Marlin Ramadhan Baidillah
Dept. of Civil and Structural Engineering, Universiti Kebangsaan Malaysia

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

The Optimum Design of 3D Sensor for Electrical Capacitance Volume-Tomography (ECVT) Marlin Ramadhan Baidillah; W. Warsito; Muhammad Mukhlisin
Jurnal Matematika & Sains Vol 16, No 3 (2011)
Publisher : Institut Teknologi Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

A tomography system based on capacitance measurement is attempts to map dielectric permittivity of materials. The measured capacitance of the pair between source and detector is dependent to surface area enclosing detector electrode. Imaging a three-dimensional object requires sensitivity matrix with three-dimensional variation, especially in axial (z-axis) direction to differentiate the depth along the sensor length. Therefore, the fundamental concept of electrical capacitance sensor design for 3-D volume imaging is to distribute equally electrical field intensity all over three-dimensional space. In ECVT, due to the weakness of the electrical field, the capacitance measurement that generates information simultaneously of the volumetric properties can be made using arbitrary shapes of sensors and vessels. In this study, we designed and analyzed the 3-D sensitivity matrix for 4 different geometry sensors: hexagonal, rectangular, trapezoid and triangular. The comparisons of sensitivity distribution showed that hexagonal sensor gives relatively more uniform sensitivity variation in both the radial and axial directions. Keywords: ECVT, 3-D volume imaging, 3-D sensitivity matrix, 3-D sensor capacitance.  Desain Optimum Sensor 3D untuk Tomografi Volum Kapasitansi Listrik Abstrak Sebuah sistem tomografi yang berdasarkan pengukuran kapasitansi diterapkan untuk pemetaan permitivitas bahan dielektrik. Kapasitansi pasangan sumber dan detektor yang diukur tergantung pada luas permukaan elektroda detektor. Pencitraan sebuah objek tiga dimensi memerlukan matriks sensitivitas tiga dimensi, terutama dalam arah aksial (sumbu z) untuk membedakan variasi sepanjang sensor. Oleh karena itu, konsep mendasar dari desain sensor kapasitansi listrik untuk pencitraan 3-D volume adalah mendistribusikan intensitas medan listrik yang sama besar di seluruh ruang tiga dimensi. Dalam ECVT, karena medan listrik yang lemah, pengukuran kapasitansi yang menghasilkan informasi secara simultan dari sifat volumetrik dapat dibuat dengan menggunakan bentuk sensor dan tabung yang sebarang. Dalam studi ini, kami merancang dan menganalisis matriks sensitivitas 3-D untuk 4 geometri sensor yang berbeda: heksagonal, segi empat, trapesium, dan segitiga. Perbandingan distribusi sensitivitas menunjukkan bahwa sensor heksagonal memberikan variasi sensitivitas  lebih seragam baik dalam arah radial dan aksial. Kata kunci: ECVT, Pencitraan 3-D volume, Matriks sensitivitas 3-D, Sensor kapasitansi 3-D.
Cardiac Imaging with Electrical Impedance Tomography (EIT) using Multilayer Perceptron Network Amelia Putri Ristyawardani; Marlin Ramadhan Baidillah; Yudi Adityawarman; Pratondo Busono; Mochamad Adityo Rachmadi; Meta Yantidewi; Endah Rahmawati
Jurnal Elektronika dan Telekomunikasi Vol. 25 No. 1 (2025)
Publisher : National Research and Innovation Agency

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55981/jet.705

Abstract

This research explores the enhancement of Electrical Impedance Tomography (EIT) for cardiac imaging using Multilayer Perceptron (MLP) networks, focusing on supervised and semi-supervised learning approaches. Using synthetic thoracic datasets simulating dynamic cardiac and respiratory conditions, the study demonstrates that supervised learning achieves lower mean squared error (MSE) values (minimum 4.76) and more stable predictions compared to semi-supervised learning (minimum MSE 5.08). However, semi-supervised learning excels in edge accuracy and noise reduction, particularly in regions with sharp conductivity gradients, making it viable for scenarios with limited labeled data. Dropout regularization at 0.3 provided optimal balance, enhancing model generalization and robustness. While supervised learning outperformed semi-supervised methods in overall accuracy, the latter showed potential for cost-effective and scalable applications in EIT-based cardiac imaging. These findings suggest that integrating advanced machine learning with EIT can improve diagnostic accuracy and enable efficient use of sparse labeled data, paving the way for future optimizations and clinical applications.