Sitompul, Fransiskus Benyamin (2025) Analisis dan Pengembangan Sistem Pemantauan Lokasi dan Deteksi Jatuh Anak Secara Jarak Jauh Melalui Wearable Device Berbasis LoRa dengan Metode Geofencing pada Aplikasi Android. Other thesis, Institut Teknologi Sepuluh Nopember.
![[thumbnail of 5027211021-Undergraduate_Thesis.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
5027211021-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 April 2027. Download (19MB) | Request a copy |
Abstract
Penelitian ini bertujuan untuk merancang dan mengembangkan sistem pemantauan keamanan anak menggunakan perangkat wearable berbasis teknologi LoRa dan aplikasi mobile Android. Sistem ini dikembangkan untuk memenuhi tiga fungsi utama: pemantauan lokasi anak jarak jauh, pendeteksian kejadian anak terjatuh dan/atau pingsan di sekolah, serta pengoptimalan proses penjemputan anak di sekolah. Sistem ini mengintegrasikan perangkat wearable yang mampu mengirimkan data GPS, mendeteksi jatuh melalui model klasifikasi yang dilatih menggunakan Edge Impulse, serta mendeteksi pingsan melalui analisis jerk magnitude dan penghitungan waktu diam. Aplikasi mobile berfungsi untuk memantau lokasi anak secara real-time, menggunakan metode geofencing untuk mendeteksi kedatangan orang tua, dan memberikan notifikasi otomatis ke perangkat wearable anak. Semua komunikasi data dilakukan melalui platform Antares IoT. Hasil pengujian menunjukkan bahwa sistem yang dikembangkan mampu bekerja sesuai rancangan. Performa komunikasi LoRa menunjukkan packet loss sebesar 4,17% pada jarak 100 meter, dengan penurunan performa pada jarak yang lebih jauh (11,46% pada 500 meter, 13,54% pada 1 kilometer, dan 14,58% pada 2 kilometer). Nilai rata-rata RSSI berkisar antara -115 dBm hingga -119 dBm, dengan kualitas sinyal masih dalam kategori "Fair" berdasarkan standar kualitas LoRa. Sistem pendeteksi jatuh berhasil mencapai akurasi tertinggi sebesar 89,3% pada model dengan window size 1.000 ms, sementara pengujian riil menggunakan perangkat menunjukkan tingkat keberhasilan deteksi jatuh sebesar 86% dan pingsan sebesar 90%. Pengujian juga menunjukkan latensi notifikasi penjemputan sebesar 9,6 detik. Sistem ini diharapkan dapat menjadi solusi yang efektif dalam meningkatkan keamanan anak serta mempermudah proses penjemputan di sekolah.
================================================================================================================================
This study aims to design and develop a child safety monitoring system using a LoRa-based wearable device and an Android mobile application. The system was developed to fulfill three primary functions: remote child location monitoring, detection of fall and/or fainting incidents at school, and optimization of the child pickup process at school. The system integrates a wearable device capable of transmitting GPS data, detecting falls through a classification model trained using Edge Impulse, and identifying fainting incidents through jerk magnitude analysis and idle time calculation. The mobile application enables real-time monitoring of the child's location, utilizes geofencing to detect parental arrival, and sends automatic notifications to the child's wearable device. All data communication is facilitated through the Antares IoT platform. Testing results show that the developed system operates as intended. LoRa communication performance indicated a packet loss of 4.17% at a distance of 100 meters, with performance declining at greater distances (11.46% at 500 meters, 13.54% at 1 kilometer, and 14.58% at 2 kilometers). The average RSSI values range between -115 dBm and -119 dBm, with signal quality classified as "Fair" according to LoRa quality standards. The fall detection system achieved a highest accuracy of 89.3% using a model with a 1000 ms window size, while real-world testing showed a fall detection success rate of 86% and fainting detection accuracy of 90%. Testing also revealed that the average latency for pickup notifications was 9.6 seconds. This system is expected to offer an effective solution for enhancing child safety while streamlining the school pickup process.
| Item Type: | Thesis (Other) |
|---|---|
| Uncontrolled Keywords: | GPS, LoRa, Wearable, Pendeteksi jatuh, Fall detection |
| Subjects: | T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK6592.A9 Automatic tracking. T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7882.P3 Pattern recognition systems T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5101 Telecommunication |
| Divisions: | Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Information Technology > 59201-(S1) Undergraduate Thesis |
| Depositing User: | Fransiskus Benyamin Sitompul |
| Date Deposited: | 23 Jan 2025 07:35 |
| Last Modified: | 23 Jan 2025 07:35 |
| URI: | http://repository.its.ac.id/id/eprint/116748 |
Actions (login required)
 |
View Item |