Maya Hilda Lestari Louk
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Maya Hilda Lestari Louk has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Bayu Adhi Tama
HARP, University of Maryland Baltimore County, Baltimore, Maryland, USA
5 shared publications - Christabel Annora Paramita Parung
Faculty of Creative Industries, Product Design Department, University of Surabaya
1 shared publication Daniel Soesanto
Program Studi Sistem Informasi, Universitas Surabaya, Indonesia
1 shared publication- Dian Prianka
University of Surabaya
1 shared publication Felix Handani
Program Studi Teknik Informatika, Universitas Surabaya, Indonesia
1 shared publication- Hairunnas Hairunnas
Universitas Surabaya
1 shared publication
Latest Publications
- Open Access
- 30 May 2025
- Published by Universitas Ciputra Surabaya in Jurnal Informatika dan Sistem Informasi
- Vol. 11 (1) , 1-12
Model Pembelajaran Interaktif Berbasis Internet of Things untuk Meningkatkan Literasi Bencana pada Anak Usia Sekolah Dasar
Abstrak: Gempa bumi dan angin puting beliung merupakan dua jenis bencana alam yang sering terjadi di Indonesia dan kerap menimbulkan kerusakan signifikan serta korban jiwa. Tingginya angka korban sering kali disebabkan oleh kurangnya edukasi kebencanaan sejak dini, terutama di tingkat sekolah dasar. Penelitian ini mengusulkan sebuah model pembelajaran interaktif berbasis Internet of Things (IoT) untuk meningkatkan literasi bencana pada anak usia sekolah dasar, khususnya terkait gempa bumi dan angin puting beliung. Sistem yang dikembangkan terdiri dari maket edukatif yang dilengkapi dengan sensor getar dan anemometer untuk mendeteksi simulasi guncangan dan hembusan angin. Sensor ini terhubung ke sebuah platform website edukasi yang menampilkan data real-time serta materi pembelajaran interaktif. Simulasi dilakukan dengan bantuan alat seperti kipas angin dan pengering rambut untuk mensimulasikan kondisi angin kencang, sedangkan guncangan dilakukan oleh pendidik secara langsung. Hasil pengujian menunjukkan bahwa sistem berjalan dengan baik dan efektif membantu guru dalam menyampaikan materi edukasi kebencanaan secara lebih menarik dan mudah dipahami oleh siswa. Model ini berpotensi menjadi media pembelajaran yang inovatif dalam mendukung program mitigasi bencana di lingkungan pendidikan dasar.
- 30 May 2025
- Published by Universitas Ciputra Surabaya in Jurnal Informatika dan Sistem Informasi
- Vol. 11 (1) , 1-12
Open AccessModel Pembelajaran Interaktif Berbasis Internet of Things untuk Meningkatkan Literasi Bencana pada Anak Usia Sekolah Dasar
Abstrak: Gempa bumi dan angin puting beliung merupakan dua jenis bencana alam yang sering terjadi di Indonesia dan kerap menimbulkan kerusakan signifikan serta korban jiwa. Tingginya angka korban sering kali disebabkan oleh kurangnya edukasi kebencanaan sejak dini, terutama di tingkat sekolah dasar. Penelitian ini mengusulkan sebuah model pembelajaran interaktif berbasis Internet of Things (IoT) untuk meningkatkan literasi bencana pada anak usia sekolah dasar, khususnya terkait gempa bumi dan angin puting beliung. Sistem yang dikembangkan terdiri dari maket edukatif yang dilengkapi dengan sensor getar dan anemometer untuk mendeteksi simulasi guncangan dan hembusan angin. Sensor ini terhubung ke sebuah platform website edukasi yang menampilkan data real-time serta materi pembelajaran interaktif. Simulasi dilakukan dengan bantuan alat seperti kipas angin dan pengering rambut untuk mensimulasikan kondisi angin kencang, sedangkan guncangan dilakukan oleh pendidik secara langsung. Hasil pengujian menunjukkan bahwa sistem berjalan dengan baik dan efektif membantu guru dalam menyampaikan materi edukasi kebencanaan secara lebih menarik dan mudah dipahami oleh siswa. Model ini berpotensi menjadi media pembelajaran yang inovatif dalam mendukung program mitigasi bencana di lingkungan pendidikan dasar.
