cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Arief Hidayat
Contact Email
arief.hidayat@unwahas.ac.id
Phone
+628156529309
Journal Mail Official
jinformatika@unwahas.ac.id
Editorial Address
JL. Menoreh Tengah X / 22, Sampangan, Gajahmungkur, Sampangan, Gajahmungkur, Kota Semarang, Jawa Tengah 50232
Location
Kota semarang,
Jawa tengah
INDONESIA
Jurnal Informatika dan Rekayasa Perangkat Lunak
Published by Universitas Wahid Hasyim Semarang
ISSN : 26562855     EISSN : 26855518     DOI : http://dx.doi.org/10.36499/jinrpl
Core Subject : Science,
Computer Science & IT
Journal of Informatics and Software Engineering accepts scientific articles in the focus of Informatics. The scope can be: Software Engineering, Information Systems, Artificial Intelligence, Computer Based Learning, Computer Networking and Data Communication, and Multimedia.
Arjuna Subject : Ilmu Komputer (semua kategori) - Perangkat Lunak
Articles 244 Documents
 21   22   23   24   25 
Perbandingan Apache Airflow dan Apache Spark dalam Proses ETL untuk Memprediksi DropOut dan Keberhasilan Akademik Mahasiswa Laksono, Triyan Agung; Andriyani, Widyastuti
Jurnal Informatika dan Rekayasa Perangkat Lunak Vol. 7 No. 2 (2025): September
Publisher : Universitas Wahid Hasyim

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

Abstract

Dropout prediction in higher education is important because it impacts the academic success of students and the overall effectiveness of educational institutions. This research aims to build an automated ETL pipeline using Apache Airflow and Apache Spark to process academic data and predict student graduation status. The dataset used consists of 4,424 samples with 36 features covering demographic, academic, and socio-economic attributes. The data is processed through the stages of extraction, transformation (including SMOTE normalization), with loading into the Random Forest model. The evaluation results showed an accuracy of 62.93% and the highest ROC-AUC value of 0.81 for the dropout class. The Airflow pipeline excels in task scheduling efficiency, while Spark is effective for large-scale data processing. This approach shows practical potential in supporting early warning systems for academic policy decision-making. This research contributes to the intergation of big data and machine learning technologies for efficient and automated higher education data processing.
Comparative Study of Recurrent Neural Network (RNN) and Extreme Learning Machine (ELM) in Predicting Bank Central Asia’s Stock Price Mukharomah, Rizanatul; Siswanah, Emy
Jurnal Informatika dan Rekayasa Perangkat Lunak Vol. 7 No. 2 (2025): September
Publisher : Universitas Wahid Hasyim

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

Abstract

Predicting stock prices is an important financial topic, especially for investors who want to maximize profit and minimize risk. This research compares two machine-learning capabilities, a Recurrent Neural Network (RNN) and an Extreme Learning Machine (ELM), in predicting Bank Cental Asia (BBCA) stock prices. These two are chosen for their capabilities in handling time-series data. This research uses the data of BBCA’s daily prices over a certain period and involves several steps such as data collecting, data pre-processing, model training, and calculation of accuracy value. This accuracy calculation will be evaluated using Mean Squared Error (MSE) and Mean Absolute Percentage Error (MAPE). This research shows ELM has better accuracy than RNN in predicting BBCA’s stock prices. ELM shows lower MSE and MAPE values than RNN, indicating the capability of ELM to predict with smaller errors. This research also concludes ELM is better in accuracy than RNN in predicting BBCA’s stock prices. Thus, ELM is the recommended method to predict stock prices.
Enhancing the Accuracy of Competency Portfolio Assesments using Machine Learning: a Comparative Analysis of Predictive Models Saputra, Aditya Cahya; Yuadi, Imam
Jurnal Informatika dan Rekayasa Perangkat Lunak Vol. 8 No. 1 (2026): Maret
Publisher : Universitas Wahid Hasyim

