AAAffandy Affandy

Affandy Affandy

*This is an algorithmically generated author record based on publicly available information.

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


Affandy Affandy has a total of 36 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    The Impact of Squeeze-and-Excitation Blocks on CNN Models and Transfer Learning for Pneumonia Classification Using Chest X-ray Images

    by Muhammad Yunan, Aris Marjuni, Affandy Affandy, Mochamad Arief Soeleman, Iqbal Firdaus

    Pneumonia is one of the leading causes of death due to respiratory tract infections, especially in children and the elderly. Early detection using chest X-ray images is crucial to accelerate diagnosis and treatment, but manual interpretation is often subjective and error-prone. This study evaluates the effect of Squeeze-and-Excitation (SE) Block integration on the performance of a custom Convolutional Neural Network (CNN) model and three popular transfer learning architectures: MobileNetV2, VGG16, and InceptionV3 in X-ray image-based pneumonia classification. A dataset of 5,856 images, taken from Chest X-ray Images (Pneumonia) on Kaggle, was processed through preprocessing, undersampling, and augmentation. Each model was tested in two configurations: without and with SE Block. Evaluation was performed using accuracy, precision, recall, F1-score, and test loss metrics. The results show that SE Block integration improves the performance of most models. The accuracy of the custom CNN increased from 95.17% to 95.88%, MobileNetV2 from 97.18% to 97.59%, and VGG16 from 96.88% to 97.69%. InceptionV3 also saw an accuracy increase from 94.06% to 94.16%, although accompanied by an increase in test loss. SE Block proved effective in strengthening the model's emphasis on important features through an inter-channel recalibration mechanism, especially on efficient architectures like MobileNetV2 and complex models like VGG16. These findings support the development of a more accurate, efficient, and adaptive deep learning-based pneumonia diagnosis system, especially for implementation in healthcare facilities with limited resources.

  • Open Access

    Enhancing Vision Transformer Performance with Rotation Based Augmentation for Classifying Images of Colon Cancer Pathology

    by Rudy Eko Prasetya, M. Arief Soeleman, Farrikh Al Zami, Affandy Affandy, Aris Marjuni, Mohammad Iqbal Saryuddin Assaqty

    Background: In medical imaging, classifying images of colon cancer pathology is still an essential challenge, especially for facilitating early diagnosis and successful intervention. Recently, Vision Transformer (ViT) models have demonstrated great promise for a variety of computer vision tasks, including the classification of medical images. However, the lack of annotated medical datasets and the intrinsic unpredictability of histopathology pictures sometimes restrict their performance. Objective: This study aims to enhance the performance of ViT models in colon cancer pathology classification by introducing a targeted data augmentation strategy, with a particular focus on rotation-based augmentation. Methods: We proposed a data augmentation pipeline that uses controlled changes to improve the number and diversity of training data. Like Rotation, Flip and Geometry are emphasized to replicate the real-world tissue orientation variations that are frequently seen in colon pathology slides. 10,000 JPEG pictures of colon cancer pathology, each with a resolution of 768 x 768 pixels, are used to train the models. We use models trained with and without the suggested augmentation pipeline to compare ViT performance across accuracy, sensitivity, and specificity in order to assess the impact of augmentation. Results: According to study results, rotation-based augmentation enhances ViT performance, achieving up to 99.30% accuracy and 99.50% sensitivity while preserving training times. In real-world pathology settings, where slide orientation varies greatly and can affect categorization consistency, these enhancements are especially pertinent. Conclusion: The proposed rotation-centric data augmentation technique enhances the performance of the ViT model in the classification of images showing colon cancer pathology.


