cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Muhammad Wali
Contact Email
muhammadwali@amikindonesia.ac.id
Phone
+6285277777449
Journal Mail Official
ijsecs@lembagakita.org
Editorial Address
Jl. Teuku Nyak Arief No. 7b 23112, Kota Banda Aceh, Banda Aceh, Provinsi Aceh
Location
,
INDONESIA
International Journal Software Engineering and Computer Science (IJSECS)
Published by Lembaga Komunitas Informasi Teknologi Aceh
ISSN : 27764869     EISSN : 27763242     DOI : https://doi.org/10.35870/ijsecs
Core Subject : Science,
Computer Science & IT
IJSECS is committed to bridge the theory and practice of information technology and computer science. From innovative ideas to specific algorithms and full system implementations, IJSECS publishes original, peer-reviewed, and high quality articles in the areas of information technology and computer science. IJSECS is a well-indexed scholarly journal and is indispensable reading and references for people working at the cutting edge of information technology and computer science applications..
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 465 Documents
 43   44   45   46   47 
Application of Random Forest Method in Predicting Chronic Obstructive Pulmonary Disease (COPD) Muhhamad Fatkhurridlo Mahendra; Nur Aeni Widiyastuti; Sarwido Sarwido
International Journal Software Engineering and Computer Science (IJSECS) Vol. 5 No. 3 (2025): DECEMBER 2025
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA), Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v5i3.5551

Abstract

Chronic Obstructive Pulmonary Disease (COPD) is one of the major global health problems and remains among the leading causes of death worldwide. Early detection plays a crucial role in preventing disease progression; however, conventional diagnostic methods such as spirometry and CT scans often require high costs, long processing time, and specialized expertise. This study aims to apply the Random Forest algorithm, one of the machine learning methods, to predict COPD based on clinical and lifestyle data. The dataset was obtained from Kaggle, consisting of attributes including age, gender, smoking status, type of occupation, sleep habits, exercise activity, insurance ownership, and history of comorbidities. The research stages include data preprocessing, train-test splitting (80:20), and model evaluation using accuracy, precision, recall, F1-score, and AUC metrics. The Random Forest model achieved an accuracy below 90% (approximately 87%), reflecting realistic performance in medical prediction while avoiding overfitting. The results indicate that Random Forest can serve as a reliable method for COPD detection and holds potential to be developed as the foundation of a Clinical Decision Support System (CDSS). This study contributes to the growing body of literature on the application of machine learning in healthcare, while also offering a faster, cost-effective, and scalable alternative for diagnosis.
Stunting Prediction in Toddlers Using the K-Nearest Neighbor (KNN) Method Based on a Web Application at Batealit Community Health Center, Jepara Lisa Falichatul Ibriza; Gentur Wahyu Nyipto Wibowo; Teguh Tamrin
International Journal Software Engineering and Computer Science (IJSECS) Vol. 5 No. 3 (2025): DECEMBER 2025
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA), Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v5i3.5553

Abstract

Stunting is still a nutritional problem that exists in Indonesia and it needs immediate intervention in Jepara Regency. At the primary healthcare level, Batealit Public Health Center uses manual anthropometric recording for toddlers' growth assessment. This method can be prone to human recording errors and operational delays which hinder prompt clinical decision-making. To improve this condition, this study develops a web-based system for predicting stunting based on the K-Nearest Neighbor (KNN) algorithm. The research method was applied research with system development using the Waterfall model by processing main variables such as age, weight, and height. We tested the algorithm intensively by trying different neighbor values (k) to obtain the maximum value for accuracy, precision, and recall. From experiments, the KNN algorithm is best at k=3 with a 95.23% accuracy rate; this configuration is better compared to larger k values since they increase misclassification rates on normal and stunted categories. By porting this logic into a web interface, detection moves from being a manual task to an automated one occurring in real-time thus application becomes an essential part of decision support enabling health workers to bypass administrative delays and find stunting much faster more accurately within Batealit service area.
Implementation of the Hybrid ARIMA-LSTM Model for Gold Price Prediction Based on Yahoo Finance Data Talitha Hananta Nurendasari; Gentur Wahyu Nyipto Wibowo; Harminto Mulyo
International Journal Software Engineering and Computer Science (IJSECS) Vol. 5 No. 3 (2025): DECEMBER 2025
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA), Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v5i3.5560

