Nur Ulfa Maulidevi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Nur Ulfa Maulidevi has a total of 74 co-authors. Here are the top co-authors by number of shared publications:
- Kridanto Surendro
School of Electrical Engineering and Informatics, Institut Teknologi Bandung, Bandung, Indonesia
11 shared publications - Nyoman Karna
School of Electrical Engineering, Telkom University, Bandung, Indonesia
7 shared publications - Suwarno
School of Electrical Engineering and Informatics, Institut Teknologi Bandung, Bandung, Indonesia
5 shared publications Iping Supriana
Sekolah Teknik Elektro dan Informatika, Institut Teknologi Bandung, Bandung, Indonesia
4 shared publications- Iping Supriana
Institut Teknologi Bandung
4 shared publications Masayu Leylia Khodra
School of Electrical Engineering and Informatics ITB, Bandung, Indonesia
4 shared publications
Latest Publications
- Open Access
- 26 July 2026
- Published by Springer Nature in Discover Artificial Intelligence
- Vol. 6  (1)
Interpretable machine learning models for pediatric type 1 diabetes risk assessment
- 26 July 2026
- Published by Springer Nature in Discover Artificial Intelligence
- Vol. 6  (1)
Open AccessInterpretable machine learning models for pediatric type 1 diabetes risk assessment
- Open Access
- 22 July 2025
- Published by Universitas Airlangga in Journal of Information Systems Engineering and Business Intelligence
- Vol. 11  (2) , 160-172
Enhancing the Comprehensiveness of Criteria-Level Explanation in Multi-Criteria Recommender System
Background: The explainability of recommender systems (RSs) is currently attracting significant attention. Recent research mainly focus on item-level explanations, neglecting the need to provide comprehensive explanations for each criterion. In contrast, this research introduces a criteria-level explanation generated in a content-based pardigm by matching aspects between the user and item. However, generation may fall short when user aspects do not match perfectly with the item, despite possessing similar semantics. Objective: This research aims to extend the aspect-matching method by leveraging semantic similarity. The extension provides more detail and comprehensive explanations for recommendations at the criteria level. Methods: An extended version of the aspect matching (AM) method was used. This method identified identical aspects between users and items and obtained semantically similar aspects with closely related meanings. Results: Experiment results from two real-world datasets showed that AM+ was superior to the AM method in coverage and relevance. However, the improvement varied depending on the dataset and criteria sparsity. Conclusion: The proposed method improves the comprehensiveness and quality of the criteria-level explanation. Therefore, the adopted method has the potential to improve the explainability of multi-criteria RSs. The implication extends beyond the enhancement of explanation to facilitate better user engagement and satisfaction. Keywords: Comprehensiveness, Content-Based Paradigm, Criteria-Level Explanation, Explainability, Multi-Criteria Recommender System
- 22 July 2025
- Published by Universitas Airlangga in Journal of Information Systems Engineering and Business Intelligence
- Vol. 11  (2) , 160-172
Open AccessEnhancing the Comprehensiveness of Criteria-Level Explanation in Multi-Criteria Recommender System
Background: The explainability of recommender systems (RSs) is currently attracting significant attention. Recent research mainly focus on item-level explanations, neglecting the need to provide comprehensive explanations for each criterion. In contrast, this research introduces a criteria-level explanation generated in a content-based pardigm by matching aspects between the user and item. However, generation may fall short when user aspects do not match perfectly with the item, despite possessing similar semantics. Objective: This research aims to extend the aspect-matching method by leveraging semantic similarity. The extension provides more detail and comprehensive explanations for recommendations at the criteria level. Methods: An extended version of the aspect matching (AM) method was used. This method identified identical aspects between users and items and obtained semantically similar aspects with closely related meanings. Results: Experiment results from two real-world datasets showed that AM+ was superior to the AM method in coverage and relevance. However, the improvement varied depending on the dataset and criteria sparsity. Conclusion: The proposed method improves the comprehensiveness and quality of the criteria-level explanation. Therefore, the adopted method has the potential to improve the explainability of multi-criteria RSs. The implication extends beyond the enhancement of explanation to facilitate better user engagement and satisfaction. Keywords: Comprehensiveness, Content-Based Paradigm, Criteria-Level Explanation, Explainability, Multi-Criteria Recommender System