  • Open Access

    Diabetic Retinopathy Detection Based on Convolutional Neural Networks with SMOTE and CLAHE Techniques Applied to Fundus Images

    by Sidhiq Mardianta, Affandy Affandy, Catur Supriyanto, Adi Wijaya

    Diabetic retinopathy (DR) is one of the major complications in diabetic patients' eyes, potentially leading to permanent blindness if not detected timely. This study aims to evaluate the accuracy of artificial intelligence (AI) in diagnosing DR. The method employed is the Synthetic Minority Over-sampling Technique (SMOTE) algorithm, applied to identify DR and its severity stages from fundus images using the public dataset "APTOS 2019 Blindness Detection." Literature was reviewed via ScienceDirect, ResearchGate, Google Scholar, and IEEE Xplore. Classification results using Convolutional Neural Network (CNN) showed the best performance for the binary classes normal (0) and DR (1) with an accuracy of 99.55%, precision of 99.54%, recall of 99.54%, and F1-score of 99.54%. For the multiclass classification No_DR (0), Mild (1), Moderate (2), Severe (3), Proliferate_DR (4), the accuracy was 95.26%, precision 95.26%, recall 95.17%, and F1-score 95.23%. Evaluation using the confusion matrix yielded results of 99.68% for binary classification and 96.65% for multiclass. This study highlights the significant potential in enhancing the accuracy of DR diagnosis compared to traditional human analysis


  • Open Access

    Leveraging Label Preprocessing for Effective End-to-End Indonesian Automatic Speech Recognition

    by Mohammad Noval Althoff, Affandy Affandy, Ardytha Luthfiarta, Mohammad Wahyu Bagus Dwi Satya, Halizah Basiron

    This research explores the potential of improving low-resource Automatic Speech Recognition (ASR) performance by leveraging label preprocessing techniques in conjunction with the wav2vec2-large Self-Supervised Learning (SSL) model. ASR technology plays a critical role in enhancing educational accessibility for children with disabilities in Indonesia, yet its development faces challenges due to limited labeled datasets. SSL models like wav2vec 2.0 have shown promise by learning rich speech representations from raw audio with minimal labeled data. Still, their dependence on large datasets and significant computational resources limits their application in low-resource settings. This study introduces a label preprocessing technique to address these limitations, comparing three scenarios: training without preprocessing, with the proposed preprocessing method, and with an alternative method. Using only 16 hours of labeled data, the proposed preprocessing approach achieves a Word Error Rate (WER) of 15.83%, significantly outperforming the baseline scenario (33.45% WER) and the alternative preprocessing method (19.62% WER). Further training using the proposed preprocessing technique with increased epochs reduces the WER to 14.00%. These results highlight the effectiveness of label preprocessing in reducing data dependency while enhancing model performance. The findings demonstrate the feasibility of developing robust ASR models for low-resource languages, offering a scalable solution for advancing ASR technology and improving educational accessibility, particularly for underrepresented languages.


  • Open Access

    Exploiting Silhouette Principle Component For Dimension Reduction In Breast Ultrasound Images Classification

    by Etika Kartikadarma, Ahmad Zainul Fanani, Pujiono Pujiono, Affandy Affandy, Sari Ayu Wulandari

    This paper proposes the use of the Dimensional Reduction method with the Silhouette Principle Component (SPC) Approach to improve the classification of breast ultrasound images. The PCA method is used to reduce the dimensions of medical images to improve classification, with MobileNet-v2 and DenseNet-121 as the optimal classification algorithm choices. The results show that the SPC method succeeded in producing efficient feature representation with data sizes that are almost the same as the original data, while PCA produces greater dimensionality reduction. The SPC model also shows the best performance in terms of accuracy and loss. This research makes a significant contribution to the development of more sophisticated and efficient medical image analysis techniques to support the diagnosis and treatment of breast cancer.

