cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Triwiyanto
Contact Email
triwiyanto123@gmail.com
Phone
+628155126883
Journal Mail Official
editorial.jeeemi@gmail.com
Editorial Address
Department of Electromedical Engineering, Poltekkes Kemenkes Surabaya Jl. Pucang Jajar Timur No. 10, Surabaya, Indonesia
Location
Kota surabaya,
Jawa timur
INDONESIA
Journal of Electronics, Electromedical Engineering, and Medical Informatics
Published by Polilteknik Kesehatan Kemenkes Surabaya
ISSN : -     EISSN : 26568632     DOI : https://doi.org/10.35882/jeeemi
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Engineering
The Journal of Electronics, Electromedical Engineering, and Medical Informatics (JEEEMI) is a peer-reviewed open-access journal. The journal invites scientists and engineers throughout the world to exchange and disseminate theoretical and practice-oriented topics which covers three (3) majors areas of research that includes 1) Electronics, 2) Biomedical Engineering, and 3)Medical Informatics (emphasize on hardware and software design). Submitted papers must be written in English for an initial review stage by editors and further review process by a minimum of two reviewers.
Arjuna Subject : Teknik (semua kategori) - Teknik Biomedis
Articles 9 Documents
 1 
Search results for , issue "Vol 6 No 3 (2024): July" : 9 Documents clear
Hybrid Radix-4 SESA/SEDA Adders for Medical Image Processing L, Sowmiya; S M, Ramesh; Shadrach, S Finney Daniel; A, Arul
Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol 6 No 3 (2024): July
Publisher : Department of Electromedical Engineering, POLTEKKES KEMENKES SURABAYA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/jeeemi.v6i3.400

Abstract

Adders play a critical role as primary modules in circuit design, supporting error-tolerant applications such as machine learning, digital image processing, and signal processing. Therefore, the development of adders with low power consumption and energy efficiency is of utmost importance. Approximate adders outperform exact adders in VLSI chips. Among approximate adders, the hybridization of Single Exact and Single Approximation (SESA) and Single Exact and Dual Approximation (SEDA) techniques has emerged as a promising solution. These hybrid adders offer superior power and energy savings relative to other accurate and approximate adder designs. In this scheme, we propose the integration of hybrid radix-4 adders with approximation adders to achieve enhanced performance and pave the way for future hybrid approximate adder circuits. Extensive simulations validated the efficacy of the proposed approach. Furthermore, practical applications demonstrated the versatility and potential of hybrid adders in real-world scenarios. The proposed methodology ensures cost-effectiveness and facilitates seamless future updates and extensions. Overall, this research contributes to the advancement of efficient and low-power adder designs, addressing the evolving requirements of modern digital systems.
Gender Classification on Social Media Messages Using fastText Feature Extraction and Long Short-Term Memory Sa’diah, Halimatus; Faisal, Mohammad Reza; Farmadi, Andi; Abadi, Friska; Indriani, Fatma; Alkaff, Muhammad; Abdullayev, Vugar
Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol 6 No 3 (2024): July
Publisher : Department of Electromedical Engineering, POLTEKKES KEMENKES SURABAYA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/jeeemi.v6i3.407

Abstract

Currently, social media is used as a platform for interacting with many people and has also become a source of information for social media researchers or analysts. Twitter is one of the platforms commonly used for research purposes, especially for data from tweets written by individuals. However, on Twitter, user information such as gender is not explicitly displayed in the account profile, yet there is a plethora of unstructured information containing such data, often unnoticed. This research aims to classify gender based on tweet data and account description data and determine the accuracy of gender classification using machine learning methods. The method used involves FastText as a feature extraction method and LSTM as a classification method based on the extracted data, while to achieve the most accurate results, classification is performed on tweet data, account description data, and a combination of both. This research shows that LSTM classification on account description data and combined data obtained an accuracy of 70%, while tweet data classification achieved 69%. This research concludes that FastText feature extraction with LSTM classification can be implemented for gender classification. However, there is no significant difference in accuracy results for each dataset. However, this research demonstrates that both methods can work well together and yield optimal results.
Comparison of the Adaboost Method and the Extreme Learning Machine Method in Predicting Heart Failure Muhammad Nadim Mubaarok; Triando Hamonangan Saragih; Muliadi; Fatma Indriani; Andi Farmadi; Rizal, Achmad
Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol 6 No 3 (2024): July
Publisher : Department of Electromedical Engineering, POLTEKKES KEMENKES SURABAYA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/jeeemi.v6i3.440

