{"id":20388168,"url":"https://github.com/kons-5/ist-aaut","last_synced_at":"2026-05-06T09:36:26.000Z","repository":{"id":262482434,"uuid":"858702504","full_name":"Kons-5/IST-AAut","owner":"Kons-5","description":"This repository contains lab materials for the IST-AAut course. ","archived":false,"fork":false,"pushed_at":"2024-11-12T17:30:13.000Z","size":115183,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-01-15T08:59:59.093Z","etag":null,"topics":["arx-model","cnn-classification","jupyter-notebooks","machine-learning","machine-learning-algorithms","optuna","outlier-removal","pytorch","pytorch-lightning","regression-models","segmentation-models","sklearn","statsmodels"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Kons-5.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-09-17T11:41:07.000Z","updated_at":"2024-11-12T17:30:19.000Z","dependencies_parsed_at":"2024-11-12T17:44:35.368Z","dependency_job_id":null,"html_url":"https://github.com/Kons-5/IST-AAut","commit_stats":null,"previous_names":["kons-5/ist-aaut"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Kons-5%2FIST-AAut","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Kons-5%2FIST-AAut/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Kons-5%2FIST-AAut/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Kons-5%2FIST-AAut/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Kons-5","download_url":"https://codeload.github.com/Kons-5/IST-AAut/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":241940529,"owners_count":20045878,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["arx-model","cnn-classification","jupyter-notebooks","machine-learning","machine-learning-algorithms","optuna","outlier-removal","pytorch","pytorch-lightning","regression-models","segmentation-models","sklearn","statsmodels"],"created_at":"2024-11-15T03:07:43.817Z","updated_at":"2026-05-06T09:36:25.940Z","avatar_url":"https://github.com/Kons-5.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# IST-AAut\n\nThis repository contains lab materials for the IST-AAut (Machine Learning) course.\n\n- Check [Report.pdf](Submissions/Report.pdf) for the methodology and analysis, with comparisons of models across different metrics.\n\n## Content\n\n### [Part 1: Regression with Synthetic Data](AAutLab2425.pdf)\n\nThis section covers regression analysis tasks using synthetic data to explore key concepts in predictive modeling.\n\n- [ML-Submission1](Submissions/ML-Submission1): Contains the Jupyter Notebook for **Multiple Linear Regression with Outliers**, implementing outlier removal, cross-validation, and tuning techniques as described in the report.\n\n- [ML-Submission2](Submissions/ML-Submission2): Contains the Jupyter Notebook for the **ARX Model**, focusing on time-series data and system response modeling, with parameter optimization techniques.\n\n#### Learning Objectives\n- Understand multiple linear regression with synthetic data containing noise and outliers.\n- Apply ARX (Auto-Regressive with eXogenous input) models for time-series data analysis.\n- Evaluate model robustness with cross-validation and tuning techniques.\n\n#### Technologies\n- Python (3.11) with `scikit-learn` and `statsmodels`.\n- MATLAB® for additional analysis and model validation.\n\n### [Part 2: Image Analysis - Martian Crater Detection](AAutLab2425.pdf)\n\nThis section explores image classification and segmentation tasks focused on low-resolution (48x48) Martian crater analysis.\n\n- [ML-Submission3](Submissions/ML-Submission3): Contains the Jupyter Notebook for **Image Classification** using SVC and CNN models, with techniques for handling imbalanced data and data augmentation.\n\n- [ML-Submission4](Submissions/ML-Submission4): Contains the Jupyter Notebook for **Image Segmentation**, implementing MLP-Fusion and U-Net models for pixel-wise segmentation.\n\n#### Learning Objectives\n- Develop machine learning models to classify crater vs. non-crater images.\n- Apply segmentation techniques (patch-based and pixel-based) to delineate crater boundaries.\n- Address data imbalance with techniques like SMOTE and data augmentation.\n\n#### Technologies\n- Python (3.11) with `torch`, `torchvision`, `torchmetrics`, and `pytorch-lightning`.\n- [Optuna](https://optuna.org/) for hyperparameter tuning.\n\n## Authors\n\n- [João Gonçalves - sqrt(-1)](https://github.com/eusouojoao)\n- [Teresa Nogueira - 13A!](https://github.com/FrolickingAsteroid)\n\n## License\n\nThis work is licensed under a [Creative Commons Attribution Non Commercial Share Alike 4.0 International][cc-by-nc-sa].\n\n[cc-by-nc-sa]: https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkons-5%2Fist-aaut","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkons-5%2Fist-aaut","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkons-5%2Fist-aaut/lists"}