Journal Of Information System And Artificial Intelligence

Anomaly Detection in Walking Data Using Isolation Forest: An Unsupervised Learning Approach

Nur Alamsyah Nur — 2025-11-26

Detecting anomalies in walking data is crucial for ensuring data quality in wearable devices and understanding irregular physical activity patterns. Traditional methods often rely on labeled data, which is scarce in real-world applications. This study presents an unsupervised learning approach using Isolation Forest to detect anomalies in walking datasets. The data, comprising features such as step count, distance, and time, was preprocessed and analyzed to identify patterns and deviations. Isolation Forest was employed due to its efficiency in handling high-dimensional data and its ability to separate anomalies without prior labeling. The model successfully detected 5 anomalous data points out of the dataset, with anomaly scores ranging from -0.15 to 0.2. These outliers corresponded to extreme walking patterns, such as unusually high step counts with disproportionate time and distance. Visualization of anomaly scores and statistical evaluations validated the model's effectiveness, showing clear distinctions between normal and abnormal data. The proposed approach highlights the potential of Isolation Forest in improving data quality and enabling real-time anomaly detection in fitness tracking applications. This work contributes to the broader field of unsupervised anomaly detection by demonstrating a scalable and effective method for handling real-world activity data.

Analysis of Website Service Quality for The Online Licensing Information System at Dpmptsp Palembang Using the Webqual 4.0 Method

Imam Mizan — 2025-11-26

The rapid development of information technology, particularly the internet, has driven governments to adopt e-government to enhance information access, improve service efficiency, and promote administrative transparency. One of its implementations is a public service website that enables citizens to access digital services and information. The success of this system highly depends on the quality of the website in terms of usability, information completeness, and service interaction. This study employs the Webqual method, which consists of Usability Quality, Information Quality, and Interaction Quality, using a quantitative approach to evaluate the website’s service quality. The results indicate that the Online Licensing Service Information System website of DPMPTSP Palembang City has improved service efficiency by accelerating the licensing process in accordance with SOP’s, allowing applicants to obtain their licensing certificates within a maximum of three days. The system implementation has successfully reduced reliance on slower manual processes. However, issues remain regarding accessibility and information updates on PPID, which may hinder transparency. Further analysis reveals that Usability Quality, Information Quality, and Interaction Quality simultaneously have a significant impact on user satisfaction. However, when examined separately, only Information Quality and Interaction Quality show a significant positive impact, while Usability Quality does not strongly influence user satisfaction. The development of public service information systems should focus on improving accessibility, creating a more intuitive interface, and ensuring regular updates of information. With these optimizations, the system can be more effective in meeting user needs and enhancing their experience in accessing government digital services.

Mapping and recommendation system for tourism objects in boyolali district based on gis (geographic information system)

Ferry Illham Setiawan — 2025-11-26

Boyolali Regency has various interesting tourist attractions, but limited information and tourist recommendations are an obstacle for tourists in planning a visit. Geographic Information System (GIS) can be a solution to present tourist location information visually and provide recommendations based on certain criteria such as distance, tourist category, and popularity. This research aims to develop a GIS that is able to recommend tourist attractions in Boyolali Regency. By utilizing spatial data and interactive features, this system is expected to facilitate tourists in finding and selecting tourist destinations that suit their preferences. The implementation results show that this GIS is effective in providing tourism recommendations and improving the accessibility of tourism information in Boyolali.

Feature importance of using explanaible artificial intelligence (xai) and machine learning for diabetes disease classification

