Claim Missing Document
Check
Articles

Found 2 Documents
Search

Propagation Characteristics of Madden Julian Oscillation in the Indonesian Maritime Continent: Case Studies for 2020-2022 Istiqomah, Fadhilatul; Yulihastin, Erma; Wiratmo, Joko; Hermawan, Eddy; Trilaksono, Nurjanna Joko; Irawan, Dasapta Erwin; Yohanes, Kristy Natasha; Ayunina, Amalia Qurrotu
Agromet Vol. 38 No. 1 (2024): JUNE 2024
Publisher : PERHIMPI (Indonesian Association of Agricultural Meteorology)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29244/j.agromet.38.1.1-12

Abstract

Madden-Julian Oscillation (MJO) can affect weather and climate variability in the Indonesian Maritime Continent. MJO propagation is not always the same, previous research has classified MJO into 4 categories: slow, fast, stand, and jump. The objective of this study is to investigate the differences in MJO propagation and the factors that impact it. Daily data for variables such as Outgoing Longwave Radiation (OLR), zonal wind, and sea surface temperature are utilized in this research. The collected data is processed using composite methods based on the 8 MJO phases, with a specific focus on the years 2020, 2021, and 2022. The research findings suggest that warm sea surface temperatures in the Pacific Ocean and zonal winds dominated by Kelvin waves are favorable for MJO propagation. Conversely, cooling sea surface temperatures in the Pacific Ocean and zonal winds dominated by equatorial Rossby waves can hinder MJO propagation. Future researchers are expected to examine the impact of MJO propagation during extreme rainfall occurrences in several regions of Indonesia, as well as the application of machine learning and deep learning methods to predict MJO propagation in the future.
Fraud Syndicates Within Digital Ecosystem: Graph Network and Transaction Analysis Approach Irawandi, Ferdi Hidayat; Yohanes, Kristy Natasha; Alham, Lalu
Asia Pacific Fraud Journal Vol. 10 No. 1: 1st Edition (January-June 2025)
Publisher : Association of Certified Fraud Examiners Indonesia Chapter

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21532/apfjournal.v10i1.381

Abstract

This paper aims to develop and test methods to detect organized crime, fraud syndicates, and Money Laundering schemes within an e-wallet ecosystem. Analytical An analyticalprocess framework combining Graph Analytics and Supervised Learning is developed and trained with sample spaces of fraud and non-fraud. The pipeline utilized Heterogeneous Graph Transformation (HGT), Graph Statistics (Centrality Measures and Community Detection), and a Gradient Boosting Model to produce models for the detection of fraud syndicate syndicatesand organized crime. Welch’s t-test is employed to infer variance differences between samples. Findings confirm the hypothesis that fraud networks are markedly different, exhibiting a more centralized and isolated network compared to the organic, interconnected behaviors of non-fraudulent users. Fraud networks are further characterized by multiple isolated clusters, indicating distinctive groups or behaviors. The proposed method can provide validated methods of fraud and money laundering detection, especially for financial decision-makers and policymakers, to enhance fraud detection systems by improving the protection, integrity, and security of customers and digital transactions.