Garuda - Garba Rujukan Digital

Article Per Year (5 Year)

All

Data Science: Journal of Computing and Applied Informatics

JoCAI
Website

Published by Universitas Sumatera Utara

ISSN : 25806769 EISSN : 2580829X DOI : -

Core Subject : Science,

Computer Science & IT

Data Science: Journal of Computing and Applied Informatics (JoCAI) is a peer-reviewed biannual journal (January and July) published by TALENTA Publisher and organized by Faculty of Computer Science and Information Technology, Universitas Sumatera Utara (USU) as an open access journal. It welcomes full research articles in the field of Computing and Applied Informatics related to Data Science from the following subject area: Analytics, Artificial Intelligence, Bioinformatics, Big Data, Computational Linguistics, Cryptography, Data Mining, Data Warehouse, E-Commerce, E-Government, E-Health, Internet of Things, Information Theory, Information Security, Machine Learning, Multimedia & Image Processing, Software Engineering, Socio Informatics, and Wireless & Mobile Computing. ISSN (Print) : 2580-6769 ISSN (Online) : 2580-829X Each publication will contain 5 (five) manuscripts published online and printed. JoCAI strives to be a means of periodic, accredited, national scientific publications or reputable international publications through printed and online publications.

Arjuna Subject : -

Articles 95 Documents

6 7 8 9 10

Optimizing K-Nearest Neighbor Using Ant Colony Optimization for Heart Disease Classification Arini, Florentina Yuni; Pongthanoo, Patcharanikarn; Salsabila, Kansa Maulina; Raihan, Muhammad; Muzakki, Naufal Habib
Data Science: Journal of Computing and Applied Informatics Vol. 10 No. 1 (2026): Data Science: Journal of Computing and Applied Informatics (JoCAI)
Publisher : Talenta Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32734/jocai.v10.i1-23647

Heart disease is one of leading causes of death globally, making early detection essential for improving clinical outcomes. This study presents a heart disease prediction approach using the K-Nearest Neighbor (KNN) algorithm, addressing class imbalance with Synthetic Minority Over-sampling Technique (SMOTE) and enhancing feature selection through Ant Colony Optimization (ACO). Exploratory data analysis identified age, gender, cholesterol, blood pressure, e xercise-Induced Angina (EIA), ST-segment depression, number of affected vessels, and thalassemia status as key indicators of disease severity. KNN model achieved 0.90 accuracy with balanced precision and recall. The employment of SMOTE improved sensitivity for the minority class, slightly reducing overall accuracy to 0.88. However, ACO as hyperparameter tuning KNN able to produce promising accuracy 0.91. This result indicate that combining KNN with metaheuristic optimization provides a reliable, interpretable method for heart disease prediction, offering valuable support for clinical decision-making and risk assessment.

Applied Data Science Framework for Incremental and Interpretable Childhood Growth Risk Screening Puguh Hiskiawan; Theresia Puspa Wijayanti; Srava Chrisdes Antoro; Metta Gautama
Data Science: Journal of Computing and Applied Informatics Vol. 10 No. 2 (2026): Data Science: Journal of Computing and Applied Informatics (JoCAI) In Press
Publisher : Talenta Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32734/jocai.v10i2.24956

Childhood growth monitoring plays an important role in the early identification of children who may experience developmental risks related to nutrition and health conditions. Conventional screening methods typically rely on anthropometric measurements that may not always be consistently obtained in community-based health environments. This study proposes an applied data science framework for incremental and interpretable screening of childhood growth risk using pose-derived body structure features combined with demographic and anthropometric attributes. Pose landmarks are extracted using the MediaPipe framework and integrated with variables including age, gender, and body weight to construct predictive models. Several machine learning algorithms are evaluated, including Logistic Regression, Random Forest, Gradient Boosting, XGBoost, K-Nearest Neighbors, and a Soft Voting Ensemble. Experimental evaluation using five-fold stratified cross-validation demonstrates that Logistic Regression achieves the highest predictive performance with a mean ROC-AUC of 0.901. Ablation analysis further indicates that incorporating pose-derived landmarks significantly improves classification performance compared with using demographic attributes alone. Interpretability analysis based on odds ratios highlights the contribution of pose features and demographic variables to prediction outcomes.

Size-Controlled Opcode Ablation for Smart Contract Vulnerability Detection Astrid Pranadani; Dhani Ariatmanto
Data Science: Journal of Computing and Applied Informatics Vol. 10 No. 2 (2026): Data Science: Journal of Computing and Applied Informatics (JoCAI) In Press
Publisher : Talenta Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32734/jocai.v10i2.26398

Smart contract vulnerability detection requires evaluation protocols that separate real representation signal from dataset-specific artifacts. DIVE provides lifecycle-based tabular features for Ethereum smart contracts, but benchmark performance alone cannot show whether a dominant feature group is useful or only benefits from having many columns. This study examines Opcode Distribution features using 22,330 contracts, 397 processed features, and eight DASP-aligned vulnerability labels. Five multi-label learning configurations were evaluated under 3 x 5 repeated cross-validation, followed by global feature-group ablation, size-controlled random opcode ablation, per-label degradation analysis, cumulative stability analysis, and opcode-profile group-aware robustness checking. MultiOutput LightGBM achieved the best baseline performance, with Micro-F1 of 0.91396, Macro-F1 of 0.82464, and Macro-PR-AUC of 0.90146. Removing the full Opcode Distribution group reduced Macro-F1 to 0.78745, while removing a same-sized random opcode subset produced Macro-F1 of 0.82404. The findings indicate that Opcode Distribution acts as a collective predictive representation rather than a feature-count artifact, without implying causal vulnerability mechanisms.

