Claim Missing Document
Check
Articles

Found 8 Documents
Search

A Probabilistic Decision Model for AI-Driven Optimization in Highly Complex Stochastic Mixed-Integer Nonlinear Programming (MINLP) Systems Sihotang, Hengki Tamando; Simbolon, Roma Sinta
Jurnal Teknik Informatika C.I.T Medicom Vol 17 No 1 (2025): March: Intelligent Decision Support System (IDSS)
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Highly complex systems present significant challenges for optimization, particularly when operating under uncertainty, high dimensionality, and dynamic environmental conditions. This study proposes a probabilistic decision model designed to enhance AI-driven optimization by integrating uncertainty quantification, adaptive decision mechanisms, and robust probabilistic reasoning. The methodology combines probabilistic modeling with machine learning techniques and is evaluated through a series of controlled experimental scenarios that simulate real-world complexity and noise. The results indicate substantial improvements in decision accuracy, solution stability, and robustness compared to traditional deterministic and heuristic-based optimization methods. The model consistently maintains high performance despite uncertain inputs and fluctuating system parameters, demonstrating its reliability in environments where conventional approaches tend to degrade. Theoretical analysis further validates the model’s feasibility and guarantees performance consistency under uncertainty. Overall, this research contributes a scalable and resilient decision-making framework capable of addressing the limitations of existing optimization models, offering significant potential for broad application in AI-driven complex systems.
Development of a Robust–Stochastic Optimization Framework for Enhancing Stability and Efficiency in Transportation Models Sihotang, Hengki Tamando; Simbolon, Roma Sinta
Jurnal Teknik Informatika C.I.T Medicom Vol 17 No 2 (2025): May: Intelligent Decision Support System (IDSS)
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This study develops a unified robust stochastic optimization framework designed to enhance the stability, efficiency, and reliability of transportation models operating under significant uncertainty. Traditional deterministic, robust-only, and stochastic-only approaches each face limitations deterministic models fail under variability, robust models tend to be overly conservative, and stochastic models struggle under extreme disruptions. To address these gaps, the proposed framework integrates worst-case uncertainty sets with probabilistic scenario modeling, enabling decisions that remain feasible under extreme conditions while maintaining optimal performance during typical operations. The methodology includes comprehensive uncertainty modeling of travel time fluctuations, demand variability, cost changes, and network disruptions; a hybrid mathematical formulation combining robust constraints with stochastic scenarios; and an efficient algorithmic structure employing enhanced decomposition techniques and scenario filtering to reduce computational complexity. Experimental results using benchmark and real-world transportation datasets show significant improvements in solution stability, travel time reliability, cost efficiency, and network resilience compared with conventional models. The hybrid framework reduces over-conservatism, lowers operational cost by up to 25%, and increases robustness under high-variability conditions, demonstrating superior performance in both normal and disrupted environments. The study advances optimization theory by offering a scalable and computationally tractable integration of two major uncertainty-handling paradigms, while contributing to transportation modeling through a practical tool capable of supporting reliable routing, scheduling, and logistics planning. Overall, this research provides a robust and adaptive optimization strategy that strengthens decision-making under uncertainty and improves the resilience of modern transportation systems.
A Fundamental Multilevel Optimization Decision Model for Complex Systems Based on an AI-Optimization Fusion Framework Sihotang, Hengki Tamando; Simbolon, Roma Sinta
Jurnal Teknik Informatika C.I.T Medicom Vol 17 No 3 (2025): July: Intelligent Decision Support System (IDSS)
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/cit.Vol17.2025.1388.pp136-147

