Claim Missing Document
Check
Articles

Found 4 Documents
Search

Weather-Aware Machine Learning for Urban Traffic Volume Prediction and Congestion Analysis Dilli Ram Rai; Maudhy Satyadharma; Edward Francis G. Gabor
Journal of Engineering and Applied Technology Vol 2 No 2 (2026): : December: Scripta Technica: Journal of Engineering and Applied Technology
Publisher : CV SCRIPTA INTELEKTUAL MANDIRI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.65310/wdt0rs27

Abstract

Hourly traffic prediction is periodic, yet weather disturbances can alter traffic demand and prediction error, creating implications for congestion management. This study evaluates weather-aware machine-learning models using a deterministic 48,204-record benchmark calibrated to the variable definitions, coverage, and scale of the UCI Metro Interstate Traffic Volume dataset. The benchmark incorporates traffic volume, temperature, rainfall, snowfall, cloud cover, weather classes, holidays, calendar variables, lagged observations, and rolling traffic means. Chronological training, validation, testing, and walk-forward evaluation were applied to prevent future information leakage and assess temporal stability. Ridge regression, Random Forest, Extra Trees, Gradient Boosting, HistGradientBoosting, and a 24-hour persistence baseline were compared using RMSE, MAE, R², and sMAPE. HistGradientBoosting achieved the lowest test error, with RMSE of 364.34 vehicles/hour, MAE of 287.64 vehicles/hour, and R² of 0.949. Adding weather variables to calendar and traffic-history features reduced RMSE by 3.39%. Congestion detection using the 80th-percentile threshold achieved precision of 0.898, recall of 0.807, and F1 of 0.850. Errors were highest during thunderstorms and fog, while weather-sensor perturbation increased RMSE by 3.93%. The findings indicate that weather provides incremental contextual information, whereas temporal structure and recent traffic state remain dominant predictors. The calibrated reconstruction requires validation against original source records before deployment.  
Artificial Intelligence Capability and SME Innovation Performance: An Integrative Review Edward Francis G. Gabor; Ariawan Ariawan; Dilli Ram Rai
Journal of Science, Technology, and Innovation Vol 2 No 2 (2026): : December: Inventa: Journal of Science, Technology, and Innovation
Publisher : CV SCRIPTA INTELEKTUAL MANDIRI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.65310/z4e6fy18

Abstract

Artificial intelligence (AI) has increasingly become an important component of digital transformation, yet its organizational value depends on how firms develop and deploy AI capability to support innovation, competitiveness, and sustainability. This study examines the relationships among digital transformation, AI capability, business innovation, competitive advantage, and sustainable firm performance through a structured integrative literature review. The analysis synthesizes evidence from 30 publications and applies directed qualitative evidence synthesis to identify recurring organizational mechanisms across the literature. The findings indicate that AI capability strengthens analytical and adaptive capacity, while business innovation provides an important mechanism for transforming technological resources into new products, processes, services, and business models. Competitive advantage is associated with dynamic capabilities, AI ambidexterity, strategic integration, and business model innovation. The sustainability dimension further reveals the importance of green innovation, green product innovation, data-driven culture, knowledge integration, green supply-chain management, and innovative work behavior. The study concludes that AI should be conceptualized as an organizational capability embedded within broader technological, managerial, innovative, and environmental systems. This integrated perspective connects digital transformation with competitiveness and sustainable performance through interconnected organizational mechanisms.  
Community Participation, Institutional Trust, and Collective Resilience in Times of Social Change: Understanding the Formation of Sustainable Community Cohesion Edward Francis G. Gabor; Yassine HADDIOUI; Mona Anju Sansena; Dilli Ram Rai
Journal of Human Interaction and Social Studies Vol. 1 No. 4 (2026): : November: Sapientia Diversalis: Journal of Human Interaction and Social Studi
Publisher : CV SCRIPTA INTELEKTUAL MANDIRI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.65310/bhetn303

Abstract

This study investigated how community participation, institutional trust, and collective resilience interacted in the formation of sustainable community cohesion during periods of social change. A corpus-based thematic co-occurrence analysis was conducted on 33 foundational and contemporary sources spanning social capital, collaborative governance, public trust, disaster resilience, co-production, and social sustainability. Each source was coded for participation, generalized trust, institutional trust, bonding ties, bridging ties, linking ties, collective efficacy, adaptive capacity, and cohesion. The analysis showed that participation alone was not sufficient to produce cohesion when institutions were perceived as unresponsive or procedurally unfair. Institutional trust had its strongest relational role when citizens experienced credible public performance, voice, and reciprocal accountability. Resilience literature consistently connected recovery capacity with dense local ties, bridging connections, and access to institutions beyond the immediate community. Co-occurrence patterns placed participation, trust, and social capital at the center of the evidence network, while adaptive capacity and cohesion appeared as downstream outcomes. The findings supported a layered cohesion model in which resilient communities combined horizontal solidarity with vertical institutional linkages and meaningful opportunities for participation.
Inclusive Teaching Practices and Classroom Participation: Examining the Role of Teacher Readiness, Differentiated Instruction, and Academic Belonging among Diverse Learners Dilli Ram Rai; Edward Francis G. Gabor; Yassine HADDIOUI; Fu'ad Sholikhi
Journal of Contemporary Pedagogy and Learning Science Vol. 1 No. 4 (2026): : November: Scientia Causa: Journal of Contemporary Pedagogy and Learning Scien
Publisher : CV SCRIPTA INTELEKTUAL MANDIRI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.65310/5r1pys21

Abstract

Inclusive teaching requires instructional responsiveness that supports participation without separating learners by ability or background. This comparative study examined teacher support, differentiated instructional responsiveness, and academic belonging across six Southeast Asian education systems using publicly available PISA 2022 indicators. Student-reported teacher interest, extra help, school belonging, loneliness, and outsider status were analysed descriptively against OECD reference values, with country-level pattern comparison used to identify configurations of support and participation. Teacher interest ranged from 57% to 79%, while extra help ranged from 64% to 86%. Belonging ranged from 73% to 86%, showing that strong social connection did not always coincide with the highest instructional-support indicators. Indonesia displayed high belonging despite below-OECD teacher-support measures, whereas Singapore combined very high extra help with belonging slightly below the OECD benchmark. The results indicate that inclusive participation depends on both instructional responsiveness and relational school conditions. Policy attention should connect teacher preparation for differentiation with routines that cultivate belonging, reduce exclusion, and sustain active participation among diverse learners.