Abstract

This paper presents a hybrid ARIMA–LSTM model to forecast daily gold price using historical data from Yahoo Finance. Gold price is highly volatile due to macroeconomic, geopolitical, and monetary factors, making accurate forecasting difficult and increasing uncertainty in investment decisions. In this study, ARIMA is used for modeling linear patterns in the time series data, while an LSTM network captures the nonlinear relationships and temporal dynamics that are not captured by statistical models. The dataset consists of daily observations of gold prices between June 2022 and June 2025. The analysis involves cleaning and normalizing the data, splitting it into training and testing subsets, estimating ARIMA parameters, extracting residuals, and forecasting these residuals with LSTM. Performance evaluation is carried out through MAE, RMSE, and MAPE metrics. The hybrid framework compares favorably against standalone ARIMA and LSTM models in terms of all three metrics used for assessment. Empirical results show that the hybrid ARIMA–LSTM model produces lower forecasting errors than the individual models on all evaluation metrics. These findings validate that combining statistical time series modeling with neural sequence learning increases predictive reliability in volatile commodity markets. The proposed framework can be considered methodologically sound for gold price forecasting and subsequently may enhance informed decision-making within financial analysis as well as investment practice.
Super Encryption Cryptography for Land Certificate Data Security: A Case Study of the Jayapura City Land Agency Ray Setiawan Panyuwa; Suharyadi Universitas Kristen Satya Wacana
International Journal Software Engineering and Computer Science (IJSECS) Vol. 5 No. 3 (2025): DECEMBER 2025
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA), Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v5i3.5652

Abstract

This study introduces a lightweight, reproducible super-encryption framework designed to protect land certificate owner data at the Jayapura City Land Office. The system combines two classical algorithms—Rail Fence Cipher for transposition and Vigenère Cipher for substitution—through a structured, layered encryption pipeline implemented in Python. Testing was conducted on 50 simulated certificate owner names (10–15 characters each) under controlled conditions (Intel i5, 8 GB RAM, Windows 10). Black-box validation demonstrated 100% decryption accuracy with sub-10 ms total processing time per record. Robustness assessments revealed an average Shannon entropy increase of 41.6% and an avalanche rate of 47.8%, indicating enhanced ciphertext randomness. Results confirm that strategically layering classical ciphers delivers reliable confidentiality and integrity for small-scale, non-transactional datasets characteristic of land administration offices operating under resource constraints. The research offers a transparent, replicable model for securing identity fields and demonstrates the practical viability of super-encryption as a computationally efficient cryptographic solution for local government digital systems
Analysis of Internet of Things Based Smart Home Systems for Electricity Consumption Efficiency Emma Budi Sulistiarini; Cut Susan Octiva; Wasiran Wasiran; Giatika Chrisnawati; Maryadi Maryadi; Sri Asfiati
International Journal Software Engineering and Computer Science (IJSECS) Vol. 5 No. 3 (2025): DECEMBER 2025
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA), Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v5i3.5668

Abstract

The IoT technology has opened up new horizons in household energy management through smart home systems. Smart home systems are based on the integration of electronic appliances with sensors and actuators, which provide automated and remote control of domestic devices. This article assesses IoT-based smart home systems as a tool for enhancing electricity consumption efficiency in residential domains. The research uses a literature-based approach complemented by prototype development using current sensors, motion sensors, and internet-connected microcontroller modules to collect real-time data about the usage of electrical energy to recognize the patterns of energy consumption among household appliances. A comparative analysis between normal operating conditions and those enabled by smart home automation is carried out. Results show that IoT-based smart homes lower electricity consumption by controlling device operation according to real usage conditions such as turning off idle devices, adjusting lighting levels based on human presence, and allowing remote control of appliances. These results prove that IoT-based smart home systems can be effectively used for reducing household electricity demand in compliance with energy sustainability efforts within digitally connected residential environments.
Identification of Key Factors in Children's Toy Product Marketing Strategy through Entropy and Gain Analysis Siti Aliyah; Efani Desi; Mas Ayoe Elhias Nst; Enni Maisaroh; Fitri Pranita Nasution
International Journal Software Engineering and Computer Science (IJSECS) Vol. 5 No. 3 (2025): DECEMBER 2025
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA), Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v5i3.5690

