Jurnal Teknologi Informasi Universitas Lambung Mangkurat (JTIULM)
Not a member yet
142 research outputs found
Sort by
Implementation of An Indonesian Vehicle License Plate Recognition System In Real-Time Using EasyOCR and Regex Pattern Validation
Get PDF This study presents the design and implementation of a real-time Automatic License Plate Recognition (ALPR) system specifically tailored for Indonesian vehicle plates, integrating EasyOCR, computer vision-based image preprocessing, and Regular Expression (regex) validation. The system captures images or video streams and applies a multi-level preprocessing pipeline, including grayscale conversion, Gaussian noise reduction, edge detection, and contour-based plate localization, before performing optical character recognition based on deep learning using a convolutional recurrent neural network with an attention mechanism. Post-recognition processing with regex filtering ensures strict compliance with the official Indonesian license plate format, thereby minimizing false positives and improving recognition accuracy. Experimental evaluation using real-world surveillance data achieved 75% accuracy, 100% precision, 75% recall, and an F1-score of 86%, indicating an optimal balance between detection precision and sensitivity. The system’s advantages include real-time performance, ease of deployment with open-source software, and adaptability to various lighting and environmental conditions. However, the system still shows limitations under extreme conditions such as nighttime, heavy rain, and dense traffic, where recognition accuracy tends to decrease. Therefore, future research will focus on algorithm optimization for low-light, adverse weather, and motion-blur scenarios, large-scale deployment in urban areas, and integration with AI-based vehicle tracking, positioning this system as a key enabling technology in the development of smart city infrastructure
Design of a Web-Based Medical Equipment Monitoring Information System at Bhakti Yudha Hospital
Get PDFEffective inventory management is a critical component for ensuring smooth operational continuity, especially in a healthcare setting where timely access to supplies directly impacts patient care. At Bhakti Yudha Hospital, this vital process is hampered by its reliance on manual, spreadsheet-based tracking. This traditional approach is highly susceptible to human error, resulting in significant data inaccuracies and a critical lack of real-time stock visibility, which can ultimately compromise service delivery. To overcome these challenges, a web-based inventory monitoring information system was developed using the Rapid Application Development (RAD) methodology, chosen for its rapid and iterative prototyping capabilities. Modeled with UML diagrams, the system is designed to automate data entry, enhance accuracy, and provide transparent, role-based stock information for both administrators and general users. Key features include an analytical dashboard for strategic oversight, automated low-stock notifications to prevent shortages, and versatile PDF report generation for documentation. Comprehensive black-box testing has confirmed that all core functionalities perform as expected, meeting the initial requirements. This positions the system as an effective solution to significantly optimize the reliability and efficiency of the inventory management process at Bhakti Yudha Hospital
Evaluating Recommendation Accuracy in E-Commerce: A Comparison Between Content-Based and Collaborative Filtering Methods
Get PDFProduct recommendation systems play an important role in helping users find products that match their interests and needs on e-commerce platforms. This research aims to compare the effectiveness of two popular methods in recommendation systems, namely Content-Based Filtering and Collaborative Filtering. The research method used is quantitative with data collection through questionnaires which are then analysed using evaluation metrics such as precision, recall, and F1-score to measure the accuracy level of each method. The results show that Content-Based Filtering provides more accurate recommendations than Collaborative Filtering in the context of this research. This finding indicates that product characteristics relevant to user preferences have a more dominant influence in generating appropriate recommendations, compared to other user preferences. This research makes an important contribution to the development of a more effective recommendation system to improve user experience in finding relevant products on e-commerce platforms. Thus, the results of this study can serve as a reference for recommendation system developers in choosing the most suitable method to improve user satisfaction and system performance