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

Abstract

This study elaborates the application of various machine learning (ML) models to measure competency portfolio assessments for job grade conversion needed of employees. The purpose is choose the best ML models to enhance the accuracy, scalability, and fairness. Logistic regression and support vector machines is two traditional methods were evaluated together with random forest and gradient boosting as ensemble models and neural network as deep learning models. This study taken data of 117 employees invited to join on the competency portfolio assessment event on November 2024, all models were measured through cross-validation on parameters such as accuracy, precision and recall by Orange Data Mining. The best performance model in this study is Random Forest, achieving the highest score on Precision and Recall parameters. While Neural Networks demonstrated potential performance that almost has the same result with logistic regression. Based on this research, Random Forest can be prioritized and implemented to help the company to enhance the accuracy of competency portfolio results that needed to develop employees career, eligible competencies, and help decision making of job grade conversion assessment. Keywords: Comparative Analysis, Competency Portfolio Assessment, Machine Learning
Classification of Article Types in the ITE Law using the KNN Algorithm with the Application of SMOTE, PCA, and GridSearchCV Hyperparameter Optimization Muharom, Alif Alpian Sahrul; Putro, Aditya Dwi; Rafika, Yohani Setya
Jurnal Informatika dan Rekayasa Perangkat Lunak Vol. 8 No. 1 (2026): Maret
Publisher : Universitas Wahid Hasyim

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

Abstract

The advancement of information technology drives digital transformation, enhancing efficiency but also presenting challenges such as data management and privacy risks due to cybercrime. The Electronic Information and Transactions Law (UU ITE) serves as an essential legal foundation for protecting data and ensuring digital justice. This study employs the K-Nearest Neighbor (KNN) algorithm to classify UU ITE violations based on chronology texts, focusing on Articles 27 and 28 from 323 violation cases. The process includes text preprocessing, weighting, modeling, and evaluation. To address data imbalance, SMOTE (Synthetic Minority Oversampling Technique) and PCA (Principal Component Analysis) were applied. Hyperparameter optimization using GridSearchCV improved model performance. Initial accuracy of 57% increased to 75% after applying SMOTE and PCA, with a final result of 82.62%, a macro average F1-score of 0.82, and a weighted average F1-score of 0.83. The model showed the best performance on "Article 28 Paragraph 2" and the lowest on "Article 27 Paragraph 1". This study demonstrates the potential of Text Mining in supporting digital law enforcement.
Forecasting Model using Single Exponential Smoothing Method on PT. Rakha Medika Christy, Hanna; Wijaya, Andri
Jurnal Informatika dan Rekayasa Perangkat Lunak Vol. 8 No. 1 (2026): Maret
Publisher : Universitas Wahid Hasyim

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

Abstract

PT. Rakha Medika is a healthcare company with a network of clinics spread across various branches in the city of Palembang. In stock management, the company faces significant challenges related to both overstocking and stock shortages, which impact operational efficiency. These issues arise because inventory orders are made without proper planning. This study aims to optimize stock management by applying the Single Exponential Smoothing forecasting method to analyze usage patterns. The data used includes inventory records spanning a one-year period (April 2023 to April 2024), comprising a total of 4,033 entries. The forecasting results indicate that an alpha value of 0.99 is the most optimal, achieving a forecasting accuracy of MAPE at 14%, MAD at 4, and MSE at 97. These results suggest that the forecasting method performs reasonably well, as the MAPE score does not exceed 20%. However, a comparison between the forecasting results and the actual values reveals a deviation of 38.24% from the total inventory. This deviation is influenced by the characteristics of the data and unavoidable external factors.
Comparison of Individual Algorithms (Decision Tree, Naïve Bayes, and Support Vector Machine) and Ensemble Voting in Predicting Students’ On-Time Graduation Based on Course Grades Ferdian, Sevtian; Miechael, Miechael; Wibowo, Arief
Jurnal Informatika dan Rekayasa Perangkat Lunak Vol. 8 No. 1 (2026): Maret
Publisher : Universitas Wahid Hasyim

