Article Per Year (5 Year)
p-Index From 2021 - 2026
3.846
P-Index
This Author published in this journals
All Journal Komunikasi Fisika Indonesia Jurnal Fisika Unand JOURNAL ONLINE OF PHYSICS ORBITA: Jurnal Pendidikan dan Ilmu Fisika Jurnal Fisika dan Terapannya Jurnal Pengabdian Masyarakat (ABDIRA) Jurnal Riset Fisika Indonesia Jurnal Pengabdian Masyarakat Pinang Masak Jurnal Tiyasadarma: Jurnal Pengabdian Kepada Masyarakat
Yoza Fendriani
UNIVERSITAS JAMBI
Aerospace Engineering Humanities Astronomy Automotive Engineering Chemical Engineering, Chemistry & Bioengineering Chemistry Civil Engineering, Building, Construction & Architecture Computer Science & IT Earth & Planetary Sciences Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Languange, Linguistic, Communication & Media Materials Science & Nanotechnology Mathematics Nursing Physics Social Sciences Other

Published : 28 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 13 Documents
Search
Journal : JOURNAL ONLINE OF PHYSICS

 1   2 
CLASSIFICATION OF LUNG DISEASE ON X-RAY IMAGES BASED ON GRAY LEVEL CO-OCCURRENCE MATRIX (GLCM) FEATURE EXTRACTION AND BACKPROPAGATION NEURAL NETWORK USING PYTHON GUI Rani, Debby Mustika; Deswardani, Frastica; Fendriani, Yoza
JOURNAL ONLINE OF PHYSICS Vol. 9 No. 2 (2024): JOP (Journal Online of Physics) Vol 9 No 2
Publisher : Prodi Fisika FST UNJA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22437/jop.v9i2.32806

Abstract

This research aims to develop an automated diagnostic system for classifying lung diseases in X-ray images based on feature extraction using the Gray Level Co-occurrence Matrix (GLCM) with a Backpropagation Artificial Neural Network employing a Python GUI. In this study, 200 lung image data were utilized, divided into four classes with 50 data points each. The four categories of image classes are normal lungs, Pneumonia, Tuberculosis, and Covid-19. The training and testing data were split in a 92:8 ratio, resulting in 184 training data and 16 testing data. The parameters include four input layers, eight hidden layers, two output layers, alpha 0.8, 2000 iteration, and target error = 0.0001. Then, it continued with feature extraction using the GLCM to obtain texture characteristics in lung images. In the training stage, the best results were obtained in iteration 2000 with a Mean Squared Error of 0.005% and a calculated time of 167.319 seconds. At the testing stage, a reasonably high accuracy was obtained, 93.75%, with a calculated time of 0.014 seconds. This result indicates that the method can prove lung images.
ANALISIS PENGARUH VARIASI FAKTOR EKSPOSI PADA CT SCAN TERHADAP KUALITAS CITRA DAN DOSIS RADIASI PADA PEMERIKSAAN ABDOMEN Noveranty, Amelia; Purwaningsih, Sri; Fendriani, Yoza
JOURNAL ONLINE OF PHYSICS Vol. 9 No. 3 (2024): JOP (Journal Online of Physics) Vol 9 No 3
Publisher : Prodi Fisika FST UNJA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22437/jop.v9i3.35155

