Qois, Zandy (2026) DEVELOPMENT OF A WEARABLE DEVICE FOR IOT-BASED MONITORING & CORRECTION OF SITTING POSTURE USING FUZZY TYPE-2 LOGIC AND SUPPORT VECTOR MACHINE. Undergraduate thesis, UPN VETERAN JAWA TIMUR.
![[img]](https://repository.upnjatim.ac.id/style/images/fileicons/text.png) |
Text (Cover)
THESIS ZANDY - untuk perpus-1-13.pdf Download (655kB) |
|
Text (Bab1)
21081010248_bab1.pdf Download (176kB) |
|
Text (Bab2)
21081010248_Bab2.pdf Restricted to Repository staff only until 15 June 2029. Download (701kB) |
|
Text (Bab3)
21081010248_Bab3.pdf Restricted to Repository staff only until 15 June 2029. Download (600kB) |
|
Text (Bab4)
21081010248_Bab4.pdf Restricted to Repository staff only until 15 June 2029. Download (847kB) |
|
Text (Bab5)
21081010248_Bab5.pdf Download (144kB) |
|
Text (Daftar Pustaka)
21081010248_Daftar Pustaka.pdf Download (180kB) |
|
Text (Lampiran)
21081010248_Lampiran.pdf Restricted to Repository staff only until 15 June 2029. Download (239kB) |
Abstract
The habit of prolonged improper sitting posture is a leading cause of musculoskeletal disorders affecting the spine, neck, and shoulders. This study designs and develops an IoT-based wearable system for real-time sitting posture detection, classification, and correction using an MPU-6500 IMU sensor on an ESP32 microcontroller. The system processes pitch and roll angles through baseline calibration, Interval Type-2 Fuzzy Logic adaptive filtering, Z-score normalization, and SVM classification with an RBF kernel and One-vs-One strategy across three posture classes: upright (0°–10°), slightly slouched (10°–20°), and slouched (>20°). Corrective feedback is delivered via a vibration motor with a 3-second temporal validation mechanism, while posture data is monitored through the Blynk IoT platform. The SVM model achieved 100% testing accuracy and 99.72% average 5 fold cross-validation accuracy. Testing on two subjects showed upright posture increased from 77.3% to 92.3% and from 85.1% to 95.4% after vibration feedback was activated, confirming the system's measurable impact on improving sitting posture habits.
| Item Type: | Thesis (Undergraduate) | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||||||||
| Subjects: | T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5105 Computer Network T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5105.882 Internet Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4050 Electronic information resources |
||||||||||||
| Divisions: | Faculty of Computer Science > Departemen of Informatics | ||||||||||||
| Depositing User: | Zandy Qois | ||||||||||||
| Date Deposited: | 15 Jun 2026 03:56 | ||||||||||||
| Last Modified: | 15 Jun 2026 04:18 | ||||||||||||
| URI: | https://repository.upnjatim.ac.id/id/eprint/53861 |
Actions (login required)
 |
View Item |