- Open Access
- 20 February 2025
- Published by Association for Computing Machinery (ACM)
- p. 267-272
Designing a Quantum Annealing-Based Method for Optimizing Backpropagation Neural Networks in Greenhouse Gas Emissions Prediction
- 20 February 2025
- Published by Association for Computing Machinery (ACM)
- p. 267-272
Open AccessDesigning a Quantum Annealing-Based Method for Optimizing Backpropagation Neural Networks in Greenhouse Gas Emissions Prediction
- Open Access
- 20 February 2025
- Published by Association for Computing Machinery (ACM)
- p. 154-160
Proposed Feature Dimensionality Reduction Method in a Predictive Model for Carbon Neutrality: A Hybrid Quantum-Classical Approach
- 20 February 2025
- Published by Association for Computing Machinery (ACM)
- p. 154-160
Open AccessProposed Feature Dimensionality Reduction Method in a Predictive Model for Carbon Neutrality: A Hybrid Quantum-Classical Approach
- Open Access
- 1 October 2024
- Published by Springer Nature in Journal of King Saud University Computer and Information Sciences
- Vol. 36  (8)
Improving embedding-based link prediction performance using clustering
- 1 October 2024
- Published by Springer Nature in Journal of King Saud University Computer and Information Sciences
- Vol. 36  (8)
Open AccessImproving embedding-based link prediction performance using clustering
- Open Access
- 23 May 2024
- Published by Ubiquity Press, Ltd. in Data Science Journal
- Vol. 23  (1)
The Optimization of n-Gram Feature Extraction Based on Term Occurrence for Cyberbullying Classification
The CODATA Data Science Journal is a peer-reviewed, open access, electronic journal, publishing papers on the management, dissemination, use and reuse of research data and databases across all research domains, including science, technology, the humanities and the arts. The scope of the journal includes descriptions of data systems, their implementations and their publication, applications, infrastructures, software, legal, reproducibility and transparency issues, the availability and usability of complex datasets, and with a particular focus on the principles, policies and practices for open data. All data is in scope, whether born digital or converted from other sources.
- 23 May 2024
- Published by Ubiquity Press, Ltd. in Data Science Journal
- Vol. 23  (1)
Open AccessThe Optimization of n-Gram Feature Extraction Based on Term Occurrence for Cyberbullying Classification
The CODATA Data Science Journal is a peer-reviewed, open access, electronic journal, publishing papers on the management, dissemination, use and reuse of research data and databases across all research domains, including science, technology, the humanities and the arts. The scope of the journal includes descriptions of data systems, their implementations and their publication, applications, infrastructures, software, legal, reproducibility and transparency issues, the availability and usability of complex datasets, and with a particular focus on the principles, policies and practices for open data. All data is in scope, whether born digital or converted from other sources.
- 7 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Reinforcement Learning for Turn-Based Strategy Game
Predictability and lack of adaptability have long been recognized as significant challenges in strategy turn-based games. This is due to the prevalent use of heuristic-based approaches in their agent's decision-making. In this paper, we attempt to solve this issue by replacing heuristics with an intelligent agent trained by Reinforcement Learning (RL). We compare the performance of our trained agent against two systemic approaches, Monte Carlo Tree Search (MCTS) and Online Evolutionary Planning (OEP). Experiments show that while RL is vulnerable to play styles that differ sharply from its training data, it is competitive against MCTS but falls short to OEP. This suggests that RL can be a promising approach after further improvement and optimization in future work.