Abstract

This study aims to analyze the factors influencing product sales success using the C4.5 algorithm data mining method implemented through the WEKA application. The research data consists of 65 instances with six main attributes, namely introduction, durability, price, size, quality, and description. The testing process is carried out using the 10-fold cross validation method to obtain an accurate classification model. The analysis results show that the Price attribute has the highest information gain value ±0.764, so it is designated as the root of the decision tree. Low prices supported by long product durability proved to be the most dominant combination in increasing sales. Conversely, high prices tended to decrease sales levels even though supported by good quality. The resulting classification model has an accuracy of 83.07%, with 54 data correctly classified out of a total of 65 data. These calculation results indicate that consumers are more sensitive to price than quality, so a marketing strategy that emphasizes competitive pricing with guaranteed product durability is the most effective approach to increase purchasing interest. This research is expected to contribute to business decision making, especially in determining product sales strategies in a competitive market.
Student Aspiration Processing Information System with Sentiment Analysis at Piksi Ganesha Polytechnic Maulidia Tuzahra; Johni S Pasaribu
International Journal Software Engineering and Computer Science (IJSECS) Vol. 5 No. 3 (2025): DECEMBER 2025
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA), Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v5i3.5719

Abstract

Student aspirations play an important role as a means of two-way communication to improve the quality of academic and non-academic services in higher education. However, manual aspiration submission systems often result in delays in follow-up and a lack of documentation. This study aims to design and implement a web-based student aspiration processing information system integrated with sentiment analysis. The development method used is Waterfall, with stages of requirements analysis, design, implementation, testing, and maintenance. The implementation was carried out using the PHP programming language and MySQL database. The main features of the system include registration, login, feedback form, feedback list, admin replies, and lexicon-based sentiment analysis. Testing using Black Box Testing showed that all functions ran according to user requirements (100% success rate), with an average system response time of 2.7 seconds and a user satisfaction rate of 92%. This system is capable of classifying aspirations into positive (46%), negative (38%), and neutral (16%) categories, thereby facilitating the evaluation of campus services. This research proves that the system is capable of accelerating the handling of aspirations by up to 40% compared to manual mechanisms and supports decision-making based on sentiment data.
A Comparative Analysis of Support Vector Machine and Artificial Neural Network Methods for Predicting Vocational High School Student Graduation Didin Sahrudin; Ferhat Aziz; Choirul Basir
International Journal Software Engineering and Computer Science (IJSECS) Vol. 5 No. 3 (2025): DECEMBER 2025
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA), Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v5i3.5742

Abstract

Identifying which students may struggle in examinations early on is a critical challenge in vocational schools. This study aims to create and compare two machine learning models to predict the graduation status of Vocational High School (SMK) students majoring in Software and Game Development (PPLG). This prediction is based on their Competency Skills Test (UKK) scores. We used data from 310 students and tested two methods: Support Vector Machine (SVM) and Artificial Neural Network (ANN). The results are very clear: the SVM model performed exceptionally well, achieving an accuracy of 99%. SVM was able to recognize both 'Competent' and 'Not Yet Competent' students in a balanced manner. Conversely, the ANN model's performance was poor, with an accuracy of only 66%. This occurred because the ANN failed to learn and simply guessed that all students would pass. This research concludes that SVM is a highly effective method to be used as an early warning system. With this system, schools can more quickly assist students who are at risk of failing. SVM achieved 99% accuracy with perfect precision for the Competent class and full recall for the Not Yet Competent class. ROC-AUC and PR-AUC indicated excellent separability and strong minority-class detection. ANN achieved only 66% accuracy, predicting all samples as Competent. Learning curves revealed stagnation and failure to learn minority class patterns. Additional baseline models (Logistic Regression, Random Forest) were tested, with SVM outperforming all others consistently. Statistical significance testing using McNemar's test confirmed that SVM provides significantly better classification performance than ANN (p < 0.01).
Advanced Persistent Threats Analysis and Intrusion Detection Systems Evaluation Dedy Wibowo; Taswanda Taryo; Ferhat Aziz
International Journal Software Engineering and Computer Science (IJSECS) Vol. 5 No. 3 (2025): DECEMBER 2025
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA), Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v5i3.5770

