cover
Contact Name
Ronal Watrianthos
Contact Email
ronal.watrianthos@gmail.com
Phone
+6281263621335
Journal Mail Official
joseitjournal@gmail.com
Editorial Address
Professional Organization - Ikatan Ahli Informatika Indonesia (IAII) / Indonesian Informatics Experts Association Jalan Jati Padang Raya No. 41 Jati Padang Pasar Minggu 12540 South Jakarta - Indonesia http://iaii.or.id/
Location
Unknown,
Unknown
INDONESIA
Journal of Systems Engineering and Information Technology
ISSN : -     EISSN : 2829310X     DOI : https://doi.org/10.29207/joseit.*
Core Subject : Science,
International Journal of Systems Engineering and Information Technology (JOSEIT) is an international journal published by Ikatan Ahli Informatika Indonesia (IAII / Association of Indonesian Informatics Experts). The research article submitted to this online journal will be peer-reviewed. The accepted research articles will be available online (free download) following the journal peer-reviewing process. The language used in this journal is English. JOSEIT is a peer-reviewed, blinded journal dedicated to publishing quality research results in Computers Engineering and Information Technology but is not limited implicitly. All journal articles can be read online for free without a subscription because all journals are open-access.
Articles 53 Documents
An Enhanced Comprehensive Study Towards Predicting Cardiovascular Disease Using Machine Learning Techniques. Anil Kumar Prajapati; Umesh Kumar Singh; Ramji Yadav
Journal of Systems Engineering and Information Technology (JOSEIT) Vol. 5 No. 1 (2026)
Publisher : Ikatan Ahli Informatika Indonesia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/joseit.v3i3.7585

Abstract

In recent years, heart and cardiovascular diseases have become more common, causing a significant increase in mortality rates worldwide. Data from various organisations highlights the severity of heart disease, which remains a major concern. Accurately and quickly identifying severe conditions, such as heart disease, is vital for effective prevention. Techniques such as data mining, machine learning, and deep learning have been used in medicine to reliably detect heart disease. However, these methods depend on data that can change over time. To ensure accurate detection, proper use of historical data is essential; otherwise, results can be inaccurate. Machine learning techniques produce outcomes based on mathematical calculations, so data cleaning and refinement are necessary. Disease-related data can include text, numbers, and images, which may vary widely, requiring extensive stratification, normalisation, cleaning, encoding, and randomisation; otherwise, results may be biased. Our previous review article addressed a specific challenge related to the CVD Prediction Model. This Enhanced review primarily examines how machine learning techniques operate on medical datasets and their effectiveness in predicting cardiovascular diseases (CVD). It also aims to analyse datasets, features, and machine learning methods used in CVD prediction
Can Artificial Intelligence Fix Bad Environmental Regulation? Evidence from Green Total Factor Productivity in China Lihua Peng; Xingtong Lin; Qiuhan Luo
Journal of Systems Engineering and Information Technology (JOSEIT) Vol. 3 No. 2 (2024)
Publisher : Ikatan Ahli Informatika Indonesia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/joseit.v3i2.8451

Abstract

Environmental regulation is often assumed to work the same way regardless of how it is designed — yet this study shows that command-and-control and market-incentive instruments pull green productivity in opposite directions, and that artificial intelligence (AI) does not treat them equally either. Drawing on panel data from 281 Chinese prefecture-level cities over 2012–2024, this study finds that command-and-control regulation, measured through text analysis of local government work reports, significantly suppresses green total factor productivity (GTFP) by raising compliance costs, while market-incentive regulation, measured as the ratio of pollutant discharge fee revenue to GDP, significantly promotes it by channeling price signals into innovation. GTFP is estimated using the SBM-ML index, which incorporates labor, capital, and energy inputs together with industrial pollution as an undesirable output. Interaction-term estimates further show that local AI development attenuates the negative effect of command-and-control regulation while amplifying the positive effect of market-incentive regulation — AI acts as a “buffer” for coercive regulation and an “amplifier” for market-based regulation, rather than a uniform productivity booster. The findings suggest that AI cannot simply substitute for well-designed environmental policy, but it can make both good and bad policy design matter less — or more — than they otherwise would.
Efficient Chain-of-Thought Guided Instruction Tuning for Graph Representation Learning Wang Yiming; LI Qian; Du Yuntao; Cui Lizhen; Yan Zhongmin
Journal of Systems Engineering and Information Technology (JOSEIT) Vol. 3 No. 3 (2024)
Publisher : Ikatan Ahli Informatika Indonesia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/joseit.v3i3.8453