- 7 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Reinforcement Learning for Turn-Based Strategy Game
Predictability and lack of adaptability have long been recognized as significant challenges in strategy turn-based games. This is due to the prevalent use of heuristic-based approaches in their agent's decision-making. In this paper, we attempt to solve this issue by replacing heuristics with an intelligent agent trained by Reinforcement Learning (RL). We compare the performance of our trained agent against two systemic approaches, Monte Carlo Tree Search (MCTS) and Online Evolutionary Planning (OEP). Experiments show that while RL is vulnerable to play styles that differ sharply from its training data, it is competitive against MCTS but falls short to OEP. This suggests that RL can be a promising approach after further improvement and optimization in future work.
- Open Access
- 23 February 2023
- Published by Association for Computing Machinery (ACM)
- p. 171-176
Improved Classification Accuracy by Feature Selection using Adaptive Support Method
- 23 February 2023
- Published by Association for Computing Machinery (ACM)
- p. 171-176
Open AccessImproved Classification Accuracy by Feature Selection using Adaptive Support Method
- Open Access
- 23 February 2023
- Published by Association for Computing Machinery (ACM)
- p. 200-205
The Use of Dynamic n-Gram to Enhance TF-IDF Features Extraction for Bahasa Indonesia Cyberbullying Classification
- 23 February 2023
- Published by Association for Computing Machinery (ACM)
- p. 200-205
Open AccessThe Use of Dynamic n-Gram to Enhance TF-IDF Features Extraction for Bahasa Indonesia Cyberbullying Classification
- Open Access
- 23 February 2023
- Published by Association for Computing Machinery (ACM)
- p. 184-191
FEATURE SELECTION METHOD BASED ON GENETIC ALGORITHM WITH WRAPPER-EMBEDDED TECHNIQUE FOR MEDICAL RECORD CLASSIFICATION
Medical records, also known as Electronic Health Records, can be used to analyze medical data which contributes to greater knowledge of information related to disease, disease phase, and early identification of disease. The main problem in medical records is how to determine the features of the selected subset to make predictions on clinical data. The problem of classifying medical record data involves many features. This creates problems in determining which features have a correlation to the predicted results. Feature selection is an appropriate technique for selecting risk factors for disease in medical records. Feature selection requires optimization techniques so that the accuracy value can be increased. Therefore, feature selection using genetic algorithms has the ability to optimize the selected features. The feature selection technique, namely the wrapper, applies a learning algorithm to test the features to be selected. The embedded engineering approach to feature selection makes it possible to apply learning in the selection process. Genetic algorithm-based feature selection method with wrapper-embedded technique is expected to produce an effective feature subset. This technique evaluates features by using combinations in fitness calculations with the aim of assessing the selected features. The development of genetic algorithms by applying fitness value evaluation and elitist aims to maintain the fitness value in the next generation.
- 23 February 2023
- Published by Association for Computing Machinery (ACM)
- p. 184-191
Open AccessFEATURE SELECTION METHOD BASED ON GENETIC ALGORITHM WITH WRAPPER-EMBEDDED TECHNIQUE FOR MEDICAL RECORD CLASSIFICATION
Medical records, also known as Electronic Health Records, can be used to analyze medical data which contributes to greater knowledge of information related to disease, disease phase, and early identification of disease. The main problem in medical records is how to determine the features of the selected subset to make predictions on clinical data. The problem of classifying medical record data involves many features. This creates problems in determining which features have a correlation to the predicted results. Feature selection is an appropriate technique for selecting risk factors for disease in medical records. Feature selection requires optimization techniques so that the accuracy value can be increased. Therefore, feature selection using genetic algorithms has the ability to optimize the selected features. The feature selection technique, namely the wrapper, applies a learning algorithm to test the features to be selected. The embedded engineering approach to feature selection makes it possible to apply learning in the selection process. Genetic algorithm-based feature selection method with wrapper-embedded technique is expected to produce an effective feature subset. This technique evaluates features by using combinations in fitness calculations with the aim of assessing the selected features. The development of genetic algorithms by applying fitness value evaluation and elitist aims to maintain the fitness value in the next generation.