Simtek : jurnal sistem informasi dan teknik komputer

GLMM AND GLMM TREE METHODS FOR MODELING STUNTING PREVALENCE IN WEST JAVA

Tue, 06 Oct 2026 00:00:00 +0000

This study compares the Generalized Linear Mixed Model (GLMM) and GLMM Tree methods in modeling stunting prevalence in West Java. Stunting is a significant public health issue, especially in developing regions, and accurate measurement is crucial for effective intervention. GLMM is a statistical method commonly used to handle hierarchical data and account for inter-group variability. At the same time, the GLMM Tree is a newer method that combines mixed models with decision tree approaches to capture complex and heterogeneous data structures. The study uses stunting data from various districts in West Java and applies both methods to evaluate their accuracy in predicting stunting prevalence. The analysis results indicate that each method has its advantages depending on the complexity and heterogeneity of the data. GLMM performs better in situations with clear and homogeneous data structures, whereas GLMM Tree performs better in heterogeneous and complex data conditions.

DESIGN AND DEVELOPMENT OF AN OBJECT-ORIENTED ONLINE STUDENT ADMISSION INFORMATION SYSTEM FOR MTSN 1 PADANG LAWAS UTARA

Tue, 06 Oct 2026 00:00:00 +0000

This study aims to design and develop an online New Student Admission (PPDB) information system at MTsN 1 Padang Lawas Utara using an object-oriented approach. The school currently faces challenges due to a manual registration process, which leads to recording errors, verification delays, document accumulation, and limited access to information. The system was designed using the Waterfall method, encompassing the stages of requirements analysis, system design, implementation, testing, and maintenance. System modeling utilized the Unified Modeling Language (UML) and Entity Relationship Diagrams (ERD) to illustrate the system's structure and workflow. Testing was conducted using the Black Box Testing method to evaluate the alignment of system functions with the predefined requirements. The test results indicate that the core features of the system operate in accordance with the test scenarios, demonstrating that this system design can serve as a supporting medium for digitalizing PPDB services and school information dissemination.

INTEGRATING FUZZY TIME SERIES AND ICHIMOKU KINKO HYO FOR STOCK MARKET FORECASTING AND TRADING SIGNAL IDENTIFICATION: EVIDENCE FROM THE JAKARTA COMPOSITE INDEX

Tue, 06 Oct 2026 00:00:00 +0000

The rapid growth of digital investment platforms has increased public participation in stock market investments, creating a need for accurate forecasting and decision-support methods. This study aims to forecast the daily closing prices of the Jakarta Composite Index (JKSE) and provide investment recommendations by integrating the Fuzzy Time Series (FTS) Chen model and the Ichimoku Kinko Hyo indicator. The dataset consists of 1,201 daily JKSE closing price observations collected from Yahoo Finance, covering the period from June 7, 2021, to June 5, 2026. The FTS model was employed to forecast future price movements, while Ichimoku Kinko Hyo was used to identify market trends and trading signals. The results indicate that the FTS model achieved high forecasting accuracy with MAPE, RMSE, and MSE values of 0.0136, 117.79, and 13,875.19, respectively. Furthermore, the Ichimoku analysis revealed a recent shift from a bullish to a bearish trend, suggesting a cautious investment strategy. Overall, the integration of FTS and Ichimoku Kinko Hyo provides an effective framework for stock market forecasting and investment decision-making.

WEB-BASED E-VOTING AS A MEDIUM FOR ELECTION OF CHAIRMAN AND VICE CHAIRMAN OF OSIS (CASE STUDY: SMKN 2 MATARAM)

Juhartini Tini, Zumratul Muahidin, Dwinita Arwidiyarti, Surni Erniwati — Tue, 06 Oct 2026 00:00:00 +0000

This study discusses the design and implementation of a website-based electronic voting (e-voting) information system for the election of the Student Council Chairperson at SMKN 2 Mataram. The conventional system currently implemented at the school faces various obstacles, such as lack of transparency, long counting times, vulnerability to human error, physical damage to ballots, and high operational costs. This study aims to design a digital solution that can simplify, accelerate, and improve the accuracy of the voting process, while reducing implementation costs. The development method used is Rapid Application Development (RAD), which is implemented concretely through joint needs planning with the school committee, prototype design workshops, and system implementation. The results of the study are a web-based e-voting system built using PHP, MySQL, and the Bootstrap framework. This system enables online, integrated, and real-time voting. Black Box testing shows that all system functionality runs validly, is proven to be able to overcome the weaknesses of the manual system and provides a security mechanism to prevent double voting.

