Article Per Year (5 Year)
p-Index From 2021 - 2026
2.307
P-Index
This Author published in this journals
All Journal IAES International Journal of Artificial Intelligence (IJ-AI) Teknik dan Ilmu Komputer Journal of Information Systems Engineering and Business Intelligence Jurnal Sistem dan Manajemen Industri Jurdimas (Jurnal Pengabdian Kepada Masyarakat) Royal ComTech: Computer, Mathematics and Engineering Applications Jurnal Teori dan Aplikasi Fisika Jurnal Ilmiah Teknik Industri Patria : Jurnal Pengabdian Kepada Masyarakat Jurnal ABDIMAS (Pengabdian kepada Masyarakat) UBJ Journal of Innovation and Community Engagement Metris: Jurnal Sains dan Teknologi
Iwan Aang Soenandi
Universitas Kristen Krida Wacana
Arts Humanities Astronomy Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Engineering Environmental Science Health Professions Industrial & Manufacturing Engineering Law, Crime, Criminology & Criminal Justice Materials Science & Nanotechnology Mathematics Physics Public Health Social Sciences Transportation Other

Published : 27 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 27 Documents
Search

 1   2   3 
Deep learning model for detection acute cardiogenic pulmonary edema in cases of preeclampsia Hayat, Cynthia; Soenandi, Iwan Aang
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 13, No 4: December 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v13.i4.pp4806-4812

Abstract

The physiological changes during the pregnancy period increase the risk of developing pulmonary edema and acute respiratory failure. This condition falls under critical medical emergencies associated with maternal mortality. This study utilized a convolutional neural networks (CNN) architectural model employing chest Xray dataset images. CNN utilizes the convolution process by moving a convolutional kernel of a certain size across an image, allowing the computer to derive new representative information from the multiplication of portions of the image with the utilized filter.To simplify, the vanishing gradient issue occurs when information dissipates before reaching its destination due to the lengthy path between input and output layers. This study was developed model for detection acute cardiogenic pulmonary Edema in pre-eclampsia cases using chest Xray images, implemented using PyTorch, Keras, and MxNet. The validated model achieved its optimum with accuracy 90.65% and binary cross-entropy loss (BCELoss) value of 0.4538. It exhibited an improved sensitivity value of 83.514% using a 5% dataset and a specificity value of 57.273%. This indicates an increase in sensitivity value by 83.514% using a 5% data set and a specificity value of 57.273%. The research results demonstrate an improvement in accuracy compared to several similar studies that also utilized CNN models.
Fatigue analysis and design of a motorcycle online driver measurement tool using real-time sensors Soenandi, Iwan Aang; Oktavera, Isnia; Lusiana, Vera; Widodo, Lamto; Harsono, Budi
Jurnal Sistem dan Manajemen Industri Vol. 7 No. 2 (2023): December
Publisher : Universitas Serang Raya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30656/jsmi.v7i2.7500

Abstract

Work fatigue is an important aspect and is very influential in determining the level of accidents, especially motorbike accidents. According to WHO, almost 30% of all deaths due to road accidents involve two- and three-wheel­ed motorized vehicles, such as motorbikes, mopeds, scooters and electric bicycles (e-bikes), and the number continues to increase. Motor­cycles dominate road deaths in many low- and middle-income countries, where nine out of ten traffic accident deaths occur among motorcyclists, as in Indonesia. However, until now, in Indonesia, there has been no monitor­ing system capable of identifying fatigue in motorbike drivers in the transportation sector. This research aims to determine fatigue patterns based on driver working hours and create a sensor system to monitor fatigue measurements in real-time to reduce the number of accidents. The research began with processing questionnaire data with Pearson correlation, which showed a close relationship between driver fatigue and driving time and a close relationship between fatigue and increased heart rate and sweating levels. From calibration tests with an error of 3% and direct measurements of working conditions, it was found that two-wheeled vehicle driver fatigue occurs after 2-3 hours of work. With a measurement system using the Box Whiskers analysis method, respondents' working conditions can also be de­ter­mined, which are divided into 4 zones, namely zone 1 (initial condition or good condition), zone 2 a declining condition, zone 3 a tired condition and zone 4 is a resting condition. Hopefully, this research will identify fati­gue zones correctly and reduce the number of accidents because it can iden­tify tired drivers so they do not have to force themselves to continue working and driving their motorbikes. As a conclusion from this research, a measure­ment system using two sensors, such as ECG and GSR can identify work fatigue zones well and is expected to reduce the number of accidents due to work fatigue.
Estimation Quality Monitoring Glycerol Esterification Process with IR Sensors Using K Nearest Neighbours Classification Soenandi, Iwan Aang; Liman, Johansah; Harsono, Budi
Metris: Jurnal Sains dan Teknologi Vol. 16 No. 02 (2015): Desember
Publisher : Prodi Teknik Industri, Fakultas Teknik - Universitas Katolik Indonesia Atma Jaya