Abstract

Large language models (LLMs) reason well over natural language but do not naturally understand graph structure, and directly applying them to graph data runs into two persistent obstacles: a wide gap between the graph and text modalities, and the difficulty of encoding structural information in a way an LLM can use. Existing graph-instruction-tuning methods typically close this gap with simple linear projections and question-answer pairs that carry no explicit reasoning trace, which leaves cross-modal alignment shallow and drives up fine-tuning cost. This paper proposes GraphCoT, a graph representation learning method built on efficient chain-of-thought (CoT) fine-tuning. Its core is a high-quality CoT distillation mechanism in which a strong teacher model generates instruction data containing explicit intermediate reasoning paths, which explicitly teaches a student model to reason in multiple steps from only a small amount of training data. GraphCoT further introduces a graph-text alignment module that maps graph representations into the language embedding space, and a lightweight two-stage training strategy that aligns modalities before task-specific fine-tuning, which keeps training cost low while preserving both reasoning quality and transferability. Node classification and link prediction experiments on multiple benchmark datasets show that GraphCoT outperforms mainstream graph learning methods in accuracy and generalization, confirming the effectiveness of the CoT distillation mechanism and the alignment strategy for graph representation learning.
Optimisation of Biotechnological Processes through a Combined Algorithm M Petrov
Journal of Systems Engineering and Information Technology (JOSEIT) Vol. 3 No. 2 (2024)
Publisher : Ikatan Ahli Informatika Indonesia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/joseit.v3i2.8454

Abstract

Choosing a good initial point matters as much as the optimisation method itself when tuning a biotechnological process, yet the two most common approaches to getting there each carry a cost: fuzzy-set methods give a direct, transparent solution but scale poorly once the decision space grows large, while random-search methods scale well but do not on their own guarantee a well-chosen starting point. This paper develops a combined algorithm that pairs a random-search-with-back-step (RSBS) method for locating a good initial point with a fuzzy-sets-theory (FST) optimisation stage, so that the random search narrows the search region before the fuzzy method is asked to discretise it — directly addressing the scale limitation that otherwise limits fuzzy optimisation. The combined algorithm is applied to the initial-condition and feeding-rate optimal control problem for the fed-batch biotransformation of whey by a strain of Kluyveromyces marxianus var. lactis MC5 in a laboratory stirred-tank bioreactor, raising the optimisation.
Quantifying Target Leakage in Rule-Derived Mental Health Screening Labels Rozi Meri; Ikhsan; Dian Eka Putra; Sofia Yosse; Ismael
Journal of Systems Engineering and Information Technology (JOSEIT) Vol. 3 No. 3 (2024)
Publisher : Ikatan Ahli Informatika Indonesia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/joseit.v3i3.8470

Abstract

Publicly hosted tabular datasets increasingly package screening-questionnaire items alongside computed, not clinically observed, risk and severity labels. This creates a risk of target leakage: if a label is a deterministic function of the same features given to a classifier, reported predictive performance measures rule reconstruction, not screening validity. We audit a recent IEEE DataPort dataset (n = 2,005) scoring 27 Likert items across five conditions – ADHD, Autism Spectrum Disorder (ASD), Social Pragmatic Communication Disorder (SPCD), Depression, and Anxiety – each with a binary risk flag and a three-level severity label. The dataset's documentation discloses that every label is generated from a threshold or tertile rule on the summed items of its own condition, yet its usage instructions recommend fitting Random Forest or XGBoost with SHAP directly on the 27 raw items. We verify the documented rule empirically, then compare a trivial single-feature decision stump (the summed score) against a 300-tree Random Forest trained on all 27 items, under identical 5-fold stratified cross-validation, across all ten condition-by-task combinations (5 conditions × {risk, severity}). The single-feature stump matches or exceeds the 27-feature ensemble in every combination, reaching 100% cross-validated accuracy on nine of ten targets. Random Forest feature importance further shows 72–88% of predictive weight concentrated on each condition's own items. These results indicate the pipeline the dataset recommends reconstructs a disclosed arithmetic rule rather than learning a clinically meaningful pattern; any predictive-validity study on this dataset should exclude a condition's own summed items from that condition's feature set.
Predicting Student Exam Performance Using Explainable Regression Models: A Learning Analytics Study Thuy Thi Vo; Vu Thien
Journal of Systems Engineering and Information Technology (JOSEIT) Vol. 3 No. 3 (2024)
Publisher : Ikatan Ahli Informatika Indonesia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/joseit.v3i3.8471