STUDENT DROPOUT RISK ANALYSIS USING A HYBRID K-MEANS AND CART METHOD

Tue, 06 Oct 2026 00:00:00 +0000

Student dropout is an important issue in higher education because it affects study continuity, resource efficiency, and institutional performance. This study aims to develop a student dropout risk analysis model using a hybrid K-Means and Classification and Regression Tree (CART) approach within a two-stage modeling framework. The data were obtained from the Academic Information System of STMIK X for the academic years 2015/2016–2018/2019. After data cleaning and selection, 631 student records were obtained, consisting of 119 dropout students and 512 active/graduated students. In the first stage, K-Means was employed to identify the underlying student segmentation structure, while in the second stage, CART was applied using the cluster labels as an additional feature. The K-Means results identified K = 10 as the statistically optimal number of clusters, with a silhouette score of 0.6330. These ten clusters were subsequently interpreted into three risk groups: low, medium, and high. On the test data, the hybrid model achieved an accuracy of 92.25%, precision of 60.87%, recall of 87.50%, and an F1-score of 71.79%, outperforming the standalone CART model, which achieved an accuracy of 88.03%, precision of 44.44%, recall of 25.00%, and an F1-score of 32.00%. Validation using Orange Data Mining also demonstrated a consistent improvement, with the hybrid model achieving an accuracy of 92.60%. Attendance was identified as the most dominant predictor, with a feature importance value of 0.71. These results indicate that K-Means segmentation can enrich the data representation prior to CART classification and improve the early detection of students at risk of dropping out

BI IMPLEMENTATION USING KPI AND BSC FOR MOOPO PERFORMANCE EVALUATION

Deni Dwi Candra, Made Kamisutara — Tue, 06 Oct 2026 00:00:00 +0000

Transaction activity on the Moopo application generates a large volume of sales data, yet its use remains limited to operational reporting and has not been processed into strategic information, making comprehensive, historical data-driven evaluation of sales performance difficult. This study designs and builds a Business Intelligence system based on Key Performance Indicators (KPI) and the Balanced Scorecard (BSC), supported by a Data Warehouse, to evaluate sales performance on the Moopo application. Development follows the Kimball approach, with a star-schema Data Warehouse combining one fact table and six dimension tables, processed through an Extract, Transform, Load (ETL) pipeline to produce 12 KPI indicators across four BSC perspectives. The system is implemented using PHP and MySQL on the server side and Vue.js on the front end. Black Box Testing across 14 scenarios covering six main features shows that all functions perform according to specification, indicating that the system can be relied upon as a tool for performance evaluation and decision-making by the Owner/Manager of the Moopo application.

WEB-BASED CORRESPONDENCE INFORMATION SYSTEM WITH SMART NUMBERING AND WHATSAPP NOTIFICATION AT THE SURAKARTA CITY EDUCATION OFFICE

Rizki Anisaul Wakhidah, Sri Sumarlinda, Eko Purwanto — Tue, 06 Oct 2026 00:00:00 +0000

The management of incoming and outgoing correspondence and disposition instructions at the Surakarta City Education Office is currently performed manually using logbooks and physical archives, resulting in delayed information delivery, numbering errors, document tracking difficulties, and administrative inefficiencies. This study aims to design and develop a web-based correspondence information system featuring "Smart Numbering" and WhatsApp notifications to enhance the effectiveness and efficiency of administrative correspondence management. The study employs the Research and Development (R&D) method using the Waterfall development model, comprising the stages of requirements analysis, system design, implementation, testing, and maintenance. The system was developed using the Laravel framework and a MySQL database, and was tested via Black Box Testing to ensure all functions operate according to user requirements. Implementation results demonstrate that the system successfully manages incoming and outgoing correspondence and electronic dispositions, automatically generates reference numbers via the Smart Numbering feature, and sends real-time WhatsApp notifications to relevant users. Testing results confirm that all system features function correctly and meet user needs. Consequently, the developed system enhances the efficiency, accuracy, and effectiveness of correspondence administration while streamlining archiving, correspondence status tracking, and the digital delivery of disposition instructions at the Surakarta City Education Office.

DESIGN AND DEVELOPMENT OF A WEB-BASED IOT MONITORING AND CONTROL SYSTEM FOR CHILI PLANT IRRIGATION

Lutfan Hadi, Agus Bahtiar — Tue, 06 Oct 2026 00:00:00 +0000

Manual irrigation of chili plants often leads to inconsistent water delivery, which negatively affects plant growth. This study aims to design and develop a web-based Internet of Things (IoT) monitoring and control system for chili plant irrigation. The system was developed using an ESP8266 microcontroller, a DHT22 sensor, a capacitive soil moisture sensor, an LDR sensor, Supabase as the cloud database, and React for the web interface. The system is capable of monitoring air temperature, air humidity, soil moisture, and light intensity at 60-second data update intervals, while supporting both manual and automatic irrigation control modes. Implementation results demonstrate that all system components function as designed, successfully recording 4,469 monitoring data points, and enabling centralized monitoring, irrigation control, and parameter configuration via a single web-based interface. The developed system provides an effective and easily manageable solution for irrigation monitoring and control.