Evaluation of Open-Source Application Utilization for Enhancing Learning Quality
Get PDFOpen-source software serves as a source of software that requires little cost, making this application easy to modify and independently develop. The Computer Education Study Program improves practical learning with the use of Open-source software, aiming to measure the effectiveness of open-source software in the practical learning conducted in the laboratory of the Computer Education Study Program. The effectiveness of open-source software was measured using a research and development method approach to determine that the open-source software can be applied to laboratory-based learning, and a survey approach using Likert scale to evaluate students' understanding of open-source software applications. The open-source software that was measured for effectiveness includes NetBeans for the Basic Programming II course, Visual Studio Code for the Web Programmers I and II Course, MATLAB for the Simulation and Modeling Course, and the use of Linux for the Operating System Course. The data sample consisted of 39 students in the Computer Education Study Program. The effectiveness was assessed in the implementation of open-source practicum learning was assessed by collecting supporting open-source software data, validating open-source software, simulating practicum on software in lecture materials, and conducting practicum material trials in real classroom practicum lectures. Based on the results of the trial, it was found that 85% of the open-source software can be used in lectures, and 80% of students were able to understand how to use the open-source software
Quality Analysis of the Digital Library Website of Universitas Lambung Mangkurat with Webqual 4.0 Method and User Experience Questionnaire (UEQ)
Get PDFThe current digital literature resources are widely provided by various libraries, especially those associated with higher education institutions. One such example of a digital library is the Lambung Mangkurat University Digital Library (Digilib ULM). Pre-evaluation results indicate that around 50% of the issues are related to the quality of the website, such as its appearance and functionality. Therefore, this research examines the quality of the ULM Digital Library to identify indicators that match user preferences and require improvement. The Webqual 4.0 method and User Experience Questionnaire are uti- lised for this purpose. The research is quantitative with a descriptive approach. Data is collected through a questionnaire, with 100 respondents sampled from the entire population, consisting of ULM students. Webqual 4.0 comprises three dimensions: usability, information quality, and service interaction. Meanwhile, UEQ consists of six aspects: attractiveness, dependability, efficiency, perspicuity, stimulation, and novelty. The research findings from Webqual 4.0 indicate a service interaction score of 2.75, information quality of 2.68, and usability of 2.45. The usability aspect falls into the low category or does not meet user expectations, while the other aspects fall into the moderate category. The UEQ results show an attractiveness score of 1.130, efficiency of 0.648, and novelty of 0.673, all scoring below the average compared to benchmarks, while other aspects score above average. Based on these results, it is evident that the Digilib ULM website does not meet user expectations and can be considered suboptimal, requiring improvement and enhancement
IOT System Design for Motion Detection from Remote Monitoring Camera with Telegram Notification to Mobile Phone
Get PDFCrime does make people restless, especially if they have to leave their hometown to travel to a faraway place. Becauseo f this concern, humans have begun to create innovations in the field of security, namely a monitoring system using CCTV (Closed Circuit Television) and NVR (Network Video Recorder) as servers and storage devices. However, it tends to be expensive, therefore a security camera monitoring system was created using a Raspberry Pi device which aims to replace the task of CCTV as a security system in a room. The method used is the Waterfall method, one type of application development model that applies sequential and systematic phases. This security system has a motion detection feature that will immediately take pictures and record what is captured by the surveillance camera, then the system will send a notification to the user's Telegram application.
