Journal of Digital Technology and Computer Science
Digital Technology and Socio-Technical Innovation, including the design, development, implementation, and evaluation of digital solutions, platforms, applications, and infrastructures that support modern socio-technical systems, digital transformation, and technology-enabled services. Computer Systems, Software, and Networking, encompassing distributed systems, computer networks, network architectures, communication protocols, network performance, next-generation connectivity, software systems, and integrated computing environments. Artificial Intelligence, Machine Learning, and Intelligent Systems, covering intelligent systems, machine learning algorithms, deep learning, natural language processing, expert systems, knowledge-based systems, computational intelligence, and applied AI across scientific, industrial, and societal domains. Decision Support, Fuzzy, and Evolutionary Systems, including decision support systems, fuzzy logic, fuzzy control, evolutionary computing, optimization algorithms, swarm intelligence, hybrid intelligent methods, and data-driven decision models. Image, Audio, and Multimedia Processing, including computer vision, image processing, sound and speech processing, multimedia analysis, signal processing, pattern recognition, and audio-visual computing applications. Information Security and Cybersecurity, focusing on information security, system security, network security, cybersecurity governance, cryptography, privacy protection, secure software engineering, threat detection, intrusion prevention, digital forensics, and cyber risk management. Cyber Crime and Digital Investigation, including cybercrime detection and analysis, cyber law and policy in digital environments, forensic investigation, online fraud, identity theft, malicious activity analysis, and digital evidence management. Social Network and Digital Security, covering security and trust in social media and online platforms, digital identity, misinformation and disinformation detection, privacy in social networks, human factors in cybersecurity, and safe digital interaction ecosystems. Operating Systems, Computer Architecture, and Embedded Computing, including operating systems, processor and memory architecture, virtualization, system-level optimization, embedded systems, real-time computing, firmware, and performance engineering. Cloud, Edge, and Ubiquitous Computing, covering cloud platforms, fog and edge computing, distributed intelligence, service orchestration, scalable infrastructures, reliability, resource management, and pervasive computing environments. Internet of Things (IoT), Sensor Networks, and Cyber-Physical Systems, including smart devices, wireless sensor networks, industrial IoT, IoT platforms, connected environments, cyber-physical systems, and real-world deployment challenges in intelligent sensing and control. Big Data, Analytics, and Data-Driven Computing, encompassing data engineering, data mining, large-scale data processing, predictive analytics, visual analytics, business intelligence, and advanced computational methods for complex datasets. Wearable Devices and Smart Sensing Technologies, including wearable computing, body-area networks, health and activity monitoring systems, smart textiles, mobile sensing, and human-centered intelligent devices. Embedded Robotics and Microcontroller Systems, including robotic systems, embedded robotics, autonomous control, low-level hardware-software integration, microcontroller-based applications, robotic sensing, and intelligent actuation systems. Micro and Nano Technology, including microelectronics, nanoelectronics, microsystems, nanosystems, MEMS/NEMS-related applications, miniaturized intelligent devices, and sensor-oriented micro/nano technological innovations. Renewable Energy and Intelligent Energy Systems, including digital technologies for renewable energy, smart energy monitoring, intelligent control systems for energy efficiency, IoT-enabled energy systems, sustainable computing, and computational methods for energy optimization. Software Engineering and Information Systems, including software design, software quality assurance, software testing, requirements engineering, enterprise systems, information systems development, human-centered software solutions, and digital service integration. Robotics, Automation, and Autonomous Systems, covering intelligent robotics, automation systems, control engineering, autonomous agents, robotic perception, human-robot interaction, and smart manufacturing applications. Human-Computer Interaction and Digital Experience, including user interface design, user experience, usability evaluation, interactive systems, accessibility, persuasive technologies, and digital behavior in technology-mediated environments. Green Computing and Sustainable Digital Systems, including energy-efficient computing, sustainable software and hardware design, green AI, carbon-aware digital infrastructures, smart resource management, and digital technologies for environmental sustainability.
