Journal of Informatics And Telecommunication Engineering
Not a member yet
373 research outputs found
Sort by
Design and Implementation of a Blockchain-Based Smart Barcode System to Enhance Supply Chain Traceability of Traditional Golok Ciomas Craftsmanship
No full textGolok Ciomas, a traditional weapon deeply rooted in Indonesian heritage, holds both cultural and economic significance for local micro-enterprises. However, the expansion of its market reach is hindered by limited supply chain transparency, inadequate product traceability, and the absence of authentication mechanisms. This study presents the design and implementation of a smart QR-based tracking system to enhance supply chain visibility and prevent counterfeiting. Employing a mixed-methods approach—combining participatory field observation with web-based software prototyping— framework embeds dynamic QR codes at every production stage, from raw material sourcing to end distribution. Pilot testing was conducted with selected blacksmiths and local traders in Banten Province. The results demonstrate that platform successfully increases information transparency, verifies product authenticity, and expands digital marketing reach. Compared to traditional manual records, the smart barcode platform significantly reduces data fragmentation and facilitates efficient access without requiring high-end infrastructure. This research contributes to the digital empowerment of heritage-based micro-enterprises while preserving product authenticity. Future improvements include blockchain integration and mobile-responsive features to extend usability. Framework serves as a scalable model for other cultural craftsmanship sectors seeking to modernize without compromising their artisanal identity
Classification of Oranges Based on Their Quality Using the YOLOv5 Algorithm
No full textIndonesia, as an agrarian country, has a wide variety of horticultural commodities, one of which is mandarin orange (Citrus reticulata). Post-harvest handling, particularly the sorting process based on fruit ripeness and defects, plays an important role in maintaining product quality and market value. However, manual sorting is considered inefficient because it is repetitive, highly dependent on operator subjectivity, and prone to inconsistency. Several studies report those manual methods can result in classification error rates exceeding 20% and longer processing times compared to computer vision-based systems. This study develops an automatic citrus fruit quality classification system using the YOLOv5 algorithm. The dataset consists of 703 citrus fruit images captured directly using a webcam under varying lighting intensities and color conditions, and is divided into 80% training data and 20% testing data. The classification is performed into three quality categories: ripe, unripe (green), and rotten oranges, based on the visual characteristics of the fruit peel. Experimental results show that a training configuration with 300 epochs, a batch size of 40, and warm white bright lighting conditions achieves the best performance. Real-time testing on 15 citrus fruits yields an average accuracy of 78.2%, indicating the potential of the proposed system as an initial sorting aid, despite limitations related to lighting conditions and the amount of test data
Implementation of IoT-Based Smart Parking with Automated Barrier and QR Code Validation
No full textThe rapid growth of vehicles in urban areas has created significant challenges in parking management, particularly regarding operational efficiency and user experience. This research develops a smart parking system leveraging Internet of Things (IoT) technology, equipped with real-time monitoring capabilities, online reservation features, and automated validation using QR codes for four-wheeled vehicles. The hardware implementation utilizes ESP8266 NodeMCU as the main controller, infrared sensors for vehicle detection, and SG90 servo motors for automated gate operation. On the software side, a web-based application was developed using PHP and Node.js, serving as both user interface and control panel for parking operators. Testing results indicate that infrared sensors perform optimally within a 5-20 cm range, achieving response times between 100-153 ms. The QR code validation mechanism successfully identifies valid, expired, and unauthorized tickets with 100% accuracy under normal operating conditions. Servo motors demonstrate consistent performance with operation times ranging from 2.2-2.7 seconds for opening and closing the gate. Data synchronization between ESP8266 and the server achieves average response times of 120-135 ms on stable connections, complemented by automatic recovery capabilities following network disruptions. The implementation of this system proves effective in enhancing parking operational efficiency through validation automation, real-time monitoring, and reduction of human errors, positioning it as a viable smart parking solution within the smart city ecosystem
A Hybrid IndoBERT-SERVQUAL Approach for Patient Satisfaction Evaluation in Hospital Services
