Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 5 of 5 for “"Cat Boost"”.

  1. Real-time intrusion detection in CubeSats using embedded TinyML

    … signal shifts, warping, and gaps. The resulting Cat Boost model reaches 99.87% weightedF1 on held-out offline data. Software-in-the-Loop (SiL) validation within the flight-software environment on 25,571 generated records from modified scripts achieved 92.0% macro F1 and 91.9% weighted F1. …

    uoit Repository record for Real-time intrusion detection in CubeSats using embedded TinyML (opens in a new tab)

  2. Development of a Condition Assessment Rating System and Prediction Model for Railway Tracks

    … learning models, including Random Forest, XGBoost, and Cat Boost, were employed to predict future conditions, such as defect tags, amplitude, and length. These models achieved a 95% accuracy for detecting defect tags and a 75% accuracy when predicting defect tags based on predicted amplitude. …

    concordia Download PDF for Development of a Condition Assessment Rating System and Prediction Model for Railway Tracks (opens in a new tab)

  3. Advancing Safety for Under-Protected Road Users: Data-Driven and Artificial Intelligence Approaches across Different Contexts and Crash Scenarios

    … Pedestrian and Bicyclist Crash Analysis Tool (PBCAT), and under-protected road user (URU) crash records from the National Transit Database (NTD) Major Safety Events dataset (2014–2023). A suite of statistical, Bayesian, artificial intelligence (AI), and machine learning (ML) methods is employed. …

    utk-theses Repository record for Advancing Safety for Under-Protected Road Users: Data-Driven and Artificial Intelligence Approaches across Different Contexts and Crash Scenarios (opens in a new tab)

  4. HIGH-RISK PREDICTION FOR COVID-19 PATIENTS USING MACHINE LEARNING

    This Machine Learning algorithm offers a prediction methodology for potentially detecting severely affected COVID-19 patients based on blood sample parameters that are readily available. The development of effective and efficient treatment regimens for critical patients as well as routine patient …

    csusb Repository record for HIGH-RISK PREDICTION FOR COVID-19 PATIENTS USING MACHINE LEARNING (opens in a new tab)

  5. Solar Irradiance Prediction Using Xg-boost With the Numerical Weather Forecast

    To defeat global warming, the world expects to look at renewable energy sources. Solar energy is one of the best renewable energy sources which causes no harm to the environment. As solar energy changes with atmospheric parameters like temperature, relative humidity, cloud coverage, dewpoint, sun …

    utahstate Repository record for Solar Irradiance Prediction Using Xg-boost With the Numerical Weather Forecast (opens in a new tab)