Muhammad Maulana Ahmad — 2025-11-26

Diabetes is one of the most significant global health problems in the modern era. This disease not only has a serious impact on the quality of life of sufferers, but also poses a great economic and social burden, both for individuals and the health service system as a whole. Therefore, early detection and effective treatment are very important in an effort to reduce the prevalence and negative impact of this disease. Therefore, the purpose of this study is to design a machine learning classification model that is able to identify feature importance with the help of the Explainable Artificial Intelligence (XAI) method in the case of diabetes. This model is expected to provide a clear interpretation of the most relevant features or symptoms, making it easier to detect whether a person has diabetes or not based on the symptoms that have been selected more optimally. The results of this study in the treatment or prediction of diabetes show that the results of the selection of LIME model features are higher than the accuracy of the SHAP model, where the highest is the LIME model which is processed using classification using the XGBoost algorithm with an accuracy of 98.47%, in addition to the LIME model using the Decisien Tree and Random Forest algorithms producing an accuracy of 91.97% and 91.49%, respectively. then the SHAP model using the XGBoost algorithm produced an accuracy of 0.9094%, the Decisien Tree algorithm produced an accuracy of 0.8059% and the Random Forest produced an accuracy of 88.46%, with the amount of data used as many as 70000 data, with 80% training data and 20% test data. The findings of this study are that the LIME feature selection combined with the XGBoost classification method has the best accuracy rate of 98.47% compared to the SHAP feature selection which is the same in combination with XGBoost with an accuracy of 90.94%. These findings also show that the selection of LIME features combined with the XGBoost algorithm is able to improve the interpretability of the model as well as maintain or even improve the accuracy of the predictions. This approach allows for the identification of the most relevant features more efficiently, thus supporting more informed decision-making in the data analysis process

Digitalization of laundry service: development of a web-based application to improve operational efficiency

Alip Lizal — 2025-11-26

The laundry business is currently experiencing significant growth as people's mobility increases. Busy daily activities make it difficult for many individuals to carry out the routine of washing clothes at home. This opens up great opportunities for the laundry business, especially in educational environments such as campus areas that have a high level of busyness. However, most operational processes of laundry businesses are still done manually, especially in recording transactions, resulting in an estimated 35-40% data error rate and significant delays in financial reporting processes. Despite the growing demand for digital solutions in service industries, there remains a significant gap in affordable, user-friendly laundry management systems specifically designed for small to medium-scale operations. To address these critical operational challenges, a website-based application called WhiteWave was developed to support the administration and management of laundry businesses. This application was built using the Laravel framework and utilizes the Aiven Console as a tool in database management, which provides ease of collaboration between developers. Based on comprehensive functionality and effectiveness testing, all features in the application run optimally according to development objectives, demonstrating a 98% user satisfaction rate and 60% improvement in operational efficiency. With this application, laundry business processes become more efficient, structured, and demonstrate minimal errors in managing operational data.

Facial image recognition using hybrid filtering models and convolutional neural networks (CNNs)

Dading Oktaviadi Resmiranta — 2025-11-26

The face is an important object in the biometric identification system. However, low image quality due to uneven lighting, noise, and variations in facial expressions can interfere with the accuracy of the recognition system. The study investigated the use of Convolutional Artificial Neural Network (CNN) combined with hybrid screening techniques to improve image quality, thereby improving the accuracy of facial recognition systems. Filters used include weight mean filtering, median filtering, Contrast-Limited Adaptive Histogram Equalization and gaussian filtering, wavelet filtering. The pre-processed image was then trained using image denoising measurements of the Structural Similarity Index, Mean Squared Error, and Peak Signal to Noise Ratio. The main objective of this study is to evaluate the best filtration combination to produce high accuracy in face classification. The datasets used were 55 classes and 100 images per class. The inceptionV3 architecture model is used for classifications with a number of epochs of 10. Evaluation was carried out on a facial data set with an 80%:20% scheme. The results of the experiment showed that the hybrid method produced the best performance with 94.5% validation accuracy, 94.2% precision, and 94.6% recall, an increase of +1.4% compared to baseline. The (original) baseline itself recorded 93.1% validation accuracy, 92.8% precision, and 93.2% recall. In addition, the loss graph shows that the pre-process model has faster and more stable convergence than the non-pre-processing model. These results confirm that the application of preprocessing, especially the hybrid approach, is able to improve the accuracy and stability of the model in image classification tasks.