Abstract

Telah dilakukan penelitian tentang analisis pengaruh variasi faktor eksposi pada CT Scan terhadap kualitas citra dan dosis radiasi pada pemeriksaan abdomen. Tujuan penelitian ini adalah untuk mengetahui pengaruh variasi faktor eksposi terhadap kualitas citra dan dosis radiasi pada pemeriksaan abdomen. Penelitian dilakukan di Instalasi Radiologi RSUD Raden Mattaher Jambi dengan menggunakan pesawat CT Scan Hitachi Scenaria 128 Slices serta phantom air sebagai objek penelitian. Variasi tegangan tabung yang digunakan yaitu 80 kV, 100 kV, dan 120 kV dengan variasi kuat arus 100 mA, 200 mA, dan 300 mA selama 1 detik pemindaian. Dari scanning yang dilakukan menghasilkan data dosis radiasi yang ditunjukkan oleh nilai CTDIvol serta data citra berupa citra digital dengan format DICOM, kemudian diolah menggunakan software RadiAnt DICOM Viewer untuk mendapatkan nilai ROI objek dan ROI background yang digunakan untuk menghitung nilai Contrast to Noise Ratio (CNR). Hasil yang diperoleh dari penelitian ini adalah variasi tegangan tabung dan kuat arus tabung berpengaruh terhadap nilai CTDIvol karena tegangan tabung menentukan energi sinar-X yang dipancarkan oleh tabung sinar-X, sedangkan kuat arus tabung menentukan jumlah elektron yang mengalir dari katoda ke anoda, yang pada gilirannya mempengaruhi jumlah foton sinar-X yang dihasilkan. Ketika tegangan tabung dan kuat arus ditingkatkan secara bersamaan, efeknya akan saling memperkuat, menghasilkan dosis radiasi yang jauh lebih tinggi. Variasi tegangan tabung dan kuat arus tabung menghasilkan nilai CNR yang meningkat seiring dengan peningkatan nilai tegangan tabung dan kuat arus. Hal tersebut dikarenakan tegangan tabung yang tinggi meningkatkan energi sinar-X, yang seharusnya meningkatkan kemampuan sinar-X untuk menembus jaringan dan meningkatkan kontras citra. Selain itu, peningkatan kuat arus akan meningkatkan jumlah sinar-X yang dihasilkan, yang dapat mengurangi noise dan meningkatkan nilai CNR. Untuk mencapai kualitas citra yang optimal dengan nilai CNR yang tinggi dan stabil perlu adanya keseimbangan yang tepat antara tegangan tabung dan kuat arus tabung.
CLASSIFICATION ANALYSIS OF BRAIN TUMOR DISEASE IN RADIOGRAPHIC IMAGES USING SUPPORT VECTOR MACHINES (SVM) WITH PYTHON Ananda, Jihan Suci; Fendriani, Yoza; Pebralia, Jesi
JOURNAL ONLINE OF PHYSICS Vol. 9 No. 3 (2024): JOP (Journal Online of Physics) Vol 9 No 3
Publisher : Prodi Fisika FST UNJA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22437/jop.v9i3.36270

Abstract

This research examines the analysis of brain tumor disease classification using radiographic images using the Python-based Support Vector Machines (SVM) method. Data was collected from the Kaggle platform with four main categories of brain tumors: normal, pituitary, glioma, and meningioma. The data is then processed, including cleaning, pixel intensity normalization, and feature extraction to distinguish brain tumor characteristics. The data were visualized to understand the distribution and characteristics of the tumor. With the implementation of Python, visual analysis becomes efficient. The SVM model was trained and evaluated, showing an accuracy of 90% with good evaluation metrics such as MAE, MSE, RMSE, and F1-SCORE. The results show that SVM has excellent potential as a diagnostic tool to support the identification and treatment of brain tumors.
Co-Authors -, Maison Afrianto, M Ficky Afrianto, Muhammad Ficky Afrianto, Muhammad Ficky Alrizal, Alrizal Ananda, Jihan Suci Anggraeni, Rista Mutia Anggraini, Rista Mutia Anjelina, Ria Atika Maulida Benedika Ferdian Hutabarat Cahyaningtyas, Saphira Indah Ermadani Ermadani Faizar Farid Febri Berthalita Pujaningsih Fernando Mersa Putra Frastica Deswardani Frayoga, Andito Haryono Haryono Haryono Haryono Husnul Hamdi Husnul Hamdi Imanuel Purba, Chrisman Jesi Pebralia Latifah, Adelia Linda Handayani Lucky Zaehir Maulana Madyawati Latief Mardian Peslinof Maulida, Atika Maulina Tanjung Noveranty, Amelia Nur Syaqila, Cindy Nurhidayah Nurhidayah Nurhidayah Nurhidayah Pebralia, Jesi Purba, Rodearni Ananda Putri Raden Mohamad Herdian Bhakti Rani, Debby Mustika Regita Kharisma Resta, Ichy Lucya Restianingsih, Tika Riany, Hesti Rista Mutia Anggraini Rista Mutia Anggraini Rodearni Ananda Putri Purba Roedearni Ananda Putri Purba Rohania, Meisa Rustan Samsidar Samsidar Samsidar Saphira Indah Cahyaningtyas Sari, Nadhia Nortania Tika Restianingsih Yurinanda, Sherli