DEVELOPMENT OF VIRTUAL LABORATORIES: INNOVATIVE DIGITAL APPLICATIONS FOR ECONOMICS AND BUSINESS LABORATORIES

Alim Bahri, Iza Guspian — Tue, 06 Oct 2026 00:00:00 +0000

Development of the Virtual Laboratory application at the Faculty of Economics and Business, University of Bangka Belitung (FEB UBB), is a strategic effort to transform practical learning toward a competitive digital campus. This application is designed to support simulation-based online learning, particularly for practical courses in statistical and econometric software such as SPSS and EViews. The system was developed using a web-based modular approach incorporating the Role-Based Access Control (RBAC) concept, allowing for structured management of access rights for lecturers, students, and administrators. Key features include experimental simulations, data analysis, asynchronous discussion forums, and monitoring of student progress. Initial testing results indicate that the application enhances learning flexibility, expands digital laboratory access, and supports the effectiveness of the practical learning process. Thus, this Virtual Laboratory serves as an innovative solution to support the transformation of higher education in the digital age.

ANALYZING THE IMPACT OF DATA AUGMENTATION ON HANDWRITING BASELINE PATTERN DETECTION PERFORMANCE USING THE YOLO FRAMEWORK

Aurahaqqi Aprianoputri, Rendra Gustriansyah, Muhammad Haviz Irfani — Tue, 06 Oct 2026 00:00:00 +0000

Handwriting baseline pattern detection is a critical step in handwriting analysis, as it reflects the directional tendencies of writing strokes. However, class imbalance in the dataset often leads to degraded model performance on minority classes. This study aims to analyze the impact of data augmentation on detection performance using YOLOv11. The dataset consists of 150 handwriting images containing 1,432 baseline instances, classified into Ascending Baseline (AB) with 530 instances, Descending Baseline (DB) with 611 instances, and Wavy Baseline (WB) with 291 instances. Experimental results show that augmentation substantially improved Precision from 0.383 to 0.517, F1-Score from 0.505 to 0.596, mAP@50 from 0.503 to 0.614, and mAP@50–95 from 0.355 to 0.470. Additionally, the detection rate for the WB class, derived from the normalized confusion matrix, increased from 4% to 37%. These findings confirm that data augmentation has a significant positive impact on handwriting baseline pattern detection using YOLOv11, and contribute to the advancement of AI-driven detection methodologies.

OPTIMIZATION OF 3D DATA FORMATS AND EFFICIENCY FOR WEB-BASED SUBSURFACE VISUALIZATION USING 3D TILES

Yusuf Almunawar, Gusti Ayu Jessy Kartini, Ketut Tomy Suhari — Tue, 06 Oct 2026 00:00:00 +0000

WebGIS-based three-dimensional (3D) data visualization often faces challenges associated with large data volumes, which can affect storage efficiency and visualization performance. This study aims to optimize 3D data formats for subsurface visualization using 3D Tiles, with Barong Cave as the case study. The 3D model was reconstructed using Agisoft Metashape and subsequently processed through four workflows comparing LAS and LAZ formats and geometry optimization through subsampling. All models were converted into 3D Tiles and visualized using CesiumJS. The results demonstrate that the optimization process reduced the number of points in the point cloud by 80.72%, while the use of the LAZ format reduced file size by approximately 67% compared with LAS. Workflow 3 achieved the fastest loading time at 180 ms, while memory usage remained stable within the range of 55.83–57.17 MB. All workflows achieved frame rates above 90 FPS, enabling real-time visualization. These findings demonstrate that the combination of LAZ and 3D Tiles can improve data and visualization efficiency while maintaining the representational quality of the 3D model.

FINAL PROJECT SCORING SYSTEM BASED ON SEMANTIC SIMILARITY OF TITLE AND DESCRIPTION USING INDOBERT

Ahmad Sihabillah, Moh. Furqan, Fathorazi Nur Fajri — Tue, 06 Oct 2026 00:00:00 +0000

Initial evaluation of final project proposals is generally conducted manually, requiring considerable time and potentially resulting in inconsistent assessments. This study aims to develop a semantic similarity-based system using IndoBERT optimized with the SimCSE approach to assist in identifying the similarity and uniqueness levels of final project proposals. The model was trained using three types of positive pairs and evaluated under three scenarios: title, description, and a combination of both, using Precision@5, Recall@5, and F1-Score@5 as evaluation metrics. The results show that model optimization increased the difference in the average cosine similarity values between positive and negative pairs from 0.040 to 0.5412. The description and combined scenarios achieved the highest F1-Score@5 of 0.71 at a threshold of 0.6. The model was subsequently implemented in a web-based application and achieved a user acceptance rate of 84.40%. These results indicate that the SimCSE approach is effective in supporting the initial evaluation of final project proposals in a faster and more objective manner.

