Ghinaa Zain Nabiilah
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Ghinaa Zain Nabiilah has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Islam Nur Alam
Bina Nusantara University
2 shared publications - Simeon Yuda Prasetyo
Bina Nusantara University
2 shared publications Ajeng Wulandari
Bina Nusantara University,School of Computer Science,Computer Science Department,Jakarta,Indonesia,11480
1 shared publication- Bakti Amirul Jabar
Bina Nusantara University
1 shared publication - Eko Setyo Purwanto
Research Centre for Veterinary Science, Organization Research for Health, The National Research and Innovation Agency. BRIN , Cibinong, West Java Province 16911
1 shared publication - Erna Fransisca Angela Sihotang
Bina Nusantara University
1 shared publication
Latest Publications
- Open Access
- 1 December 2024
- Published by Institute of Advanced Engineering and Science in IAES International Journal of Artificial Intelligence (IJ-AI)
- Vol. 13 (4) , 4169-4177
Pneumonia detection on x-ray image using improved depthwise separable convolutional neural networks
A single neural network model cannot capture intricate and diverse features due to its ability to learn only a finite set of patterns from the data. Additionally, training and utilising a single model can be computationally demanding. Experts propose incorporating multiple neural network models to address these constraints to extract complementary attributes. Previous research has highlighted challenges network models face, including difficulties in effectively capturing highly detailed spatial features, redundancy in network structure parameters, and restricted generalisation capabilities. This study introduces an innovative neural network architecture that combines the Xception module with the inverse residue structure to tackle these issues. Considering this, the paper presents a model for detecting pneumonia in X-ray images employing an improved depthwise separable convolutional network. This network architecture integrates the inverse residual structure from the MobileNetV2 model, using the rectified linear unit (ReLU) non-linear activation function throughout the entire network. The experimental results show an impressive recognition rate with a test accuracy of 97.24% on the chest x-ray dataset. This method can extract more profound and abstract image features while mitigating overfitting issues and enhancing the network's generalisation capacity.
- 1 December 2024
- Published by Institute of Advanced Engineering and Science in IAES International Journal of Artificial Intelligence (IJ-AI)
- Vol. 13 (4) , 4169-4177
Open AccessPneumonia detection on x-ray image using improved depthwise separable convolutional neural networks
A single neural network model cannot capture intricate and diverse features due to its ability to learn only a finite set of patterns from the data. Additionally, training and utilising a single model can be computationally demanding. Experts propose incorporating multiple neural network models to address these constraints to extract complementary attributes. Previous research has highlighted challenges network models face, including difficulties in effectively capturing highly detailed spatial features, redundancy in network structure parameters, and restricted generalisation capabilities. This study introduces an innovative neural network architecture that combines the Xception module with the inverse residue structure to tackle these issues. Considering this, the paper presents a model for detecting pneumonia in X-ray images employing an improved depthwise separable convolutional network. This network architecture integrates the inverse residual structure from the MobileNetV2 model, using the rectified linear unit (ReLU) non-linear activation function throughout the entire network. The experimental results show an impressive recognition rate with a test accuracy of 97.24% on the chest x-ray dataset. This method can extract more profound and abstract image features while mitigating overfitting issues and enhancing the network's generalisation capacity.
- Open Access
- 1 February 2024
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 14 (1) , 1071-1078
Indonesian multilabel classification using IndoBERT embedding and MBERT classification
The rapid increase in social media activity has triggered various discussion spaces and information exchanges on social media. Social media users can easily tell stories or comment on many things without limits. However, this often triggers open debates that lead to fights on social media. This is because many social media users use toxic comments that contain elements of racism, radicalism, pornography, or slander to argue and corner individuals or groups. These comments can easily spread and trigger users vulnerable to mental disorders due to unhealthy and unfair debates on social media. Thus, a model is needed to classify comments, especially toxic ones, in Indonesian. Transformer-based model development and natural language processing approaches can be applied to create classification models. Some previous research related to the classification of toxic comments has been done, but the classification results of the model still require exploration to get optimal results. So, this research uses the proposed model by using different pre-trained models at the embedding and classification stages, in the embedding stage using Indonesia bidirectional encoder representations from transformers (IndoBERT), and classification using multilingual bidirectional encoder representations from transformers (MBERT). The proposed model provides optimal results with an F1 value of 0.9032.
- 1 February 2024
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 14 (1) , 1071-1078
Open AccessIndonesian multilabel classification using IndoBERT embedding and MBERT classification
The rapid increase in social media activity has triggered various discussion spaces and information exchanges on social media. Social media users can easily tell stories or comment on many things without limits. However, this often triggers open debates that lead to fights on social media. This is because many social media users use toxic comments that contain elements of racism, radicalism, pornography, or slander to argue and corner individuals or groups. These comments can easily spread and trigger users vulnerable to mental disorders due to unhealthy and unfair debates on social media. Thus, a model is needed to classify comments, especially toxic ones, in Indonesian. Transformer-based model development and natural language processing approaches can be applied to create classification models. Some previous research related to the classification of toxic comments has been done, but the classification results of the model still require exploration to get optimal results. So, this research uses the proposed model by using different pre-trained models at the embedding and classification stages, in the embedding stage using Indonesia bidirectional encoder representations from transformers (IndoBERT), and classification using multilingual bidirectional encoder representations from transformers (MBERT). The proposed model provides optimal results with an F1 value of 0.9032.