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

Abstract

Education plays an important role in improving the quality of human resources and supporting a country’s progress toward becoming a developed nation. Higher education institutions serve as one of the providers of formal education, where the quality of these institutions is measured through accreditation. One of the key indicators influencing accreditation is the outcomes and achievements of the Tri Dharma of higher education, which include the timeliness of student graduation. This study aims to compare models for predicting on-time student graduation using three machine learning algorithms, namely Decision Tree, Naïve Bayes, and Support Vector Machine (SVM), as well as their combination through the Ensemble Voting method. The prediction is based on historical grade data from courses taken during semesters one to four. The research methodology adopts the Cross-Industry Standard Process for Data Mining (CRISP-DM), which consists of six stages: business understanding, data understanding, data preparation, modeling, evaluation, and deployment. The dataset used in this study consists of 2,471 records with 11 attributes. Data preprocessing was conducted through data cleaning and class balancing using under sampling techniques. The results indicate that the Ensemble Voting model using the Soft Voting method achieves the best performance, with an accuracy of 91.80%, precision of 91.87%, and recall of 91.80%, outperforming the individual models of Decision Tree, Naïve Bayes, and SVM. The implementation of this model can be utilized to predict students’ on-time graduation based on course grade inputs. Therefore, this research can serve as a supporting tool for early detection of potential delays in student graduation.
Implementation of Peresean Game as a Medium to Enhance Sasak Cultural Appreciation Among Young Generation Hamzan Ahmadi; Aris Sudianto; Hariman Bahtiar
Jurnal Informatika dan Rekayasa Perangkat Lunak Vol. 8 No. 1 (2026): Maret
Publisher : Universitas Wahid Hasyim

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

Abstract

Peresean is a traditional custom of the Lombok Sasak Tribe, which is armed with rattan (jalin), using a shield (ende) made from cow skin and when the peresean event takes place it will be accompanied by the typical music of the Lombok Sasak Tribe, namely gendang beleq. The clothing worn by peresean participants (pepadu) is a headband (sapuq), sarong (selewoq), cloth belt (bebet) and bare chest. The peresean culture is now starting to be held less frequently and is not very popular with Lombok youth in particular. This is because today's youth prefer digital games that are more varied and do not require a lot of stamina. So from there it became a reference for making a fighting type peresean game using the GDLC method as a means to preserve the Sasak tribe's peresean culture. adjust regulations according to the target audience. The final result of this production is a fighting game that runs on a PC (personal computer), and is targeted at all ages. The features that have been designed have fulfilled what was desired. In this fighting type research game, there is information and moral messages about preserving local culture. It is hoped that this peresean game application can become a medium of introduction and education for the wider community, especially the people of Lombok, about the peresean culture of the Lombok Sasak Tribe.
The Implementation of an Artificial Intelligence-Based Virtual Assistant Chatbot for Academic Information Services -, Baiq Andriska Candra Permana; Aris Sudianto; Toriq Alfan Yasir
Jurnal Informatika dan Rekayasa Perangkat Lunak Vol. 8 No. 1 (2026): Maret
Publisher : Universitas Wahid Hasyim

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

Abstract

The academic information services at the Faculty of Engineering, Hamzanwadi University currently still rely on manual methods that require considerable time and effort, especially in answering repetitive questions. Therefore, this study proposes the use of an artificial intelligence-based chatbot to provide academic information automatically through the WhatsApp platform. This chatbot system is built using the n8n platform for workflow automation and Gemini AI for natural language processing (NLP), enabling it to understand and provide relevant answers to students' questions. In this study, the system was tested through a series of trials to evaluate the effectiveness of the chatbot in delivering academic information services, such as academic schedules, course registration (KRS), and other related information. The results showed that the implementation of this chatbot can improve the efficiency of academic services by providing fast and accurate responses, as well as reducing the workload of administrative staff.
Application of the MOORA and TOPSIS Methods in the Evaluation of Tax Administration Strategies based on Taxpayer Identification Numbers (NPWP), Services, Sanctions, and Taxpayer Understanding Andayani, Sri Umiatun; Kusumawati, Dyah; Mustagfirin, Mustagfirin
Jurnal Informatika dan Rekayasa Perangkat Lunak Vol. 8 No. 1 (2026): Maret
Publisher : Universitas Wahid Hasyim

