Search Results for "auc"

This repository is a visually rich and well-organized “cheat sheet” summarizing core machine learning concepts, algorithms, formulas, and best practices. It includes summaries of supervised and unsupervised learning methods, model evaluation metrics (accuracy, precision, recall, ROC/AUC), overfitting/underfitting, regularization (L1/L2), cross-validation, feature engineering techniques, and perhaps tips for hyperparameter tuning. Each section is presented concisely, often with diagrams, formula snippets, and short explanatory notes to serve as quick reference for students, practitioners, or interview prep. The repository is ideal for those who want a compact, at-a-glance reminder of ML fundamentals without diving back into textbooks. ...

...The prediction model is based on the distribution patterns of amino acid properties along the sequence. Our optimal model, AmPEP with 1:3 data ratio achieved a very high accuracy of 96%, MCC of 0.9, AUC-ROC of 0.99 and Kappa statistic of 0.9. AmPEP outperforms existing methods with respect to accuracy, MCC, and AUC-ROC when tested using the benchmark datasets. Server online at https://cbbio.online/AxPEP

Manifold is a model-agnostic visual debugging tool for machine learning. Understanding ML model performance and behavior is a non-trivial process, given the intrisic opacity of ML algorithms. Performance summary statistics such as AUC, RMSE, and others are not instructive enough to identify what went wrong with a model or how to improve it. As a visual analytics tool, Manifold allows ML practitioners to look beyond overall summary metrics to detect which subset of data a model is inaccurately predicting. Manifold also explains the potential cause of poor model performance by surfacing the feature distribution difference between better and worse-performing subsets of data.

knnAUC : k-nearest neighbors AUC test. In the knnAUC framework, we first calculated the AUC estimator based on a k-nearest neighbors classifier, and then evaluate the significance of the AUC based statistic (Alternative hypothesis: AUC > 0.5, that is to say, X has prediction power for Y).

Version 1.1.5 - Added: Added the ability to edit the EMV panel - You can change which tags show, and what order they are in - Added: Tag 9F10 (Issuer Application Data) to which also includes CVR (a subtag of 9F10) - Added: Menu link to the homepage (sourceforge) - Fixed: 9F07/AUC had the wrong tag details - Fixed: File>Close now saves notes and config updates before exiting - Fixed: Tag 95/TVR title had a spelling mistake - Fixed: Homepage wasn't populating EMV page names - Fixed: EMV menu would prompt to update even if there was nothing changed - Changed: Removed unused classes, old stuff that isn't used - Changed: Reverted home page image - Changed: Removed some test prints and refactored EMV classes - Changed: No longer prompts to restart after EMV menu change, just changes it - Changed: EMV Navigation Panel button generation (for the dynamic buttons) thetoolbox2013@gmail.com

Plethora is a NetBeans plugin that provides a designer and a code-generator for Looking Glass 3D (http://www.sun.com/software/looking_glass) applications. You can download a live CD for LG3D from: http://sourceforge.net/projects/lg3d-livecd

AUC-DBMS is an XML-based DBMS. Created by: Mohamed El-Geish and Ahmed Hamza. Supervised by: Dr. Awad Khalil and Mohamed Attia. The American University in Cairo - Computer Science Department (http://www.cs.aucegypt.edu).

The main goal of Cerberus is to combine state of the art intrusion detection systems, firewalls and routers using the concept of agents