cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Masduki
Contact Email
lppi@ums.ac.id
Phone
-
Journal Mail Official
khif@ums.ac.id
Editorial Address
Program Studi Teknik Informatika, Fakultas Komunikasi dan Informatika, Universitas Muhammadiyah Surakarta Gedung J Lantai 1 Sayap Barat Jl. A. Yani No 1, Pabelan 57162, Surakarta Indonesia
Location
Kota surakarta,
Jawa tengah
INDONESIA
Khazanah Informatika : Jurnal Ilmu Komputer dan Informatika
Published by Universitas Muhammadiyah Surakarta
ISSN : 2621038X     EISSN : 2477698X     DOI : -
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering
Khazanah Informatika : Jurnal Ilmu Komputer dan Informatika, an Indonesian national journal, publishes high-quality research papers in the broad field of Informatics and Computer Science, which encompasses software engineering, information system development, computer systems, computer network, algorithms and computation, and social impact of information and telecommunication technology
Arjuna Subject : Ilmu Komputer (semua kategori) - Sistem Informasi
Articles 28 Documents
 1   2   3 
Using SVM and KNN for Predicting Customer Response Sentiment of M-PAJAK Application Muhammad Titan Rama Adi Wijaya; Ida Widaningrum; Angga Prasetyo; Dyah Mustikasari
Khazanah Informatika : Jurnal Ilmu Komputer dan Informatika Vol. 11 No. 1 (2025): April 2025
Publisher : Universitas Muhammadiyah Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23917/khif.v11i1.4528

Abstract

M-Pajak, an application initiated by the Directorate General of Taxes, signifies the modernization of taxation and serves a crucial function. This application facilitates taxpayers in meeting their tax obligations. User satisfaction with this application may be assessed via reviews on the Google Play Store. While this application fulfills client satisfaction, its sustained success is significantly contingent upon user contentment and experience. Sentiment analysis is essential for elucidating user evaluations and interactions with the program. This research analyses the sentiment of M-Pajak application reviews on Google Play using Support Vector Machine (SVM) and K-Nearest Neighbour (KNN), supported by the Term Frequency-inverse Document Frequency (TF-IDF) feature extraction method. A total of 1000 reviews between December 11, 2022 and December 2, 2023 were processed using KNN and SVM. The KNN algorithm yielded 153 positive predictions and 847 negative predictions and achieved 94% of accuracy. Meanwhile, SVM achieved an accuracy of 88.10%, with 325 positive predictions and 675 negative predictions. The results demonstrate the superiority of KNN in sentiment classification of M-Pajak reviews. This study also indicates that negative comments outnumber positive ones in this application. This serves as a signal for the Directorate General of Taxation to enhance user satisfaction with the M-Pajak application through continuous updates.
Region Enhanced Edge-Based Multi-Class Object Proposal for Self-Driving Vehicles Haq, Muhamad Amirul; Huy, Le Nam Quoc; Ridlwan, Muhammad
Khazanah Informatika : Jurnal Ilmu Komputer dan Informatika Vol. 11 No. 1 (2025): April 2025
Publisher : Universitas Muhammadiyah Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23917/khif.v11i1.4662

Abstract

On-road object detection is a fundamental element for the safety and reliability of autonomous driving systems. A primary challenge is developing object detection algorithms that are both fast and robust. This paper introduces a novel object proposal algorithm, named Region Enhanced Edge-Based (REEB) proposal, designed to accelerate object detection by significantly reducing the number of candidate regions requiring evaluation by a subsequent classification network. REEB leverages edge-map cues to score and rank initial proposals. To further enhance both detection quality and processing speed, the algorithm integrates efficient complementary techniques: image entropy is used to guide proposal generation density in relevant image regions, and road segmentation aids in refining proposal scores by differentiating road from non-road areas. Experimental evaluations on the KITTI dataset demonstrate that REEB achieves an average recall rate of 72.1% across four classes (pedestrian, cyclist, car, and truck) with an average processing time of 15 milliseconds per image. These results indicate strong performance when compared to other traditional, non-deep learning object proposal algorithms.
Performance Comparison of Random Forest, Bagging, and CART Methods in Classifying Recipients of the Family Program in North Aceh Hari Yanni, Meri; Anwar Notodiputro, Khairil; Sartono, Bagus
Khazanah Informatika : Jurnal Ilmu Komputer dan Informatika Vol. 11 No. 1 (2025): April 2025
Publisher : Universitas Muhammadiyah Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23917/khif.v11i1.5098

