UMD Data Collection

Permanent URI for this collectionhttp://hdl.handle.net/1903/27670

University of Maryland faculty and researchers can upload their research products in DRUM for rapid dissemination, global visibility and impact, and long-term preservation. Depositing data in DRUM can assist in compliance with data management and sharing requirements from the NSF, NIH, and other funding agencies and journals. You can also deposit code, documents, images, supplemental material, and other research products. DRUM tracks views and downloads of your research, and all DRUM records are indexed by Google and Google Scholar. Additionally, DRUM assigns permanent DOIs for your items, making it easy for other researchers to cite your work.

Submissions to the Data Collection

To add files to the UMD Data Collection, submit a new item through your associated department or program's DRUM collection and check the box indicating your upload contains a dataset.

Find more information and guidelines for depositing into the Data Collection on the University of Maryland Libraries' DRUM for Data page.

Assistance

Please direct questions regarding the UMD Data Collection or assistance in preparing and depositing data to: lib-research-data@umd.edu.

Browse

Subject: search.filters.subject.machine learning

Search Results

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    Example code and data for "Identifying physical structures in our Galaxy with Gaussian Mixture Models: An unsupervised machine learning technique"
    (2023) Tiwari, Maitraiyee; Kievit, Rens; Kabanovic, Slawa; Bonne, Lars; Falasca, F.; Guevara, Cristian; Higgins, Ronan; Justen, M.; Karim, Ramsey; Pabst, Cornelia; Pound, Marc W.; Schneider, Nicola; Simon, R.; Stutzki, Jurgen; Wolfire, Mark; Tielens, Alexander G. G. M.
    We present a python software repository implementing the PyGMMis (Melchior & Goudling 2018) method to astronomical data cubes of velocity resolved line observations. This implementation is described extensively in Tiwari et al. 2023, ApJ. An example is included in /example/ containing the SOFIA data of RCW120 used in Tiwari et al. 2023, ApJ, along with example scripts describing the full implementation of our code. The majority of parameter tweaking can be performed within 'rcw120-params.txt' which is continuously called during the procedure. A full description of the code and how to use it is in README.md (markdown file).
  • No Thumbnail Available
    Item
    Supplementary materials for machine learning-driven multifunctional peptide engineering for sustained ocular drug delivery
    (2023) Chou, Renee Ti; Hsueh, Henry T.; Rai, Usha; Liyanage, Wathsala; Kim, Yoo Chun; Appell, Matthew B.; Pejavar, Jahnavi; Leo, Kirby T.; Davison, Charlotte; Kolodziejski, Patricia; Mozzer, Ann; Kwon, HyeYoung; Sista, Maanasa; Anders, Nicole M.; Hemingway, Avelina; Rompicharla, Sri Vishnu Kiran; Edwards, Malia; Pitha, Ian; Hanes, Justin; Cummings, Michael P.; Ensign, Laura M.; Cummings, Michael P.; Ensign, Laura M.
    Sustained drug delivery strategies have many potential benefits for treating a range of diseases, particularly chronic diseases that require treatment for years. For many chronic ocular diseases, patient adherence to eye drop dosing regimens and the need for frequent intraocular injections are significant barriers to effective disease management. Here, we utilize peptide engineering to impart melanin binding properties to peptide-drug conjugates to act as a sustained-release depot in the eye. We developed a super learning-based methodology to engineer multifunctional peptides that efficiently enter cells, bind to melanin, and have low cytotoxicity. When the lead multifunctional peptide (HR97) was conjugated to brimonidine, an intraocular pressure (IOP)-lowering drug that is prescribed for three times per day topical dosing, IOP reduction was observed for up to 18 days after a single intracameral HR97-brimonidine injection in rabbits. Further, the cumulative IOP-lowering effect was increased ~17-fold compared to free brimonidine injection. Engineered multifunctional peptide-drug conjugates are a promising approach for providing sustained therapeutic delivery in the eye and beyond.
  • Thumbnail Image
    Item
    Predicting flood damage using the Flood Peak Ratio and Giovanni Flooded Fraction - Code
    (2022-07-11) Ghaedi, Hamed; Baroud, Hiba; Ferreira, Celso; Perrucci, Daniel; Reilly, Allison; Reilly, Allison
    A spatially-resolved understanding of the intensity of a flood hazard is required for accurate predictions of infrastructure reliability and losses in the aftermath. Currently, researchers who wish to predict flood losses or infrastructure reliability following a flood usually rely on computationally intensive hydrodynamic modeling or on flood hazard maps (e.g., the 100-year floodplain) to build a spatially-resolved understanding of the flood’s intensity. However, both have specific limitations. The former requires both subject matter expertise to create the models and significant computation time, while the latter is a static metric that provides no variation among specific events. The objective of this work is to develop an integrated data-driven approach to rapidly predict flood damages using two emerging flood intensity heuristics, namely the Flood Peak Ratio (FPR) and NASA’s Giovanni Flooded Fraction (GFF). This study uses data on flood claims from the National Flood Insurance Program (NFIP) to proxy flood damage, along with other well-established flood exposure variables, such as regional slope and population. The approach uses statistical learning methods to generate predictive models at two spatial levels: nationwide and statewide for the entire contiguous United States. A variable importance analysis demonstrates the significance of FPR and GFF data in predicting flood damage. In addition, the model performance at the state-level was higher than the nationwide level analysis, indicating the effectiveness of both FPR and GFF models at the regional level. A data-driven approach to predict flood damage using the FPR and GFF data offer promise considering their relative simplicity, their reliance on publicly accessible data, and their comparatively fast computational speed.