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

Abstract

Taxpayer compliance is a crucial factor in optimizing state revenue through the taxation sector. Although the number of taxpayers in Indonesia continues to increase, the level of voluntary compliance is still relatively low, so an effective tax administration strategy is needed to improve it. This study aims to analyze the influence of the benefits of Taxpayer Identification Number (NPWP), service quality, administrative sanctions, and tax understanding on taxpayer compliance, and determine the most optimal tax administration strategy using the Multi-Objective Optimization on the Basis of Ratio Analysis (MOORA) and Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) methods. This approach was chosen because it is able to provide objective and measurable analysis results based on complex criteria. The MOORA method is used to normalize and weight each criterion, while TOPSIS is used to determine the most ideal strategic solution. The results show that the strategy of increasing tax socialization and sending warning letters to taxpayers who violate is the most effective step to increase taxpayer compliance. Sensitivity analysis shows that the MOORA method has a better level of stability of results with an average sensitivity value of -1.61%, compared to TOPSIS at -7.96%. Thus, the MOORA method is considered more appropriate for use in the context of evaluating tax administration strategies. This research significantly contributes to the development of data-driven tax policies and enriches the literature on the application of multicriteria decision-making methods in tax administration in Indonesia.
Comparison of BioBERT and DistilBERT for Named Entity Recognition on Indonesian Radiology Clinical Data Aprilia, Nadia Eka; Utomo, Danang Wahyu
Jurnal Informatika dan Rekayasa Perangkat Lunak Vol. 8 No. 1 (2026): Maret
Publisher : Universitas Wahid Hasyim

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

Abstract

Named Entity Recognition (NER) in Indonesian language radiology reports faces significant challenges due to the limited availability of labeled data for model training. This constraint is a major obstacle to developing an accurate medical information extraction system. Pseudo-labeling emerges as a potential solution by leveraging abundant unlabeled data to expand the training dataset without the need for time-consuming manual annotation. This study aims to compare the performance of two transformer models, BioBERT and DistilBERT, fine-tuned on pseudo-labeled data for extracting medical entities from Indonesian radiology reports. The research methodology encompasses three main stages text preprocessing and normalization, text alignment using regular expressions with BIO labeling, and model fine-tuning with a pseudo-labeling strategy. Model performance was evaluated using Precision, Recall, and F1-score metrics on an adapted radiology dataset. The results indicate that pseudo-labeling was effective in enhancing the performance of both models. DistilBERT achieved a higher accuracy of 96,4, while BioBERT reached 92.78%. Nonetheless, DistilBERT demonstrated superior computational efficiency with faster training time. This study provides valuable insight for selecting an optimal model architecture for NER tasks on Indonesian medical text, considering the balance between accuracy and computational efficiency.

Page 23 of 25 | Total Record : 244

 21   22   23   24   25 

Filter by Year

2019 2026


Reset
Filter By Issues
All Issue Vol. 8 No. 1 (2026): Maret Vol. 7 No. 2 (2025): September Vol. 7 No. 1 (2025): Maret Vol 6, No 2 (2024): September Vol. 6 No. 2 (2024): September Vol 6, No 1 (2024): Maret Vol 5, No 2 (2023): September Vol 5, No 1 (2023): Maret Vol 4, No 2 (2022): September Vol 4, No 1 (2022): Maret Vol 3, No 2 (2021): September Vol 3, No 1 (2021): Maret Vol 2, No 2 (2020): September Vol 2, No 1 (2020): Maret Vol 1, No 2 (2019): September Vol 1, No 1 (2019): Maret More Issue