Articles
53 Documents
<![CDATA[KNN Vs Naive Bayes: An Innovative Comparison in Predictive AI Learning With Association Data Support ]]>
<![CDATA[Devi Miftahul Jannah]]>;
<![CDATA[Aprilianti Nirmala S]]>
<![CDATA[ Journal of Digital Technology and Computer Science Vol. 3 No. 1 (2025): November 2025 ]]>
Publisher : <![CDATA[Academic Bright Collaboration ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.61220/dtcs.v3i1.324
<![CDATA[This study analyzes how Naive Bayes and K-Nearest Neighbor (KNN) predict learning outcomes based on artificial intelligence (AI). The main focus of this study is the difficulty of algorithms in handling complex learning data and the contribution of Association Rule Mining (ARM) attribute features in improving prediction accuracy. The methods applied include two classification algorithms (KNN and Naive Bayes) in an exploratory-comparative quantitative research design, as well as the application of ARM to uncover hidden patterns among variables using the apriori algorithm. Data for 368 students with prior experience in artificial intelligence technology was collected through an online survey. Although KNN outperforms in recall, the study results show that Naive Bayes has higher precision. By detecting hidden correlation patterns that cannot be identified by conventional classification methods, ARM improves classification results. The discussion emphasizes that the selection of the best algorithm depends on the application's objectives, namely whether the priority is on classification accuracy or the range of relevant results. Based on these findings, a hybrid technique combining KNN, Naive Bayes, and ARM is highly recommended for creating a more efficient and accurate prediction system to support AI-based education.]]>
<![CDATA[Development of an IoT-based Smart Farming System using ESP32 for Livestock Monitoring ]]>
<![CDATA[Rizki Fikriansyah]]>;
<![CDATA[Siti Mutmainah]]>;
<![CDATA[Dahlan]]>
<![CDATA[ Journal of Digital Technology and Computer Science Vol. 3 No. 2 (2026): April 2026 ]]>
Publisher : <![CDATA[Academic Bright Collaboration ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.66053/dtcs.v3i2.607
<![CDATA[Purpose – Livestock farming is a vital sector of the Indonesian economy, yet the common practice of allowing livestock to roam freely renders manual monitoring inefficient and exposes farmers to risks of loss, accidents, and theft. This study presents an IoT-based livestock monitoring prototype designed to enable real-time location tracking and automated boundary violation alerts, addressing the lack of affordable and practical smart monitoring solutions for smallholder farmers. Methods – The system was developed using an ESP32 microcontroller integrated with a Neo-6M GPS module and a Telegram bot for automatic notifications. A geofencing boundary of 50 meters was configured from a fixed reference point. Twelve trials were conducted across morning, afternoon, and evening sessions to evaluate system performance under varying conditions. Findings – The system delivered location alerts every ten minutes with Google Maps links and coordinates. Under normal conditions, livestock positions were detected within 5.0–12.7 meters of the reference point. Boundary violations exceeding 50 meters triggered immediate alerts, with notification latency ranging from 3 to 8 seconds under stable network conditions. GPS baseline error was approximately 5.0–5.5 meters, with an accuracy variation of ±2–3 meters. Research Implications – System performance is constrained by Wi-Fi network stability and environmental factors affecting GPS accuracy, limiting its generalizability to areas with reliable connectivity. Further field testing is required before broader implementation. Originality – This study contributes a low-cost, ESP32-based geofencing solution integrated with Telegram, offering a practical and scalable approach to smart livestock monitoring in developing agricultural contexts.]]>
<![CDATA[YOLOv9-Based Classification of Ganyong Plant Health for Early Detection of Leaf Spot Disease ]]>
<![CDATA[M Fikram]]>;
<![CDATA[Siti Mutmainah]]>;
<![CDATA[Dahlan]]>
<![CDATA[ Journal of Digital Technology and Computer Science Vol. 3 No. 2 (2026): April 2026 ]]>
Publisher : <![CDATA[Academic Bright Collaboration ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.66053/dtcs.v3i2.551
<![CDATA[Purpose – This study implements the YOLOv9 architecture to automatically classify the health condition of ganyong leaves (Canna edulis Kerr.) as an early-detection tool for leaf spot disease. The study addresses the limitations of subjective manual identification and supports farmers in Bumipajo Village, Bima Regency, in reducing potential crop failure. Methods – A primary field dataset consisting of 1,383 image objects was collected and divided into training, validation, and testing sets using a 70:20:10 ratio. YOLOv9 was implemented by integrating Programmable Gradient Information (PGI) and the Generalized Efficient Layer Aggregation Network (GELAN). Model training was conducted in Google Colab using GPU acceleration, a batch size of 4, and 50 epochs. Findings – Evaluation on independent test data showed strong detection performance, with mAP@50 of 99%, Precision of 99%, Recall of 100%, and an average inference speed of 58.4 ms per image. These results indicate that YOLOv9 can effectively preserve disease-related morphological features in visually complex biological objects. Research implications – The findings are limited to the environmental conditions of the data collection site and one disease type. The reported time efficiency also depends on GPU-based hardware and requires further validation on mobile devices. Originality – This study contributes a field-based primary dataset of ganyong leaves and validates YOLOv9 for a local agricultural commodity that remains underexplored.]]>