Abstract

Identifying which behavioral and demographic factors most strongly predict student academic performance is a long-standing goal of learning analytics. We apply linear regression, ridge regression, random forest, and gradient boosting to a 1,000-student behavioral and demographic dataset. Five-fold cross-validated R² shows that linear and ridge regression (R²=0.656) explain more variance than the ensemble methods (R²≈0.57), indicating a primarily additive structure in the data. To test this additive structure for residual non-linear or interaction effects and to obtain individual-level explanations, we apply SHapley Additive exPlanations (SHAP) to the random forest model via TreeExplainer, and cross-validate the resulting feature ranking against the standardized coefficients of the top-performing linear model. SHAP analysis identifies study time as the dominant predictor, with a mean |SHAP| of 4.93 points (approximately 4.1 exam-score points per additional study hour), followed by prior academic performance (mean |SHAP|=3.44) and attendance (mean |SHAP|=2.38). Internet access and part-time employment emerge as statistically meaningful binary factors (mean score gap: +5.0 and −3.3 points respectively), consistent with literature on the digital divide and academic workload. Parental education, gender, and extracurricular participation contribute negligible SHAP values (mean |SHAP| ≤0.16), a pattern that also holds for the corresponding linear coefficients. These results suggest that actionable behavioral variables – particularly study time and attendance – account for the bulk of explainable variance in examination outcomes, while fixed demographic characteristics contribute little incremental predictive power.
Near-Trivial Separability and Statistical Power Limitations in a Small Anthrax Symptom Dataset Khin Hnin Naing
Journal of Systems Engineering and Information Technology (JOSEIT) Vol. 3 No. 3 (2024)
Publisher : Ikatan Ahli Informatika Indonesia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/6n7m2c61

Abstract

A recently released IEEE DataPort dataset frames 49 binary-labeled livestock symptom records as a resource for few-shot learning and robust classification under data scarcity. We audit the dataset's suitability for this role by computing per-symptom discriminative statistics and then assessing whether n=49 leaves meaningful room for the complex models the dataset is intended to evaluate. A single symptom – the presence of bloody discharge – reconstructs the anthrax label with 91.8% accuracy (sensitivity 77.8%, specificity 100.0%, MCC φ=0.83, 95% Wilson CI [80.8%, 96.8%]), and adding a second symptom (edema) raises this to 93.9%. A leave-one-out cross-validated logistic regression and a 300-tree random forest achieve 89.8% and 93.9% accuracy respectively, numerically no better than the trivial single-symptom rule; paired McNemar tests confirm that neither classifier's errors differ significantly from those of the trivial rule (p=1.00 for both). A power analysis shows that n=49 provides only 9.1% power to detect a 2.2-percentage-point improvement over the trivial rule at α=0.05. Reliably detecting even a 6.2-point improvement would require n≈90. These results indicate that this dataset cannot discriminate between trivial threshold rules and genuinely learned classifiers, and any reported accuracy near 92–94% on this dataset should be interpreted as evidence of near-trivial separability, not few-shot learning capability.
Does Bigger Beat Simpler? Multilayer Perceptrons versus Recurrent Networks in Trade Export Price Forecasting Kim Ji Hun; Lee Jee Hang
Journal of Systems Engineering and Information Technology (JOSEIT) Vol. 4 No. 3 (2025)
Publisher : Ikatan Ahli Informatika Indonesia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/8szpka26

