Article Per Year (5 Year)
p-Index From 2021 - 2026
3.525
P-Index
This Author published in this journals
All Journal IAES International Journal of Artificial Intelligence (IJ-AI) International Journal of Informatics and Communication Technology (IJ-ICT) IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Bulletin of Electrical Engineering and Informatics Jurnal Informatika dan Teknik Elektro Terapan JOIN (Jurnal Online Informatika) BAREKENG: Jurnal Ilmu Matematika dan Terapan Building of Informatics, Technology and Science Indonesian Journal of Electrical Engineering and Computer Science Computer Science and Information Technologies Brahmana : Jurnal Penerapan Kecerdasan Buatan Journal La Multiapp Action Research Literate (ARL) Malcom: Indonesian Journal of Machine Learning and Computer Science Cerdika: Jurnal Ilmiah Indonesia The Indonesian Journal of Computer Science
Zahra, Amalia
Unknown Affiliation
Aerospace Engineering Humanities Automotive Engineering Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Health Professions Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Mathematics Mechanical Engineering Physics Public Health Social Sciences Transportation

Published : 23 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 23 Documents
Search

 1   2   3 
The use of generative adversarial network as a domain adaptation method for cross-corpus speech emotion recognition Farhan Fadhil, Muhammad; Zahra, Amalia
Bulletin of Electrical Engineering and Informatics Vol 14, No 1: February 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v14i1.8339

Abstract

The research of speech emotion recognition (SER) is growing rapidly. However, SER still faces a cross-corpus SER problem which is performance degradation when a single SER model is tested in different domains. This study shows the impact of implementing a generative adversarial network (GAN) model for adapting speech data from different domains and performs emotion classification from the speech features using a 1D convolutional neural network (CNN) model. The results of this study found that the domain adaptation approach using a GAN model could improve the accuracy of emotion classification in speech data from 2 different domain such as the ryerson audio-visual database of emotional speech and song (RAVDESS) speech corpus and the EMO-DB speech corpus ranging from 10.88% to 28.77%, with the highest average performance increase across three different class balancing method reaching 18.433%.
The Website Optimization and Analysis on XYZ Website using the Web Core Vital Method Kristian Handoko Wijaya Sukardjoh; Zahra, Amalia
The Indonesian Journal of Computer Science Vol. 12 No. 5 (2023): The Indonesian Journal of Computer Science (IJCS)
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v12i5.3364

Abstract

XYZ website is a business website that operates in the field of e-commerce which is implemented through websites and applications, for several years the website has had a percentage of users' usage speed which has decreased quite a bit and has become old, due to lack of maintenance of some of the features contained in the website application which have an impact on the lack of customer interest in buying goods on the XYZ website and more influential in terms of access from searching e-commerce notifications from Google that if the percentage of websites decreases over a long period of time, this will result in websites not being allowed to publish advertisements. In this study, we analyze the problem to understand the problem starting from small things, namely from the use of programming languages, the data provided, the use of writing code, third party or vendor support, filling out website content, and websites using vital core web architecture. So that the website used has good comfort, accelerates the use of the website which can be affected by the large number of customer visitors, and can facilitate the development team's performance in management and maintenance and provide many positive things from customers so that business runs fast and provides convenience for customers and the XYZ website can received by Google.
The Impact of Data Augmentation Techniques on Improving Speech Recognition Performance for English in Indonesian Children Based on Wav2Vec 2.0 Maskur, Maimunah; Zahra, Amalia
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 19, No 2 (2025): April
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.104646

Abstract

Early childhood education is a crucial phase in shaping children's character and language skills. This study develops an Automatic Speech Recognition (ASR) model to recognize the speech of Indonesian children speaking English. The process begins with collecting and processing a dataset of children's speech recordings, which is then expanded using data augmentation techniques to enhance pronunciation variations. The pre-trained ASR Wav2Vec 2.0 model is fine-tuned with both the original and augmented datasets. Evaluation using Word Error Rate (WER) and Character Error Rate (CER) shows a significant accuracy improvement, with WER decreasing from 53% to 45% and CER from 33% to 27%, reflecting a performance increase of approximately 15%. Further analysis reveals pronunciation errors in phonemes such as /ð/, /θ/, /r/, /v/, /z/, and /ʃ/, which are uncommon in the Indonesian language, manifesting as substitutions, omissions, or additions in words like "three," "that," "rabbit," "very," and "zebra." These findings highlight the need for targeted phoneme training, audio-based approaches with ASR feedback, and the listen-and-repeat technique in English language instruction for children.Keywords— Early childhood education, Automatic Speech Recognition, Augmentation, Character Error Rate, Word Error Rate
Low-resolution image quality enhancement using enhanced super-resolution convolutional network and super-resolution residual network Riftiarrasyid, Mohammad Faisal; Halim, Rico; Novika, Andien Dwi; Zahra, Amalia
Indonesian Journal of Electrical Engineering and Computer Science Vol 39, No 1: July 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v39.i1.pp634-643