<![CDATA[Implementation of K-Means Algorithm in Data Mining for Drug Market Segmentation ]]>
<![CDATA[Joko Prasetiana]]>;
<![CDATA[Feby Charlos]]>
<![CDATA[ Journal of Digital Technology and Computer Science Vol. 3 No. 2 (2026): April 2026 ]]>
Publisher : <![CDATA[Academic Bright Collaboration ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.66053/dtcs.v3i2.582
<![CDATA[Purpose – This study aims to implement the K-Means clustering algorithm in data mining to segment pharmaceutical products based on stock and sales patterns. The study addresses the need for data-driven product classification to support more effective inventory management and marketing decision-making in pharmaceutical businesses. Methods – This research applied a quantitative data mining approach using secondary sales transaction data from a pharmaceutical distributor covering the period from January 2022 to December 2023. The dataset consisted of 1,248 transaction records, which were aggregated into 12 pharmaceutical products based on stock quantity and sold quantity variables. Data preprocessing included cleaning, transformation, aggregation, and scale checking through Min-Max normalization. The reported K-Means calculation was presented using original-scale stock and sold quantity values for interpretability, while the optimal number of clusters was determined using the Elbow Method and validated with the Silhouette Score. Findings – The Elbow Method indicated that three clusters were optimal, supported by a Silhouette Score of 0.71. The clustering results classified products into high-demand, moderate-demand, and low-demand segments. High-demand products require prioritized stock replenishment and distribution, while low-demand products need tighter inventory control and targeted promotional strategies. Research implications – The findings provide practical insights for improving procurement planning, inventory optimization, and promotional decision-making. However, the analysis is limited to 12 aggregated products and two variables. Originality – This study contributes by applying K-Means clustering specifically to pharmaceutical product-level market segmentation using stock and sales data.]]>
<![CDATA[Implementation of the K-Means Clustering Algorithm to Identify Student Discipline Patterns Based on Attendance Data ]]>
<![CDATA[Hermila A.]]>;
<![CDATA[Haeriani H]]>;
<![CDATA[Wildan]]>
<![CDATA[ Journal of Digital Technology and Computer Science Vol. 3 No. 2 (2026): April 2026 ]]>
Publisher : <![CDATA[Academic Bright Collaboration ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.66053/dtcs.v3i2.652
<![CDATA[Purpose – Student attendance data in vocational schools are often collected digitally but remain underutilized for managerial decision-making. This study aims to apply the K-Means Clustering algorithm to identify student discipline patterns based on attendance behavior and support objective, data-driven intervention planning. Methods – This study employed a quantitative computational experiment using attendance data from 23 students at SMK Negeri 1 Bolango Utara over 33 effective school days. Student identities were anonymized using subject codes. Two variables were analyzed: on-time attendance frequency and tardiness frequency. The number of clusters was set to K=3 based on managerial discipline categories and validated using the Elbow Method through Within-Cluster Sum of Squares analysis. Findings – The results classified students into three discipline profiles. Cluster 1 consisted of 13 students categorized as highly disciplined, Cluster 3 consisted of 5 students categorized as moderately disciplined, and Cluster 2 consisted of 5 students categorized as less disciplined. The less disciplined cluster showed a critical pattern, with an average tardiness frequency of 16.80, exceeding its average on-time attendance frequency of 16.20. Research implications – The findings indicate that K-Means clustering can transform passive attendance records into actionable discipline profiles. However, the study was limited to one school, 23 students, and two attendance variables. Originality – This study contributes a simple computational framework for developing an attendance-based early warning system for student discipline management in vocational education.]]>
<![CDATA[Crude Palm Oil (CPO) Production Prediction Information System Using A Linear Regression Algorithm ]]>
<![CDATA[Erin Triani Sipayung]]>;
<![CDATA[Ritna Wahyuni]]>;
<![CDATA[Ratu Mutiara Siregar]]>
<![CDATA[ Journal of Digital Technology and Computer Science Vol. 3 No. 2 (2026): April 2026 ]]>
Publisher : <![CDATA[Academic Bright Collaboration ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.66053/dtcs.v3i2.679
