Hasil Pencarian  ::  Simpan CSV :: Kembali

"The premise of this short essay is to question ; why are these images so significant to the concept of architecture and the physical of the architecture? The question above comes to my attention, because I consider an image is an image, without the personal interpretation the image has no meaning or could possibly have a thousand meanings. Reading of image is personal, culturally significant, and knowledge of the object present. How do you make these certain images as a base of the architecture concept if the fact of the image does not mean anything or could possibly have a thousand meanings? In the medical environment for example; in several cases it has been proven that the reading of X-Ray images from beast cancer patients were false. The certain reading of the images could lead up to poor judgement. on the rest if the paper i will show you my observation on the images, how i interpret the images, how i navigate people to read my images and how i relate the architecture through the images that i produce."

"Dalam konteks estimasi usia gigisebagai metode non-invasif untuk determinasi usia kronologis pasien, teknik orthopantomography (OPG) telah luas diaplikasikan meski menghadapi kendala seperti biaya tinggi dan eksposur radiasi. Merespons limitasi pendekatan konvensional, paradigma machine learning dan deep learning kini dioptimalkan untuk mengidentifikasi pola intrinsik pada data pencitraan medis kompleks. Penelitian ini bertujuan mengembangkan algoritma YOLOv8 untuk meningkatkan akurasi estimasi usia gigi, menggunakan dataset dari RSGMP Universitas Airlangga dengan subjek pediatrik 5—15 tahun. Dataset dimodifikasi menjadi tiga variasi: tanpa augmentasi, augmentasi tiga kali per sampel, dan augmentasi lima kali per sampel. Hasil optimal dicapai oleh variasi ketiga dengan augmentasi lima kali per sampel, mendemonstrasikan akurasi 60% dan F1-Score 61,05%, mengindikasikan potensi signifikan teknik augmentasi data dalam meningkatkan kinerja algoritma deep learning untuk estimasi usia gigi.

---

In the context of dental age estimation as a non-invasive method for determining patients' chronological age, orthopantomography (OPG) techniques have been widely applied despite facing challenges such as high costs and radiation exposure. Responding to the limitations of conventional approaches, machine learning and deep learning paradigms are now being optimized to identify intrinsic patterns in complex medical imaging data. This research aims to develop the YOLOv8 algorithm to improve the accuracy of dental age estimation, using a dataset from the Dental and Oral Hospital of Airlangga University with pediatric subjects aged 5-15 years. The dataset was modified into three variations: without augmentation, triplet augmentation, and quintuplet augmentation per sample. Optimal results were achieved by the third variation with quintuplet augmentation, demonstrating 60% accuracy and 61.05% F1-Score, indicating significant potential for data augmentation techniques in enhancing the performance of deep learning algorithms for dental age estimation."

