RGRahmat Gernowo

Rahmat Gernowo

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Rahmat Gernowo has a total of 114 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Stay-Contextual Trigger: A Confidence-Based Algorithm for Energy-Efficient and Behaviorally Grounded Mobile Notifications

    by Yudhy Setyo Purwanto, Rahmat Gernowo, Dinar Mutiara Kusumo Nugraheni

    Context-aware mobile applications often trigger notifications based solely on geofence entry, leading to high battery consumption and disruptive alerts during transient movement. To address this, we propose the Stay-Contextual Trigger (SCT) framework, which gates high-power GNSS activation behind low-power activity recognition and enforces a context-adaptive dwell-time requirement before delivering any notification. We evaluate SCT through a 14-day field study with 60 compliant Android users (Per-Protocol analysis after attrition filtering), comparing it against standard geofencing in four real-world outdoor zones. The SCT system computes a Contextual Readiness Score via a Confidence-Based Weighted Algorithm (CBWA), dynamically adjusting the weights of activity, proximity, dwell time, and behavioral history based on location semantics. Results show that SCT reduces daily battery drain by 40.3% (from 19.30% to 11.52%), increases notification acceptance from 32.5% to 89.4%, and achieves a System Usability Scale score of 81.25, an 18.8-point improvement over the control group’s 62.42. The high acceptance rate (89.4%) further validates sustained user engagement, ensuring metrics reflect consistent usage. These findings demonstrate that behavioral readiness, not mere proximity, is essential for sustainable and user-respectful mobile systems.

  • Open Access

    Stacking ensemble for multilingual aspect-based sentiment analysis of tourism reviews

    by Basworo Ardi Pramono, Rahmat Gernowo, Aghus Sofwan

    Multilingual tourism reviews often express opinions about multiple destination attributes within a single text, making aspect-level sentiment classification challenging. This study compares classical machine learning and ensemble methods for multilabel aspect-based sentiment analysis of amenities, attractions, and accessibility. The dataset comprises 13,085 Indonesian- and English-language Google Reviews labeled through a rule-based procedure. Reviews were represented using term frequency-inverse document frequency features and classified using logistic regression, multinomial naive Bayes, random forest, soft voting, adaptive boosting (AdaBoost), and stacking under a one-vs-rest framework. The stacking classifier combined logistic regression and random forest as base learners with logistic regression as the meta-learner. It achieved the best performance among the evaluated models, with a micro-F1 of 0.8626, macro-F1 of 0.7285, Hamming loss of 0.0633, and subset accuracy of 0.6825. These findings indicate that stacking effectively integrates complementary decision patterns and provides a reproducible framework for multilingual multilabel analysis of tourism reviews.

  • Open Access

    Explainable Multilingual Aspect-Based Sentiment Analysis for Tourism Using SHAP and LIME

    by Basworo Ardi Pramono, Rahmat Gernowo, Aghus Sofwan

    Online tourism analytics increasingly relies on Aspect-Based Sentiment Analysis (ABSA) to extract fine-grained visitor perceptions; however, prior tourism ABSA studies often emphasize predictive performance while providing limited and rarely quantified evidence on explanation reliability. To address this gap, this study proposes an explainable multilingual ABSA framework for tourism reviews that combines one-vs-rest Logistic Regression (LR) with linear coefficients, SHAP, and LIME, and augments them with a quantitative trustworthiness evaluation. Experiments were conducted on a bilingual corpus of 2,891 Indonesian and English Google Reviews collected from 10 tourist destinations in Central Java and annotated into 9 multi-label classes derived from the dimensions of attractions, amenities, and accessibility, and their sentiment polarities. The selected model achieved a Macro-F1 of 0.4586, a Hamming loss of 0.1505, and an exact match of 0.2512. The global explanation analysis showed substantial agreement between the LR coefficients and SHAP rankings, with overlap@10 generally ranging from 0.70 to 0.80 across most labels. Eraser-based evaluation at = 10 preserved predictions for 0.72–1.00 of cases, indicating strong fidelity of influential features. At the local level, SHAP and LIME consistently highlighted salient tokens associated with both correct and incorrect predictions, while sanity checks showed sharp degradation under model randomization, confirming that the explanations were tied to learned model parameters rather than superficial artifacts. These findings demonstrate that multilingual tourism ABSA can be made both interpretable and quantitatively auditable, thereby providing a transparent analytical basis for tourism service evaluation, destination management, and future decision-support applications.

