cover
Contact Name
Hengki Tamando Sihotang
Contact Email
hengkitamando26@gmail.com
Phone
+6281381251442
Journal Mail Official
hengkitamando26@gmail.com
Editorial Address
Romeby Lestari Housing Complex Blok C, No C14 Deliserdang, North Sumatra, Indonesia
Location
Unknown,
Unknown
INDONESIA
International Journal of Basic and Applied Science
ISSN : 23018038     EISSN : 27763013     DOI : https://doi.org/10.35335/ijobas
International Journal of Basic and Applied Science provides an advanced forum on all aspects of applied natural sciences. It publishes reviews, research papers, and communications. Our aim is to encourage scientists to publish their experimental and theoretical results in as much detail as possible. There is no restriction on the length of the papers. The full experimental details must be provided so that the results can be reproduced. Electronic files and software regarding the full details of the calculation or experimental procedure, if unable to be published in a normal way, can be deposited as supplementary electronic material.
Arjuna Subject : Umum - Umum
Articles 134 Documents
Spatio-Temporal Disinformation Detection Using GNN–LSTM and Cross-Attention for South China Sea Information Analysis Adam Mardamsyah; Marsetio Marsetio; Bambang Irwanto; Robby Mochammad Taufik
International Journal of Basic and Applied Science Vol. 15 No. 2 (2026): Basic and Applied Science
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/ijobas.v15i2.915

Abstract

The rapid propagation of disinformation through social media presents a significant challenge because information diffusion is characterized by complex interactions among users and continuously evolving temporal patterns. Conventional deep-learning and transformer-based approaches primarily focus on textual or sequential representations and may not fully capture the structural and temporal characteristics of information propagation. This study proposes a spatio-temporal framework for disinformation detection that integrates Graph Neural Network (GNN)-based spatial representation, Long Short-Term Memory (LSTM)-based temporal modeling, and an adaptive cross-attention mechanism for spatial–temporal fusion. The GNN is employed to model relational dependencies within social-media interaction networks, while LSTM captures the temporal evolution of graph-based representations. Cross-attention is subsequently introduced to adaptively model the interaction between spatial and temporal representations rather than relying solely on fixed feature concatenation. The proposed framework is evaluated using a social-media dataset associated with the South China Sea and compared with CNN, LSTM, GNN, BERT, and GAT-BERT baselines. Experimental results show that the proposed model achieves 95.84% accuracy, 95.30% precision, 95.60% recall, and 95.45% F1-score, outperforming the strongest baseline, GAT-BERT, by 2.63 percentage points in accuracy and 2.55 percentage points in F1-score. The ablation analysis further demonstrates that integrating LSTM with GNN improves accuracy by 5.32 percentage points, while the subsequent incorporation of cross-attention provides an additional improvement of 3.74 percentage points. These findings indicate that adaptive spatial–temporal fusion contributes beyond the independent use of graph and sequential encoders and provides a potential decision-support approach for analyzing dynamic disinformation propagation in geopolitical social-media environments.
Slice-Group-Level Brain Tumor Classification Using CRNN-GRU Mohammed Z.M. Almadani; Maslita Abd Aziz; T. Zalizam T. Muda
International Journal of Basic and Applied Science Vol. 15 No. 2 (2026): Basic and Applied Science
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/ijobas.v15i2.944

Abstract

Interpreting brain MRI for tumor diagnosis is time-consuming and varies between raters, and single-slice decisions can be fragile. This paper compares two classification pipelines on the Brain Tumor Classification (MRI) Dataset from Kaggle (glioma, meningioma, pituitary, no-tumor) of T1-contrast-enhanced images. The first is a per-slice CNN. The second is a per-group CRNN-GRU that reads an ordered sequence of ten slices with a bidirectional GRU and inter-slice attention. Because the dataset provides no patient identifiers, the analysis unit is a surrogate slice group, and the splits are group-disjoint by construction; all models are compared at the group-level. The per-slice CNN reached 80.0% slice-level accuracy. Aggregated to the group-level, the same CNN reached 92.68% by majority voting and 95.12% by mean-probability pooling. The CRNN-GRU reached 90.2% in a single pass, and 87.8% with test-time augmentation. No pairwise difference is statistically significant (exact McNemar, all p >= 0.25). The results do not show that sequential modelling and inter-slice attention improve on simple probability aggregation on this dataset, and the simplest configuration was the most accurate. A content-level audit found a small number of images duplicated across partitions, so all figures should be read as upper bounds. These results describe internal performance on one dataset under group-disjoint evaluation with a content-level leakage audit and do not establish clinical generalization.
Financial News Sentiment Classification: A Comparative Evaluation of Lexicon-Based and Machine Learning Approaches Hasanul Fahmi Zuhri; Noor Azma Ismail; Fazidah Wahit; Amalia Amalia
International Journal of Basic and Applied Science Vol. 15 No. 2 (2026): Basic and Applied Science
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/ijobas.v8i2.873

