Skip to content
SDGs Center UDINUS

Evidence record · UDINUS · SDGs

Non-Invasive Blood Sugar Detection Using Principal Component Analysis Extraction

Rektorat UDINUS 2021 Published 2026-10-30

Evidence record · UDINUS · SDGs

Unit
Rektorat UDINUS
Period
2021
Goals
Record
fc0278d1-fa6b-4425-a097-61f61fa55fba
Published
2026-10-30

Universitas Dian Nuswantoro conducted an activity on non-invasive blood sugar detection using Principal Component Analysis (PCA) as an extraction method. The activity involved UDINUS researchers Arabelle, Annelicia Eunice; Prasetyanto, Wisnu Adi; and Wulandari, Sari Ayu. It addressed Diabetes Mellitus (DM), identified in the source as a non-communicable disease that can cause complications including heart disease, stroke, and blood-vessel problems.

The activity focused on the need for early detection of DM. The source explains that existing detection tools are usually invasive because they use blood from the fingertip, and that this condition reduces public interest in routine checks. The activity therefore considered a non-invasive detection tool, defined in the source as a tool that does not injure the body, to help increase public interest in routine diabetes checks.

For signal processing, the activity used PCA. The source describes PCA as a method with a relatively easy learning process and states that previous researchers had reported higher accuracy for PCA than for another method. The results of PCA extraction were subsequently classified using a Support Vector Machine (SVM) with a linear line to separate DM and non-DM data. The reported classification result was an accuracy of 83.333 percent.

In relation to RAW_GOALS, the activity concerns health research addressing early DM detection and the processing of detection-tool signals. Through this activity, UDINUS presents research on a non-invasive approach to diabetes detection and its classification process.

Reference https://www.scopus.com/pages/publications/85118941450?origin=resultslist