<![CDATA[Purpose – Crude Palm Oil (CPO) production fluctuates with Fresh Fruit Bunches (FFB) supply and operational conditions, making production planning difficult for palm oil mills. This study develops a CPO production prediction information system that integrates a simple linear regression model into a Progressive Web Application (PWA) to provide an accessible decision-support tool. Methods – The model was developed using simple linear regression based on 39 monthly production records. Model performance was evaluated using Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and the coefficient of determination (R²), and implemented in a PWA-based system using PHP and MySQL. Findings – The regression model produced the equation Y = -101.869 + 0.238X. The model achieved R² = 0.8716, MAE = 279.80 tons, and RMSE = 335.72 tons. With average monthly CPO production of 2,000–3,000 tons, the MAE represents an approximate error rate of 10–14%, indicating moderate predictive performance. Research implications – The findings are useful for preliminary production planning, but generalization is limited by the use of one predictor, 39 observations, one palm oil mill, and the absence of k-fold cross-validation. Originality – This study contributes by combining an interpretable linear regression model with a PWA-based system for real-time CPO prediction and visualization.]]>
<![CDATA[Identifying Commercial Sweet Spots: A Geomarketing Approach to Coffee Shop Spatial Competitiveness in Yogyakarta ]]>
<![CDATA[Gulam Hazmin]]>
<![CDATA[ Journal of Digital Technology and Computer Science Vol. 3 No. 2 (2026): April 2026 ]]>
Publisher : <![CDATA[Academic Bright Collaboration ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.66053/dtcs.v3i2.682
<![CDATA[Purpose – This study maps coffee shop locations in the Yogyakarta–Sleman area to support evidence-based site selection for small businesses. It integrates competitor distribution and online customer-response data to identify areas with strong demand signals but relatively limited nearby competition. Methods – The study used 216 coffee shop POI records from Yogyakarta City and Sleman Regency. Geographic coordinates, ratings, and review counts were analyzed through competitor-radius counts, Kernel Density Estimation, Voronoi/grid-based logic, and a standardized sweet-spot score. Competitive pressure was measured using Haversine-distance buffers, while demand potential was proxied by rating multiplied by ln(1 + review count). Findings – Yogyakarta City was more saturated, with an average of 12.69 competitors within 1 km and 18.08 within 1.25 km per shop. Sleman showed lower local pressure, with 7.23 competitors within 1 km and 10.93 within 1.25 km. Ratings were nearly equivalent across areas, indicating that spatial exposure, rather than rating quality alone, better differentiates commercial opportunity. Correlation tests showed no statistically significant association between local competition and rating. Research implications – The framework provides business owners with a practical preliminary screening tool before conducting field surveys, lease negotiations, or financial planning. It also helps urban planners visualize business concentration and manage neighborhood commercial growth. Originality – The study proposes an integrated score combining online reviews, ratings, and local competition, while demonstrating that market crowding and customer-response strength should be assessed as separate decision layers.]]>
<![CDATA[Comparative Analysis of Structural-Based Reduction and Brute Force Algorithms for Determining Metric Dimensions in Tree Graphs ]]>
<![CDATA[Afifah Farhanah Akadji]]>;
<![CDATA[Abdul Gani F. S. H. Lihawa]]>;
<![CDATA[Maharani Eka]]>;
<![CDATA[Karina A. Sasmito]]>;
<![CDATA[Hendy Prasetyo]]>;
<![CDATA[Andi Sitti Dwi Auliyani]]>
<![CDATA[ Journal of Digital Technology and Computer Science Vol. 3 No. 2 (2026): April 2026 ]]>
Publisher : <![CDATA[Academic Bright Collaboration ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.66053/dtcs.v3i2.696
<![CDATA[Purpose – This study aims to overcome the computational inefficiency of the Brute Force method in determining the metric dimension of tree graphs by evaluating the performance of a Structural-Based Reduction Algorithm. The study addresses the high computational cost of exhaustive search approaches and proposes a more efficient structural alternative. Methods – This research applies a comparative computational experimental approach by implementing both the Brute Force method and the proposed reduction algorithm on non-isomorphic tree graphs obtained from the McKay dataset. The algorithm is based on Slater’s theorem regarding leaves and stem vertices in tree graphs. Instead of testing all possible vertex combinations, the algorithm utilizes structural relationships to determine the metric dimension more efficiently. The comparison focuses on result consistency and computational execution time. Findings – Experimental results show that the proposed reduction algorithm achieves 100% accuracy, producing metric dimension values identical to those generated by the Brute Force method for all tested graphs. In terms of efficiency, the proposed method performs significantly better. For a tree graph with 20 vertices, the Brute Force method requires approximately 79 seconds, while the reduction algorithm completes the computation in only 0.005 seconds. Research implications – The findings indicate that structural analysis can reduce computational complexity in determining metric dimensions of tree graphs. However, the current approach is limited to acyclic graph structures and may require modification for cyclic graphs. Originality – This study introduces a deterministic and scalable alternative for determining metric dimensions in tree graphs through structural reduction principles.]]>
