Fadhil Muhammad

Fadhil Muhammad, Alif Bintang Elfandra, Iqbal Pahlevi Amin et al.

The rich biodiversity of coral reefs in Indonesian waters represents a valuable asset that must be preserved. Rapid climate change and uncontrolled human activities have caused significant degradation of coral reef ecosystems, including coral bleaching, which is a critical indicator of declining reef health. Therefore, this study aims to develop an accurate classification model to distinguish between healthy corals and bleached corals. This research utilizes a specialized dataset consisting of 923 images collected from Flickr using the Flickr API. The dataset comprises two distinct classes: healthy corals (438 images) and bleached corals (485 images). All images were resized so that the maximum width or height does not exceed 300 pixels, ensuring consistent image dimensions across the dataset. The proposed approach employs machine learning techniques, particularly convolutional neural networks (CNNs), to identify and differentiate visual patterns associated with healthy and bleached corals. The dataset can be used to train and evaluate various classification models in order to achieve optimal performance. Using the ResNet architecture, the results indicate that a ResNet model trained from scratch outperforms pretrained models in terms of both precision and accuracy. The successful development of an accurate classification model provides substantial benefits for researchers and marine biologists by enabling a deeper understanding of coral reef health. Furthermore, these models can be applied to monitor environmental changes in coral reef ecosystems, thereby contributing meaningfully to conservation and restoration efforts that are vital to sustaining marine life.

Fadhil Muhammad, Alwin Djuliansah, Adrian Aryaputra Hamzah et al.

Automatic speech recognition systems have achieved remarkable performance on fluent speech but continue to degrade significantly when processing stuttered speech, a limitation that is particularly acute for low-resource languages like Indonesian where specialized datasets are virtually non-existent. To overcome this scarcity, we propose a data augmentation framework that generates synthetic stuttered audio by injecting repetitions and prolongations into fluent text through a combination of rule-based transformations and large language models followed by text-to-speech synthesis. We apply this synthetic data to fine-tune a pre-trained Indonesian Whisper model using transfer learning, enabling the architecture to adapt to dysfluent acoustic patterns without requiring large-scale real-world recordings. Our experiments demonstrate that this targeted synthetic exposure consistently reduces recognition errors on stuttered speech while maintaining performance on fluent segments, validating the utility of synthetic data pipelines for developing more inclusive speech technologies in under-represented languages.