Abstract

Complex systems in modern domains such as transportation, energy, supply chains, and autonomous multi-agent networks require decision-making frameworks capable of handling hierarchical structures, dynamic environments, and high levels of uncertainty. Traditional multilevel optimization models offer a structured approach but often struggle with computational complexity, nonlinear interactions, and incomplete information. This research proposes a fundamental multilevel optimization decision model based on an AI-Optimization Fusion Framework designed to overcome these limitations. The model integrates bilevel and trilevel hierarchical structures with artificial intelligence learning paradigms, including supervised learning, deep learning, and reinforcement learning, to form a unified architecture that adapts to evolving system behaviors. A hybrid algorithmic formulation is developed to merge optimization procedures with learning-based approximations, enabling faster convergence, improved robustness, and enhanced decision quality. The experimental and simulation results demonstrate that the proposed framework outperforms traditional optimization approaches in accuracy, computational efficiency, scalability, and resilience under uncertainty. The model’s hierarchical decision mechanisms allow for dynamic coordination across decision levels, while AI-driven components provide predictive and adaptive capabilities that mitigate complexity in high-dimensional environments. The research contributes a novel integrated architecture, theoretical enhancements in multilevel decision modeling, and algorithmic innovations for hybrid AI–optimization systems. Limitations related to data availability, computational resources, and structural assumptions are acknowledged, offering directions for future exploration. Overall, this study establishes a new foundation for intelligent, scalable, and robust decision-making in complex systems, positioning AI–optimization integration as a key enabler for next-generation autonomous and adaptive decision frameworks.
A Mathematical Framework for Integrating Neural Networks into Stochastic DEA Models to Reduce Variance and Improve Prediction Stability Sihotang, Hengki Tamando; Simbolon, Roma Sinta
Jurnal Teknik Informatika C.I.T Medicom Vol 17 No 4 (2025): Intelligent Decision Support System (IDSS)
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/cit.Vol17.2025.1394.pp196-206

Abstract

This study proposes a novel mathematical framework that integrates neural networks into Stochastic Data Envelopment Analysis (SDEA) to reduce variance and enhance the stability of efficiency prediction under uncertainty. Traditional DEA models rely on linear or piecewise-linear frontiers and are highly sensitive to noise, resulting in unstable efficiency scores and unreliable rankings. The proposed hybrid framework addresses these limitations by combining stochastic frontier modeling, noise-distribution assumptions, and neural network function approximation to construct a smooth, flexible, and noise-resilient efficiency frontier. Neural components capture nonlinear relationships among inputs and outputs, while regularization and bootstrapping techniques stabilize estimation and mitigate variance inflation. Empirical experiments demonstrate that the integrated model outperforms classical DEA, stochastic DEA, and bootstrap-corrected DEA in terms of variance reduction, robustness to noise, and stability across repeated sampling. Efficiency scores exhibit narrower confidence intervals, more consistent DMU rankings, and improved frontier curvature representation. Sensitivity analyses further show that the model remains robust under different noise structures and hyperparameter settings. The findings highlight the potential of combining machine learning with stochastic optimization to advance the methodological foundation of DEA. By enhancing frontier flexibility and reducing noise-induced bias, the proposed framework provides a more reliable tool for efficiency evaluation in complex and uncertain production environments. Future work should focus on enhancing interpretability, reducing computational cost, and relaxing distributional assumptions to further extend the applicability of this hybrid approach.
Design and Testing of an Energy-Saving Ultrasonic Rat Repeller Prototype for Open Agricultural Environments Sihotang, Hengki Tamando; Simbolon, Roma Sinta
Jurnal Teknik Informatika C.I.T Medicom Vol 15 No 3 (2023): July: Intelligent Decision Support System (IDSS)
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Rat infestations are a major threat to agricultural productivity in open-field environments, causing significant crop damage and economic losses. Conventional control methods, such as chemical poisons and mechanical traps, are often labor-intensive, environmentally harmful, and pose risks to non-target species. This research focuses on the design, development, and testing of an energy-saving ultrasonic rat repeller prototype tailored for open agricultural fields, aiming to provide an environmentally friendly and practical pest control solution. The prototype integrates a microcontroller-based control system, ultrasonic transducer, and energy-efficient power management, including low-power modes and intermittent frequency emission to reduce energy consumption while maintaining repellent effectiveness. Laboratory testing verified frequency accuracy, operational stability, and power usage, while field testing assessed rat activity reduction, crop damage mitigation, and device endurance under varying environmental conditions. Results indicate that the prototype effectively deters rats within its coverage area, reduces crop damage, and consumes significantly less energy compared to conventional continuous-emission devices. The study demonstrates the feasibility of energy-efficient ultrasonic technology for sustainable pest management and provides a foundation for future enhancements, such as solar-powered operation, IoT-based monitoring, and multi-pest control integration.
Effectiveness of Ultrasonic Frequencies on the Behavior and Migration Patterns of Rice Field Rats (Rattus argentiventer) Sihotang, Hengki Tamando; Sihotang, Jonhariono; Simbolon, Romasinta
International Journal of Enterprise Modelling Vol. 16 No. 3 (2022): Sep: Enterprise Modelling
Publisher : International Enterprise Integration Association