<![CDATA[IoT-Based Automatic Ornamental Plant Watering System Using Mamdani Fuzzy Logic With Real-Time Web Monitoring ]]>
<![CDATA[Jaikarna]]>;
<![CDATA[Niko Pahala Sihite]]>;
<![CDATA[Vincent Angelo]]>;
<![CDATA[Kristian Fredrico Aritonang]]>;
<![CDATA[Jijon Raphita Sagala]]>
<![CDATA[ Journal of Digital Technology and Computer Science Vol. 3 No. 2 (2026): April 2026 ]]>
Publisher : <![CDATA[Academic Bright Collaboration ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.66053/dtcs.v3i2.772
<![CDATA[Purpose – Ornamental plants require consistent watering to maintain optimal growth; however, manual watering often causes uneven water distribution and inefficient water usage. This study aims to develop an Internet of Things (IoT)-based automatic watering system using the Mamdani fuzzy logic method to improve watering accuracy and water efficiency. Methods – The system utilizes an ESP32 microcontroller integrated with capacitive soil moisture, DHT22 temperature, and BH1750 light intensity sensors. The Mamdani fuzzy logic method with 27 rule bases was implemented to determine adaptive watering duration. A real-time monitoring website was developed using Node.js, WebSocket, and SQLite. Findings – The system generated watering durations of 48–51 seconds under dry soil conditions, 28–32 seconds under normal conditions, and 9–12 seconds under wet soil conditions. Sensor validation produced RMSE values of ±0.48°C for temperature, ±18 lux for light intensity, and ±4.7% for soil moisture measurements. In addition, the proposed system improved water usage efficiency by approximately 60.5% compared to manual watering. Research Implications – The developed system supports smart agriculture implementation through adaptive irrigation, reduced water waste, and real-time environmental monitoring. The results demonstrate that the proposed IoT-based Mamdani fuzzy watering system can function as an adaptive and water-efficient solution for ornamental plant maintenance, although its implementation remains limited to the tested prototype environment. Originality – This research integrates multi-sensor monitoring, Mamdani fuzzy logic with 27 rule bases, and real-time web-based monitoring into a single adaptive ornamental plant watering system.]]>
<![CDATA[Web-Based ERP Dashboard Integrated with Aerial Imagery for Oil Palm Harvest Monitoring and Plantation Decision Support ]]>
<![CDATA[M. Ilham Saputra]]>;
<![CDATA[Raden Aris Sugianto]]>;
<![CDATA[Andi Prayogi]]>;
<![CDATA[Febriani Putri Wulandari]]>
<![CDATA[ Journal of Digital Technology and Computer Science Vol. 3 No. 2 (2026): April 2026 ]]>
Publisher : <![CDATA[Academic Bright Collaboration ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.66053/dtcs.v3i2.824
<![CDATA[Purpose – Oil palm plantation operations often rely on fragmented reporting systems that hinder information synchronization, operational visibility, and monitoring effectiveness. This study aims to develop a web-based Enterprise Resource Planning (ERP) dashboard integrated with Geographic Information System (GIS) mapping and aerial imagery visualization to support harvest scheduling and operational monitoring. Methods – This study employed a Research and Development (R&D) approach using the System Development Life Cycle (SDLC), including requirement analysis, design, implementation, testing, and evaluation. The system was developed using Laravel, MySQL, Bootstrap, and Leaflet GIS. Usability evaluation was conducted based on the ISO 9241-11 framework involving 11 participants consisting of plantation managers, field assistants, supervisors, and administrative staff at PT. Gerbang Benuaraya. Findings – The developed system successfully integrated operational reporting, plantation block mapping, aerial imagery visualization, and harvest monitoring within a centralized dashboard. Usability evaluation produced effectiveness, efficiency, satisfaction, learnability, and memorability scores of 72.12%, 69.70%, 72.12%, 65.45%, and 70.91%, respectively, resulting in an overall usability score of 70.06%, which indicates good usability based on the percentage-based evaluation criteria applied in this study. Research implications – The findings suggest that the system can support operational monitoring and information integration in plantation environments. However, the evaluation was conducted in a single plantation company with 11 participants, limiting broader generalization. Originality – This study contributes an integrated platform that combines ERP operational modules, GIS-based plantation mapping, aerial imagery visualization, and harvest monitoring within a single dashboard specifically designed for oil palm plantation management.]]>
