Garuda - Garba Rujukan Digital

K-Cube Consensus Clustering with Centroid Improvement and Variance-Based Metrics on High-Dimensional Data Efori Bu'ulolo; Poltak Sihombing; Sutarman Sutarman; Mohammad Andri Budiman
Journal of Applied Data Sciences Vol 7, No 2: May 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i2.1209

High-dimensional and multidimensional cube data structures (K-Cube) are posing a significant challenge for conventional clustering algorithms due to the effect of dimensionality, uniform feature weight assumptions, and loss of hierarchical information. Therefore, this study aimed to propose K-Cube Consensus Clustering framework, which integrates Variance-Based Centroid Refinement, Weighted Distance Metrics, and consensus voting mechanism to overcome the challenges of high-dimensional cube data. The proposed method systematically clustered all dimensions and sub-dimensions of cube data, refined centroid by emphasizing more stable low-variance attributes, and applied adaptive distance weighting based on variance-derived feature weights integrated into the distance metric to improve cluster assignment. The final clusters were obtained through majority voting of the clustering results for each dimension. Unlike existing consensus clustering methods that operate on flat data representations or combine independent clustering results, the proposed framework explicitly exploits the hierarchical structure of multidimensional cube data by clustering dimensions and sub-dimensions prior to consensus integration. Moreover, variance-based centroid refinement and weighted distance metrics are jointly embedded within each cube dimension rather than applied as isolated enhancements. This hierarchy-aware design preserves cube semantics while simultaneously improving centroid stability and distance adaptivity, resulting in a distinct and scalable clustering framework for complex high-dimensional cube data. The framework processes cube dimensions independently with iterative convergence control, enabling scalable application to large-scale cube data. The results of synthetic and real-world high-dimensional datasets, including cube data with approximately 2.2 million instances, showed that the proposed method consistently outperformed K-Means, K-Medoids, and Hamiltonian formulations. The method produced lower SSE such as 3,179,328 on Arcene and 1,422.21 on Lung Cancer, higher Silhouette Score of approximately 0.5718 and 0.4905 for consensus results, better cluster stability of 0.9947, and faster convergence. These results confirmed the effectiveness of K-Cube Consensus Clustering in producing stable and meaningful clusters in large-scale high-dimensional data applications.

Pengembangan Otomasi Inventaris Farmasi Rumah Sakit Gigi dan Mulut dengan Metode Convolutional Neural Network Khairul Abdi; Amalia; Mohammad Andri Budiman
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 7 No. 4 (2026): Juni 2026
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v7i4.9832

Pengelolaan inventaris farmasi di Rumah Sakit Gigi dan Mulut memerlukan proses yang cepat, teliti, dan terdokumentasi karena ketersediaan obat serta bahan kedokteran gigi berpengaruh langsung terhadap kelancaran pelayanan klinis. Penelitian ini mengembangkan prototipe otomasi inventaris berbasis citra menggunakan model deteksi objek YOLO11s yang dibangun di atas prinsip Convolutional Neural Network. Dataset terdiri atas 2.562 citra, 11 kelas produk, dan 5.486 anotasi bounding box yang dibagi menjadi data latih, validasi, dan uji dengan rasio 70:15:15. Tahapan penelitian meliputi akuisisi citra, anotasi, quality control dataset, praproses, augmentasi, pelatihan, evaluasi, serta perancangan integrasi hasil deteksi ke rekap inventaris. Pada data uji terbatas, model menghasilkan precision 99,37%, recall 98,86%, mAP@0.5 99,41%, dan mAP@0.5:0.95 90,03%. Hasil ini menunjukkan bahwa YOLO11s berpotensi membantu pengenalan jenis produk, lokalisasi objek, dan perhitungan jumlah item pada skenario inventaris farmasi yang tercakup dalam dataset. Namun, klaim kinerja masih perlu divalidasi lebih lanjut pada jumlah kelas yang lebih besar dan kondisi rak farmasi nyata yang lebih beragam.