- Open Access
- 13 November 2022
- Published by MDPI AG in Big Data and Cognitive Computing
- Vol. 6 (4) , 137
PSO-Driven Feature Selection and Hybrid Ensemble for Network Anomaly Detection
As a system capable of monitoring and evaluating illegitimate network access, an intrusion detection system (IDS) profoundly impacts information security research. Since machine learning techniques constitute the backbone of IDS, it has been challenging to develop an accurate detection mechanism. This study aims to enhance the detection performance of IDS by using a particle swarm optimization (PSO)-driven feature selection approach and hybrid ensemble. Specifically, the final feature subsets derived from different IDS datasets, i.e., NSL-KDD, UNSW-NB15, and CICIDS-2017, are trained using a hybrid ensemble, comprising two well-known ensemble learners, i.e., gradient boosting machine (GBM) and bootstrap aggregation (bagging). Instead of training GBM with individual ensemble learning, we train GBM on a subsample of each intrusion dataset and combine the final class prediction using majority voting. Our proposed scheme led to pivotal refinements over existing baselines, such as TSE-IDS, voting ensembles, weighted majority voting, and other individual ensemble-based IDS such as LightGBM.
- 13 November 2022
- Published by MDPI AG in Big Data and Cognitive Computing
- Vol. 6 (4) , 137
Open AccessPSO-Driven Feature Selection and Hybrid Ensemble for Network Anomaly Detection
As a system capable of monitoring and evaluating illegitimate network access, an intrusion detection system (IDS) profoundly impacts information security research. Since machine learning techniques constitute the backbone of IDS, it has been challenging to develop an accurate detection mechanism. This study aims to enhance the detection performance of IDS by using a particle swarm optimization (PSO)-driven feature selection approach and hybrid ensemble. Specifically, the final feature subsets derived from different IDS datasets, i.e., NSL-KDD, UNSW-NB15, and CICIDS-2017, are trained using a hybrid ensemble, comprising two well-known ensemble learners, i.e., gradient boosting machine (GBM) and bootstrap aggregation (bagging). Instead of training GBM with individual ensemble learning, we train GBM on a subsample of each intrusion dataset and combine the final class prediction using majority voting. Our proposed scheme led to pivotal refinements over existing baselines, such as TSE-IDS, voting ensembles, weighted majority voting, and other individual ensemble-based IDS such as LightGBM.
- 17 October 2022
- Published by Elsevier in Expert Systems with Applications
- Vol. 213
Dual-IDS: A bagging-based gradient boosting decision tree model for network anomaly intrusion detection system
- 17 October 2022
- Published by Elsevier in Expert Systems with Applications
- Vol. 213
Dual-IDS: A bagging-based gradient boosting decision tree model for network anomaly intrusion detection system
- Open Access
- 17 September 2022
- Published by MDPI AG in Algorithms
- Vol. 15 (9) , 332
Tree-Based Classifier Ensembles for PE Malware Analysis: A Performance Revisit
Given their escalating number and variety, combating malware is becoming increasingly strenuous. Machine learning techniques are often used in the literature to automatically discover the models and patterns behind such challenges and create solutions that can maintain the rapid pace at which malware evolves. This article compares various tree-based ensemble learning methods that have been proposed in the analysis of PE malware. A tree-based ensemble is an unconventional learning paradigm that constructs and combines a collection of base learners (e.g., decision trees), as opposed to the conventional learning paradigm, which aims to construct individual learners from training data. Several tree-based ensemble techniques, such as random forest, XGBoost, CatBoost, GBM, and LightGBM, are taken into consideration and are appraised using different performance measures, such as accuracy, MCC, precision, recall, AUC, and F1. In addition, the experiment includes many public datasets, such as BODMAS, Kaggle, and CIC-MalMem-2022, to demonstrate the generalizability of the classifiers in a variety of contexts. Based on the test findings, all tree-based ensembles performed well, and performance differences between algorithms are not statistically significant, particularly when their respective hyperparameters are appropriately configured. The proposed tree-based ensemble techniques also outperformed other, similar PE malware detectors that have been published in recent years.