In this study, 3 tests were carried out, namely motion detection testing which resulted in overall data being sent, then the second was telegram bot notification testing which resulted in an average loading time of 18.81 seconds, then the last Google Drive auto backup testing which was able to send the most data of 14 images and 14 videos with a time of 69.39 seconds. After several tests, it can be concluded that using a Raspberry Pi device and a web camera can replace CCTV tasks with additional notification features in the Telegram application and auto backup to Google Drive cloud storage
Web-Based Contract Employee Payroll Information System at PT.Bridgestone Kalimantan Plantation
Get PDFThe payroll system for contract employees used by PT. Bridgestone Kalimantan Plantation has been relying on Microsoft Excel to calculate contract employee salaries. However, using Microsoft Excel has several drawbacks when it comes to payroll processing, one of which is its inefficiency when dealing with large datasets. This study aims to analyze and design a web-based payroll system for contract employees to assist and simplify the process of calculating payroll for contract employees at PT. Bridgestone Kalimantan Plantation. The methods used in this study include system requirements analysis, database design, and the implementation of a web-based system using Laragon as the database. This research was conducted by analyzing the current system, obtaining data from direct interviews with parties involved in the employee payroll system, and conducting observations. The results of this research simplify the processing of contract employee data, minimize data errors, accelerate data verification and validation, and make salary calculations easier, thereby generating more effective and efficient information
Comparative Evaluation of Data Mining Classification Algorithms For Predicting Earthquake Alert Levels
Get PDFEarthquakes are one of the most destructive natural disasters, particularly in Indonesia, which is located at the convergence of three active tectonic plates. Conventional early warning systems generally rely on real-time vibration detection but lack the capability to provide comprehensive predictions about the potential severity of an earthquake. This study aims to address these limitations by applying data mining techniques and machine learning algorithms to classify earthquake alert levels based on seismic parameters, including magnitude, depth, Community Determined Intensity (CDI), Modified Mercalli Intensity (MMI), and significance (Sig). A dataset of 1,300 earthquake records was obtained and processed using the Knowledge Discovery in Database (KDD) methodology, which includes data selection, preprocessing, transformation, modeling, and evaluation. Five classification algorithms were compared: Decision Tree, Random Forest, Naïve Bayes, K-Nearest Neighbor (KNN), and Neural Network. Model performance was evaluated using confusion matrix metrics such as accuracy, precision, recall, and F1-score. The results indicate that Random Forest achieved the highest performance with an accuracy of 88.52% and macro recall of 88.90%, outperforming other algorithms. Decision Tree ranked second with balanced performance, while KNN and Neural Network achieved moderate results. Naïve Bayes performed the weakest. Overall, Random Forest is the most reliable algorithm for supporting earthquake early warning systems
Analysis of the KompuLearn Application to Improve Cognitive Skills According to the Growth Mindset Framework
Get PDFInformatics education at the vocational high school level continues to face challenges, particularly in students' limited understanding of algorithmic and programming concepts and the prevalence of a fixed mindset. This study aims to enhance students’ cognitive skills and foster a growth mindset by integrating a growth mindset framework into the instructional design of informatics learning. The learning design incorporates the Problem-Based Learning (PBL) model and is supported by a digital mobile application called KompuLearn. The research employed a Research and Development (R&D) methodology using the ADDIE model and a one-group pretest-posttest design. The participants consisted of 30 tenth-grade students from a vocational high school. Results showed an improvement in average scores from 52.6 (pretest) to 76.2 (posttest), with a normalized gain (N-gain) of 51.1%, categorized as moderate. One-way ANOVA analysis revealed a significant difference (p < 0.001) in cognitive gains among students with different mindset tendencies. Moreover, the proportion of students exhibiting growth mindset characteristics increased, as reflected in both the data distribution across learning phases and the questionnaire responses. These findings indicate that integrating a growth mindset framework into informatics learning design—through a PBL approach and digital support—positively contributes to cognitive improvement and mindset development among vocational high school students
Application of the Heart Metrics Method in Analyzing User Experience on the Rayz UMM Website
Get PDFThe Rayz UMM Hotel website serves as the primary medium for conveying information about services and facilities, but so far, the quality of the user experience (UX) on the website has not been studied in depth. Based on the initial questionnaire results, there were also several negative responses that indicated dissatisfaction with the aspects of Happiness and Adoption. Therefore, a comprehensive UX evaluation is needed. This study uses the HEART Framework method, which covers five aspects, namely Happiness, Engagement, Adoption, Retention, and Task Success. The research instrument is a questionnaire with 20 questions distributed to website users, which is then analyzed through validity and reliability tests, hypothesis testing, and measurement of the level of usability. The results show that the variables of Happiness and Task Success are in the very high category, Retention is in the very high category, while Engagement and Adoption are in the very high category. These findings confirm that the Hotel Rayz UMM website has generally been able to provide a fairly good user experience, but still needs development in terms of navigation and system performance in order to optimize UX quality