FCI-ANTREE: A GUI-Centric Method for Schema Recovery and Conceptual Database Model Reconstruction in Legacy Form-Based Systems Juanda Hakim Lubis; Elviawaty Muisa Zamzami; Mahyuddin K. M Nasution; Mohammad Andri Budiman
Journal of Applied Data Sciences Vol 7, No 3: September 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i3.1383

Legacy systems that lack technical documentation present significant challenges for database schema recovery, particularly when access to source code and SQL queries is unavailable. Existing reverse engineering approaches predominantly rely on backend artifacts such as database logs, schema definitions, or program code, limiting their applicability in undocumented environments. Although GUI-based approaches offer an alternative by utilizing interface-level information, many existing methods still rely on shallow visual parsing and lack systematic mechanisms to capture structural and interaction semantics. To address this limitation, this study proposes FCI–ANTREE, a GUI-centric method for reconstructing conceptual database schemas from legacy form-based systems. The method integrates Form-Centric Interaction (FCI) to extract candidate entities, attributes, relationships, constraints, and data types from user interactions and validation logic, and Admin Interface Tree (ANTREE) to model hierarchical relationships and transform them into logical and relational schemas. The objective of this research is to provide a systematic, interpretable, and semi-automated approach for database reverse engineering without relying on backend access. The proposed method was evaluated using three case studies: an online store application, a library system, and an inventory application. The evaluation employed structural consistency analysis, confusion-matrix-based metrics, and quantitative error measurements. The results show that the method achieved a mean MAE of 1.77, RMSE of 3.16, and R² of 97.09%, along with an average F1-score of 0.8768, indicating a high level of agreement between reconstructed and reference schemas. These findings demonstrate that FCI–ANTREE provides an effective and practical solution for database schema reconstruction in legacy systems with limited or no backend accessibility. The method contributes by introducing an interaction-aware and rule-based framework that enhances the accuracy, interpretability, and applicability of GUI-driven reverse engineering.

Diffusion2D and Anchored Inference for Asymptotic Stabilization of Diffusion-Convolutional Neural Networks in Multidomain Medical Image Classification Hanna Willa Dhany; Sutarman Sutarman; Poltak Sihombing; Mohammad Andri Budiman
Journal of Applied Data Sciences Vol 7, No 3: September 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i3.1215

Medical image classification across heterogeneous domains remains challenging due to domain shift, spatial variability, and unstable inference behavior. This study proposes a diffusion-stabilized Diffusion-Convolutional Neural Network (DCNN) framework that integrates Diffusion2D and post-hoc Anchored Diffusion to improve inference stability, probabilistic consistency, and robustness in multidomain medical image classification. The main contribution of this work is the introduction of a two-stage stabilization mechanism in which Diffusion2D performs controlled intra-image diffusion on feature representations before graph construction, while Anchored Diffusion refines uncertain predictions in the logit space through a k-nearest neighbors graph without retraining. The framework was evaluated on heterogeneous medical imaging datasets consisting of brain MRI, leukemia microscopy, and COVID-19 chest radiographs. Experimental results show that the proposed approach maintained baseline classification performance with an accuracy of 64.70% while improving the Macro-F1 score from 0.7045 to 0.7061. The diffusion mechanism reduced the average Laplacian value from 0.864355 to 0.187525, corresponding to a 78.23% reduction in spatial gradient variability. Internal analysis further demonstrated stable diffusion coefficients with a mean value of 0.141734 and a standard deviation of 0.003757, indicating controlled diffusion behavior. Anchored Diffusion selectively refined uncertain predictions, affecting only 0.6% of evaluated samples while preserving overall decision consistency. Repeated inference experiments across 40 iterations also revealed highly stable confidence trajectories with no observable variance after diffusion stabilization. The novelty of this research lies in combining feature-level diffusion stabilization, post-hoc anchored inference, and asymptotic regularization within a unified DCNN framework, providing a theoretically grounded and uncertainty-aware approach for robust multidomain medical image classification.

A Hybrid AES–NTRU Cryptographic Framework with Deterministic Dynamic S-Box for Secure Data Transmission Purwanto Simamora; Poltak Sihombing; Mohammad Andri Budiman; Jos Timanta Tarigan
Journal of Applied Data Sciences Vol 7, No 3: September 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i3.1307