  • Open Access

    Enhancing Machine Learning Accuracy in Detecting Preventable Diseases using Backward Elimination Method

    by Muhammad Dliyauddin, Guruh Fajar Shidik, Affandy Affandy, M. Arief Soeleman

    In the current landscape of abundant high-dimensional datasets, addressing classification challenges is pivotal. While prior studies have effectively utilized Backward Elimination (BE) for disease detection, there is a notable absence of research demonstrating the method's significance through comprehensive comparisons across diverse databases. The study aims to extend its contribution by applying BE across multiple machine learning algorithms (MLAs)Nave Bayes (NB), k-Nearest Neighbors (KNN), and Support Vector Machine (SVM)on datasets associated with preventable diseases (i.e. heart failure (HF), breast cancer (BC), and diabetes). This study aims to elucidate and recommend significant differences observed in the application of BE across diverse datasets and machine learning (ML) methods. This study conducted testing on four distinct datasetsraisin, HF, BC, and early-stage diabetes risk prediction datasets. Each dataset underwent evaluation with three MLAs: NB, KNN, and SVM. The application of BE successfully eliminated non-significant attributes, retaining only influential ones in the model. In addition, t-test results revealed a significant impact on accuracy across all datasets (p-value < 0.05). In specific algorithmic evaluations, SVM exhibited the highest accuracy for the raisin dataset at 87.22%. Additionally, KNN attained the utmost accuracy in the heart failure dataset with an accuracy of 86.31%. In the breast cancer dataset, KNN again excelled, achieving an accuracy of 83.56%. For the diabetes dataset, KNN proved the most accurate, reaching 96.15%. These results underscore the efficacy of BE in enhancing the execution of MLAs for disease detection.


  • Open Access

    Menumbuhkan Minat dan Keterampilan Produksi Film Dokumenter pada Generasi Muda: Pelatihan pada Siswa-Siswi SMA Negeri 3 Kota Semarang

    by Erna Zuni Astuti, Arni Ernawati, Auria F Yogananti, Affandy Affandy

    Film dokumenter telah menjadi media yang kuat dalam menyampaikan pesan-pesan penting dan mempengaruhi opini publik. Namun, masih terdapat tantangan dalam menumbuhkan minat dan keterampilan produksi film dokumenter pada generasi muda. Siswa-siswi di SMA masih belum memahami pembuatan film dokumenter, sehingga pelatihan produksi film dokumenter di SMA sangatlah penting untuk mengatasi masalah ini. Dalam membuat film dokumenter ada beberapa tahapan yang perlu diperhatikan, di antaranya pra produksi, produksi dan pascaproduksi. Tahapan ini membantu memahami dan mengelola permasalahan yang diangkat dengan seksama, sehingga dapat menghasilkan film yang optimal. Metode yang digunakan melalui pendekatan Participatory Action Research (PAR), memberikan kesempatan kepada siswa-siswi SMA Negeri 3 Kota Semarang untuk aktif berpartisipasi dalam pengembangan minat dan keterampilan produksi film dokumenter. Tujuan dari pengabdian ini yaitu untuk meningkatkan pemahaman, minat, dan ketrampilan siswa/i dalam proses pembuatan produksi film dokumenter serta memberikan mereka kesempatan untuk mengembangkan kreativitas dan pengetahuan. Pengabdi memberi pelatihan kepada siswa/i SMA Negeri 3 Semarang kesempatan untuk belajar dan berlatih secara praktis dalam produksi film dokumenter. Mereka mendapatkan pengetahuan dan keterampilan melalui ceramah, diskusi, demonstrasi, dan praktik langsung dalam pengambilan gambar, pengeditan, naskah dan penyusunan storyboard film dokumenter.


