Nugraha, Muhammad Rahadian (2026) Penerapan KNN untuk Mendeteksi Gerakan Jatuh pada Lansia Berbasis Sistem Tertanam. Undergraduate thesis, Politeknik Negeri Jember.
![[img]](https://sipora.polije.ac.id/style/images/fileicons/text.png) |
Text (Abstract)
Abstract.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (204kB) |
|
Text (Bab 1 Pendahuluan)
Bab 1 Pendahuluan.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (202kB) |
|
Text (Daftar Pustaka)
Daftar Pustaka.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (169kB) |
|
Text (Laporan Lengkap)
Laporan Lengkap.pdf - Submitted Version Restricted to Registered users only Download (2MB) | Request a copy |
Abstract
As age increases, the decline in motor functions among the elderly significantly heightens the risk of fall incidents. These incidents can be fatal if the victim does not receive immediate medical attention due to a lack of supervision. This research aims to design and implement a fall detection system based on an embedded system using the MPU6050 Inertial Measurement Unit (IMU) sensor and the ESP32 microcontroller. The K-Nearest Neighbor (KNN) machine learning classification algorithm is embedded directly into the device to recognize movement patterns in real-time. The data pre-processing involves the Low-Pass Filter (LPF) method to reduce transitional movement noise, followed by Signal Vector Magnitude (SVM) feature extraction to detect impact force spikes, and Min-Max normalization. The KNN model (K=11) was trained using 120 primary data points simulated through a mannequin. Based on 40 real-time testing observations covering Standing, Sitting, Lying down, and Falling activity classes, the system demonstrated highly reliable performance. Evaluation using the Confusion Matrix showed an Accuracy rate of 97,5%, Sensitivity of 100% (zero false negative), and Specificity of 96,67%. This proves that the device can precisely detect all fall scenarios without omission, while effectively distinguishing them from normal daily activities with minimal false alarms.
| Item Type: | Thesis (Undergraduate) | ||||||
|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||
| Uncontrolled Keywords: | Fall Detection, K-Nearest Neighbor, Elderly, MPU6050, Embedded System | ||||||
| Subjects: | 340 - Rumpun Ilmu Kesehatan > 350 - Ilmu Kesehatan Umum > 351 - Kesehatan Masyarakat 410 - Rumpun Ilmu Teknik > 450 - Teknik Elektro dan Informatika > 457 - Teknik Komputer 410 - Rumpun Ilmu Teknik > 450 - Teknik Elektro dan Informatika > 458 - Teknik Informatika 410 - Rumpun Ilmu Teknik > 450 - Teknik Elektro dan Informatika > 462 - Teknologi Informasi |
||||||
| Divisions: | Jurusan Teknologi Informasi > Prodi D4 Teknik Informatika > Tugas Akhir | ||||||
| Depositing User: | Muhammad Rahadian Nugraha | ||||||
| Date Deposited: | 13 Jul 2026 03:52 | ||||||
| Last Modified: | 13 Jul 2026 03:52 | ||||||
| URI: | https://sipora.polije.ac.id/id/eprint/57747 |
Actions (login required)
 |
View Item |
