Skip to content
SDGs Center UDINUS

Evidence record · UDINUS · SDGs

Improved Adaptive Neuro-Fuzzy Inference System for HIV/AIDS Time Series Prediction

Rektorat UDINUS 2011 Published 2026-10-30

Evidence record · UDINUS · SDGs

Unit
Rektorat UDINUS
Period
2011
Goals
Record
dd5c231c-adce-4f98-9d82-5a3256158b1b
Published
2026-10-30

Universitas Dian Nuswantoro (UDINUS), with Purwanto, C. Eswaran, and R. Logeswaran as activity participants, conducted research on improving accuracy in HIV/AIDS time series prediction. The activity addressed the challenge of predicting healthcare time series data and the importance of HIV/AIDS data for healthcare management. It examined statistical techniques including moving average, weighted moving average, and autoregressive integrated moving average models. These techniques have limitations in handling non-linear relationships among data.

The activity also considered artificial intelligence techniques, including neural networks, for predicting non-linear data. The source explains that complex healthcare data may be difficult to predict with high accuracy when statistical or artificial intelligence models are used individually. To address this issue, UDINUS proposed an improved adaptive neuro-fuzzy inference system model for HIV/AIDS data prediction. The proposed model was a hybrid model developed for the prediction task described in the source.

The proposed model was compared with moving average, weighted moving average, autoregressive integrated moving average, and neural network models using HIV/AIDS data. The comparison used Root Mean Square Error and Mean Absolute Error as statistical indicators of prediction accuracy. The results indicated that the proposed model yielded improvements as high as 87.84% compared with the other models. This activity frames UDINUS research around healthcare data, HIV/AIDS prediction, non-linear relationships, and evaluation of an improved hybrid model.

Reference https://www.scopus.com/pages/publications/82955194514?origin=resultslist