Financial information system at krustyzone playground based on android

Safari Nurliana — 2025-11-26

The development of information technology encourages the need for efficient and mobile systems, especially in the small business sector such as playgrounds. This research aims to design and develop an Android-based Financial Information System at Krustyzone Playground to overcome the obstacles of manual recording, report delays, and lack of real-time data. The method used is Rapid Application Development (RAD), which allows a fast development process through design iterations and direct feedback from users. The system was developed using the CodeIgniter framework and MySQL database, and modeled with UML (Use Case Diagram, Activity Diagram, and Class Diagram). The implementation results show that the system is able to record income and expenses, display real-time financial reports, and manage users with different access rights. Tests through the Black Box Testing method prove that all functions run as expected. Validation by users shows the application is easy to use, efficient, and responsive. In conclusion, this system supports more accurate, secure, and structured financial management, as well as being an appropriate technology solution in assisting businesses in making decisions based on actual data.

Usability evaluation of the state junior high school 40 palembang website using the system usability scale (SUS)

Muhammad Yunus Syafaruddin — 2025-11-26

The increasing reliance on digital platforms in education highlights the importance of website usability for supporting academic and administrative activities. This study evaluates the usability of the State Junior High School 40 Palembang website using the System Usability Scale (SUS), a widely adopted and reliable method for measuring user experience. Data were collected from 50 respondents representing students, teachers, and administrative staff through observations, documentation, and an online SUS questionnaire. The overall SUS score achieved was 75.6, which places the website in the Good usability category. Further analysis revealed differences among user groups: administrative staff rated the system as Excellent (82.5), teachers as Good but close to Excellent (78.0), and students as Good but with the lowest score (72.5). These variations indicate that user familiarity, task type, and device context strongly influence usability perception. Benchmark comparisons confirmed that while the website surpasses the global average threshold, improvements are required to elevate it to the Excellent level consistently across all groups. Key areas for enhancement include navigation consistency, user guidance, and mobile responsiveness. Addressing these aspects will ensure broader user satisfaction, higher efficiency, and alignment with best practices in educational website usability.

The Development of interactive learning media using the design thinking method for indonesian language subjects: a case study of muhammadiyah 1 elementary school in purworejo regency

Cahyo Anggoro — 2025-11-26

This study attempts to create interactive learning media using Articulate Storyline software for
Indonesian language lessons in grade IV at Muhammadiyah 1 Elementary School in Purworejo Regency.
The development was carried out in accordance with the Design Thinking Method, which consists of five
stages, namely empathize, define, ideate, prototype, and test. This study was motivated by the low
application of technology in learning and the need for media that can be used to increase students' interest
in learning. Data was collected through observation and interviews with students and teachers. The learning
media designed combines multimedia in the form of videos, audio, animations, and interactive quizzes
based on Google Forms that are directly connected to Google Spreadsheets for assessment. The media is
stored in HTML5 and APK application formats so that it can be accessed via computers or smartphones.
The results of the pilot test showed that the learning media developed was categorized as highly
effective with an average effectiveness score of 4.34 based on the signs of learning interest according to
Slameto (2011), which consist of the elements of interest, involvement, enjoyment, and attention. Therefore, this learning media can be used as an alternative solution to improve the quality of interactive Indonesian language learning in elementary schools.

Implementation of a lecturer agenda management application using the scrum method at UIN Jurai Siwo Lampung

Krisna Widatama — 2025-11-26

Lecturers at UIN Jurai Siwo Lampung faced significant challenges in schedule management due to the lack of a centralized system, leading to frequent agenda conflicts and coordination inefficiencies. This research aimed to develop a functional agenda management application and evaluate the effectiveness of the Scrum method in this context. The software development process utilized the Scrum framework, emphasizing iterative sprints to adaptively handle changing user requirements. The results showed that the developed application successfully minimized scheduling overlaps through automated conflict detection features. Additionally, the Scrum method proved effective in accelerating the development cycle and ensuring the product met specific user needs. This study contributes a practical solution for enhancing academic productivity and offers empirical insights into implementing Agile methodologies within educational institutions.