Jurnal Otomasi Kontrol dan Instrumentasi (JOKI) is a peer-reviewed open access journal published by Institut Teknologi Bandung, focusing on automation engineering, control systems, instrumentation technologies, robotics, Industry 4.0, and intelligent industrial applications.
Peer-reviewed research in automation, control systems, instrumentation, robotics, artificial intelligence, industrial IoT, and Industry 4.0 technologies.
This journal is indexed and abstracted in leading academic databases.
Browse recent volumes, current issues, and published article collections from this journal.
VOL. 18 NO. 1
A curated issue featuring research on geoscience exploration, transportation emissions, tunnel engineering, advanced materials, renewable feedstock, electric motor cooling, concrete structures, seismic hazards, and timber joint performance.
Explore selected research articles based on editorial recommendation, readership engagement, and scholarly impact.
View All News%22%2F%3E%3C%2Fsvg%3E)
Editor's Choice
Research Article
This study maps public emotions in Indonesian-language tweets related to the 2025 UTBK announcement using multi-label emotion classification. The main challenges in multi-label emotion classification on social media include extreme label imbalance, distribution shift between training and application data, and weak lexical signals for specific emotions. This study aims to build a reliable emotion modeling framework for long-tail social media corpora while demonstrating generalizable post-training calibration practices. The novelty lies in the integration of four components: (1) per-label posterior calibration using Platt scaling, (2) precision-targeted per-label thresholding frozen from the development set, (3) score-quantile–based rate targeting to align predicted prevalence with domain-based rates, and (4) context-limited lexicon-aware boosting with a final clamp. The proposed pipeline is lightweight and model-agnostic. This research adopts a quantitative experimental approach by varying post-training calibration components to measure their impact on classification performance. An IndoBERTweet model is trained using BCEWithLogitsLoss on manually annotated data, then calibrated and evaluated on development and test sets. The results demonstrate balanced micro- and macro-level performance, improved detection of minority labels, and emotion mapping over 3,500 tweets with prevalence distributions consistent with Plutchik’s theory of emotions.
%22%2F%3E%3C%2Fsvg%3E)
Most Viewed
Water level monitoring is generally still done manually. To improve monitoring effectiveness, a real-time water level monitoring system was designed using an aquarium simulator. This simulator represents three scenario conditions: Normal, Alert, and Danger. This system uses an ultrasonic sensor to measure water levels, a microcontroller as a data processor, and a wireless communication module to transmit data to a central server. The collected data is displayed on a local display for easy access by readers. Through testing, this system demonstrated an accuracy of 96,43% with a swift data transmission time of 0,05-0,07 seconds. The implementation of this system provides an effective automated monitoring solution, minimizing the need for manual observation, and this system has the potential to improve flood risk mitigation through more accurate and responsive early warnings.
Read more10.5614/joki.2026.18.1.2
Highly Cited
Coffee bean quality control is a critical stage in processing industries to meet export and consumption standards. Traditional visual manual inspection often results in inconsistency, subjectivity, and reduced production throughput. This research implements the Roboflow Detection Transformer (RF-DETR), an end-to-end transformer-based object detection architecture, to identify subtle and complex coffee bean defects. The study uses image processing and machine learning with a labeled dataset of 2,010 coffee bean images classified into five defect categories: brown, black, unripe, broken black, and partially black. The data are split into 75% training, 17% validation, and 8% testing. Performance evaluation shows RF-DETR detects and classifies all defect types effectively, achieving a mean Average Precision (mAP) of 97,6%, with 95,7% precision, 91,0% recall, and an F1 score of 93,29%. These results indicate that RF-DETR balances accurate spatial localization with reliable class prediction, minimizes false positives, and maintains strong detection sensitivity. Therefore, RF-DETR provides a solid technological basis for high-precision, real-time automated coffee bean sorting in industrial settings. For deployment, it can be integrated with production cameras and conveyor sorting actuators to deliver fast, consistent decisions. Future work may optimize augmentation, lighting calibration, and edge computing deployment to improve robustness across varied production lines in practice.
Read more10.5614/joki.2026.18.1.3
Invited Paper
The batik industry generates wastewater with elevated pH levels due to sodium hydroxide usage in dyeing processes, frequently exceeding the regulatory standard of pH 6–9. Traditional dilution methods prove economically inefficient, necessitating more adaptive control strategies. This research designs and simulates a nonlinear adaptive control system based on Model Reference Adaptive Control (MRAC) for pH neutralization using acetic acid. The Continuous Stirred Tank Reactor (CSTR) mathematical model was developed from mass balance, acid-base equilibrium, and electroneutrality principles, then simulated using Ordinary Differential Equation (ODE) functions in MATLAB. MRAC performance was compared with conventional PI controller across various initial wastewater pH conditions. Simulation results demonstrate that MRAC achieves faster convergence, reaching pH 7 in 2488.68 seconds from initial pH 9, compared to PI controller (3080.96 seconds) or uncontrolled system (10225 seconds). With settling time of 2377 seconds versus 2566.4 seconds for PI, MRAC reduces neutralizer consumption by 0.61% (9.5380 L versus 9.5969 L) while maintaining safety criteria above the lower pH bound of 6.80. Lyapunov stability analysis confirms the asymptotic stability of the adaptive controller. This study demonstrates that MRAC offers superior performance for batik wastewater pH control while reducing dependency on uneconomical dilution methods.
Read more10.5614/joki.2026.18.1.4
A multidisciplinary editorial board with expertise in peer review, publication ethics, and research dissemination.
Browse recently published journal volumes and issues.