PERFORMANCE ANALYSIS AND OPTIMIZATION OF YOLOV8 FOR UNDERWATER FISH DETECTION AND COUNTING

M. Ikbal Siami, Lukman Saleh — Tue, 06 Oct 2026 00:00:00 +0000

Manual monitoring of fish populations in floating net cages is time-consuming and prone to producing inconsistent data. This study evaluated the performance of YOLOv8n, a lightweight variant of YOLOv8, for automated fish detection and counting in floating net cages in Ambon, Indonesia. A total of 780 underwater images, obtained from publicly available datasets on Kaggle and field data collection, were annotated and preprocessed through resizing, contrast enhancement using contrast-limited adaptive histogram equalization (CLAHE), and grayscale conversion. Two models were trained and compared: Model 1 without data augmentation and Model 2 with horizontal flipping and rotation. Model 1 achieved a more balanced performance, with an mAP@0.5:0.95 of 0.603, an mAP@0.5 of 0.762, a precision of 0.737, a recall of 0.711, and an F1-score of 0.724. Model 2 achieved a higher precision of 0.861 but a lower recall. Field testing integrating YOLOv8n with DeepSORT demonstrated reliable fish detection and counting, although accuracy declined in turbid water and densely packed fish schools. These findings suggest that a lightweight YOLOv8 model without architectural modifications can serve as a viable starting point for developing automated fish monitoring systems for precision aquaculture in coastal regions such as Ambon.

DEVELOPMENT OF A WEB-BASED OMNICHANNEL INFORMATION SYSTEM FOR BRIGHT ENGLISH COURSE PALOPO

Valentino Aris, Fadil Muhammad, Airul Syahrif, Adawiyah Asti Khalil — Tue, 06 Oct 2026 00:00:00 +0000

Changes in digital service processes within non-formal educational institutions require better integration of information, registration, communication, and data management channels. This study aims to develop a web-based omnichannel information system for Bright English Course to support online registration, user management, grade management, and service continuity through social media and WhatsApp. The study employed the Design Science Research Methodology (DSRM), consisting of problem identification, definition of solution objectives, design and development, demonstration, evaluation, and communication. The resulting artifact is a web-based application with access rights for administrators, instructors, students, and parents or guardians. The system was evaluated using black-box testing and semi-structured interviews with the course owner. The testing results showed that all 13 functional scenarios were successfully executed, while the interviews indicated that the system met operational needs and supported registration, user management, and access to learning outcomes. The developed system provides a foundation for a more structured omnichannel service, although further development is required to achieve full data integration across platforms.

DELIVERY METHOD PREDICTION USING BORUTA FEATURE SELECTION AND RANDOM FOREST ALGORITHM

Tiara Farhana Salsabila Putri, Rendra Gustriansyah, Zaid Romegar Mair — Tue, 06 Oct 2026 00:00:00 +0000

The subjective nature of delivery method decisions may affect the accuracy of maternal referrals. This study aims to develop an objective prediction model for delivery methods using the Random Forest algorithm and Boruta feature selection. The study utilized 503 medical records of pregnant women from Dr. Mohammad Hoesin Hospital Palembang. The Boruta algorithm was applied to select the most relevant features from 13 initial variables for training the Random Forest model. The results showed that Boruta successfully identified 12 important features, with preeclampsia, history of cesarean section, and mean arterial pressure as the primary clinical predictors. Evaluation of the Random Forest model achieved an accuracy of 94.00% with balanced performance and no indication of overfitting. In conclusion, the combination of Boruta and Random Forest methods produced an accurate delivery method prediction model with strong potential for application as a clinical decision support system.

PERFORMANCE AND RATE LIMITING TESTING OF AN ACADEMIC INFORMATION SYSTEM USING THE K6 TESTING TOOL: A CASE STUDY OF POLITEKNIK XYZ

Alif Shofa Danutirta, Mitsal Shafiq Sulasno, Dwi Anto, Miftahunnisa’ Igriza — Tue, 06 Oct 2026 00:00:00 +0000

Ensuring the reliability of the Academic Information System (SIAKAD) in handling user access loads requires rigorous performance testing. This study examines response time, throughput, and error rate on the SIAKAD website of Politeknik XYZ using k6, while also identifying the rate-limiting mechanism that affects testing validity. The methodology comprised four stages: test environment planning, scenario planning, execution, and data interpretation and analysis. A step-ladder calibration approach was employed to determine the Maximum Safe Rate (MSR) before conducting four standard load scenarios, namely Smoke, Load, Stress, and Break-point Test, each proportionally scaled to the MSR. The findings indicate that the system's MSR is 2 requests per second, achieving a 0% error rate and a median response time below 100 milliseconds. Request rejections began occurring consistently within the 3.0–3.8 requests-per-second range, with uniform rejection responses suggesting that they originate from the Web Application Firewall (WAF) or reverse proxy layer rather than the backend application itself. These results demonstrate that request-rate-based calibration provides a more representative approach than the conventional virtual-user scheme for generating valid and reproducible performance testing data.

