Deteksi Multilevel Diabetes secara NonInvasive dengan Analisis Napas Manusia menggunakan Breathalyzer

-, Hariyanto (2017) Deteksi Multilevel Diabetes secara NonInvasive dengan Analisis Napas Manusia menggunakan Breathalyzer. Undergraduate thesis, Institut Teknologi Sepuluh Nopember.

[img] Text
5113100061-Undergraduate-Theses.pdf
Restricted to Repository staff only

Download (3MB) | Request a copy

Abstract

Diabetes merupakan penyakit metabolic yang banyak diderita. Namu sayangnya, hanya sedikit orang yang mengetahui penyakit metabolic ini, terutama di Indonesia dimana orang hanya melakukan pemeriksaan kesehatan saat mereka merasa sakit. Oleh karena itu, dalam penelitian ini kami mengusulkan sistem non-invasive yang mudah digunakan dan berbiaya rendah yang dapat membedakan orang sehat dan orang diabetes sehingga dapat dilakukan pencegahan dini. Ada tujuh tahap utama untuk membangun sistem ini, pembuatan perangkat keras e-Nose menggunakan sensor mikrokontroler dan gas, akuisisi data ground-truth untuk set pelatihan, pemrosesan sinyal menggunakan Discrete Wavelet Transform (DWT) dan normalisasi Z-score, fitur statistik Ekstraksi, pemilihan fitur untuk optimasi, klasifikasi, dan evaluasi kinerja e-Nose. Hasil percobaan menunjukkan bahwa sistem ini dapat membedakan pasien sehat dan diabetes dengan kinerja yang menjanjikan (95,0% akurasi, ketepatan 91,30% diabetes, ketepatan 94,12% sehat dan 0,898 kappa statistik) dengan menggunakan classifier k-NN. ================================================================= Diabetes is a disease that many people suffer. However, unfortunately only a few people that aware of this metabolic disease especially in Indonesia where people only do health check when they are feeling sick. Therefore, in this research we propose non-invasive, easy to use, and low-cost system that can distinguish healthy or diabetes people so they can have early preventive action. There are seven main stages to build this system, the making of e-Nose hardware using microcontroller and gas sensors, ground-truth data acquisitions for the training set, signal processing using Discrete Wavelet Transform (DWT) and Z-score normalization, statistical features extraction, feature selection for optimization, classification, and e-Nose performance evaluation. The experiment results show that this system can distinguish healthy and diabetes patients with promi sing performance (95.0% of accuracy, 91.30% precision of diabetes, 94.12% precision of healthy and 0.898 kappa statistic’s value) using k-NN classifier.

Item Type: Thesis (Undergraduate)
Additional Information: RSIf 006.42 Har d
Uncontrolled Keywords: klasifikasi, diabetes, e-Nose, k-nn, mikrokontroler, sinyal proses, classification, diabetes, e-Nose, microcontroller, signal processing
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
T Technology > TA Engineering (General). Civil engineering (General) > TA1637 Image processing--Digital techniques
Divisions: Faculty of Information Technology > Informatics Engineering > (S1) Undergraduate Theses
Depositing User: Hariyanto . .
Date Deposited: 10 Nov 2017 08:14
Last Modified: 13 Dec 2017 03:11
URI: http://repository.its.ac.id/id/eprint/43338

Actions (login required)

View Item View Item