Abstract

This research explores the integration of enhanced super-resolution convolutional network (ESPCN) and super-resolution residual network (SRResNet) to enhance image quality captured by low-resolution (LR) cameras and in internet of things (IoT) devices. Focusing on face mask prediction models, the study achieves a substantial improvement, attaining a peak signal-to-noise ratio (PSNR) of 28.5142 dB and an execution time of 0.34704638 seconds. The integration of super-resolution techniques significantly boosts the visual geometry group-16 (VGG16) model’s performance, elevating classification accuracy from 71.30% to 96.30%. These findings highlight the potential of super-resolution in optimizing image quality for low-performance devices and encourage further exploration across diverse applications in image processing and pattern recognition within IoT and beyond.
Multilingual hate speech detection using deep learning Vincent, Vincent; Zahra, Amalia
International Journal of Informatics and Communication Technology (IJ-ICT) Vol 14, No 3: December 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijict.v14i3.pp1015-1023

Abstract

The rise of social media has enabled public expression but also fueled the spread of hate speech, contributing to social tensions and potential violence. Natural language processing (NLP), particularly text classification, has become essential for detecting hate speech. This study develops a hate speech detection model on Twitter using FastText with bidirectional long short-term memory (Bi-LSTM) and explores multilingual bidirectional encoder representations from transformers (M-BERT) for handling diverse languages. Data augmentation techniques-including easy data augmentation (EDA) methods, back translation, and generative adversarial networks (GANs)-are employed to enhance classification, especially for imbalanced datasets. Results show that data augmentation significantly boosts performance. The highest F1-scores are achieved by random insertion for Indonesian (F1-score: 0.889, Accuracy: 0.879), synonym replacement for English (F1-score: 0.872, Accuracy: 0.831), and random deletion for German (F1-score: 0.853, Accuracy: 0.830) with the FastText + Bi-LSTM model. The M-BERT model performs best with random deletion for Indonesian (F1-score: 0.898, Accuracy: 0.880), random swap for English (F1 score: 0.870, Accuracy: 0.866), and random deletion for German (F1-score: 0.662, Accuracy: 0.858). These findings underscore that data augmentation effectiveness varies by language and model. This research supports efforts to mitigate hate speech’s impact on social media by advancing multilingual detection capabilities.
MATHEMATICAL MODEL OF THREE SPECIES FOOD CHAIN WITH INTRASPECIFIC COMPETITION AND HARVESTING ON PREDATOR Manaqib, Muhammad; Suma'inna, Suma'inna; Zahra, Amalia
BAREKENG: Jurnal Ilmu Matematika dan Terapan Vol 16 No 2 (2022): BAREKENG: Jurnal Ilmu Matematika dan Terapan
Publisher : PATTIMURA UNIVERSITY

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (715.177 KB) | DOI: 10.30598/barekengvol16iss2pp551-562

Abstract

This research develops a mathematical model of three species of food chains between prey, predator, and top predator by adding intraspecific competition and harvesting factors. Interaction between prey with predator and interaction between predator with top predator uses the functional response type II. Model formation begins with creating a diagram food chain of three species compartments. Then a nonlinear differential equation system is formed based on the compartment diagram. Based on this system four equilibrium points are obtained. Analysis of local stability at the equilibrium points by linearization shows that there is one unstable equilibrium point and three asymptotic stable local equilibrium points. Numerical simulations at equilibrium points show the same results as the results of the analysis. Then numerical simulations on several parameter variations show that intraspecific competition has little effect on population changes in predator and top predator. While the harvesting parameter predator affects the population of predator and top predator.
Prediksi Kelulusan Siswa Sekolah Menengah Pertama Menggunakan Machine Learning Naibaho, Agusti Frananda Alfonsus; Zahra, Amalia
Brahmana : Jurnal Penerapan Kecerdasan Buatan Vol 4, No 2 (2023): Edisi Juni
Publisher : LPPM STIKOM Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/brahmana.v4i2.192

Abstract

In recent years, there have been students who have not graduated on time at Lubuk Alung 1 Public Junior High School. This statement is supported by graduation data from SMP Negeri 1 Lubuk Alung. Therefore it is necessary to predict student graduation status to identify factors that influence student graduation, which can also be used to help schools solve problems more easily. To overcome this problem, researchers predict student graduation based on student graduation information. The attributes used are personal data related to students, student academic data, and data related to the work of students' parents. Researchers obtained data on student graduation from schools that had been recapitulated. The classification algorithms used are decision tree, random forest, and extreme gradient boosting with grid searchCV and k-fold=5. Predictive accuracy using the random forest algorithm outperforms other methods with a value of 99.5%.
Implementation of Apriori Algorithm for Music Genre Recommendation Henry, Michael; Chandra, Wiryanata; Zahra, Amalia
JOIN (Jurnal Online Informatika) Vol 7 No 1 (2022)
Publisher : Department of Informatics, UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/join.v7i1.819

