{"id":27603978,"url":"https://github.com/killflex/robotika-uts-uas","last_synced_at":"2025-10-09T08:41:56.328Z","repository":{"id":289028931,"uuid":"969877955","full_name":"killflex/robotika-uts-uas","owner":"killflex","description":null,"archived":false,"fork":false,"pushed_at":"2025-06-23T01:36:26.000Z","size":6853,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-06-23T02:37:56.967Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/killflex.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,"zenodo":null}},"created_at":"2025-04-21T04:51:11.000Z","updated_at":"2025-06-23T01:36:30.000Z","dependencies_parsed_at":"2025-06-09T12:36:24.370Z","dependency_job_id":null,"html_url":"https://github.com/killflex/robotika-uts-uas","commit_stats":null,"previous_names":["killflex/robotika-uts-uas"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/killflex/robotika-uts-uas","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/killflex%2Frobotika-uts-uas","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/killflex%2Frobotika-uts-uas/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/killflex%2Frobotika-uts-uas/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/killflex%2Frobotika-uts-uas/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/killflex","download_url":"https://codeload.github.com/killflex/robotika-uts-uas/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/killflex%2Frobotika-uts-uas/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279001047,"owners_count":26082991,"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","status":"online","status_checked_at":"2025-10-09T02:00:07.460Z","response_time":59,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":[],"created_at":"2025-04-22T19:21:26.982Z","updated_at":"2025-10-09T08:41:56.323Z","avatar_url":"https://github.com/killflex.png","language":"Jupyter Notebook","readme":"# 🧠 Project Title\n\n## 👥 Kelompok Peneliti\n\n| Nama                | NIM         |\n| ------------------- | ----------- |\n| Yudhistira Nanda K. | 22081010055 |\n| Daniel Perdana M.   | 22081010064 |\n| Ferry Hasan         | 22081010085 |\n| Suwito              | 22081010102 |\n| Jerry Ramadhani C.  | 22081010140 |\n\n---\n\n## 📌 Deskripsi Singkat Proyek\n\nProyek ini bertujuan untuk membangun model klasifikasi gambar berbasis CNN (Convolutional Neural Network) untuk mengidentifikasi objek: **Kursi**, **Meja**, **Pintu**, dan **Manusia**.\n\n---\n\n## 🔍 Metodologi Penelitian\n\n1. **Dataset**  \n   Dataset berisi gambar 4 kelas: Kursi, Meja, Pintu, dan Manusia.  \n   📁 _Jumlah data per kelas_: 40 gambar validasi dan 40 gambar test per kelas.  \n   🔗 **Link dataset**: [Dataset di Google Drive / Kaggle](#)\n\n2. **Arsitektur Model**\n\n   - Transfer Learning menggunakan arsitektur pretrained seperti VGG16/VGG19\n   - Fully Connected Layers di akhir untuk klasifikasi 4 kelas\n   - Fungsi aktivasi: ReLU dan Softmax\n\n3. **Training Setup**\n   - Epoch: 20\n   - Optimizer: Adam\n   - Loss Function: Categorical Crossentropy\n   - Batch size: disesuaikan dengan resource\n\n---\n\n## 📈 Proses Training Model\n\nBerdasarkan **gambar Epoch logs dan grafik**:\n\n- **Accuracy dan Loss** selama training terlihat sangat tinggi di data training dan juga validasi (akurasi validasi mencapai ~99.37% pada epoch ke-20).\n- Namun terjadi indikasi **overfitting** karena model terlalu akurat pada data training dan validasi, tapi performa pada test dan klasifikasi per kelas buruk.\n\n#### Gambar Grafik Akurasi \u0026 Loss:\n\n- Kiri: Akurasi training dan validasi naik drastis\n- Kanan: Loss training turun tajam, sementara **loss validasi naik** setelah beberapa epoch → indikasi overfitting.\n\n---\n\n## ✅ Evaluasi Model\n\n### 📋 Classification Report (Validasi)\n\n| Class   | Precision | Recall | F1-Score |\n| ------- | --------- | ------ | -------- |\n| Kursi   | 0.17      | 0.17   | 0.17     |\n| Manusia | 0.22      | 0.23   | 0.22     |\n| Meja    | 0.23      | 0.23   | 0.23     |\n| Pintu   | 0.23      | 0.23   | 0.23     |\n\n\u003e **Accuracy hanya 21% pada data validasi meski akurasi sistem menunjukkan 99.37% → Overfitting parah.**\n\n### 🧾 Confusion Matrix (Validasi)\n\n![Confusion Matrix](path_to_confusion_matrix.png)\n\n- Klasifikasi sangat tidak akurat, hampir semua kelas saling tertukar.\n- Contoh: Gambar “Manusia” banyak diklasifikasikan sebagai “Kursi”.\n\n### 🧪 Evaluasi Test Data\n\n- **Test Accuracy**: 96.88%\n- **Test Loss**: 0.4101\n\n\u003e Namun sama seperti validasi, akurasi tinggi ini menyesatkan karena model kemungkinan besar hanya hafal data training.\n\n## 📂 Struktur Proyek\n\n```\n├── model/\n│   └── saved_model.h5\n├── notebooks/\n│   └── model_training.ipynb\n├── evaluation/\n│   ├── confusion_matrix.png\n│   └── training_graphs.png\n└── README.md\n```\n\n---\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkillflex%2Frobotika-uts-uas","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkillflex%2Frobotika-uts-uas","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkillflex%2Frobotika-uts-uas/lists"}