"Age-related macular degeneration (AMD) adalah penyakit degeneratif pada makula yang menyebabkan gangguan penglihatan sentral pada orang lanjut usia. Secara global, orang yang didiagnosis mengalami AMD mencapai 170 juta orang. Pada 2018, AMD menjadi penyebab kebutaan terbesar ketiga di Indonesia, setelah katarak dan gangguan refraksi. Salah satu pendekatan teknologi dalam bidang kedokteran adalah menggunakan sains data dan deep learning untuk mendeteksi dan mendiagnosis penyakit mata. Salah satu metode deep learning yang paling efektif untuk memahami data berbasis citra adalah Convolutionl Neural Network (CNN). Di antara arsitektur CNN yang dikembangkan, arsitektur EfficientNet merupakan salah satu yang paling efektif untuk mencapai akurasi terbaik pada tugas klasifikasi gambar serta efisien secara komputasional. Data yang digunakan dalam penelitian ini adalah data citra fundus retina yang bersumber dari empat open source database. Terdapat dua kelas yang akan diklasifikasi yaitu Normal dan AMD. Dengan penggabungan beberapa dataset muncul beberapa masalah yaitu terdapat perbedaan dimensi dan kontras pada citra. Sebelum dataset digunakan untuk melatih model, dilakukan preprocessing dengan centered crop, resize, dan Contrast Limited Adaptive Histogram Equalization (CLAHE). Masalah lain yang muncul adalah ukuran dataset yang kecil karena sulitnya mendapatkan data medis pasien. Salah satu metode yang dapat menjadi solusi adalah Generative Adversarial Network (GAN) yang digunakan untuk menghasilkan data citra sintetis. Penelitian ini diajukan untuk menerapkan metode GAN guna meningkatkan kinerja model EfficientNet dalam mendeteksi AMD. Untuk melakukan hal tersebut dibuat tiga skenario untuk membandingkan kinerja EfficientNet. Skenario A yaitu melakukan klasifikasi dengan dataset asli, tanpa preprocessing CLAHE dan tanpa augmentasi GAN. Skenario B melakukan klasifikasi dengan dataset yang sudah diaugmentasi dengan GAN. Sedangkan, skenario C melakukan klasifikasi dengan dataset yang diaugmentasi dengan GAN dan melalui preprocessing CLAHE. Metrik evaluasi yang digunakan untuk mengukukur kinerja adalah akurasi, sensitivity, dan specifity. Pada skenario A dengan rasio splitting data 70:15:15 dan 80:10:10 didapat rata-rata akurasi sebesar 89,01% dan 88,52%. Sedangkan, pada skenario B dengan rasio 70:15:15 dan 80:10:10 didapat rata-rata akurasi sebesar 87,10% dan 89,86%. Pada Skenario C dengan rasio 70:15:15 dan 80:10:10 didapat rata-rata akurasi sebesar 88,97% dan 91,27%. Skenario terbaik adalah skenario C dengan rasio 80:10:10 dengan nilai akurasi tertinggi 92,96%, sensitivity tertinggi mencapai 93,55%, dan specifity tertinggi mencapai 95,00%.

---

Age-related macular degeneration (AMD) is a degenerative disease of the macula that causes central vision impairment in the elderly. Globally, the number of people diagnosed with AMD reaches 170 million. In 2018, AMD became the third leading cause of blindness in Indonesia, following cataracts and refractive errors. One technological approach in the field of medicine is utilizing data science and deep learning to detect and diagnose eye diseases. One of the most effective deep learning methods for understanding image-based data is the Convolutional Neural Network (CNN). Among the developed CNN architectures, EfficientNet is one of the most effective in achieving the best accuracy in image classification tasks while being computationally efficient. The data used in this research consists of fundus retinal images sourced from four open source databases. There are two classes: Normal and AMD. Combining multiple datasets presents several issues, such as differences in image dimensions and contrast. Before the dataset is used to train the model, preprocessing is conducted using centered crop, resize, and Contrast Limited Adaptive Histogram Equalization (CLAHE). Another emerging issue is the small dataset size due to the difficulty of obtaining patient medical data. One method that can provide a solution is the Generative Adversarial Network (GAN), which is used to generate synthetic image data. This study proposes to implement GAN to enhance the performance of the EfficientNet model in detecting AMD. To achieve this, three scenarios were created to compare the performance of EfficientNet. Scenario A involves classification with the original dataset, without CLAHE preprocessing and without GAN augmentation. Scenario B involves classification with the dataset augmented by GAN. Scenario C involves classification with the dataset augmented by GAN and processed through CLAHE preprocessing. The evaluation metrics used to measure performance are accuracy, sensitivity, and specificity. In Scenario A, with data splitting ratios of 70:15:15 and 80:10:10, the average accuracy obtained was 89.01% and 88.52%, respectively. In Scenario B, with the same data splitting ratios, the average accuracy obtained was 87.10% and 89.86%, respectively. In Scenario C, with data splitting ratios of 70:15:15 and 80:10:10, the average accuracy obtained was 88.97% and 91.27%, respectively. The best scenario is Scenario C with a ratio of 80:10:10, achieving the highest accuracy of 92.96%, the highest sensitivity of 93.55%, and the highest specificity of 95.00%."