USABILITY EVALUATION OF THE CORRECTIONAL DATABASE SYSTEM APPLICATION USING THE SYSTEM USABILITY SCALE (SUS): A CASE STUDY OF STATE DETENTION CENTER (RUTAN)

Mitsal Shafiq Sulasno, Alif Shofa Danutirta — Tue, 06 Oct 2026 00:00:00 +0000

Digital transformation in public governance requires information systems that are not only functionally effective but also easy to use. The Correctional Database System (Sistem Database Pemasyarakatan/SDP) plays a strategic role in supporting administrative and operational management within Indonesian correctional institutions; therefore, its usability is a critical factor in determining the effectiveness of system utilization. This study aimed to evaluate the usability of the SDP application using the System Usability Scale (SUS). A descriptive quantitative approach was employed, involving 30 correctional officers from the Class I Bandung Detention Center, the Class IIB Banda Aceh Detention Center, and the Class IIB Boyolali Detention Center. The findings revealed SUS scores of 58.25, 54, and 62, respectively, resulting in an overall average score of 58.08. Based on the SUS interpretation framework, the overall score falls within the Poor adjective rating and Marginal acceptability range and remains below the commonly referenced SUS benchmark of 68. These findings indicate that, although the SDP application remains operationally usable, substantial improvements are required to enhance the user experience. Improvements should particularly focus on navigation, interface consistency, and ease of use. The study recommends adopting a User-Centered Design (UCD) approach to support the iterative improvement of the SDP application and to ensure that future system development is more responsive to the needs and characteristics of correctional officers.

INVENTORY INFORMATION SYSTEM AT 3R TOY STORE INDRALAYA

Rendy Juliansyah, Rahayu Amalia — Tue, 06 Oct 2026 00:00:00 +0000

Inventory management at 3R Toy Store Indralaya still faces challenges due to the lack of an integrated information system. The ineffective monitoring of stock levels and recording of incoming and outgoing goods has resulted in difficulties in providing responsive and accurate inventory data for store management. To address these issues, this research focuses on designing and developing a web-based inventory information system to improve the efficiency of inventory management at 3R Toy Store Indralaya. The software development process applies the Extreme Programming framework through four main phases: planning, designing, coding, and testing. Research data were collected through field observations, interviews, and literature reviews. The system was developed using Native PHP with a MySQL database and provides three levels of access rights, namely administrator, cashier, and store owner. The integrated functionalities include product data management, product categorization, supplier database management, recording of incoming goods, sales transaction management, stock availability monitoring, and report generation. The validation results using Black Box Testing confirmed that all core system functions operated accurately according to the specified user requirements. The implementation of the system has transformed inventory management into a more structured process while ensuring the effective availability of accurate and up-to-date stock information.

REVENUE PREDICTION BASED ON TIME SERIES DATA USING THE CONVOLUTIONAL NEURAL NETWORK (CNN) METHOD AT PISANG KEJU BATAM 80 MSME

Nadia Amanda, Lastri Widya Astuti, Purnamasari Evi — Tue, 06 Oct 2026 00:00:00 +0000

Pisang Keju Batam 80 MSME faces challenges in managing sales and production due to fluctuations in revenue across different periods. This condition makes it difficult for the business to estimate future revenue and determine optimal production planning and sales strategies. This study aims to develop a revenue prediction model based on time series patterns using the Convolutional Neural Network (CNN) method. The dataset consists of 2,192 historical sales records. The research stages include data preprocessing, dataset splitting, normalization using Min-Max Scaling, CNN implementation, and evaluation using Mean Absolute Percentage Error (MAPE). The dataset was chronologically divided into 60% training data and 40% testing data. The model was trained for 100 epochs using the Adam optimizer with MSE as the loss function. The testing results obtained a MAPE value of 1.6496%, indicating that the CNN model was able to produce predictions close to the actual values and has the potential to support production planning and sales strategies for MSMEs

IMPLEMENTASI DASHBOARD ANALITIK UNTUK MONITORING KINERJA OPERASIONAL PADA PT TOPAN LOGISTIK INTERNASIONAL

St. Astianti Salmah, Valentino Aris, Syamsu Alam — Tue, 06 Oct 2026 00:00:00 +0000

Penelitian ini bertujuan untuk mengimplementasikan dashboard analitik sebagai alat bantu visual dalam memantau kinerja operasional di PT Topan Logistik Internasional. Kompleksitas distribusi logistik di wilayah Indonesia Timur menuntut pengelolaan armada dan rute pengiriman yang terintegrasi secara cepat dan akurat. Penelitian ini menggunakan pendekatan Research and Development (R&D) dengan menerapkan model perancangan System Development Life Cycle (SDLC). Perancangan dashboard dilakukan menggunakan aplikasi Microsoft Power BI, sementara pengujian fungsionalitas sistem dievaluasi melalui metode black box testing. Hasil penelitian menunjukkan bahwa dashboard analitik yang diimplementasikan mampu menyajikan ringkasan indikator kinerja utama secara visual seperti tren volume pengiriman, akumulasi beban operasional, sebaran titik lokasi pengiriman, performa pengemudi, hingga utilitas penggunaan armada. Implementasi dashboard membantu mengurangi ketergantungan terhadap proses pelaporan manual serta meningkatkan kemudahan akses informasi untuk mendukung pengambilan keputusan berbasis data

