Claim Missing Document
Check
Articles

Found 3 Documents
Search

Perceived Accuracy and User Behavior: Exploring the Impact of AI-Based Air Quality Detection Application (AIKU) Qurotul Aini; Irwan Sembiring; Adi Setiawan; Iwan Setiawan; Untung Rahardja
Indonesian Journal of Applied Research (IJAR) Vol. 4 No. 3 (2023): Indonesian Journal of Applied Research (IJAR)
Publisher : Universitas Djuanda

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30997/ijar.v4i3.356

Abstract

The accuracy of air quality detection is a crucial aspect influencing user trust and satisfaction with artificial intelligence (AI) based air quality detection applications. However, only a few studies have tested the effect of the accuracy of AI-based quality detection on users' acceptance and use of these applications. This study aims to fill this gap by addressing the impact of perceived accuracy on behavioral intention and behavior using the AIKU application. This research uses a quantitative approach with the online survey method, distributed in January 2023 - February 2023 to AIKU users. Valid data were 287 respondents from 317 who were received and analyzed using partial least squares structural equation modeling (PLS-SEM). This study uses a modified technology acceptance (TAM) model by adding perceived intelligence as a mediating variable between perceived accuracy and usefulness. The results showed that nine hypotheses were accepted from the 13 hypotheses proposed. The results section of hypothesis testing shows that the effect of perceived AIKU application accuracy on perceived usability and ease of use is insignificant. However, these influences indirectly affect the behavioral intentions and attitudes of users. Even if users do not perceive purity as an essential factor, the user's attitude towards the application is still positive. This study makes a theoretical contribution by developing the TAM model by incorporating variables of perceived accuracy and perceived intelligence relevant to the AI-based context.
Empowering Digital Literacy through Blockchain Based AlphaSign for Secure and Sustainable E-Governance Danang Danang; Hendriyati Haryani; Qurotul Aini; Fikri Arsla Ramahdan; John Edwards
ADI Pengabdian Kepada Masyarakat Vol 6 No 1 (2025): ADI Pengabdian Kepada Masyarakat
Publisher : ADI Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34306/adimas.v6i1.1207

Abstract

Self Supervised Transformers for High Dimensional Time Series Anomaly Detection Aswadi Jaya; Derlina; Qurotul Aini; Agung Rizky; Richard Evans
Blockchain Frontier Technology Vol. 6 No. 1 (2026): Blockchain Frontier Technology
Publisher : Indonesian Association of Higher Education in Informatics and Computing (APTIKOM)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34306/b-front.v6i1.1078

Abstract

This study addresses anomaly detection in high dimensional time series data within the context of Artificial Intelligence (AI) driven software development, where modern systems generate large temporal data streams and reliable monitoring remains difficult due to noise, complexity, and limited labeled anomalies. The objective of this research is to develop an effective and scalable anomaly detection framework based on self supervised transformer models that can learn meaningful temporal representations without heavy reliance on manual annotation. The proposed method applies self supervised pretraining through masked sequence reconstruction and contrastive temporal learning on large scale, unlabeled multivariate time series datasets, followed by transformer based attention mechanisms to capture long range dependencies and compute anomaly scores. Experiments are conducted using benchmark datasets and real world system log data implemented with Python based deep learning tools and transformer architectures to evaluate detection performance. The results indicate that the proposed approach improves detection accuracy and reduces false positive rates compared to traditional statistical techniques and supervised deep learning models, particularly in high dimensional and low label settings. In conclusion, integrating self supervised learning with transformer architectures provides a robust and generalizable solution for time series anomaly detection, contributing to software analytics and monitoring systems by lowering labeling costs and improving adaptability across application domains.