  • Open Access

    Hybrid Top-K Feature Selection to Improve High-Dimensional Data Classification Using Naïve Bayes Algorithm

    by Riska Wibowo, M. Arief Soeleman, Affandy Affandy

    Purpose: The naive bayes algorithm is one of the most popular machine learning algorithms, because it is simple, has high computational efficiency and has good accuracy. The naive bayes method assumes each attribute contributes to determining the classification result that may exist between attributes, this can interfere with the classification performance of naive bayes. The naïve bayes algorithm is sensitive to many features so this can reduce the performance of naïve bayes. Efforts to improve the performance of the naïve bayes algorithm by using a hybrid top-k feature selection method that aims to handle high-dimensional data using the naïve bayes algorithm so as to produce better accuracy.Methods: This research proposes a hybrid top-k feature selection method with stages 1. Prepare the dataset, 2. Replace the missing value with the average value of each attribute, 3. Calculate the weight of the attribute value using the weight information gain method, 4. Select attributes using the top-k feature selection method, 5. Backward Elimination with the naïve bayes algorithm, 6. Datasets that have been selected new attributes, then validated using 10 fold-cross validation where the data is divided into training data and testing data, 7. Calculate the accuracy value based on the confusion matrix table.Result: Based on the experimental results of performance and performance comparison of several methods that have been presented (Naïve Bayes, deep feature weighting naïve bayes, top-k feature selection, and hybrid top-k feature selection). The experimental results in this study show that from 5 datasets from UCI Repository that have been tested, the accuracy value of the hybrid top-k feature selection method increases from the previous method. From the accuracy comparison results that the proposed hybrid top-k feature selection method is ranked the first best method.Novelty: Thus it can be concluded that the Hybrid top-k feature selection method can be used to handle dimensional data in the Naïve Bayes algorithm.


  • Antecedents of Wedding Expenditure Management: A Document Analysis

    by Syh Noorul Madihah Syed Husin, Normadiah Daud, Tengku Fatimah Muliana Tengku Muda, Zurita Mohd Yusoff, Siti Khatijah Ismail, Aiman Izuddin Mohd Affandy

    Objective - This paper seeks to unravel the element of wedding expenditure in Islam and to present the concept of wedding expenditure management that is encouraged by Islamic law. Methodology/Technique - This qualitative study employs document analysis methods through data collection from scholarly writings in the field of family management. Data will be analysed based on content analysis methods and presented in an organised manner through thematic methods. Finding - This study found two important features outlined by Islam in managing the early preparations of weddings; and three concepts of spending for the purpose of wedding preparation. Previous research has concentrated on the reality of Malay society's marriage spending behaviour. Previous research has demonstrated the necessity for a guideline to lessen the financial load that today's youths endure. Novelty - This study presents the Malay Muslim community with a better and effective management of wedding expenditure as encouraged by Islam. The notion of wedding expenditure management promulgated by Islam is a structured expenditure approach that may be applied by all communities, particularly the Malays, who have a variety of traditions and cultures that involve a variety of expenditure requirements. Type of Paper - Review Keywords: Wedding Expenditure; Wedding Expenses; Wedding Management JEL Classification: D69, H53, J12.


  • Open Access

    Sentiment Analysis Berbasis Algoritma Naïve Bayes Classsifier untuk Identifikasi Persepsi Masyarakat Terhadap Produk / Layanan Perusahaan

    by Affandy Affandy, Oktania Nandiyati

    Twitter is the most popular microblogging service in Indonesia, with nearly 23 million users. In the era of big data such as the current tweets from customers, observers, potential consumers, or the community of users of products or services of a company will greatly help companies in knowing the industrial and consumer landscape, so as to determine strategic plans that will contribute to the company's growth. However, the use of data from social media such as Twitter is hampered by a number of technical difficulties in the process of collecting, processing, and analysing. Specifically, this research applies the Naïve Bayes Classifier algorithm in the process of sentiment analysis of tweets data into a prototype application that is intended to make it easier for companies / organizations to know people's perceptions of their products or services. The NBC algorithm was chosen because this algorithm is able to do a good classification even though it uses small training data, but has high accuracy and process speed for handling large training data. From the evaluation results found a prototype running well where the keywords entered will trigger the Twitter API to crawl the data then the mining process can be monitored at each stage and at the end of the process, the system will show the final sentiment level values and the representation of the calculation results log in a chart form over a certain period of time.