No full textThe development of information and communication technology (ICT) provides opportunities for healthcare institutions to improve service quality through the digitisation of patient satisfaction evaluation processes. XYZ Hospital still uses manual methods to measure patient satisfaction, resulting in a slow and error-prone recapitulation process. This study aims to design and implement a sentiment analysis-based patient satisfaction system using the IndoBERT method integrated with quantitative Likert scale measurements based on the SERVQUAL dimensions. The IndoBERT model is used to classify positive and negative sentiments, while the Likert score provides a numerical representation of service quality. The study uses a hybrid approach by processing qualitative data in the form of 2,358 patient text reviews and quantitative data from the SERVQUAL questionnaire, which has been tested for validity and reliability. The IndoBERT model was trained and tested with an 80:20 data split and evaluated using accuracy, precision, recall, and F1-score metrics. The results show that the IndoBERT model is capable of classifying patient satisfaction sentiment with 91.10% accuracy and relatively balanced performance across both sentiment classes. The integration of sentiment analysis results and SERVQUAL scores is presented in an interactive dashboard to support decision-making at XYZ Hospital. This research contributes to the development of a more comprehensive, automated, and data-driven patient satisfaction evaluation system to support improvements in healthcare quality
IoT System for Monitoring Protection IED Switch Status
No full textThe reliability of protection systems in transmission networks depends on the readiness of devices, particularly the switch status that governs trip functions during a fault. In many substations, monitoring is still manual, conducted via panel checks or photos, which can lead to delays and misconfigurations, especially after maintenance. This risks protection unreadiness, causing operational delays or trip failures. This research develops an IoT-based system to monitor the status of protection switches, ensuring real-time readiness. The system reads IED coil registers via Modbus TCP, processes data using Node-RED, and displays results on a Node-RED UI dashboard. Results show the system reads switch status with 100% communication success. Status changes are detected in 0.2–0.3 seconds, matching the 0.5-second polling interval. Tests conducted on four IED test scenarios demonstrated full conformity between the IED status and the dashboard. All five protection channels per IED were read without discrepancies, and the dashboard handled parallel IED updates without data loss. This demonstrates that the system can replace slow and error-prone manual methods. This IoT system enhances protection reliability and supports efficient subsystem management. The implication is that this digital monitoring can be implemented without additional SCADA infrastructure
Identifikasi Sentimen pada Data Teks Media Sosial Melalui Pendekatan Pembelajaran Terawasi
No full textAnalisis sentimen pada data teks media sosial menjadi penting untuk memahami opini publik, sehingga penelitian ini bertujuan untuk mengidentifikasi sentimen pada data teks media sosial melalui pendekatan pembelajaran terawasi. Dataset yang digunakan terdiri dari tweet dan ulasan produk yang telah dilabeli sentimen positif maupun negatif. Proses penelitian dilakukan melalui beberapa tahapan, yaitu prapemrosesan data (Removal of Stopwords, Lemmatization and Word Stemming, Spell Correction), Ekstraksi Fitur (N-Grm, Word count dan Tf-Idf Vectorizer) serta penerapan algoritma Multinomial Naive Bayes, dan Support Vector Machine (SVM). Hasil penelitian menunjukkan bahwa penghapusan stopwords menurunkan kinerja model, sehingga tetap menggunakan stopwords. Stemming dan lemmatization juga tidak memberikan pengaruh terhadap kinerja model, sedangkan spell correction dapat meningkatkan akurasi sekitar 2% tetapi dengan trade-off waktu komputasi yang tinggi. Pada tahap ekstraksi fitur, TF-IDF menghasilkan akurasi yang lebih tinggi dibandingkan Word Count. Algoritma Multinomial Naive Bayes menghasilkan akurasi sebesar 79,73% dengan AUC-ROC sebesar 0,85. Sedangkan SVM dengan kernel linear mendapatkan hasil terbaik dengan akurasi 82% dan AUC-ROC 0,88, lebih tinggi daripada RBF kernel yang hanya mencapai akurasi 77,79% dan AUC-ROC 0,82. Hasil penelitian ini dapat disimpulkan bahwa SVM dengan kernel linear lebih sesuai untuk klasifikasi teks berdimensi tinggi
Optimizing Real-Time Weather Data and Information Services with Frameworks and Application Programming Interfaces
No full textThe need for fast, accurate, and secure weather information is a major challenge in BMKG public services. This research aims to develop a web-based information system capable of presenting real-time weather, climate, and flight forecast data, as well as supporting transaction services and digital data distribution at the BMKG Balikpapan Meteorological Station. The method employed is Research and Development (R&D), utilizing a Waterfall model in conjunction with the Network Development Life Cycle (NDLC). The research stages include needs analysis, system design, implementation using a web framework, and integration of Application Programming Interface (API) for real-time data synchronization. The system utilizes PostgreSQL as a database and the SMTP protocol for sending verification emails. Key features developed include login and registration with layered verification, uploading proof of payment, and automatic sending of documents to user emails. With a responsive interface design and good data integration, this system improves the efficiency, security, and transparency of public services. The results of Black Box Testing on six items were declared successful. Additionally, system quality testing, conducted among 17 respondents through six questions using a Likert scale, yielded an average of 95.08%, indicating a very good category. This system supports the digital transformation. These findings imply that the developed system has the potential to be adapted to other sectors, such as health and agriculture, to support more efficient and secure digitalization of public service
