selected based on popularity. 
Registration form: https://forms.office.com/r/n4UznxruNg

More details at https://research.cec.sc.edu/aii/roundtable-discussion

Hope you have had a wonderful start of the semester. Women in Computing will be hosting its first meeting of the Fall semester 6 – 7:30pm, Thursday August 29, in Honors Residence Hall B110! Women in Computing is open to all majors and students interesting in topics of computing technology, and diversity/inclusion within the tech industry. Everyone – all genders and majors is welcome!

Author : Yang Ren
Advisor : Dr. Dezhi Wu, IIT Dept. & Dr. Yan Tong, CSE Dept
Date : Aug 26th
Time:  9:00 am – 11: 00 am
Place : Teams

Link: https://teams.microsoft.com/dl/launcher/launcher.html?url=%2F_%23%2Fl%2…

Dial in by phone

+1 803-400-6044,,897438708# United States, Columbia
Find a local number
Phone conference ID: 897 438 708#

Abstract

          Low Birthweight (LBW) is a major public health issue resulting in increased neonatal mortality and long-term health complications. Traditional LBW analysis methods, focusing on incidence rates and risk factors through statistical models, often struggle with complex unseen data, and thus their effectiveness is limited in early prevention of LBW. As such, more advanced LBW prediction models are needed, so this dissertation delves into this important research area through proposing and examining novel machine learning (ML) and deep learning (DL) algorithms to more accurately predict LBW during the early stage of birthing individuals’ pregnancy period. This dissertation consists of three studies, which covers the following three major research topics.  

     The first topic focuses on the examination of the effectiveness and impact of various data rebalancing techniques for LBW prediction to solve extremely imbalanced data issues. Through this investigation, we established a foundational pipeline for LBW prediction, paving the way for further development and refinement in subsequent studies. This first study also included an extensive feature importance analysis to identify key factors in LBW classification, crucial to guiding targeted interventions to improve birth outcomes.
     The second topic aims to develop a novel longitudinal transformer-based LBW prediction framework, which integrates prenatal mothers’ historical health records and current pre-delivery data, making it possible to provide more comprehensive and relevant input features for LBW prediction. This framework’s ability to effectively process and analyze these diverse data inputs marks a more significant advancement than previous approaches that primarily focus on immediate pre-delivery factors. As a result, this enhanced model is proved to improve the accuracy of LBW predictions, and thus offering a more robust tool for more effective early intervention strategies.
     The third topic is to propose and examine a pioneering fusion framework that combines structured medical records with rich text-based data. This large language model (LLM)-based approach aims to explore and optimize the strengths of both quantitative and qualitative data sources, for enhancing the predictive accuracy and explainability of the LBW prediction models. By integrating diverse data types, this proposed method is expected to offer in-depth insights into the myriad factors contributing to LBW, potentially unveiling previously unrecognized and more granular risk factors to refine the prediction models further.
     In summary, this dissertation presents a comprehensive exploration of using advanced ML and DL algorithms in the prediction of LBW through a series of three studies. From establishing LBW prediction pipeline with rebalancing strategies (Study 1), developing a transformer-based approach (Study 2) to introducing a tabular-text fusion framework (Study 3), this research will contribute to a substantial advancement in prenatal care. By enabling earlier and more accurate identification of LBW risks, this work has the potential to transform prenatal intervention strategies, leading to improved health outcomes for both mothers and their infants.

DISSERTATION DEFENSE

Author : Rui Xin

Advisor : Dr. Jijun Tang

Date : July 15, 2024

Time:  9:00 am – 11: 00 am

Place : Zoom

Link:https://zoom.us/j/94479902244?pwd=8XbYQPbZaxXXeBt4e1r5gqrBy6upb4.1

Meeting ID: 944 7990 2244

Passcode: 126908

Abstract

    Deep Learning is pivotal in advancing data analysis across various scientific fields, from genomics to materials discovery. Despite its widespread use, efficiently learning from limited data and operating under resource constraints remains a significant challenge, often limiting its full potential in environments where data is scarce or resources are restricted. This dissertation explores Active Learning and Automated Machine Learning (AutoML) powered by Bayesian Optimization to enhance the efficiency of machine learning across multiple disciplines. It focuses on algorithm optimization and data management through three interconnected studies.

In the first study, we investigate how data management technique - active learning helps discover new materials with target properties in limited dataset considering the vast chemical design space. We propose an active generative inverse design method that combines active learning with a deep autoencoder neural network and a generative adversarial deep neural network model to discover new materials with a target property in the whole chemical design space. Our experiments demonstrate that although active learning may select chemically infeasible candidates, these samples are beneficial for training robust screening models. These models effectively filter and identify materials with desired properties from those generated hypothetically by the generative model. The results confirm the success of our active generative inverse design approach.

In the second study, we explore cancer heterogeneity and specificity through the analysis of mutational signatures, using collinearity analysis and machine learning techniques. These techniques include either a decision tree-based ensemble model or a flexible neural network-based method with automated hyperparameter optimization, each customizing a neural network for individual sub-tasks. Through thorough training and independent validation, our results reveal that although the majority of mutational signatures are distinct, similarities between certain mutational signature pairs are observed through both mutation patterns and mutational signature abundance. These observations can potentially assist in determining the etiology of still elusive mutational signatures. Further analysis using machine learning approaches indicates specific mutational signature relevance to cancer types, with skin cancer showing the strongest specificity among all cancer types.

Finally, we analyze cancer heterogeneity by examining immune cell compositions in tumor microenvironments, using neural architecture search to develop tailored models for classification subtasks. By analyzing transcriptome profiles from 11,274 patients across 33 cancer types to identify 22 immune cell types, we employ deep learning to model outcomes for cancer type and tumor-normal distinctions, utilizing the Shannon index for immune cell diversity and Cox regression for prognostic evaluations. Our findings reveal significant immune cell differences between tumors and normal tissues, with some discrepancies in directional differences across cancers. Immune cell composition patterns modestly differentiate cancer types, with sixteen significant prognostic associations identified, such as in kidney renal clear cell carcinoma. Additionally, immune cell diversity shows marked differences in seven cancer types and correlates positively with survival in some cases, underscoring the lack of a universal standard across all cancers.