Abstract

Financial news sentiment classification can support the extraction of market-relevant information from unstructured financial text. This study compares a general-purpose lexicon-based method, Valence Aware Dictionary and Sentiment Reasoner (VADER), with three supervised classifiers: Random Forest, Multinomial Naive Bayes, and linear Support Vector Machine (SVM). The experiments use 4,846 labelled statements from the Financial PhraseBank dataset to classify sentiment into positive, neutral, and negative categories. The supervised classifiers use term frequency–inverse document frequency (TF-IDF) features and an 80:20 train-test split, while VADER serves as a rule-based baseline. Based on the reported evaluation, SVM achieves the highest accuracy (0.76) and macro F1-score (0.69), followed by Random Forest, with an accuracy of 0.75 and a macro F1-score of 0.66. VADER yields the lowest reported performance, with an accuracy of 0.55 and a macro F1-score of 0.48. The confusion matrix indicates that positive and negative statements are frequently misclassified as neutral. These findings suggest that supervised classifiers provide stronger sentiment-classification performance than the general-purpose lexicon under the evaluated conditions. However, the results do not establish direct improvements in financial-risk forecasting, and further validation is required to assess generalisability across datasets and market conditions
Agentic AI-Enabled Autonomous Business Process Management: Design and Evaluation of a Multi-Agent Workflow System (MAWS) Bambang Saras Yulistiawan; Dwi Arman Prasetya; Rohani Situmorang; Hengki Tamando Sihotang
International Journal of Basic and Applied Science Vol. 15 No. 2 (2026): Basic and Applied Science
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/ijobas.v15i2.921

Abstract

Traditional Business Process Management (BPM) faces significant challenges in addressing the increasing complexity, uncertainty, and dynamic nature of modern business environments due to its reliance on static rule-based automation approaches. Although Artificial Intelligence (AI) has been increasingly integrated into BPM through Intelligent Process Automation, process mining, and predictive analytics, most existing solutions remain focused on task-level automation and have not achieved process-level autonomy. This limitation highlights the need for autonomous workflow architectures capable of adaptive decision-making and dynamic process orchestration. To address this gap, this study proposes a Multi-Agent Workflow System (MAWS) as an Agentic Artificial Intelligence-based framework for autonomous Business Process Management. The research adopts the Design Science Research (DSR) methodology, encompassing problem identification, artifact design and development, demonstration, and evaluation through five complementary validity dimensions: instrument validity, technical validity, design validity, purpose validity, and generalization. The evaluation results indicate that MAWS improves process execution efficiency, reduces human intervention requirements, and enhances processing accuracy compared with traditional Robotic Process Automation (RPA) approaches. Furthermore, the autonomous agents embedded within MAWS demonstrate capabilities for goal-oriented reasoning, multi-step planning, self-correction, and adaptive workflow orchestration under dynamic operational conditions. The primary contribution of this research lies in the development and validation of a BPM architecture based on multi-agent reasoning that bridges the gap between Agentic AI theory and enterprise-scale autonomous workflow implementation. The findings suggest that Agentic AI has the potential to transform BPM from rule-driven automation into goal-driven autonomous operations, while emphasizing the importance of robust AI governance mechanisms to ensure transparency, accountability, and operational trustworthiness.

Filter by Year

2019 2026


Filter By Issues
All Issue Vol. 15 No. 2 (2026): Basic and Applied Science Vol. 15 No. 1 (2026): Basic and Applied Science Vol. 14 No. 4 (2026): March: Computer Science Vol. 14 No. 3 (2025): Optimization and Artificial Intelligence Vol. 14 No. 2 (2025): Optimization and Computer Science Vol. 14 No. 1 (2025): Computer Science, Engineering, Basic and Applied mathematics Science Vol. 13 No. 4 (2025): Computer Science, Engineering, Basic and Applied mathematics Science Vol. 13 No. 3 (2024): Dec: Optimization and Artificial Intelligence Vol. 13 No. 2 (2024): Sep: Basic and Applied Science Vol. 13 No. 1 (2024): June: Basic and Aplied Science Vol. 12 No. 4 (2024): March: Basic and Applied Science Vol. 12 No. 3 (2023): December: Basic and Applied Science Vol. 12 No. 2 (2023): Sep: Basic and Applied Science Vol. 12 No. 1 (2023): June: Basic and Applied Science Vol. 11 No. 4 (2023): March: Basic and Applied Science Vol. 11 No. 3 (2022): December: Basic and Applied Science Vol. 11 No. 2 (2022): Sep: Basic and Applied Science Vol. 11 No. 1 (2022): June: Basic and Applied Science Vol. 10 No. 4 (2022): March: Basic and Applied Science Vol. 10 No. 3 (2021): December: Basic and Applied Science Vol. 10 No. 2 (2021): September: Basic and Applied Science Vol. 10 No. 1 (2021): June: Basic and Applied Science Vol. 9 No. 4 (2021): March: Basic and Applied Science Vol. 9 No. 3 (2020): December: Basic and Applied Science Vol. 9 No. 2 (2020): September: Basic and Applied Science Vol. 9 No. 1 (2020): June: Basic and Applied Science Vol. 8 No. 4 (2020): March: Basic and Applied Science Vol. 8 No. 3 (2019): December: Basic and Applied Science Vol. 8 No. 2 (2019): September: Basic and Applied Science More Issue