  • Open Access

    RW-UCFI: A Risk-Weighted Uncertainty-Conditioned Explainability Framework for Stacked Ensemble Models in B2B Financial Risk Profiling

    by Carolus Borromeus Widiyatmoko, Rahmat Gernowo, Budi Warsito

    Interpretability in corporate financial risk profiling must support not only predictive performance but also governance-oriented decision-making. This study proposes a three-class financial risk assessment workflow for B2B settings and introduces Risk-Weighted Uncertainty-Conditioned Feature Importance (RW-UCFI) as a post-explanation prioritization framework. RW-UCFI is not a new attribution method; rather, it reorganizes existing explanation outputs according to class sensitivity, predictive uncertainty, and asymmetric risk relevance. The empirical analysis uses a single cross-sectional dataset of 954 Indonesia Stock Exchange-listed firms with organizationally provided Low Risk, Medium Risk, and High Risk labels. A stacked ensemble model is used as the explanatory substrate, followed by calibration analysis, uncertainty analysis, and governance-oriented explainability aggregation. On the held-out validation set, the model achieved an accuracy of 0.7487 and a macro ROC-AUC of 0.8630. Repeated stratified validation indicated moderately stable aggregate performance, although class-level reliability remained uneven, with High Risk recall emerging as the weakest and most variable component. The original model showed the most favorable probability reliability among the evaluated variants, whereas temperature scaling and one-vs-rest isotonic regression did not improve calibration. Uncertainty analysis further showed that the most uncertain cases concentrated substantially more misclassifications and High Risk misses; the top 30% most uncertain cases captured 52.1% of all errors and 43.8% of High Risk misses. RW-UCFI produced a materially different feature-priority structure from standard global SHAP ranking, suggesting that explanation outputs may become more decision-relevant for governance-oriented review when contextualized by uncertainty and asymmetric risk conditions in the present setting.

  • Open Access

    Rainfall Prediction at Ahmad Yani Meteorological StationUsing Integration ARIMA and LSTM

    by Naufal Daffa Pramudya, Rahmat Gernowo, Indra Waspada

    Purpose: Predicting rainfall using ARIMA, LSTM, and Hybrid ARIMA-LSTM models to obtain accuracy values on data at the Ahmad Yani Semarang station. Methods: This study implements the ARIMA, LSTM, and hybrid ARIMA-LSTM models to determine which of these models produces the most significant predictions using rainfall data at the Ahmad Yani Meteorological Station in Semarang. This method proves whether using the hybrid ARIMA-LSTM, which is a combination of the two models, is able to provide greater accuracy compared to the ARIMA/LSTM model. The results of these predictions can certainly help relevant stakeholders to improve rainfall accuracy, especially at the Ahmad Yani Meteorological Station. Result: By utilizing the power of statistical models (ARIMA) with deep learning (LSTM), the results of these two models provide higher accuracy compared to each model, as seen from the accuracy of the best ARIMA model using RMSE 15.8 and MAE 8.7, the best LSTM model RMSE 14.65 and MAE 9.06, while in the HYBRID ARIMA-LSTM model the best RMSE is 14.1 and MAE 9.06. Novelty: This research adds to the knowledge regarding the accuracy or combination of ARIMA and LSTM models which are rarely used, especially in the world of meteorology or rainfall. By utilizing the ARIMA model which is able to read linear patterns and the LSTM model which reads non-linear patterns, the accuracy of rainfall increases and can help related stakeholders.

  • Open Access

    A Hybrid BWM-GRA-PROMETHEE Framework for Ranking Universities Based on Scientometric Indicators

    by Dedy Kurniadi, Rahmat Gernowo, Bayu Surarso

    University rankings based on scientometric indicators frequently rely on compensatory aggregation models that allow extreme values to dominate the evaluation, while also remaining sensitive to outliers and unstable weighting procedures. These issues reduce the reliability and interpretability of the resulting rankings. This study proposes a hybrid BWM–GRA–PROMETHEE (BGP) framework that combines judgement-based weighting Best-Worst Method (BWM), outlier-resistant normalization Grey Relational Analysis (GRA), and a non-compensatory outranking method Preference Ranking Organization Methods for Enrichment Evaluation (PROMETHEE II). The framework is applied to an expert-validated set of scientometric indicators to generate more stable and behaviorally grounded rankings. The results show that the proposed method maintains stability under weight and threshold variations and preserves ranking consistency even under outlier-contaminated scenarios. Comparative experiments further demonstrate that BGP is more robust than Additive Ratio Assesment (ARAS), Multi-Attributive Border Approximation Area Comparison (MABAC), and The Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS), achieving the highest Spearman. This study contributes a unified evaluation framework that jointly addresses three major methodological challenges in scientometric ranking, outlier sensitivity, compensatory effects, and instability from data-dependent weighting. By resolving these issues within a single integrated model, the proposed BGP approach offers a more reliable and methodologically rigorous foundation for researchers and policymakers seeking to evaluate and enhance research performance.


