Connor McManigal's repositories
IoT-IDS-VAE-Classification
Training VAE and an Mixed-Loss VAE with normal network traffic, then implementing validation and test steps that fold in the attack traffic to ensure models' reconstruction error satisfactorily separates data at with accuracy. Leveraging Bayesian optimization to tune hyperparameters and testing one anomaly at a time hold out strategy with AUCs.
Data-Analysis-SanDiegoCountyAutoAccidents
Data analysis aimed at better understanding San Diego County automobile accidents while analyzing various features such as weather and dates from the 2021 year.
Data-Analysis-EffectofNBAInjuriesonTeamRecord
Statistical analysis of potential association between a NBA team’s number and type of injuries to their record from the 2010-15 seasons. Prediction of 2016 season records given injury types and numbers.
Diabetes-Supervised-Machine-Learning-Analysis-And-Prediction
Comparing logistic regression, decision tree, random forest, k-nearest neighbors, and SVMs in regard to binary prediction performance metrics.
sorting-algorithm-analysis
Implementation of MergeSort, QuickSort, InsertionSort, ShellSort, BucketSort, RadixSort, Binary Insertion Sort, and Tim Sort followed by time complexity analysis.
bin-packing-analysis
Implementation of next fit, first fit, best fit, first fit decreasing, and best fit decreasing bin packing algorithms followed by time and space complexity analysis.
Traveling-Salesman-BranchandBoundDFS-StochasticLocalSearch
Bidirectional traveling salesman problem using branch and bound depth-first search and stochastic local search followed by a time complexity analysis.
Recipe-Review-Scoring-Algorithm-Regression
Leveraging sentiment analysis and data augmentation to recreate recipe scoring algorithm with sparse data. Used MLPs and Gradient Boosting Regressors to compare regression metrics such as RMSE and MSE between raw data and raw data in conjunction with augmented data.