- 1 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 82-86
Comparing Convolutional Neural Network Models with MobileNet-Based in Diabetic Retinopathy Classification
Diabetic Retinopathy (DR), a severe complication of diabetes, can lead to blindness. Early detection and classification of DR stages are essential, given the global rise in Diabetes Mellitus cases. This study explores the application of Convolutional Neural Network Models with the base MobileNet to automate the early detection and severity classification of Diabetic Retinopathy. Using the Diabetic Retinopathy Arranged Dataset, the models are developed through transfer learning with fine-tuning. MobileNetV2, especially during fine-tuning, exhibits the highest accuracy. In the fine-tuning phase, it achieves an accuracy of 72.5% in the testing dataset, highlighting the efficacy of this process. The findings emphasize the potential of MobileNetV2 for early Diabetic Retinopathy detection and severity classification. As the prevalence of diabetes continues to rise globally, automated systems like this play a vital role in reducing the risk of permanent vision loss. Future research can explore alternative CNN architectures and optimization through ensemble methods to further enhance performance. This study provides a valuable contribution to addressing the urgent healthcare challenges posed by Diabetic Retinopathy in the context of the growing diabetes epidemic.
- 1 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 82-86
Comparing Convolutional Neural Network Models with MobileNet-Based in Diabetic Retinopathy Classification
Diabetic Retinopathy (DR), a severe complication of diabetes, can lead to blindness. Early detection and classification of DR stages are essential, given the global rise in Diabetes Mellitus cases. This study explores the application of Convolutional Neural Network Models with the base MobileNet to automate the early detection and severity classification of Diabetic Retinopathy. Using the Diabetic Retinopathy Arranged Dataset, the models are developed through transfer learning with fine-tuning. MobileNetV2, especially during fine-tuning, exhibits the highest accuracy. In the fine-tuning phase, it achieves an accuracy of 72.5% in the testing dataset, highlighting the efficacy of this process. The findings emphasize the potential of MobileNetV2 for early Diabetic Retinopathy detection and severity classification. As the prevalence of diabetes continues to rise globally, automated systems like this play a vital role in reducing the risk of permanent vision loss. Future research can explore alternative CNN architectures and optimization through ensemble methods to further enhance performance. This study provides a valuable contribution to addressing the urgent healthcare challenges posed by Diabetic Retinopathy in the context of the growing diabetes epidemic.
- Open Access
- 4 July 2023
- Published by Sekolah Tinggi Teknologi Terpadu Nurul Fikri in Jurnal Teknologi Terpadu
- Vol. 9 (1) , 29-34
Perbandingan Model Machine Learning pada Klasifikasi Tumor Otak Menggunakan Fitur Discrete Cosine Transform
Tumor otak adalah pertumbuhan jaringan abnormal yang ditandai dengan pertumbuhan sel yang berlebihan di bagian otak tertentu. Salah satu teknik andal saat ini yang tersedia untuk mengidentifikasi tumor otak adalah penggunaan pemindaian Magnetic Resonance Imaging (MRI). Gambar MRI yang dipindai dipantau dan diperiksa untuk deteksi tumor oleh dokter spesialis. Mengembangkan alat yang lebih efektif dan efisien untuk membantu profesional medis mengidentifikasi tumor otak dirasa cukup mendesak karena jumlah orang yang menderita tumor otak melonjak dan tingkat kematian yang mencapai 18.600 pada tahun 2021. Dalam penelitian sebelumnya, model berbasis pembelajaran mesin mampu menunjukkan kemampuan untuk mendeteksi tumor otak dengan akurasi klasifikasi 92% dan hal hasil ini dapat diandalkan. Untuk mendapatkan akurasi klasifikasi biner yang paling andal dalam gambar otak MRI, kami menguji secara komputasi beberapa hyperparameter menggunakan kumpulan data MRI yang tersedia untuk umum. Tingkat akurasi model yang tinggi dicapai dengan menguji berbagai arsitektur model machine learning yang ada, diikuti dengan memasukkan feature map yang diekstraksi dari Discrete Cosine Transform (DCT). Klasifikasi gambar MRI mencapai akurasi pada data test tertinggi sebesar 93% dengan menggunakan model Support Vector Machine (SVM).
- 4 July 2023
- Published by Sekolah Tinggi Teknologi Terpadu Nurul Fikri in Jurnal Teknologi Terpadu
- Vol. 9 (1) , 29-34
Open AccessPerbandingan Model Machine Learning pada Klasifikasi Tumor Otak Menggunakan Fitur Discrete Cosine Transform
Tumor otak adalah pertumbuhan jaringan abnormal yang ditandai dengan pertumbuhan sel yang berlebihan di bagian otak tertentu. Salah satu teknik andal saat ini yang tersedia untuk mengidentifikasi tumor otak adalah penggunaan pemindaian Magnetic Resonance Imaging (MRI). Gambar MRI yang dipindai dipantau dan diperiksa untuk deteksi tumor oleh dokter spesialis. Mengembangkan alat yang lebih efektif dan efisien untuk membantu profesional medis mengidentifikasi tumor otak dirasa cukup mendesak karena jumlah orang yang menderita tumor otak melonjak dan tingkat kematian yang mencapai 18.600 pada tahun 2021. Dalam penelitian sebelumnya, model berbasis pembelajaran mesin mampu menunjukkan kemampuan untuk mendeteksi tumor otak dengan akurasi klasifikasi 92% dan hal hasil ini dapat diandalkan. Untuk mendapatkan akurasi klasifikasi biner yang paling andal dalam gambar otak MRI, kami menguji secara komputasi beberapa hyperparameter menggunakan kumpulan data MRI yang tersedia untuk umum. Tingkat akurasi model yang tinggi dicapai dengan menguji berbagai arsitektur model machine learning yang ada, diikuti dengan memasukkan feature map yang diekstraksi dari Discrete Cosine Transform (DCT). Klasifikasi gambar MRI mencapai akurasi pada data test tertinggi sebesar 93% dengan menggunakan model Support Vector Machine (SVM).