SecureLite: Lightweight Vulnerability Detection on CVEFixes with TF‑IDF, Gradient Boosting, and a Tiny Transformer plus LLM‑Assisted Triage Qi Xin
Data Science: Journal of Computing and Applied Informatics Vol. 10 No. 2 (2026): Data Science: Journal of Computing and Applied Informatics (JoCAI) In Press
Publisher : Talenta Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32734/jocai.v10i2.24898

Static application security testing remains difficult to deploy at scale in Python repositories because practical tools must be accurate, fast, and interpretable under extreme class imbalance. This paper introduces SecureLite, a lightweight pipeline that combines (i) a compact vulnerability detector trained on statement‑annotated data and (ii) an LLM‑assisted triage stage that converts detector evidence into actionable fix guidance. We conduct experiments on the DetectVul/CVEFixes dataset, using its provided train/test splits (4,584/1,146 Python functions). Each function is represented as a sequence of statements, statement types, and per‑statement vulnerability labels. We convert these labels into a function‑level target and compare four efficient detectors: token TF‑IDF + logistic regression (SGD), type‑aware token TF‑IDF, character TF‑IDF, and a LightGBM model over 15 static features. We additionally train a tiny Transformer encoder (TinyVulFormer‑XS) to test whether a minimal self‑attention model can compete with linear baselines under small‑data constraints. On the test set, the best lightweight models (character TF‑IDF and type‑aware token TF‑IDF) achieve AUROC 0.925 and AUPRC 0.381 with an F1 score of 0.421 at a 0.5 decision threshold, outperforming both static‑feature boosting and the tiny Transformer. We further analyze threshold sensitivity, error modes, and how LLM triage can reduce analyst time by proposing fixes and unit tests for high‑risk predictions. The resulting system offers a reproducible, CPU‑friendly baseline for Python vulnerability screening and a practical blueprint for integrating lightweight detection with LLM‑guided remediation.

Applied Informatics: Librarian Scepticism of Artificial Intelligence in Information Retrieval — Does AI Promote Library Usage or Displace It? Evidence from the Nigerian University Library Landscape: Applied Informatics: Librarian Scepticism of Artificial Intelligence in Information Retrieval Kayode Sunday John Dada
Data Science: Journal of Computing and Applied Informatics Vol. 10 No. 2 (2026): Data Science: Journal of Computing and Applied Informatics (JoCAI) In Press
Publisher : Talenta Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32734/jocai.v10i2.25832

Librarian scepticism towards artificial intelligence (AI) tools in information retrieval is routinely reframed in African higher education discourse as a capacity gap. This paper challenges that reframing. Using a convergent mixed-methods design — a survey of 214 librarians across 27 Nigerian universities, 32 semi-structured interviews, and documentary analysis of 81 institutional documents spanning 2015–2025 — the study pursues three objectives: (1) to examine the nature and structural determinants of librarian scepticism towards AI-assisted retrieval; (2) to determine whether AI adoption promotes or displaces substantive library usage in resource-constrained institutions; and (3) to investigate gendered and geographic dimensions of differential AI scepticism. Findings confirm that scepticism is epistemically rational and structurally grounded. In institutions where AI chatbots generate citation lists that the local collection cannot fulfil, the information outcome is zero regardless of interface sophistication — what the study theorises as an information supply chain failure (ISCF), structurally analogous to a health system that achieves a correct diagnosis but cannot dispense the medication. Only 27.1% of librarians reported that AI-generated references were typically retrievable locally (17.8% in rural institutions). Female librarians in northern Nigeria reported the highest scepticism and the lowest institutional support. No sampled institution held an operational AI-resource integration policy. The study concludes that AI adoption without collection integrity undermines library utility, and recommends a policy-first, resource-second integration framework.

Page 10 of 10 | Total Record : 95

6 7 8 9 10

Filter by Year

2017 2026

Filter By Issues

Home Page

OAI Link

Editorial Team

Contact

Reviewer

Google Scholar

Contact Name
Ainul Hizriadi, S.Kom., M.Sc.

Contact Email
ainul.hizriadi@usu.ac.id

Phone
-

Journal Mail Official
jocai@usu.ac.id

Editorial Address
-

Location
Kota medan,

Sumatera utara

INDONESIA

Abstract

Abstract

Abstract

Abstract

Abstract

Home Page

OAI Link

Editorial Team

Contact

Reviewer

Google Scholar

Contact Name Ainul Hizriadi, S.Kom., M.Sc.

Contact Email ainul.hizriadi@usu.ac.id

Phone -

Journal Mail Official jocai@usu.ac.id

Editorial Address -

Location Kota medan, Sumatera utara INDONESIA

Abstract

Abstract

Abstract

Abstract

Abstract

Contact Name
Ainul Hizriadi, S.Kom., M.Sc.

Contact Email
ainul.hizriadi@usu.ac.id

Phone
-

Journal Mail Official
jocai@usu.ac.id

Editorial Address
-

Location
Kota medan,

Sumatera utara

INDONESIA