- 17 September 2022
- Published by MDPI AG in Algorithms
- Vol. 15 (9) , 332
Open AccessTree-Based Classifier Ensembles for PE Malware Analysis: A Performance Revisit
Given their escalating number and variety, combating malware is becoming increasingly strenuous. Machine learning techniques are often used in the literature to automatically discover the models and patterns behind such challenges and create solutions that can maintain the rapid pace at which malware evolves. This article compares various tree-based ensemble learning methods that have been proposed in the analysis of PE malware. A tree-based ensemble is an unconventional learning paradigm that constructs and combines a collection of base learners (e.g., decision trees), as opposed to the conventional learning paradigm, which aims to construct individual learners from training data. Several tree-based ensemble techniques, such as random forest, XGBoost, CatBoost, GBM, and LightGBM, are taken into consideration and are appraised using different performance measures, such as accuracy, MCC, precision, recall, AUC, and F1. In addition, the experiment includes many public datasets, such as BODMAS, Kaggle, and CIC-MalMem-2022, to demonstrate the generalizability of the classifiers in a variety of contexts. Based on the test findings, all tree-based ensembles performed well, and performance differences between algorithms are not statistically significant, particularly when their respective hyperparameters are appropriately configured. The proposed tree-based ensemble techniques also outperformed other, similar PE malware detectors that have been published in recent years.
- Open Access
- 22 August 2022
- Published by Institute of Advanced Engineering and Science in Journal of Education and Learning (EduLearn)
- Vol. 16 (3) , 318-329
Teaching experience on online learning in higher education: Generational analysis
A transition in learning model implementation occurred in higher education during the COVID-19 pandemic. Online learning answers the needs of long-distance learning. However, not all higher education institutions are thoroughly prepared for online learning. Therefore, this study aimed to understand the online learning experience at higher education institutions from the perspectives of multigenerational teaching staff. This study utilized mixed-method research through a quantitative and qualitative study. A total of 93 participants; male (n=40) and female (n=57) teaching staff filled out a research questionnaire consisting of closed and open questions about online learning. The data were analyzed using descriptive statistics and qualitative thematic analysis. The results indicated positive and negative contributions of the online learning process that affect the effectiveness of online learning according to multigenerational teaching staff perspectives. These findings contribute to the global discussion about the online learning process in higher education and recommend the usage of online learning for teaching staff across generations, complemented with an effective instructional design that would help provide a rigorous learning environment.
- 22 August 2022
- Published by Institute of Advanced Engineering and Science in Journal of Education and Learning (EduLearn)
- Vol. 16 (3) , 318-329
Open AccessTeaching experience on online learning in higher education: Generational analysis
A transition in learning model implementation occurred in higher education during the COVID-19 pandemic. Online learning answers the needs of long-distance learning. However, not all higher education institutions are thoroughly prepared for online learning. Therefore, this study aimed to understand the online learning experience at higher education institutions from the perspectives of multigenerational teaching staff. This study utilized mixed-method research through a quantitative and qualitative study. A total of 93 participants; male (n=40) and female (n=57) teaching staff filled out a research questionnaire consisting of closed and open questions about online learning. The data were analyzed using descriptive statistics and qualitative thematic analysis. The results indicated positive and negative contributions of the online learning process that affect the effectiveness of online learning according to multigenerational teaching staff perspectives. These findings contribute to the global discussion about the online learning process in higher education and recommend the usage of online learning for teaching staff across generations, complemented with an effective instructional design that would help provide a rigorous learning environment.
- Open Access
- 26 July 2022
- Published by IEOM Society International
- Vol. 12 (3)
The Effect of Background Music on Immersion in Virtual Social Game Experience
Background music is one of inseparable and indispensable elements in video games. It is considered as one of the aesthetic elements that contributes to players' enjoyment. This research is a part of ludo-musicology studies, which aims to investigate the effect of background music on the players' immersion, including sense of spatial presence, and emotions during the game. Participants were assigned in groups to play the same virtual social game experience (VSGE) two times-one time with their headphones on, and the second time without any headphones. Every game lasted for 15-20 minutes. After the experiments, participants were asked to fill questionnaires to compare both experiences regarding the immersion, spatial presence, and the emotions they feel during the game using Likert scales. To validate the participants' answers, we held a forum group discussion (FGD) consisting of 5 participants to gain deeper understanding regarding the causes that support the players' immersion.
- 26 July 2022
- Published by IEOM Society International
- Vol. 12 (3)
Open AccessThe Effect of Background Music on Immersion in Virtual Social Game Experience
Background music is one of inseparable and indispensable elements in video games. It is considered as one of the aesthetic elements that contributes to players' enjoyment. This research is a part of ludo-musicology studies, which aims to investigate the effect of background music on the players' immersion, including sense of spatial presence, and emotions during the game. Participants were assigned in groups to play the same virtual social game experience (VSGE) two times-one time with their headphones on, and the second time without any headphones. Every game lasted for 15-20 minutes. After the experiments, participants were asked to fill questionnaires to compare both experiences regarding the immersion, spatial presence, and the emotions they feel during the game using Likert scales. To validate the participants' answers, we held a forum group discussion (FGD) consisting of 5 participants to gain deeper understanding regarding the causes that support the players' immersion.