Abstract

Music interest is diverse yet enticing to be a part of knowledge discovery. It influences how people feel, study, work, etc. A lot of things are to be considered in producing brand new music with its correlation to its genre. We have already collected the dataset that we can utilize in this research, which is the history of every song listened to by several users in a total of 20.000 records from a million song dataset. This study implements the Apriori algorithm which can handle a large amount of data while simplifying the data to create a recommendation system where the result is a pattern from the music genre according to the interests of each user with the help of the RapidMiner tool. The purpose of this research is that the pattern which has been found can become a reference for music producers in terms of making or distributing their brand-new music. The result of the best combination of genres states that listeners of the rock genre will also hear the pop genre with a combination frequency of 50, support value of 21.2%, and confidence value of 51%.
Player Churn Prediction In Free To Play Game Using Ensemble Learning David, David; Zahra, Amalia
Action Research Literate Vol. 8 No. 4 (2024): Action Research Literate
Publisher : Ridwan Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46799/arl.v8i4.280

Abstract

Player churn is a prevalent challenge in the gaming industry. Most predictions of player churn utilize private datasets that are not easily accessible to the public. This study aims to investigate the performance of Logistic Regression, Random Forest, Support Vector Machines, and Ensemble Learning models using a dataset from a public API for predicting player churn, in comparison to other studies that typically rely on private game logs. In this research, the dataset consists of 418 unique player IDs, with a churn rate of 15%. After training the models, it was found that Logistic Regression and SVM achieved an accuracy of 95%, Random Forest achieved an accuracy of 96%, and Ensemble Learning, with Neural Network as the meta-learner, achieved an accuracy of 92%. These results underscore the validity of using public API data as an alternative data source for predicting player churn. n.
Speech Recognition Dengan Whisper Dalam Bahasa Indonesia William, Ezra; Zahra, Amalia
Action Research Literate Vol. 9 No. 2 (2025): Action Research Literate
Publisher : Ridwan Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46799/arl.v9i2.2573

Abstract

Perkembangan teknologi kecerdasan buatan telah mendorong kemajuan dalam pengenalan suara (speech recognition), terutama dalam mendukung komunikasi digital yang lebih efisien. Salah satu model terbaru yang banyak digunakan adalah Whisper, yang dikembangkan oleh OpenAI dengan kemampuan pengenalan suara multibahasa yang diklaim memiliki akurasi tinggi. Namun, tantangan utama dalam implementasi teknologi ini di Indonesia adalah keterbatasan sumber daya data dalam bahasa lokal serta variasi aksen yang signifikan. Oleh karena itu, penelitian ini dilakukan untuk mengevaluasi kinerja model Whisper dalam mengenali dan mentranskripsi suara berbahasa Indonesia. Penelitian ini bertujuan untuk menganalisis tingkat akurasi Whisper dalam pengenalan ucapan bahasa Indonesia berdasarkan Word Error Rate (WER) serta membandingkannya dengan model XLS-R dan XLSR-53. Metode yang digunakan dalam penelitian ini adalah pendekatan komparatif dengan melakukan fine-tuning terhadap model Whisper menggunakan dataset Common Voice 13 dalam bahasa Indonesia. Evaluasi model dilakukan dengan mengukur WER pada tahap pelatihan dan pengujian. Hasil penelitian menunjukkan bahwa model Whisper memiliki performa terbaik dibandingkan model XLS-R dan XLSR-53 dalam mengenali ucapan bahasa Indonesia. Nilai WER Training yang diperoleh adalah 22.33505%, sedangkan nilai WER Testing adalah 19.774909%. Hal ini menunjukkan bahwa model Whisper lebih unggul dalam menangani variasi aksen dan kondisi akustik dibandingkan dengan model lainnya. Keunggulan ini terutama disebabkan oleh pelatihan berbasis data yang lebih besar serta kemampuan adaptasi model terhadap berbagai bahasa. Implikasi penelitian ini memberikan kontribusi dalam pengembangan teknologi speech recognition berbahasa Indonesia serta meningkatkan aksesibilitas bagi pengguna dalam berbagai sektor, seperti pendidikan, layanan publik, dan teknologi komunikasi.
Co-Authors Al Mukarram, Khasyi Cahyadi, Jonathan Caprisiano, Ebenhaiser Jonathan Chandra, Wiryanata David David Fadhil, Muhammad Farhan Fadzlul Rahman, Ferry Faldi, Faldi Farhan Fadhil, Muhammad Fathur Rahman Halim, Rico Harits, Sayekti Hendra Saputra Henry, Michael Himawan, Randy Joko Pranoto, Wawan Karyawati, Tati Kristian Handoko Wijaya Sukardjoh Martulandi, Adipta Maskur, Maimunah Michael, Stefanus Muhammad Manaqib, Muhammad Mukhlas, M. Anang Naibaho, Agusti Frananda Alfonsus Novika, Andien Dwi Raharjo, Alim Ramadhansyah, Muhammad Hafizh Riftiarrasyid, Mohammad Faisal Roesmiatun Purnamadewi, Yasinta Sams, Andrew Steven Setyoko, Andreas Dimas Seventina, Healthy Suma'inna, Suma'inna Vincent Vincent, Vincent William, Ezra