Please use this identifier to cite or link to this item:
http://repository.ipb.ac.id/handle/123456789/169636| Title: | Penggunaan Algoritma K-Nearest Neighbors Untuk Mengatasi Temperature Drift Pada Sensor Load Cell Dalam Sistem Rak Senjata Otomatis |
| Other Titles: | Application of K-Nearest Neighbors to Mitigate Temperature Drift in Load Cell Sensors for Automated Weapon Racks |
| Authors: | Novianty, Inna Ilham, Fauzan Perdana |
| Issue Date: | 2025 |
| Publisher: | IPB University |
| Abstract: | Temperature drift yang terjadi pada sensor load cell merupakan tantangan signifikan dalam memastikan akurasi pembacaan berat pada sistem rak senjata otomatis. Drift yang dipengaruhi oleh perubahan suhu ini dapat menyebabkan kesalahan dalam mendeteksi kondisi senjata, seperti membedakan senjata dengan atau tanpa magazine. Penelitian ini bertujuan untuk mengatasi efek temperature drift dengan mengembangkan model KNN (K-Nearest Neighbors) yang mampu mengklasifikasikan kondisi senjata secara akurat berdasarkan data berat dari sensor load cell. Data diambil pada berbagai kondisi suhu menggunakan perangkat pemanas dan pendingin untuk mensimulasikan suhu lingkungan yang berbeda. Model KNN kemudian dibangun dan dievaluasi menggunakan metrik akurasi, precision, recall, dan F1-score. Diharapkan model ini dapat meningkatkan keandalan dan akurasi sensor load cell dalam menghadapi pengaruh temperature drift, sehingga memperkuat performa sistem rak senjata otomatis dalam mendeteksi kondisi rak senjata. Temperature drift that occurs in the load cell sensor is a significant challenge in ensuring the accuracy of weight readings in the automatic weapon rack system. Drift influenced by temperature changes can cause errors in detecting weapon conditions, such as distinguishing weapons with or without magazines. This study aims to overcome the effects of temperature drift by developing a KNN (K-Nearest Neighbors) model that is able to accurately classify weapon conditions based on weight data from the load cell sensor. Data was taken at various temperature conditions using heating and cooling devices to simulate different environments. The KNN model was then built and evaluated using accuracy, precision, recall, and F1-score metrics. It is expected that this model can improve the reliability and accuracy of the load cell sensor in dealing with the effects of temperature drift, thereby strengthening the performance of the automatic weapon rack system in detecting weapon rack conditions. |
| URI: | http://repository.ipb.ac.id/handle/123456789/169636 |
| Appears in Collections: | UT - Computer Engineering Tehcnology |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| cover_J0304211032_f78bc5cd636445bbba686bac0576ce06.pdf | Cover | 401.01 kB | Adobe PDF | View/Open |
| fulltext_J0304211032_da854636dc6644358f42460eee07d3f4.pdf Restricted Access | Fulltext | 3.86 MB | Adobe PDF | View/Open |
| lampiran_J0304211032_f8876210f421457f98fc1b9e9757f4ea.pdf Restricted Access | Lampiran | 200.39 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.