Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Firman Arifman has a total of 11 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Enhancing Multi-Level Spatio-Temporal Forecasting of Adjudicated Crime Occurrence Trends in Indonesia

    by Firman Arifman, Teddy Mantoro, Media Anugerah Ayu

    Indonesia faces persistent challenges in crime forecasting and judicial resource management, compounded by chronic underreporting and inconsistent spatial resolution in official crime statistics. In this study, a multi-level spatio-temporal machine learning framework is developed and applied to 95,666 adjudicated crime records from the Supreme Court of Indonesia spanning January 2023 to June 2024. Following the CRISP-DM methodology, a hybrid STL-XGBoost v. 3.2.0 model is trained on a chronological split to forecast daily judicial caseloads, achieving an R2 of 0.8070, MAE of 16.52, and sMAPE of 9.76% on the held-out test set. DBSCAN spatial clustering, parameterized via k-distance plot analysis (ϵ=0.3∘, minPts = 3) and validated through Jaccard Similarity Index sensitivity analysis, identifies 29 distinct adjudicated crime hubs concentrated along Java and Sumatra’s urban and transit corridors. Comparative analysis of reported versus adjudicated crime data reveals systematic judicial funnel attrition ranging from 199.12% in Riau to 2436.02% in Papua, establishing that adjudicated crime records provide a reliable indicator of judicial workload rather than a comprehensive measure of social deviance. Key limitations, including the 18-month observation window that may not capture long-term policy shifts and the use of city centroids as spatial proxies that introduces a degree of ecological fallacy, are acknowledged. The framework offers a scalable, interpretable decision support tool for evidence-based judicial resource planning across national, provincial, and city scales in Indonesia.

  • Open Access

    A Hybrid Machine Learning Approach for Classifying Indonesian Cybercrime Discourse Using a Localized Threat Taxonomy

    by Firman Arifman, Teddy Mantoro, Dini Oktarina Dwi Handayani

    Indonesia’s rapid digital growth has been accompanied by escalating cyber threats, with public discourse on social media emerging as a critical but underutilized source of threat intelligence. This discourse is characterized by informal language and local nuances that render existing international cybercrime taxonomies ineffective, creating a gap in scalable, locally relevant threat analytics. This study introduces the Indonesian Cybercrime Threat Taxonomy (ICTT), a novel five-dimensional framework tailored to Indonesian online environments. An end-to-end OSINT pipeline was developed to collect 2344 samples from X (formerly Twitter) and YouTube, employing weak supervision with 12 high-precision regex patterns to generate training labels. A state-of-the-art IndoBERT model was fine-tuned on this data, and its performance was compared against rule-based and hybrid classification models. On a manually annotated gold-standard dataset of 600 samples, both the IndoBERT and hybrid models achieved 96.8% accuracy, significantly outperforming the rule-based baseline (66.7%). The models demonstrated strong generalization across both social media platforms, and the hybrid approach provided an effective balance of high performance and interpretability. This research demonstrates that informal public discourse can be systematically transformed into structured threat intelligence. The ICTT and the accompanying hybrid classification system provide a scalable, interpretable, and locally relevant foundation for cyber threat analytics in Indonesia, establishing a methodological blueprint for other low-resource language contexts.

  • Open Access

    A Canonical Computational Intelligence Framework for Adaptive Traffic Volume and Density Estimation From Legacy Analog Surveillance Systems

    by Dini Oktarina Dwi Handayani, Teddy Mantoro, Firman Arifman, Ben Rahman, Media Anugerah Ayu, Rahmadya Trias Handayanto

    Accurate traffic volume and density estimation are critical for intelligent transportation systems, yet most existing computer vision approaches assume high-quality digital video streams. In many developing regions, legacy analog CCTV infrastructure remains widely deployed, producing degraded video characterized by motion blur, frame drops, and inconsistent illumination. These conditions severely challenge reliable vehicle analytics. This paper proposes ACI-TA, a computational intelligence framework for robust vehicle counting and traffic density estimation from analog surveillance footage. The framework formalizes surveillance intelligence as a canonical computational intelligence architecture that transforms degraded sensing signals into decision-level traffic analytics into a unified canonical CI architecture tailored for degraded input streams. Beyond algorithmic performance, ACI-TA formalizes traffic analytics as a layered canonical transformation from physical signal uncertainty to decision-level intelligence. Experimental evaluation on real analog toll road footage demonstrates that the proposed framework significantly reduces counting error and improves density stability compared to baseline approaches. The system achieves 96.3% counting accuracy while reducing mean absolute error by over 60%. Designed for low-resource deployment, the framework enables scalable modernization of legacy surveillance infrastructure without requiring hardware replacement. The results indicate that analog monitoring systems can be systematically transformed into reliable traffic intelligence platforms through a reusable architectural blueprint for uncertainty-aware surveillance analytics.


  • Crime Time-Series Forecasting in Indonesia Using Neural Network and Linear Regression

    by Firman Arifman, Nanan Soekarna, Teddy Mantoro, Media Anugerah Ayu

    Crime is a harmful and widespread social issue affecting individuals globally, including in Indonesia, requiring not only reactive but also predictive measures for effective prevention. Lack of continuously updated official crime information and predictions can lead to a variety of adverse outcomes. Without current data, law enforcement agencies may struggle to allocate resources effectively, potentially leaving some communities underserved and vulnerable. Public safety could be compromised as patterns of criminal activity shift without being detected in real-time, preventing the implementation of proactive measures. Furthermore, the absence of accurate predictions hampers the ability to forecast and prepare for possible crime waves or emerging threats. This deficiency can also undermine public trust in law enforcement's capacity to protect citizens and maintain order. This research employed data mining and machine learning methods to forecast crime trends in Indonesia. The approach depends on continuously refreshed and accurate data derived from public court rulings. Data from the Supreme Court of Indonesia was gathered, stored, and pre-processed, after which various machine learning models were utilized to produce crime time-series forecasting. These predictions aim to provide law enforcement and the society with actionable insights for targeted crime prevention, enhancing public safety and preparedness. This research demonstrates the potential of data mining and machine learning in accurately predicting crimes, supporting efforts to safeguard society.