- Open Access
- 16 April 2022
- Published by MDPI AG in Big Data and Cognitive Computing
- Vol. 6 (2) , 41
Revisiting Gradient Boosting-Based Approaches for Learning Imbalanced Data: A Case of Anomaly Detection on Power Grids
Gradient boosting ensembles have been used in the cyber-security area for many years; nonetheless, their efficacy and accuracy for intrusion detection systems (IDSs) remain questionable, particularly when dealing with problems involving imbalanced data. This article fills the void in the existing body of knowledge by evaluating the performance of gradient boosting-based ensembles, including gradient boosting machine (GBM), extreme gradient boosting (XGBoost), LightGBM, and CatBoost. This paper assesses the performance of various imbalanced data sets using the Matthew correlation coefficient (MCC), area under the receiver operating characteristic curve (AUC), and F1 metrics. The article discusses an example of anomaly detection in an industrial control network and, more specifically, threat detection in a cyber-physical smart power grid. The tests’ results indicate that CatBoost surpassed its competitors, regardless of the imbalance ratio of the data sets. Moreover, LightGBM showed a much lower performance value and had more variability across the data sets.
- 16 April 2022
- Published by MDPI AG in Big Data and Cognitive Computing
- Vol. 6 (2) , 41
Open AccessRevisiting Gradient Boosting-Based Approaches for Learning Imbalanced Data: A Case of Anomaly Detection on Power Grids
Gradient boosting ensembles have been used in the cyber-security area for many years; nonetheless, their efficacy and accuracy for intrusion detection systems (IDSs) remain questionable, particularly when dealing with problems involving imbalanced data. This article fills the void in the existing body of knowledge by evaluating the performance of gradient boosting-based ensembles, including gradient boosting machine (GBM), extreme gradient boosting (XGBoost), LightGBM, and CatBoost. This paper assesses the performance of various imbalanced data sets using the Matthew correlation coefficient (MCC), area under the receiver operating characteristic curve (AUC), and F1 metrics. The article discusses an example of anomaly detection in an industrial control network and, more specifically, threat detection in a cyber-physical smart power grid. The tests’ results indicate that CatBoost surpassed its competitors, regardless of the imbalance ratio of the data sets. Moreover, LightGBM showed a much lower performance value and had more variability across the data sets.
- Open Access
- 6 December 2021
- Published by MDPI AG in Big Data and Cognitive Computing
- Vol. 5 (4) , 72
Exploring Ensemble-Based Class Imbalance Learners for Intrusion Detection in Industrial Control Networks
Classifier ensembles have been utilized in the industrial cybersecurity sector for many years. However, their efficacy and reliability for intrusion detection systems remain questionable in current research, owing to the particularly imbalanced data issue. The purpose of this article is to address a gap in the literature by illustrating the benefits of ensemble-based models for identifying threats and attacks in a cyber-physical power grid. We provide a framework that compares nine cost-sensitive individual and ensemble models designed specifically for handling imbalanced data, including cost-sensitive C4.5, roughly balanced bagging, random oversampling bagging, random undersampling bagging, synthetic minority oversampling bagging, random undersampling boosting, synthetic minority oversampling boosting, AdaC2, and EasyEnsemble. Each ensemble’s performance is tested against a range of benchmarked power system datasets utilizing balanced accuracy, Kappa statistics, and AUC metrics. Our findings demonstrate that EasyEnsemble outperformed significantly in comparison to its rivals across the board. Furthermore, undersampling and oversampling strategies were effective in a boosting-based ensemble but not in a bagging-based ensemble.
- 6 December 2021
- Published by MDPI AG in Big Data and Cognitive Computing
- Vol. 5 (4) , 72
Open AccessExploring Ensemble-Based Class Imbalance Learners for Intrusion Detection in Industrial Control Networks
Classifier ensembles have been utilized in the industrial cybersecurity sector for many years. However, their efficacy and reliability for intrusion detection systems remain questionable in current research, owing to the particularly imbalanced data issue. The purpose of this article is to address a gap in the literature by illustrating the benefits of ensemble-based models for identifying threats and attacks in a cyber-physical power grid. We provide a framework that compares nine cost-sensitive individual and ensemble models designed specifically for handling imbalanced data, including cost-sensitive C4.5, roughly balanced bagging, random oversampling bagging, random undersampling bagging, synthetic minority oversampling bagging, random undersampling boosting, synthetic minority oversampling boosting, AdaC2, and EasyEnsemble. Each ensemble’s performance is tested against a range of benchmarked power system datasets utilizing balanced accuracy, Kappa statistics, and AUC metrics. Our findings demonstrate that EasyEnsemble outperformed significantly in comparison to its rivals across the board. Furthermore, undersampling and oversampling strategies were effective in a boosting-based ensemble but not in a bagging-based ensemble.