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

Abstract

The commercial synthesis of fatty acid esters of glycerol is important because it can be used for other derivative production varieties. This research aims to construct the quality monitoring system for esterification condition faster and more efficient for the production of esterification glycerol. The monitoring systems were based on the measurement parameters from two inputs LED mid IR 3,4 and 5,5 μm sensors that using the data acquisition with computer database via USB 2.0 using Arduino Leonardo microcontroller and classifying the esterification quality condition using the classification method K-Nearest Neighborhood (KNN) The purpose of KNN method is to classify the variations of parameter inputs from the LED mid IR sensors in quality monitoring. In this research the condition of esterification was divided into three conditions: not good, fair,good., these classification was trained and tested in Orange Software for data mining using receiver operating characteristic (ROC) curve that is a graphical plot that illustrates the excellent performance of a classifier system for esterification condition with AUC . In application for quality monitoring, the influence of various parameters such as temperature set in the reactor has relation to the quality of product. By using this system, we obtained the optimum process conditions is 200oC and time needed for the process was 200 minutes.
Hybrid Architecture Model of Genetic Algorithm and Learning Vector Quantization Neural Network for Early Identification of Ear, Nose, and Throat Diseases Hayat, Cynthia; Soenandi, Iwan Aang
Journal of Information Systems Engineering and Business Intelligence Vol. 10 No. 1 (2024): February
Publisher : Universitas Airlangga

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20473/jisebi.10.1.1-12

Abstract

Background: In 2020, the World Health Organization (WHO) estimated that 466 million people worldwide are affected by hearing loss, with 34 million of them being children. Indonesia is identified as one of the four Asian countries with a high prevalence of hearing loss, specifically at 4.6%. Previous research was conducted to identify diseases related to the Ear, Nose, and Throat, utilizing the certainty factor method with a test accuracy rate of 46.54%. The novelty of this research lies in the combination of two methods, the use of genetic algorithms for optimization and learning vector quantization to improve the level of accuracy for early identification of Ear, Nose, and Throat diseases. Objective: This research aims to produce a hybrid model between the genetic algorithm and the learning vector quantization neural network to be able to identify Ear, Nose, and Throat diseases with mild symptoms to improve accuracy. Methods: Implementing a 90:10 ratio means that 90% (186 data) of the data from the initial sequence is assigned for training purposes, while the remaining 10% (21 data) is allocated for testing. The procedural stages of genetic algorithm-learning vector quantization are population initialization, crossover, mutation, evaluation, selection elitism, and learning vector quantization training. Results The optimum hybrid genetic algorithm-learning vector quantization model for early identification of Ear, Nose, and Throat diseases was obtained with an accuracy of 82.12%. The parameter values with the population size 10, cr 0.9, mr 0.1, maximum epoch of 5000, error goal of 0.01, and learning rate (alpha) of 0.5. Better accuracy was obtained compared to backpropagation (64%), certainty factor 46.54%), and radial basic function (72%). Conclusion: Experiments in this research, successed identifying models by combining genetic algorithm-learning vector quantization to perform the early identification of Ear, Nose, and Throat diseases. For further research, it's very challenging to develop a model that automatically adapts the bandwidth parameters of the weighting functions during trainin   Keywords: Early Identification, Ear-Nose-Throat Diseases, Genetic Algorithm, Learning Vector Quantization
Pemulihan Kesehatan Dan Fasilitas Pendidikan Pasca Gempa Cianjur Di Wilayah Cugenang Soenandi, Iwan Aang; Peranginangin, Prasasti; Silalahi, Malianti; Mokorowu, Yanny Yeski; Ginting, Meriastuti
Jurdimas (Jurnal Pengabdian Kepada Masyarakat) Royal Vol. 6 No. 3 (2023): Juli 2023
Publisher : STMIK Royal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33330/jurdimas.v6i3.2274