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/int.jo.emod.v16i3.163

Abstract

Rat infestation by Rattus argentiventer remains a serious problem in irrigated rice fields, causing significant yield losses and threatening sustainable rice production. Conventional control methods rely heavily on chemical rodenticides, which pose environmental risks and show declining long-term effectiveness. Ultrasonic deterrent technology has been proposed as an alternative; however, its effectiveness in open-field agricultural environments remains inconsistent and poorly understood. This study aims to analyze the behavioral and migration responses of rice field rats to different ultrasonic frequency ranges to clarify the mechanisms underlying ultrasonic deterrence. A field-based experimental design was applied using paired treatment and control plots, with ultrasonic frequencies ranging from 20 to 40 kHz. Rat activity and movement were monitored through camera traps and motion sensors, and spatial behavior was analyzed using activity reduction rates, migration distance, and path deviation indices. The results indicate a clear frequency-dependent response, with ultrasonic exposure at 30–35 kHz producing the strongest avoidance behavior and directional displacement. These findings suggest that ultrasonic deterrence primarily induces spatial displacement rather than population elimination and provide important implications for the development of adaptive ultrasonic–IoT systems to support smart and sustainable pest management in rice agriculture.
Adaptive Scheduling Model of Ultrasonic Frequencies Based on Environmental Data for Rice Field Rat Pest Control Sihotang, Hengki Tamando; A, Galih Prakoso Rizky; Sihotang, Jonhariono; Simbolon, Romasinta
International Journal of Enterprise Modelling Vol. 19 No. 3 (2025): September: Enterprise Modelling
Publisher : International Enterprise Integration Association

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/int.jo.emod.v19i3.164

Abstract

Rat infestation remains a major constraint to rice production, causing significant yield losses and threatening food security in many rice-growing regions. Although ultrasonic deterrent systems have been promoted as an environmentally friendly alternative to chemical rodenticides, their effectiveness is often inconsistent due to static frequency emission and rapid behavioral habituation. This study proposes an adaptive scheduling model for ultrasonic frequencies based on real-time environmental data to enhance long-term deterrence effectiveness. The model integrates environmental sensing, stochastic frequency selection, and habituation-aware control within a context-aware scheduling framework. Environmental data were acquired using field-deployed sensors, while the adaptive algorithm dynamically adjusted ultrasonic frequency, emission duration, and interval. Field evaluations compared the proposed system with static ultrasonic control. Results demonstrate sustained spectral diversity, reduced habituation, and significant decreases in rat activity and crop damage, alongside improved energy efficiency. These findings highlight the potential of adaptive ultrasonic control as a scalable and sustainable solution for smart agriculture, supporting chemical-free pest management and precision rice farming.
Klinik penulisan artikel ilmiah: Strategi peningkatan kompetensi publikasi masyarakat akademik menuju jurnal terakreditasi Sinta Sihotang, Hengki Tamando; Rizky A, Galih Prakoso
Lebah Vol. 19 No. 3 (2026): January: Pengabdian
Publisher : IHSA Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/lebah.v19i3.520

Abstract

Kegiatan pengabdian kepada masyarakat ini bertujuan meningkatkan kompetensi penulisan dan publikasi ilmiah masyarakat akademik menuju jurnal terakreditasi SINTA melalui model Klinik Penulisan Artikel Ilmiah. Latar belakang kegiatan ini adalah rendahnya kemampuan publikasi dosen, guru, dan peneliti muda di daerah akibat keterbatasan kompetensi teknis dan minimnya pendampingan publikasi berkelanjutan. Metode yang digunakan adalah clinic-based training berbasis daring yang mengombinasikan webinar penulisan artikel ilmiah, praktik penulisan berbasis naskah nyata, serta pendampingan teknis submission melalui sistem Open Journal System (OJS). Evaluasi dilakukan menggunakan pre-test, post-test, dan pemantauan luaran publikasi. Hasil kegiatan menunjukkan peningkatan kompetensi peserta secara signifikan, ditandai dengan seluruh peserta (100%) memperoleh skor post-test di atas batas kompetensi minimal dan berhasil melakukan submit artikel ke jurnal ilmiah nasional. Sebagian naskah telah berstatus published dan accepted, sementara lainnya masih dalam tahap review. Kegiatan ini efektif meningkatkan kapasitas publikasi ilmiah dan berpotensi direplikasi sebagai model pengabdian berbasis literasi akademik yang berkelanjutan