Abstract

Machine learning is a method in data mining, it is used to study large data patterns through classification methods including Random Forest, Bagging, and CART. The Random Forest method develops the Bagging technique and Decision Tree components (CART) in decision-making. The difference between RF and Bagging is the selection of random features in forming a decision tree. It is only found in RF. Bagging can improve performance, model stability, and reduce variance by forming many different models. The research aims to see the performance of the Random Forest, Bagging, and CART methods in classifying family recipient programs in North Aceh. The results show that the performance of the RF, Bagging, and CART classification methods using the SMOTE technique for handling unbalanced classes is better than before handling unbalanced data. The classification method is evaluated through each model's accuracy, sensitivity, specificity, precision, F1 score, and AUC values. The results show good performance with accuracy values of 90% Smote-RF and 86% Smote Bagging. The best performance was seen in the Smote-RF model which was obtained by tuning the Grid Search CV model parameters with k = 5 and repeat = 1 for a data set proportion of 90:10. This shows that the model can correctly predict all observations with an accuracy percentage of 90% with an average AUC value of 93.52%. On the other hand, the CART method has a very low accuracy value, so the model is less able to accurately predict all observations. Measurement of the level of importance of predictor variables that have the greatest influence in predicting recipient households is the floor area of the house, the number of household members aged 10 years and over, and the type of work of the head of the household.
Optimizing Learning Management Systems for Elderly Teachers in Indonesia Using a User Experience-Based Design Thinking Approach: A Case Study at SMAN 77 Jakarta Muhamad Nursalman; Rosa Ariani Sukamto; Ahmad Fathi Ibrahimov; Amelia Zalfa; Salma Ghaida; Natasha Adinda Cantika; Muhammad Ruby PS
Khazanah Informatika : Jurnal Ilmu Komputer dan Informatika Vol. 11 No. 2 (2025): October 2025
Publisher : Universitas Muhammadiyah Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Learning Management Systems (LMS) have become essential tools in educational institutions for delivering online learning experiences. Despite their widespread adoption, many elderly teachers face considerable challenges in navigating and operating these platforms, which can hinder the effectiveness of the teaching and learning process. Recognizing this issue, the present study focused on developing a more user-friendly LMS tailored specifically for elderly teachers by employing a design thinking approach. This approach, known for its human-centered and iterative nature, involves five key stages: empathy, problem definition, ideation, prototyping, and testing. The study involved 30 participants, including senior teachers, younger teachers, and LMS administrators, to ensure a comprehensive understanding of user needs and to foster collaborative development. During the empathy stage, the specific difficulties faced by elderly teachers were identified, and these insights guided the formulation of the core problems. Ideas for improving the LMS interface and functionality were generated and transformed into prototypes, which were subsequently tested and refined based on user feedback. Evaluation of the final LMS design involved expert validation in UI/UX, as well as the use of two established usability instruments: the User Experience Questionnaire (UEQ) and the System Usability Scale (SUS). Results showed significant improvements in user satisfaction and usability. The UEQ scores reached the “excellent” category, with the lowest score being 1.815, indicating high user experience across various dimensions. Additionally, the SUS score improved markedly from 50 to 76, highlighting a substantial increase in perceived usability. These findings suggest that the design thinking approach is highly effective in addressing usability issues and can lead to the development of more accessible and comfortable LMS platforms for elderly educators.
Hyperparameter Optimization of TF-IDF and SVM via Grid Search for Sentiment Analysis of Traveloka Customer Reviews Muhammad Bayu Kurniawan; Hanafi; Riki Hikmianto; Isnawati Muslihah
Khazanah Informatika : Jurnal Ilmu Komputer dan Informatika Vol. 11 No. 2 (2025): October 2025
Publisher : Universitas Muhammadiyah Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Customer reviews on digital platforms are crucial for improving services and making business decisions. This study focuses on automated sentiment analysis for Traveloka, a leading Indonesian online travel application. We propose a systematic hyperparameter optimization of a combined TF-IDF and Support Vector Machine (SVM) pipeline. A dataset of 20,200 user reviews was collected from the Google Play Store. After preprocessing and a two-stage labeling process, the data was split using stratified sampling (70% training, 30% testing). We conducted a comprehensive Grid Search with stratified 5-fold cross-validation to jointly optimize TF-IDF n-gram ranges (unigram, bigram, trigram) and SVM hyperparameters across four kernel types (Linear, RBF, Polynomial, Sigmoid). The results show that the Polynomial kernel with trigram features (C=5, gamma=1, degree=5, coef0=10) performs best. It achieves a test accuracy of 87.10% and a macro F1-score of 86.9%. Error analysis revealed the model's high reliability in detecting negative feedback (precision: 90.4%) but also its difficulty with contrastive sentences and informal language. The minimal performance differences among top configurations suggest the task is robust to specific parameter choices. However, the model's bag-of-ngrams approach shows limitations in processing contrastive sentences and informal language. For future work, employing contextual embeddings (e.g., IndoBERT) and exploring alternative algorithms like Random Forest or Neural Networks could address these challenges. This research presents a thoroughly optimized traditional ML methodology that establishes a strong baseline for automated sentiment analysis of Indonesian user feedback.
Android-Based Application of Dispensation Licensing System for Urban Freight Transport in Surakarta City Budi Yulianto; Setiono; Nurul Hidayati; Salsabila Naura Putri
Khazanah Informatika : Jurnal Ilmu Komputer dan Informatika Vol. 12 No. 1 (2026): April 2026