Abstract

Abstract: The Community Service Program, LDDIKTI 3 in collaboration with DITJENDIKTIRISTEK and Universities launched an Incentive Program for Assignment to Private Universities for the Implementation of Community Service in the Cianjur Earthquake Area based on Key Performance Indicators with a focus on the goal of Recovery for Victims of the Cianjur Earthquake Natural Disaster, West Java. From the results of observations made in the Cianjur and surrounding areas which were affected by the earthquake, many locations in Wangunjaya Village, Cugenang Regency, have not been touched and received assistance. Many people in this area experience health problems due to unbalanced nutritional intake and unclean lifestyle, damage to learning tools in schools and early childhood education, especially at SMPN 2 Cugenang and in early childhood education. The aim of the activity is to improve public health from a physical and mental perspective and to help restore education using digital learning. The activities carried out included conducting free examinations and treatment, teaching Progressive Muscle Relaxation (PMR) therapy to reduce anxiety in the community, distributing healthy food parcels, providing trauma healing for school children, and providing school facilities for schools. Keywords: cianjur earthquake; cugenang; community service; educational facilities; health recovery. Abstrak: Program Pengabdian Masyarakat, LDDIKTI 3 bekerjasama dengan DITJENDIKTIRISTEK dan Perguruan Tinggi mencanangkan Program Insentif Penugasan kepada Perguruan Tinggi Swasta untk Pelaksanaan Pengabdian Kepada Masyarakat di Wilayah Gempa Cianjur berbasis Kinerja Indikator Kinerja Utama dengan fokus tujuan Pemulihan Korban Bencana Alam Gempa Cianjur Jawa Barat. Dari hasil pengamatan yang dilakukan di daerah Cianjur dan sekitarnya yang terkena dampak gempa, lokasi Desa Wangunjaya Kabupaten Cugenang masih banyak yang belum tersentuh dan mendapatkan bantuan. Para masyarakat didaerah ini banyak yang mengalami masalah kesehatan karena asupan gizi yang tidak seimbang serta perilaku hidup yang tidak bersih, kerusakan alat-alat pembelajaran di sekolah dan PAUD khususnya di SMPN 2 Cugenang dan di PAUD. Tujuan kegiatan adalah untuk meningkatkan kesehatan masyarakat dari segi jasmani serta mental dan membantu memulihkan Pendidikan menggunakan pembelajaran digital. Kegiatan yang dilakukan adalah melakukan pemeriksaan dan pengobatan gratis, mengajarkan terapi Progressive Muscle Relaxation (PMR) untuk menurunkan ansietas pada masyarakat,  membagikan parcel makanan sehat, memberikan trauma healing bagi anak sekolah, serta memberikan bantuan fasilitas sekolah bagi sekolah. Hasil dari kegiatan ini menunjukkan bahwa terjadinya peningkatan perasaan bahagia siswa dan masyarakat (+52%), siswa menjadi bisa merasakan pembelajaran digital (+34%) dan masyarakat menjadi lebih merasakan jasmani yang lebih sehat (+17%). Kata kunci: cugenang; fasilitas pendidikan; gempa cianjur; pemulihan kesehatan; pengabdian masyarakat.
Deep Learning Architecture with Attention-Enhanced U-Net for Analyzing Cell Nuclei in H&E-Stained Tissue Slides Hayat, Cynthia; Soenandi, Iwan Aang
Journal of Information Systems Engineering and Business Intelligence Vol. 12 No. 1 (2026): February
Publisher : Universitas Airlangga

