Journal of Enhanced Studies in Informatics and Computer Applications

Implementation of K-Nearest Neighbours for Automotive Body Surface Defect Detection

Ninuk Wiliani — 2025-07-31

A body repair shop company that handles surface damage to vehicles is very necessary because the exterior appearance of the vehicle plays an important role in creating a good and attractive impression to others. Therefore, body repair companies must be able to adapt and keep up with the times. By combining advanced technology solutions, such as image processing, companies can streamline the identification phase, reduce human error, and optimize the allocation of repair resources. The problem discussed in this study is how to classify the surface of the vehicle body so that the classification model built can increase the accuracy in classifying the surface of the vehicle body. The steps taken in this study are to collect images of the surface of the vehicle body, and then the image data goes through a preprocessing process using median filtering to remove noise and segmentation techniques to improve image results. After preprocessing, the next step is to extract features based on texture using the Gray Level Co-occurrence Matrix (GLCM) and Statistical methods. Next, the images will be classified using the K-Nearest Neighbors (KNN) method, and the accuracy obtained is 56.80% for k = 3. After that, the classification model will be evaluated using the Area Under the Curve (AUC), and the AUC value obtained is 68.75%. With this approach, body repair workshop companies can improve the efficiency and accuracy in classifying vehicle body surfaces by utilizing image processing technology and techniques, allowing for better resource allocation and more reliable repair results

Digital Dashboard Technology for Spatial-Based Disease Distribution Mapping: Systematic Mapping Studies of Indonesia's Garuda Database

M Syauqi Haris — 2025-07-31

The utilization of Digital Dashboard Technology in disease spatial mapping offers a more interactive and insightful approach to presenting health data. This study employs a Systematic Mapping Studies (SMS) to examine the technologies applied in disease mapping dashboard development over the past five years. The findings reveal that digital mapping tools, including Geographic Information Systems (GIS) software such as QGIS and ArcGIS, as well as Leaflet.js, are widely used for spatial data visualization. Furthermore, the integration of advanced technologies, such as big data analytics, machine learning, and the Internet of Things (IoT), significantly enhances the dashboard’s capability for in-depth analysis and real-time data processing. The most commonly mapped diseases in the reviewed studies include Dengue Fever, Tuberculosis (TB), and Stunting, highlighting the critical role of digital dashboards in monitoring and controlling infectious diseases and public health issues. However, challenges such as data validity and system interoperability remain significant obstacles. This study offers valuable insights into the evolution of digital dashboard technology and its potential to support evidence-based decision-making in the healthcare sector.

Analyzing the Distribution of Household Electricity Usage in Indonesia Using Two-Way ANOVA

Fonda Leviany — 2025-07-31

Indonesia continues to experience notable challenges in providing equal access to electricity across its vast territory. In recent years, the government has made substantial progress through its national electrification initiatives. By the end of 2024, the National Electrification Ratio had reached 99.83%. However, despite this remarkable development, many remote and inland areas—particularly in certain regions of Papua—remain disconnected from the national electricity grid. Recent data on the percentage of households using electricity as the main lighting source in 38 provinces during 2023 and 2024 presents an opportunity for comparative analysis to assess equity in electricity access across regions and over time. This study proposes an analytical approach using Two-Way ANOVA, with location (urban vs. rural) and year (2023 vs. 2024) as the independent variables. The two-way ANOVA further confirmed that the main effect of location (urban vs. rural) was statistically significant (F = 10.049, p = 0.002), indicating a persistent gap in access between the two locations. However, the overall change from 2023 to 2024 was not statistically significant (p = 0.273), and the urban-rural gap remained relatively stable. These findings emphasize the importance of targeted policies to improve rural electrification and reduce regional disparities in access to electricity.

Performance Analysis of Sorting Algorithm in Student Data Processing

Maulana Aditya — 2025-07-31

The arrangement of large amounts of student data typically presents a challenge for administrators in completing student administrative tasks. Several sorting algorithms are used to solve this problem; however, with the evolution of technology, various new sorting algorithms have emerged. This study examines the performance of four widely used sorting algorithms—Bubble Sort, Insertion Sort, Merge Sort, and QuickSort—in sorting data based on student ID numbers, names, and GPAs. The study involves testing the algorithms across several scenarios, including pre-sorted data, random data, and data with duplicate elements, by measuring execution time and the number of computational operations as indicators of efficiency. The results show that Bubble Sort and Insertion Sort perform well on small datasets but are less effective on large datasets. Conversely, Merge Sort and Quick Sort are highly effective on complex datasets. While Merge Sort is more stable for large datasets with specific structures, Quick Sort operates faster on random data. These results provide practical guidance for selecting the best sorting algorithm based on data size and complexity. These results can support data management efficiency in academic environments. With the results obtained, this research can serve as an important reference for developing more efficient academic information systems and data management in educational institutions.

Comparison of Breadth-First Search (BFS) and Depth-First Search (DFS) Algorithms for Shortest Search in Campus Labyrinth

Ardhan Aghsal Dwi Putra — 2025-07-31

Finding the shortest path in a complex campus environment is a challenge, especially for new students who are not familiar with the layout of buildings and available paths. Efficient path finding can help improve mobility on campus, especially in areas with many branching paths and possible dead ends. In this study, an analysis of the shortest path search was conducted by comparing the Breadth-First Search (BFS) and Depth-First Search (DFS) algorithms in a campus environment represented as a maze-shaped graph. The research methods include literature study, simulation design, data collection, algorithm implementation, and performance evaluation based on execution speed, memory usage, and processor efficiency. Data were obtained from field surveys and secondary studies on campus layout. Simulations were conducted by implementing BFS and DFS in a graph model to measure the effectiveness of both algorithms. The results show that DFS has advantages in execution speed and lower memory usage, while BFS is more consistent in finding optimal solutions. DFS is more suitable for scenarios with fast search time requirements, while BFS is more effective in ensuring the shortest path in an environment with a complex graph structure. The conclusion of this study emphasizes that the selection of algorithms must be adjusted to the specific needs of navigation applications.