WEATHER PREDICTION USING A COMPARISON OF LSTM AND GRU METHODS

Muhammad Adjie Setiawan, Gasim Astuti, Lastri Widya Astuti — Tue, 06 Oct 2026 00:00:00 +0000

Accurate weather condition prediction is essential to support various community activities, particularly in tropical regions where weather patterns are relatively complex. This study was conducted to evaluate and compare the capabilities of Long Short-Term Memory and Gated Recurrent Unit in classifying weather conditions into three categories: sunny, cloudy, and rainy. The research data consisted of monthly climatological data from January 2021 to December 2025 obtained from the South Sumatra Climatology Station. The data were processed using linear interpolation to generate daily data comprising 1,796 observations. The research process included data cleaning, normalization, class encoding, sequence formation using a sliding window, training and testing data splitting, and model evaluation based on accuracy, precision, recall, and F1-score. The results showed that the Gated Recurrent Unit achieved an accuracy of 88%, while the Long Short-Term Memory achieved 77%. Therefore, the Gated Recurrent Unit demonstrated superior performance in weather condition classification.

WEB-BASED SALES MANAGEMENT INFORMATION SYSTEM USING THE LARAVEL FRAMEWORK AT "GURIH" CRACKER MANUFACTURER

Danisa Renita Putri Anggraini, Mardi Yudhi Putra — Tue, 06 Oct 2026 00:00:00 +0000

"GURIH" Cracker Manufacturer is a micro, small, and medium enterprise (MSME) in Mampir Village, Bogor Regency, that still records sales transactions and inventory manually using logbooks. This manual system has led to a 30 percent decline in sales over the last three months, slow daily reporting, and inaccuracies in calculating the Cost of Goods Manufactured (COGM). This study aims to design and develop a web-based sales management information system using the Laravel framework with the Extreme Programming approach. Data collection was conducted through observation, interviews, and literature reviews, while the system design utilized Unified Modeling Language and Entity Relationship Diagrams. The developed system provides real-time raw material and product inventory management, minimum stock and expiration notifications, automated COGM calculations, a profitability dashboard, and report exporting to Excel and PDF formats. Black Box testing demonstrated that all functions operate as required, while user acceptance testing with seven respondents achieved a feasibility percentage of 93.33 percent, placing it in the "Highly Feasible" category.

DESIGN AND DEVELOPMENT OF A MOBILE-BASED STUDENT ATTENDANCE SYSTEM INTEGRATING GEOLOCATION AND FACE RECOGNITION USING MOBILEFACENET AT THE D-III INFORMATICS ENGINEERING STUDY PROGRAM, PONTIANAK STATE POLYTECHNIC

Yusril Eka Mahendra, Nurul Fadillah, Karfindo — Tue, 06 Oct 2026 00:00:00 +0000

Student attendance in the D-III Informatics Engineering Study Program at Pontianak State Polytechnic is still recorded manually, making it prone to recording errors and time-consuming recapitulation. This applied research designs and develops a mobile-based attendance prototype that integrates on-device MobileFaceNet face verification with geofencing-based location validation using a prototyping approach. The prototype consists of a Flutter application, a Laravel backend, and a web dashboard featuring a liveness challenge, one-time attendance permits, offline attendance, attendance recapitulation, and an early warning mechanism for Warning Letters. All 255 automated backend tests and 214 mobile application tests passed. Evaluation of 1,485 impostor face pairs resulted in a False Accept Rate (FAR) of 0% at a threshold of 0.60, while load testing with 20–40 concurrent users produced 95th-percentile response times below 2 seconds. However, the False Reject Rate (FRR) has not yet been measured, location and facial evidence are still computed on the device, and the liveness mechanism has not been tested against photo attacks, video replay, or deepfakes. Therefore, the system cannot yet be claimed to prevent proxy attendance or location spoofing.

DEVELOPMENT OF AN IOT-BASED ECOSYSTEM FOR AUTOMATIC MONITORING AND CONTROL OF TEMPEH FERMENTATION USING ESP32

Tue, 06 Oct 2026 00:00:00 +0000

Tempeh fermentation is a traditional bioprocess that is highly sensitive to fluctuations in temperature and humidity, as well as ammonia gas accumulation, which can adversely affect product quality in small-scale household industries. This study aims to design and implement an Internet of Things (IoT) ecosystem encompassing hardware development, a monitoring dashboard, and an ESP32-based automatic control system for tempeh fermentation. The Rapid Application Development (RAD) method was adopted, including the calibration of DHT21 and MQ-135 sensors to ensure measurement accuracy. The implementation results demonstrate that the system was able to maintain the temperature within a range of 30–35 °C and relative humidity between 60% and 80% RH, while detecting ammonia concentrations ranging from 0.13 to 0.32 ppm during a 24-hour fermentation process. Compared with the conventional fermentation method, the proposed system accelerated mycelial growth, resulting in denser and more compact tempeh. Furthermore, the developed monitoring dashboard successfully displayed real-time fermentation data and provided relevant information to support user decision-making. These results indicate that the proposed IoT-based system offers a practical approach to improving environmental monitoring and process control in small-scale tempeh fermentation.