- Open Access
- 5 July 2018
- Published by Institut Informatika Indonesia Surabaya in Teknika
- Vol. 7 (1) , 16-20
Sistem Kriptografi di Komputasi Awan Untuk Kebutuhan Data Medis
Komputasi awan adalah sebuah metode komputasi yang sedang berkembang saat ini untuk berbagi data dan pemrosesan data baik secara terbuka/umum atau pribadi. Komputasi awan adalah jawaban atas lingkungan komputasi yang lebih efektif dan efisien. Hal itu akan mengurangi biaya komputasi dan tenaga ahli komputasi. Komputasi awan dapat digunakan tidak hanya untuk tujuan bisnis tetapi juga untuk tujuan medis/kesehatan yang akan digunakan oleh pasien, spesialis, apoteker, perawat, dokter, dan pegawai administrasi rumah sakit. Sebagai implikasi pada sisi yang lain, keamanan adalah isu penting di dalam Komputasi awan. Perlindungan privasi data dan kontrol penerimaan data adalah tantangan keamanan di dalam Komputasi awan. Penulisan ini secara singkat membuat sketsa penggunaan sistem Kriptografi untuk kebutuhan data medis menggunakan Komputasi awan, khususnya fungsi enkripsi ulang (re-enkripsi fungsional) "tag" dan "tanda" untuk melakukan akses data. Penulisan ini memberi solusi alternatif untuk keamanan data pada Komputasi awan berdasarkan layanan enkripsi dan dekripsi dengan re-enkripsi fungsional untuk kebutuhan data medis dan data pelayanan kesehatan. Data dapat diakses dari mana saja dan oleh siapa saja yang memiliki hak akses untuk mengakses data sesuai dengan kebijakan akses tersebut. Penulisan ini diusulkan dan terdiri dari pembahasan terhadap ide dari penggunaan Komputasi awan dan keamanan data pada data medis dan data pleayanan kesehatan.
- 5 July 2018
- Published by Institut Informatika Indonesia Surabaya in Teknika
- Vol. 7 (1) , 16-20
Open AccessSistem Kriptografi di Komputasi Awan Untuk Kebutuhan Data Medis
Komputasi awan adalah sebuah metode komputasi yang sedang berkembang saat ini untuk berbagi data dan pemrosesan data baik secara terbuka/umum atau pribadi. Komputasi awan adalah jawaban atas lingkungan komputasi yang lebih efektif dan efisien. Hal itu akan mengurangi biaya komputasi dan tenaga ahli komputasi. Komputasi awan dapat digunakan tidak hanya untuk tujuan bisnis tetapi juga untuk tujuan medis/kesehatan yang akan digunakan oleh pasien, spesialis, apoteker, perawat, dokter, dan pegawai administrasi rumah sakit. Sebagai implikasi pada sisi yang lain, keamanan adalah isu penting di dalam Komputasi awan. Perlindungan privasi data dan kontrol penerimaan data adalah tantangan keamanan di dalam Komputasi awan. Penulisan ini secara singkat membuat sketsa penggunaan sistem Kriptografi untuk kebutuhan data medis menggunakan Komputasi awan, khususnya fungsi enkripsi ulang (re-enkripsi fungsional) "tag" dan "tanda" untuk melakukan akses data. Penulisan ini memberi solusi alternatif untuk keamanan data pada Komputasi awan berdasarkan layanan enkripsi dan dekripsi dengan re-enkripsi fungsional untuk kebutuhan data medis dan data pelayanan kesehatan. Data dapat diakses dari mana saja dan oleh siapa saja yang memiliki hak akses untuk mengakses data sesuai dengan kebijakan akses tersebut. Penulisan ini diusulkan dan terdiri dari pembahasan terhadap ide dari penggunaan Komputasi awan dan keamanan data pada data medis dan data pleayanan kesehatan.