The rapid expansion of interconnected sensing and monitoring systems has significantly increased the volume of digital data exchanged across distributed environments. While these systems provide substantial benefits for real-time monitoring and automated decision making, they also introduce critical challenges related to data confidentiality and secure communication. This study proposes a hybrid cryptographic framework designed to strengthen secure data transmission in distributed sensing environments. The primary objective of this research is to integrate a symmetric encryption mechanism with a lattice-based public-key cryptographic scheme within a hybrid key protection architecture. In addition, a deterministic round-dependent substitution mechanism is introduced into the symmetric encryption process to provide controlled structural variability during data encryption while preserving compatibility with the standard round-based encryption structure. The proposed framework was implemented in a software-based prototype environment and evaluated through a series of encryption and decryption experiments using representative data payloads that emulate typical communication scenarios in distributed sensing systems. The evaluation focused on three aspects: implementation correctness, computational performance, and diffusion characteristics of the encryption process. Experimental results confirm that all encrypted data payloads were successfully decrypted to their original plaintext without bit errors, demonstrating the functional correctness of the integrated cryptographic architecture. The encryption process achieved an avalanche effect of 47.01 percent, with an average encryption time of 118.99 milliseconds and a decryption time of 5.91 milliseconds in the prototype environment. These results indicate consistent diffusion behavior within acceptable experimental bounds while maintaining reasonable computational overhead for gateway-level communication nodes. The findings suggest that integrating adaptive substitution mechanisms within hybrid cryptographic architectures can provide flexible encryption structures suitable for secure data transmission in distributed monitoring systems, while remaining compatible with widely deployed symmetric encryption frameworks.

A Hybrid AES–NTRU Cryptographic Framework with Deterministic Dynamic S-Box for Secure Data Transmission Purwanto Simamora; Poltak Sihombing; Mohammad Andri Budiman; Jos Timanta Tarigan
Journal of Applied Data Sciences Vol 7, No 3: September 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i3.1307

The rapid expansion of interconnected sensing and monitoring systems has significantly increased the volume of digital data exchanged across distributed environments. While these systems provide substantial benefits for real-time monitoring and automated decision making, they also introduce critical challenges related to data confidentiality and secure communication. This study proposes a hybrid cryptographic framework designed to strengthen secure data transmission in distributed sensing environments. The primary objective of this research is to integrate a symmetric encryption mechanism with a lattice-based public-key cryptographic scheme within a hybrid key protection architecture. In addition, a deterministic round-dependent substitution mechanism is introduced into the symmetric encryption process to provide controlled structural variability during data encryption while preserving compatibility with the standard round-based encryption structure. The proposed framework was implemented in a software-based prototype environment and evaluated through a series of encryption and decryption experiments using representative data payloads that emulate typical communication scenarios in distributed sensing systems. The evaluation focused on three aspects: implementation correctness, computational performance, and diffusion characteristics of the encryption process. Experimental results confirm that all encrypted data payloads were successfully decrypted to their original plaintext without bit errors, demonstrating the functional correctness of the integrated cryptographic architecture. The encryption process achieved an avalanche effect of 47.01 percent, with an average encryption time of 118.99 milliseconds and a decryption time of 5.91 milliseconds in the prototype environment. These results indicate consistent diffusion behavior within acceptable experimental bounds while maintaining reasonable computational overhead for gateway-level communication nodes. The findings suggest that integrating adaptive substitution mechanisms within hybrid cryptographic architectures can provide flexible encryption structures suitable for secure data transmission in distributed monitoring systems, while remaining compatible with widely deployed symmetric encryption frameworks.

A Fibonacci-Based Dynamic Neural Network Architecture for Imbalanced Classification of Higher Education Performance Muhammad Ardiansyah Sembiring; Syahril Efendi; Mohammad Andri Budiman; T.Henny Febriana Harumy
Journal of Applied Data Sciences Vol 7, No 4: December 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i4.1459

This study aims to address two problems in neural network design: the lack of a principled method for choosing hidden-layer neuron counts, and the reliability loss caused by severe class imbalance. To meet this objective, the study propose the Fibonacci Dynamic Neural Network, contributing, to our knowledge, the first architecture unifying number-theoretic hidden-layer sizing with imbalanced-learning correction, an unbiased selection property proven formally, and cross-domain validation. Conceptually, candidate hidden-layer widths are generated from the Fibonacci sequence: because consecutive terms grow proportionally toward the Golden Ratio, the resulting set spans a non-redundant, well-distributed range of capacities, unlike arbitrary sets from conventional methods. One candidate is drawn per layer via a discrete uniform distribution, giving every option equal selection probability, while class imbalance is corrected through synthetic minority oversampling applied only to training data. The architecture was evaluated experimentally on three benchmark datasets spanning higher education, credit card fraud, and charitable donation prediction, with imbalance ratios from about eighteen-to-one to nearly five hundred eighty-to-one, tested across five seeds against five baselines and an ablation study via the Wilcoxon signed-rank test. It achieved macro F1-scores of approximately 0.83, 0.94, and 0.81, improvements of sixteen, five, and sixteen percent over the strongest baseline, with the smallest training-test performance gap of any model tested; oversampling and Fibonacci spacing contributed most to these gains. These findings suggest number-theoretic structures offer a practical, reproducible basis for architecture design under class imbalance, useful for future work on automated range selection and for deploying reliable classifiers in imbalanced real-world settings.