IMAGE-BASED CLASSIFICATION OF SIX PATHOGENIC BACTERIAL SPECIES USING EFFICIENTNET

Tue, 06 Oct 2026 00:00:00 +0000

Image-based classification of pathogenic bacteria is a deep learning approach that can support automated bacterial identification. This study aimed to evaluate the performance of EfficientNet-Lite0 in classifying images of six pathogenic bacterial species, namely Bacillus cereus, Clostridium perfringens, Escherichia coli, Listeria monocytogenes, Salmonella typhimurium, and Staphylococcus aureus. The image data underwent preprocessing and augmentation during the training stage, followed by model evaluation using accuracy, precision, recall, and F1-score. The evaluation results showed that EfficientNet-Lite0 achieved 100% accuracy, precision, recall, and F1-score, with no misclassified images in the validation data. The model consisted of 3,378,694 parameters, with a computational complexity of 397.45 MFLOPs and a latency of 4.31 ms per image. These results indicate that EfficientNet-Lite0 achieved high classification performance for the six bacterial species under the dataset and evaluation conditions used in this study.

DIGITALIZATION, E-GOVERNMENT, AND INNOVATION IN IMPROVING THE QUALITY OF PUBLIC SERVICES: A SYSTEMATIC LITERATURE REVIEW

Siti Auliya, Willy Prihartono — Wed, 14 Oct 2026 00:00:00 +0000

Digital transformation drives changes in public service delivery, but the application of technology does not always automatically result in improved service quality. This study aims to analyze the development of digitalization, e-government, and innovation in improving the quality of public services. The study used the Systematic Literature Review (SLR) method with PRISMA 2020 guidelines. Literature was obtained from the Scopus database with a publication period of 2021–2026. Of the 168 identified articles, after a selection process, 12 articles were selected for descriptive analysis and thematic synthesis. The study results indicate that digitalization can improve accessibility, efficiency, speed, and ease of service delivery, as well as encourage process innovation. However, its success is influenced by organizational readiness, infrastructure, human resources, governance, security, public trust, and equality of access. Digitalization needs to be integrated with organizational changes and community needs to improve service quality and create public value.

ANALYSIS OF THE EFFECTS OF USER INTERFACE AND USER EXPERIENCE ON INTENTION TO USE THE INDONESIAN NATIONAL POLICE PUBLIC RELATIONS NEWS PORTAL

Muhamad Dody Firmansyah, Ayesha Nashwa Ferya Putri; Syaeful Anas Aklani — Wed, 14 Oct 2026 00:00:00 +0000

This study aims to examine the effects of User Interface (UI) and User Experience (UX) on intention to use the Indonesian National Police Public Relations News Portal, while also providing qualitative explanations for the quantitative findings. The study employed an explanatory sequential mixed-methods design involving 421 respondents from Batam City and four informants in the qualitative phase. Quantitative data were analyzed using multiple linear regression and bootstrapping with 5,000 replications, while interview data were analyzed using Reflexive Thematic Analysis. The results indicate that both UI and UX have positive and statistically significant effects on intention to use, with UX demonstrating a greater relative contribution. The model explains 59.8% of the variance in intention to use. Four qualitative themes further elucidate aspects of interface design, navigation, user experience, information needs, and source credibility. The findings from both phases provide complementary explanations of the use of the portal.

COMPARATIVE EVALUATION OF MACHINE LEARNING AND DEEP LEARNING FOR GOLD PRICE PREDICTION USING HISTORICAL DATA AND MACROECONOMIC INDICATORS

Wed, 21 Oct 2026 00:00:00 +0000

Gold price forecasting is an important problem in financial market analysis because gold prices are influenced by historical price dynamics as well as various economic and financial market conditions. This study comparatively evaluates the performance of Random Forest, Extreme Gradient Boosting, Long Short-Term Memory, and Gated Recurrent Unit models for one-step-ahead gold price forecasting under two input scenarios: historical gold price data alone and historical data combined with macroeconomic indicators. The dataset covers the period 2016–2025, and model performance is evaluated using Mean Absolute Error, Root Mean Squared Error, Mean Absolute Percentage Error, and the coefficient of determination. The test results show that the naïve baseline achieves the lowest prediction errors, with an MAE of 25.9345, an RMSE of 37.3274, and a MAPE of 0.8684%. Adding macroeconomic indicators did not improve model performance. The substantial difference in price distributions between the training and test datasets also affected model performance, particularly for tree-based models.