Abstract

- Advanced Persistent Threats are significant cybersecurity threats that employ covert and strategically planned operations to achieve long-term unauthorized access and data exfiltration. PT XYZ, a logistics company with considerable operational and customer data, is more susceptible to APTs, which is why the company decided to implement Wazuh as an open-source SIEM platform for improved intrusion detection capabilities. We assessed how effectively this IDS-SIEM implementation could detect and respond to APT scenarios by analyzing multi-source logs from Wazuh, Sysmon, and endpoint telemetry across PT XYZ’s PC infrastructure between June 3-30, 2025—capturing 35,333 records in total. Simulated APT attacks were carried out using Atomic Red Team with detection mapping based on MITRE ATT&CK tactics. Most of the early stages of attack phases were identified by Wazuh particularly Initial Access and Execution phases where the system logged 1,060 true positives; 8,537 true negatives; 563 false positives; and 440 false negatives at an accuracy rate of 91%. Normal traffic detection results were good with a precision of 0.95, recall of 0.94 F1-score at the same value whereas attack detection had a precision value of 0.65 with a recall of 0.71 giving it an F1 score of 0.68 making macro-averaged metrics fall at values such as 0.80 for precision and 0.82 for recall which further brought the F1 score up to 0.81 while weighted averages peaked at 0.91.Our results indicate that an open-source SIEM like Wazuh can be used effectively for the detection of APTs in logistics operations when configured appropriately using MITRE ATT&CK-based threat simulations – hence having real-world applicability towards improving cybersecurity defenses within this sector.
Optimization of Employee Burnout Prediction Using Explainable Boosting Machine, Long Short-Term Memory, and Extreme Gradient Boosting Methods in Human Resource Management at PT. XYZ Syahrul Kahfi; Sudarno Wiharjo; Abu Khalid Rivai
International Journal Software Engineering and Computer Science (IJSECS) Vol. 5 No. 3 (2025): DECEMBER 2025
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA), Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v5i3.5772

Abstract

- Employee burnout threatens organizational sustainability through reduced productivity, compromised mental health, and elevated turnover rates. Early detection remains critical for maintaining workforce stability. We address burnout prediction optimization at PT. XYZ through three advanced machine learning models: Explainable Boosting Machine (EBM), Long Short-Term Memory (LSTM), and Extreme Gradient Boosting (XGBoost). Our methodology incorporates structured data preprocessing, model construction, training protocols, and rigorous performance evaluation. We assessed models using MAE, RMSE, and R² for regression tasks, alongside Accuracy, Precision, Recall, F1-score, Confusion Matrix, Feature Importance, and ROC curves for classification. Cross-validation ensured robust evaluation, with burnout labels derived from established psychosocial factor assessments. Results reveal LSTM's superior performance at 0.99 accuracy, followed by EBM (0.96) and XGBoost (0.95). LSTM demonstrates exceptional capability in identifying subtle burnout patterns, while EBM delivers high interpretability regarding causal factors. These findings offer a data-driven framework for human resource management, enabling precise, proactive intervention through evidence-based decision-making.

Page 46 of 47 | Total Record : 465

 43   44   45   46   47 

Filter by Year

2021 2026


Reset
Filter By Issues
All Issue Vol. 6 No. 2 (2026): AUGUST 2026 Vol. 6 No. 1 (2026): APRIL 2026 Vol. 5 No. 3 (2025): DECEMBER 2025 Vol. 5 No. 2 (2025): AUGUST 2025 Vol. 5 No. 1 (2025): APRIL 2025 Vol. 4 No. 3 (2024): DECEMBER 2024 Vol. 4 No. 2 (2024): AUGUST 2024 Vol. 4 No. 1 (2024): APRIL 2024 Vol. 3 No. 3 (2023): DECEMBER 2023 Vol. 3 No. 2 (2023): AUGUST 2023 Vol. 3 No. 1 (2023): APRIL 2023 Vol. 2 No. 2 (2022): OCTOBER 2022 Vol. 2 No. 1 (2022): MAY 2022 Vol. 1 No. 2 (2021): AUGUST 2021 Vol. 1 No. 1 (2021): APRIL 2021 More Issue