Publisher : Universitas Muhammadiyah Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Urban freight transport poses significant challenges to traffic management, road safety, and environmental sustainability in Surakarta City. This study examines the development and implementation of the SIMABA application, operationalized as the SIDJAKA digital dispensation licensing system, for monitoring and controlling urban freight transport movements. The freight transport trip characteristic survey was conducted to identify origin-destination trips, frequency, weight and type of cargo, and distribution patterns. The road inventory survey was intended to obtain road geometry data, while the traffic count survey was done to collect traffic volume during peak hours. Meanwhile, secondary data consisting of information on road functions and bearing capacity, land use of activity centers, traffic signs, and administrative licenses submitted through SIDJAKA application from January 2020 to December 2025 were obtained from relevant institutions. This study demonstrates that the SIMABA application, implemented through the SIDJAKA system, effectively regulates the licensing of freight transport in Surakarta City. Monitoring of this application can be carried out systematically and transparently, ensuring that administrative and technical requirements, particularly vehicle roadworthiness, are met, thus ensuring more controlled urban freight transport. The analysis of origin-destination trips indicates that freight transport flows are significantly influenced by changes in the road network and infrastructure development, with the distribution activities remaining concentrated in market areas and major commercial corridors. Although effective, the system faces limitations in terms of cross-regional scale, data integration, maintenance systems, and digital user literacy, which may hinder its adoption and optimal utilization. As a future research agenda, developing the system into an integrated platform that connects cross-regional licensing, vehicle inspection systems, and electronic law enforcement is recommended to achieve greater adaptability and efficiency.
Temporal Video Analysis for Identifying Traditional Malay Buildings Using Residual Network and Vision Transformer Sri Winiarti; Sunardi; Abdul Fadlil
Khazanah Informatika : Jurnal Ilmu Komputer dan Informatika Vol. 12 No. 1 (2026): April 2026
Publisher : Universitas Muhammadiyah Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The lack of digital documentation in preserving traditional Malay architecture faces serious challenges, especially with the modernization that slowly obscures the shape and authenticity of the building. Essential elements such as roof shapes, stage structures, and typical ornamental carvings are difficult to identify manually without special skills and considerable time. Malay architecture is an integral part of Indonesia's cultural heritage that needs to be documented systematically and digitally. Along with advances in Artificial Intelligence (AI) technology, traditional buildings' intense learning, identification, and classification can now be done automatically through video-based visual data processing. This study uses a video-based deep learning approach to develop and evaluate a classification system for traditional Malay buildings. Two types of architecture are used: Residual Network (ResNet) and Vision Transformer (ViT). The dataset in the form of videos of traditional buildings was collected from the Pekanbaru, Riau Province, then processed through frame extraction, spatial-temporal augmentation, and visual annotation, resulting in a total of 1,500 frames as training data. This study also presents a novel aspect by comparing the performance of five deep learning models: ResNet18, ResNet34, ResNet50, ResNet101 (CNN), and ViT based on self-attention. ViT, which is rarely used in traditional video-based architecture, shows competitive accuracy and proves its effectiveness in understanding global visual relationships. The training method is carried out using supervised learning and evaluated based on classification accuracy. The test results show that all models can accurately identify visual features of Malay architecture. ResNet50 recorded the highest accuracy (100%), followed by ResNet18 (96.0%), ResNet101 (94.9%), ResNet34 (93.9%), and ViT (93.9%). These findings strengthen the potential for utilizing deep learning in cultural preservation through a video-based automatic documentation system.
Application of Mini-Batch K-Means Algorithm for Clustering Divorce Verdict Document Data Of Indramayu District Religious Court Nurissaidah Ulinnuha; Raudah Yasmin Ghozali; Wika Dianita Utami
Khazanah Informatika : Jurnal Ilmu Komputer dan Informatika Vol. 11 No. 2 (2025): October 2025
Publisher : Universitas Muhammadiyah Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Divorce occurs because married couples are no longer able to achieve the main goals of marriage. According to data from the West Java Central Bureau of Statistics, Indramayu Regency recorded the highest number of divorces in West Java during 2021-2023. This condition underscores the need for research to categorize the Plaintiff's or Applicant's arguments, as set out in the divorce decision issued by the Indramayu Regency Religious Court. The textual arguments of the Plaintiff or Petitioner will be pre-processed text and term weighting using Term Frequency-Inverse Document Frequency (TF-IDF). The term weighting results will be clustered using the Mini-Batch K-Means method. Mini-Batch K-Means speeds up computation by using a subset of data per iteration. In addition, the initial centroids are randomly initialized using K-Means++. The evaluation of Mini-Batch K-Means is measured based on the Silhouette coefficient, the number of iterations, and the speed of computation time. The results of this study show that Mini-Batch K-Means with random initialization is the best model, with a Silhouette coefficient of 0.5293, 4 iterations, and a running time of 0.0653 seconds. Based on the visualization results for each cluster, 2 topic groups were identified: quarrel and dispute factors, and work, children, and financial factors.

Page 3 of 3 | Total Record : 28

 1   2   3 

Filter by Year

2024 2026


Reset
Filter By Issues
All Issue Vol. 12 No. 1 (2026): April 2026 Vol. 11 No. 2 (2025): October 2025 Vol. 11 No. 1 (2025): April 2025 Vol. 10 No. 2 (2024): Oktober 2024 Vol. 10 No. 1 (2024): April 2024