Abstract

South Korea’s trade agency, KOTRA, publishes annual trade data under the Ministry of Trade, Industry and Energy that reports gross domestic product (GDP), customs tariffs, an ease-of-business score, and the previous- and current-year price for each traded item, broken down by item and by country. The sheer volume of items and years this data accumulates over makes it hard to extract a meaningful signal by hand, and manual analysis every year is costly in both time and expertise. This paper implements and evaluates a multilayer-perceptron (MLP) model that learns from a single year of this large-scale data to forecast next-year item-level export prices at low computational and human cost. The deep-learning model is first compared against a conventional multivariate-regression model, where it shows a statistically better prediction error and shorter training time. Because export-price data plausibly carries time-series structure, the same task is also modeled with a fully connected MLP and with a recurrent neural network (RNN). While the recurrent model generalizes somewhat better to unseen data, the MLP achieves the stronger overall prediction accuracy on this single-year dataset. Given a longer time series in future work, a recurrent or Transformer-based deep-learning model is expected to improve export-price prediction further.
A TF-IDF Symptom-Matching Framework for Tabular Knowledge-Based Tomato Disease Decision Support Akinde Ogunmolu
Journal of Systems Engineering and Information Technology (JOSEIT) Vol. 4 No. 3 (2025)
Publisher : Ikatan Ahli Informatika Indonesia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/bnnejy35

Abstract

Early and accurate field identification of tomato diseases is critical for timely intervention, yet farmers in resource-limited settings frequently lack access to expert diagnosis. This paper proposes a lightweight, knowledge-based decision support system (DSS) for differentiating nine economically important tomato diseases and pests using a recently published tabular knowledge base. The DSS operates in two stages: first, it represents each disease's symptom description as a TF-IDF vector (unigram and bigram, lemmatized, with domain-specific stopword filtering) and retrieves the best-matching disease via cosine similarity to an observed symptom query; second, it refines the ranking using a rule-based environmental condition filter (warm-humid or cool-wet) when field context is available. We evaluate the framework on 121 individual symptom sentences extracted from the knowledge base as independent field-observation queries. The symptom-similarity stage alone achieves a sentence-level top-1 retrieval accuracy of 99.2% (120/121 sentences), with only one Mosaic Virus sentence – the non-specific phrase ‘stunted growth and reduced yields’ – initially misranked. Symptom cosine similarity analysis reveals that Target Spot is the most structurally confusable disease, sharing the highest off-diagonal similarity with Early Blight (0.144), Late Blight (0.137), and Septoria (0.131). Treatment complexity analysis further shows a clinically important distinction between fungal/pest diseases (20 or more chemical treatment options each) and viral diseases (Mosaic Virus: 2; Yellow Leaf Curl Virus: 1), where chemical interventions are ineffective and prevention-only strategies are documented.
Data Integrity and Its Impact on Machine Learning Models: A Critical Audit of a Lung Cancer Dataset Syeda Afroz Fatima; Nida Mussarat; Swarna Jaya Vardhan
Journal of Systems Engineering and Information Technology (JOSEIT) Vol. 4 No. 3 (2025)
Publisher : Ikatan Ahli Informatika Indonesia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/dq775h27

Abstract

Subscription-gated IEEE DataPort datasets are difficult to verify before reuse because independent inspection requires access most researchers do not have; we obtained direct access to one such case. We apply a six-stage, three-layer audit (provenance, structural/duplication plausibility, target validity) to “An Anonymized Feature-Based Dataset for Lung Cancer Prediction Using Explainable AI Models,” a 15-feature, binary-symptom-checklist dataset presented as newly compiled to support explainable-AI research. The delivered file contains 2,457 rows, of which 2,132 (86.8%) are exact duplicates of another row, leaving 325 unique records. The dataset’s own hosting page links a peer-reviewed “Research Article” co-authored by two of this dataset’s three listed authors; that 2024 publication states its dataframe “contains 309 entries” with “no null values” — figures that match neither the delivered file’s row count nor its 325 unique records. The same publication’s introduction and methods describe a multi-source study drawing on major imaging and genomic repositories, none of which appear in the delivered file or in the publication’s own reported results, which instead use the same 16-column schema and encoding as a long-circulating public dataset. Within the 325 unique records, duplication is class-dependent: unique cancer-negative rows are repeated 14.1 times on average (up to 86), versus 4.5 times for cancer-positive rows, shifting the delivered file’s class balance relative to the unique data without documentation. Separately, the linked publication reports identical accuracy, precision, recall, F1, and AUC-ROC for five structurally different classifiers, a pattern inconsistent with independent model evaluation.