DEVELOPMENT OF WEBGIS FOR VISUALIZING TOMATO LAND SUITABILITY CLASSIFICATION BASED ON RAINFALL INTERPOLATION

Zubair Abdurrohman, Anggi Muhammad Rifa'i, Supriyanto — Wed, 21 Oct 2026 00:00:00 +0000

Rainfall in Indonesia is often limited to tabular formats from scattered stations, hindering effective spatial analysis for agricultural planning—particularly for water-sensitive crops like tomatoes. This study aims to develop a WebGIS system to visualize rainfall distribution and analyze land suitability for tomato cultivation in West Java. The methodology involves data acquisition via web scraping using Python, spatial interpolation to convert point data into continuous raster surfaces, and the application of zonal statistics based on FAO agroclimatic criteria for a 90–120-day growing season. The system utilizes a client-side architecture with Leaflet.js and asynchronous data loading to ensure efficiency. Results reveal distinct spatial rainfall patterns and categorized land suitability classes (S1, S2, S3, and N). The developed WebGIS provides an interactive platform with dynamic filtering, serving as an effective decision-support tool for farmers and stakeholders to identify optimal planting locations and schedules.

IMPLEMENTATION OF MERGE SORT AND SEQUENTIAL SEARCH METHODS IN A PRACTICUM PARTICIPANT DATA MANAGEMENT SYSTEM

Vista Mellyna Atsfi, Anton Prafanto, Novianti Puspitasari — Mon, 26 Oct 2026 00:00:00 +0000

Data management for Basic Physics practicum students at the Faculty of Engineering, Mulawarman University, was previously handled in multiple separate spreadsheets, creating risks of data duplication and errors in searching, sorting, attendance tracking, grading, and grade recapitulation. This study aims to develop a web-based data management system for practicum students by implementing the Merge Sort algorithm for sorting and Sequential Search for data retrieval. The system was developed using the Waterfall methodology, comprising requirements analysis, design, implementation, testing, and evaluation. Built with Laravel and MySQL, the system used data from 538 students from the 2025 academic year, along with synthetic datasets containing 100, 500, 1,000, and 5,000 entries. We conducted functional testing using Black-Box Testing, and performance testing measured execution time, memory usage, iteration counts, and comparison counts. Test results indicate that all key features operate as designed, and both algorithms achieved lower execution times and memory usage compared to MySQL.

IMPLEMENTATION OF A WEB-BASED ACADEMIC INFORMATION SYSTEM USING THE EXTREME PROGRAMMING METHOD

Frendi Ramadandi, Rahayu Amalia — Mon, 26 Oct 2026 00:00:00 +0000

Academic data at SMP Negeri 2 Suak Tapeh are still managed manually using notebooks and physical records, making data retrieval, updating, and archiving time-consuming and prone to inaccuracies. This study aimed to design and implement a web-based academic information system using the Extreme Programming (XP) framework to improve educational services. The study adopted the XP software development methodology, comprising planning, design, coding, and testing. The application was developed using PHP with the Laravel framework and a MySQL database. Its features include the management of student and teacher data, classes, subjects, class schedules, attendance, assessment scores, report cards, and academic announcements, with role-based access for administrators, teachers, school principals, and students. Black-box testing was conducted using 12 scenarios covering the application's main functions. The results showed that all test scenarios passed and the tested functions operated as expected. The developed system helps the school manage academic records efficiently, accurately, and systematically while making it easier for users to retrieve academic data.

ANALYSIS OF USER SATISFACTION WITH TIKTOK SHOP AS AN ONLINE SHOPPING PLATFORM USING THE END USER COMPUTING SATISFACTION (EUCS) METHOD

Salsabila Putri, Domi Sepri, Novia Lestari — Mon, 26 Oct 2026 00:00:00 +0000

The development of digital technology has driven the growth of social commerce, which integrates social media and electronic commerce into online shopping activities. One of the widely used platforms in Indonesia is TikTok Shop. However, users still face several issues, including discrepancies in product information, difficulties in searching for products, system interface problems, transaction disruptions, and concerns about user security. This study aims to analyze how the five dimensions of End User Computing Satisfaction (EUCS), namely content, accuracy, format, ease of use, and timeliness, reflect User Satisfaction, as well as to examine the contribution of security to user satisfaction with TikTok Shop. This study employed a quantitative approach using purposive sampling involving 200 university students in Padang who use TikTok Shop. Data were analyzed using Partial Least Squares–Structural Equation Modeling (PLS-SEM) with SmartPLS 4. The results show that all five EUCS dimensions significantly reflect User Satisfaction. Accuracy has the strongest reflective relationship, while Content has the weakest. In addition, Security makes a positive and significant contribution to User Satisfaction. These findings indicate that user satisfaction with TikTok Shop is reflected in information quality, ease of use, system presentation, and service timeliness, while also being supported by security in digital transactions.