  • Open Access

    A Smart Business Intelligence Model Based on HGO Discovery Approach for Precision in Inpatient Care in Regional General Hospitals

    by Hengki, Rahmat Gernowo, Oky Dwi Nurhayati

    In Bangka Belitung Archipelago Province, the Crude Death Rate (CDR), which represents the general mortality rate per 1000 discharged patients, exceeded 100. This figure indicates a significantly high mortality rate compared to the government standard of fewer than 45. Similarly, the Net Death Rate (NDR), defined as the mortality rate occurring after 48 h of hospitalization per 1000 discharged patients, was also above the national standard of fewer than 25. These findings highlight fundamental issues within hospital healthcare management system. As a potential solution, this study proposes the application of smart Business Intelligence (BI) through the Hierarchy, Governance, Outlook (HGO) Discovery approach. This approach is designed to optimize smart business intelligence in inpatient services in regional general hospitals, with the primary objective of addressing multidimensional challenges, including patient attribute management, human resource management as a strategic element, and the enhancement of inpatient care quality. The HGO Discovery method functions as an information system that identifies hidden patterns within a sequence of events (sequential patterns) by reorganizing existing hospital workflows. Thus, this approach facilitates accelerated inpatient care processes, improves operational efficiency, and provides more interactive support for decision-making. The implementation of HGO Discovery-based business intelligence is expected to produce a more integrated healthcare service system by combining hierarchical service structures, transparent governance, and strategic outlooks in every stage of decision-making, supported by the integration of smart business intelligence, data warehouse and data mining techniques.

  • Adaptive Traffic Signal Control: A Comprehensive Bibliometric Analysis

    by Hendra Marcos, Rahmat Gernowo, Adi Wibowo, Imam Tahyudin, Akhlis Munazilin

    Adaptive Traffic Signal Control (ATSC) has emerged as a key solution to address urban congestion by dynamically adjusting signal timing based on real-time traffic conditions. Despite growing academic interest, systematic mapping of the intellectual structure, thematic evolution, and research gaps in this field remains limited. This study presents a comprehensive bibliometric analysis of 1,287 scholarly articles from Scopus (1973-2024) to map the global landscape of ATSC. Using Bibliometrix (R) and VOSviewer, we performed performance analysis (publication trends, countries, institutions, journals) and scholarly mapping (keyword cooccurrence, thematic clustering). Results show exponential growth since 2015, with dominance from the United States (406 publications) and China (348). Four main thematic clusters were identified: (1) Reinforcement Learning and Multi-Agent Systems, (2) Connected and Autonomous Vehicles (CAVs) as Data Sources, (3) Real-Time Simulation and Field Evaluation, and (4) Sustainability and Resilience in Urban Mobility. This study also reveals future research directions such as federated learning for data privacy, fairness in signal prioritization, and integration with climate adaptation strategies.

  • Open Access

    Decision Prioritization with MCDM in Post-Disaster Management: A PRISMA-Guided Systematic Review and Bibliometric Mapping

    by Agusta Praba Ristadi Pinem, Rahmat Gernowo, Sorja Koesuma

    Prioritizing post-disaster actions requires balancing multiple, often conflicting criteria. To consolidate scattered evidence, this study reviews decision prioritization with Multi-Criteria Decision-Making (MCDM) in post-disaster management using a PRISMA-guided systematic review and bibliometric mapping. Initial searches returned 18,454 records from Scopus, 47,206 from Google Scholar, 650 from Emerald Insight, 30,975 from ProQuest, and 4,468 from IEEE Xplore. We included English-language articles published between 2014 and 2025—a window chosen to capture the rise of hybrid and fuzzy variants and early integrations with GIS, AI, and big data—that apply MCDM to prioritizing projects, interventions, or sites. We excluded non-English items, duplicates, and incomplete records; screening and eligibility followed PRISMA. We combined SLR procedures with bibliometric analysis in VOSviewer and R-bibliometrix to map co-occurrence. From the pool, 32 studies met the criteria. Distance-based methods (TOPSIS, VIKOR, EDAS) and AHP dominate; hybrid and fuzzy variants are increasing. Objective and mixed weighting are common, while normalization choices and ranking rules vary by context. Validation is uneven: case applications and expert judgment are common, but sensitivity tests and cross-method comparisons are scarce. We connect objectives, weighting and normalization, ranking, and validation, identify method–context fit, and spotlight reporting gaps. We provide method-selection cues and a reporting checklist for practitioners, and a roadmap for standardized validation, transparent parameterization, and integration with GIS, AI, and big data for researchers.


  • Open Access

    Unstacking the Stack: Synthesis of Optimization Strategies for Stacked Ensemble Models in Multi-Domain Contexts

    by Carolus Borromeus Widiyatmoko, Rahmat Gernowo, Budi Warsito

    Stacked ensemble models (SEMs) remain widely used for integrating multiple learning algorithms into a single predictive system. However, SEMs continue to face challenges such as accuracy limitations, overfitting, high computational expenses, and limited interpretability. This study conducts a systematic review of 269 peer-reviewed papers published between 2020 and 2025, following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) methodology to ensure transparency and rigor in article selection. The review identifies key technical issues in SEM implementations and synthesizes their corresponding optimization strategies. To address these challenges, a method-engineering-based modular three-stage framework is proposed, consisting of pre-processing, processing, and post-processing phases. Each stage targets specific weaknesses by improving data quality, optimizing models and hyperparameters, and enhancing interpretability and adaptability. The framework provides a structured foundation that links SEM optimization approaches with their development stages, supporting the design of robust, efficient, and interpretable ensemble models for practical applications.