Design and Field Evaluation of a Smart-Contract FinTech Model for MSME Financial Accountability and Transparency in Medan
No full textDigital transformation requires Micro, Small, and Medium Enterprises (MSMEs) to enhance financial transparency and accountability in order to support Indonesia’s digital economic growth. This research is motivated by the limitations of traditional MSME accounting systems, which are still dominated by manual record-keeping, vulnerable to data manipulation, and characterized by limited access to digital accounting technologies. These conditions may reduce trust from business partners and financial institutions. Blockchain-based smart contract technology offers an innovative solution by enabling transparent, automated, and immutable financial transactions. This study aims to design a smart contract–based digital accounting system suitable for implementation by MSMEs in Medan City. The research adopts a Research and Development (R&D) approach combined with Design Science Research (DSR). The research stages include user needs identification, system design using the Solidity programming language, prototype development on the Ethereum Testnet, and testing through MSME transaction scenarios. System evaluation was conducted through functional testing and end-user interviews, revealing significant improvements in key financial accountability indicators, along with a high system usability score (SUS = 77.12) and strong adoption intention. The proposed system is expected to deliver a real-time, automated, and tamper-resistant accounting model that strengthens MSME financial accountability and competitiveness within the digital economy ecosystem.
Yolov12N: Implementation and Measuring an Ingredient-Detection Recipe App for Household Food-Waste Reduction
No full textHousehold food waste remains pervasive, driven by suboptimal meal planning and the underuse of available ingredients, with particularly acute impacts in Indonesia. This study presents a mobile application using YOLOv12n for multi-ingredient detection that translates recognized items into actionable recipes, and it evaluates user acceptance through the Technology Acceptance Model. On this implementation, the detection module attains mAP at 0.5 of 0.579 and mAP from 0.5 to 0.95 of 0.331. This study implements a Flutter application with YOLOv12n multi-ingredient detection integrated with TheMealDB and observes 219 users. The instrument validity is established and reliability is strong. While, Structural Equation Modelling supports 3 hypotheses, meanwhile Perceived Usefulness to Behavior Intention is not significant, indicating an indirect pathway via attitude. In conclusion, the solution is feasible for daily use, and strengthening perceived usefulness and ease of use appears to be a promising route to increase adoption and help reduce household waste
Improving Imbalanced Polycystic Ovary Syndrome Classification Using a Leakage-Free Machine Learning Pipeline
No full textPolycystic Ovarian Syndrome (PCOS) is a complex endocrine disorder affecting women of reproductive age and poses challenges for early diagnosis due to heterogeneous clinical presentations and imbalanced clinical datasets. This study aims to develop a data leakage–free machine learning pipeline to enhance the accuracy and reliability of PCOS classification using clinical data. The dataset underwent preprocessing and normalization, followed by stratified data splitting with an 80:20 ratio to maintain class proportions. The proposed pipeline was implemented within a unified computational framework integrating feature selection based on the ANOVA F-test, class imbalance handling using the Synthetic Minority Over-sampling Technique (SMOTE), and classification using a Support Vector Machine (SVM) with a Radial Basis Function (RBF) kernel. Hyperparameter tuning was performed using GridSearchCV combined with K-Fold Cross-Validation to ensure model robustness and consistency. The experimental results indicate that the proposed model achieved an accuracy of 0.9074, with precision, recall, and F1-score values of 0.8378, 0.8857, and 0.8611, respectively. Furthermore, ten dominant clinical features were identified, primarily related to hormonal profiles and ovarian morphology. These results demonstrate that the data leakage–free pipeline improves the validity and stability of PCOS prediction. The findings suggest that this approach may serve as a supportive tool for clinical decision-making, particularly in facilitating early and objective identification of PCOS