FCI-ANTREE: A GUI-Centric Method for Schema Recovery and Conceptual Database Model Reconstruction in Legacy Form-Based Systems Juanda Hakim Lubis; Elviawaty Muisa Zamzami; Mahyuddin K. M Nasution; Mohammad Andri Budiman
Journal of Applied Data Sciences Vol 7, No 3: September 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i3.1383

Legacy systems that lack technical documentation present significant challenges for database schema recovery, particularly when access to source code and SQL queries is unavailable. Existing reverse engineering approaches predominantly rely on backend artifacts such as database logs, schema definitions, or program code, limiting their applicability in undocumented environments. Although GUI-based approaches offer an alternative by utilizing interface-level information, many existing methods still rely on shallow visual parsing and lack systematic mechanisms to capture structural and interaction semantics. To address this limitation, this study proposes FCI–ANTREE, a GUI-centric method for reconstructing conceptual database schemas from legacy form-based systems. The method integrates Form-Centric Interaction (FCI) to extract candidate entities, attributes, relationships, constraints, and data types from user interactions and validation logic, and Admin Interface Tree (ANTREE) to model hierarchical relationships and transform them into logical and relational schemas. The objective of this research is to provide a systematic, interpretable, and semi-automated approach for database reverse engineering without relying on backend access. The proposed method was evaluated using three case studies: an online store application, a library system, and an inventory application. The evaluation employed structural consistency analysis, confusion-matrix-based metrics, and quantitative error measurements. The results show that the method achieved a mean MAE of 1.77, RMSE of 3.16, and R² of 97.09%, along with an average F1-score of 0.8768, indicating a high level of agreement between reconstructed and reference schemas. These findings demonstrate that FCI–ANTREE provides an effective and practical solution for database schema reconstruction in legacy systems with limited or no backend accessibility. The method contributes by introducing an interaction-aware and rule-based framework that enhances the accuracy, interpretability, and applicability of GUI-driven reverse engineering.

Diffusion2D and Anchored Inference for Asymptotic Stabilization of Diffusion-Convolutional Neural Networks in Multidomain Medical Image Classification Hanna Willa Dhany; Sutarman Sutarman; Poltak Sihombing; Mohammad Andri Budiman
Journal of Applied Data Sciences Vol 7, No 3: September 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i3.1215

Medical image classification across heterogeneous domains remains challenging due to domain shift, spatial variability, and unstable inference behavior. This study proposes a diffusion-stabilized Diffusion-Convolutional Neural Network (DCNN) framework that integrates Diffusion2D and post-hoc Anchored Diffusion to improve inference stability, probabilistic consistency, and robustness in multidomain medical image classification. The main contribution of this work is the introduction of a two-stage stabilization mechanism in which Diffusion2D performs controlled intra-image diffusion on feature representations before graph construction, while Anchored Diffusion refines uncertain predictions in the logit space through a k-nearest neighbors graph without retraining. The framework was evaluated on heterogeneous medical imaging datasets consisting of brain MRI, leukemia microscopy, and COVID-19 chest radiographs. Experimental results show that the proposed approach maintained baseline classification performance with an accuracy of 64.70% while improving the Macro-F1 score from 0.7045 to 0.7061. The diffusion mechanism reduced the average Laplacian value from 0.864355 to 0.187525, corresponding to a 78.23% reduction in spatial gradient variability. Internal analysis further demonstrated stable diffusion coefficients with a mean value of 0.141734 and a standard deviation of 0.003757, indicating controlled diffusion behavior. Anchored Diffusion selectively refined uncertain predictions, affecting only 0.6% of evaluated samples while preserving overall decision consistency. Repeated inference experiments across 40 iterations also revealed highly stable confidence trajectories with no observable variance after diffusion stabilization. The novelty of this research lies in combining feature-level diffusion stabilization, post-hoc anchored inference, and asymptotic regularization within a unified DCNN framework, providing a theoretically grounded and uncertainty-aware approach for robust multidomain medical image classification.

Title

Found 29 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 29 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 29 Documents
Search