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

Abstract

Background: Accurate segmentation of cell nuclei in histopathological images plays a crucial role in computational pathology, as the results serve as a foundation for various clinical practices, including disease diagnosis, prediction, and prognosis. Deep learning methods like U-Net have greatly enhanced performance, but challenges such as tissue heterogeneity, cell nucleus overlap, and complex staining patterns still exist. Objective: This study aims to assess the effectiveness of the Attention Mechanism model within the U-Net architecture for cell nucleus segmentation in Hematoxylin and Eosin (H&E) stained histopathology images. By focusing on relevant spatial features, the Attention Mechanism is expected to improve the model’s ability to accurately distinguish and segment areas with overlapping cells. Specifically, this study also aims to examine whether the proposed model outperforms the conventional U-Net model. Methods: This study used a quantitative experimental approach, utilizing an H&E-stained histopathology image dataset from Saitama Medical University International Medical Center (SIMC). The Attention-Enhanced U-Net Model was trained and tested on pathologist-annotated cell nucleus data, then evaluated using performance metrics such as Dice Coefficient, Accuracy, Precision, Recall, F1-Score, AUROC Mean, and Intersection over Union (IoU). The experimental results showed that the model produced a Dice Coefficient of 0.927, Precision of 0.889, Recall of 0.861, F1-Score of 0.875, and IoU of 0.793. These findings indicate that the model can accurately capture the structure of a cell nucleus, even in challenging conditions such as different cell shapes and the presence of H&E staining. Results: Furthermore, integrating Attention Mechanisms allows the model to focus on extracting relevant features while reducing background noise. This improves its potential as a reliable segmentation solution in clinical pathology workflows. For future research, it is recommended to validate the model using a larger, more diverse dataset to improve its generalization and reliability in real-world clinical practice. Conclusion: The research concludes that the Attention-Enhanced U-Net model effectively achieves high-precision cell nucleus segmentation in H&E-stained histopathology images. It demonstrates strong performance across five metrics: Dice (0.927), Precision (0.889), Recall (0.861), F1-Score (0.875), and IoU (0.793). The model accurately detects nuclei, even in challenging conditions such as morphological variation, staining artifacts, and overlapping structures. Its attention mechanism improves feature extraction by focusing on relevant regions and reducing background noise, enhancing localization and delineation. The lightweight design supports clinical use with limited resources. Future studies should validate its generalizability on larger, more diverse datasets and clinical scenarios.   Keywords: Cell Nuclei Segmentation, Attention Enhanced U-Net, H&E Staining; Deep Learning, Medical Image Analysis.
Sintesis dan Karakterisasi Sifat Optik Material Feroelektrik Barium Zirkonium Titanat (BaZr0,5Ti0,5O3) dengan Variasi Suhu Kalsinasi Johansah Liman; Budi Harsono; Iwan Aang Soenandi
Jurnal Teori dan Aplikasi Fisika Vol. 11 No. 1 (2023): Jurnal Teori dan Aplikasi Fisika
Publisher : Department of Physics, Faculty of Mathematics and Natural Sciences, University of Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/jtaf.v11i1.333

Abstract

Dalam penelitian ini, film tipis material feroelektrik Barium Zirkonium Titanat (BaZr0,5Ti0,5O3) disintesis dan pengaruh variasi suhu annealing terhadap sifat optiknya dipelajari. Film tipis BaZr0,5Ti0,5O3 ditumbuhkan di atas substrat Silikon (Si (100)) menggunakan metode Chemical Solution Deposition (CSD) dengan bantuan perangkat spin coater. Film tipis yang telah dibuat kemudian di-annealing pada tiga suhu berbeda (750 oC, 800 oC dan 850 oC). Karakterisasi sifat optik dari film tipis yang telah dibuat dilakukan menggunakan Spektrometer Ultraviolet-Visible (UV-Vis) Ocean Optics USB4000. Hasil karakterisasi menunjukkan bahwa film tipis BaZr0,5Ti0,5O3 yang dibuat memiliki nilai reflektansi yang tinggi pada panjang gelombang cahaya tampak dan nilai koefisien absorbansi yang tinggi pada panjang gelombang cahaya ultraviolet (UV). Nilai bandgap pada masing-masing film tipis BaZr0,5Ti0,5O3 dengan suhu annealing 750 oC, 800 oC dan 850 oC adalah 3,04 eV, 3,07 eV dan 3,22 eV. Semakin tinggi suhu annealing maka semakin tinggi nilai bandgap yang dihasilkan. Dari hasil yang diperoleh, terlihat bahwa film tipis BaZr0,5Ti0,5O3 yang dihasilkan memiliki sifat semikonduktor dan berpotensi digunakan sebagai sensor atau komponen elektronik yang bekerja memanfaatkan energi pada panjang gelombang cahaya ultraviolet.
Co-Authors Angin, Prasasti Perangin Antika Ningrum Sundoro Anu, Benisius BUDI HARSONO Budi Harsono Budi Harsono Budi Marpaung Budi Marpaung Cynthia Hayat Doddy Budiawan Eilen Celsia Florensa Rosani Purba Harya, Eka Mulyo Isnia Oktavera Johansah Liman Johansah Liman Johansah Liman Joice Joice Joice, Joice lamto widodo Lusiana, Vera Malvin, Raymond Marcelle Marcelle Marpaung, Budi Meriastuti Ginting Meriastuti Ginting Mokorowu, Yanny Yeski Novita Yulianti Oktavera, Isnia Peranginangin, Prasasti Prasasti Peranginangin Raymond Malvin Ronaldo Josua Ondang Silalahi, Malianti Tanra, Ivan Vera Lusiana Wilson Kosasih Yanny Yeski Mokorowu