Abstract

Heart disease, which is classified as a non-communicable disease, is the main cause of death every year. The involvement of experts is considered very necessary in the process of diagnosing heart disease, considering its complex nature and potential severity. Machine Learning Algorithms have emerged as powerful tools capable of effectively predicting and detecting heart diseases, thereby reducing the challenges associated with their diagnosis. Notable examples of such algorithms include Extreme Learning Machine Algorithms and Adaptive Boosting, both of which represent Machine Learning techniques adapted for classification purposes. This research tries to introduce a new approach that relies on the use of one parameter. Through careful optimization of algorithm parameters, there is a marked improvement in the accuracy of machine learning predictions, a phenomenon that underscores the importance of parameter tuning in this domain. In this research, the Heart Failure dataset serves as the focal point, with the aim of demonstrating the optimal level of accuracy that can be achieved through the use of Machine Learning algorithms. The results of this study show an average accuracy of 0.83 for the Extreme Learning Machine Algorithm and 0.87 for Adaptive Boosting, the standard deviation for both methods is “0.83±0.02” for Extreme Machine Learning Algorithm and “0.87±0.03” for Adaptive Boosting thus highlighting the efficacy of these algorithms in the context of heart disease prediction. In particular, entering the Learning Rate parameter into Adaboost provides better results when compared with the previous algorithm. Our research findings underline the supremacy of Extreme Learning Machine Algorithms and Adaptive Improvement, especially when combined with the introduction of a single parameter, it can be seen that the addition of parameters results in increased accuracy performance when compared to previous research using standard methods alone.
Simple Data Augmentation and U-Net CNN for Neclui Binary Segmentation on Pap Smear Images Desiani, Anita; Irmeilyana; Zayanti, Des Alwine; Utama, Yadi; Arhami, Muhammad; Affandi, Azhar Kholiq; Sasongko, Muhammad Aditya; Ramayanti, Indri
Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol 6 No 3 (2024): July
Publisher : Department of Electromedical Engineering, POLTEKKES KEMENKES SURABAYA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/jeeemi.v6i3.442

Abstract

The nuclei and cytoplasm can be detected through Pap smear images. The image consists of cytoplasm and nuclei. In Pap smear image, nuclei are the most critical cell components and undergo significant changes in cervical cancer disorders. To help women avoid cervical cancer, early detection of nuclei abnormalities can be done in various ways, one of which is by separating the nuclei from the non-nucleis part by image segmentation it. In this study, segmentation of the separation of nuclei with other parts of the Pap smear image is carried out by applying the U-Net CNN architecture. The amount of pap smear image data is limited. The limiter data can cause overfitting on U-Net CNN model. Meanwhile, U-Net CNN needs a large amount of training data to get great performance results for classification. One technique to increase data is augmentation. Simple techniques for augmentation are flip and rotation. The result of the application of U-Net CNN architecture and augmentation is a binary image consisting of two parts, namely the background and the nuclei. Performance evaluation of combination U-Net CNN and augmentation technique is accuracy, sensitivity, specificity, and F1-score. The results performance of the method for accuracy, sensitivity, and F1-score values are greater than 90%, while the specificity is still below 80%. From these performance results, it shows that the U-Net CNN combine augmentation technique is excellent to detect nuclei in compared to detect non nuclei cell on pap smear image.
A Comparative Study: Application of Principal Component Analysis and Recursive Feature Elimination in Machine Learning for Stroke Prediction Hermiati, Arya Syifa; Herteno, Rudy; Indriani, Fatma; Saragih, Triando Hamonangan; Muliadi; Triwiyanto, Triwiyanto
Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol 6 No 3 (2024): July
Publisher : Department of Electromedical Engineering, POLTEKKES KEMENKES SURABAYA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/jeeemi.v6i3.446

Abstract

Stroke is a disease that occurs in the brain and can cause both vocal and global brain dysfunction. Stroke research mainly aims to predict risk and mortality. Machine learning can be used to diagnose and predict diseases in the healthcare field, especially in stroke prediction. However, collecting medical record data to predict a disease usually makes much noise because not all variables are important and relevant to the prediction process. In this case, dimensionality reduction is essential to remove noisy (i.e., irrelevant) and redundant features. This study aims to predict stroke using Recursive Feature Elimination as feature selection, Principal Component Analysis as feature extraction, and a combination of Recursive Feature Elimination and Principal Component Analysis. The dataset used in this research is stroke prediction from Kaggle. The research methodology consists of pre-processing, SMOTE, 10-fold Cross-Validation, feature selection, feature extraction, and machine learning, which includes SVM, Random Forest, Naive Bayes, and Linear Discriminant Analysis. From the results obtained, the SVM and Random Forest get the highest accuracy value of 0.8775 and 0.9511 without using PCA and RFE, Naive Bayes gets the highest value of 0.7685 when going through PCA with selection of 20 features followed by RFE feature selection with selection of 5 features, and LDA gets the highest accuracy with 20 features from feature selection and continued feature extraction with a value of 0. 7963. It can be concluded in this study that SVM and Random Forest get the highest accuracy value without PCA and RFE techniques, while Naive Bayes and LDA show better performance using a combination of PCA and RFE techniques. The implication of this research is to know the effect of RFE and PCA on machine learning to improve stroke prediction.
A Comparative Study of Improved Ensemble Learning Algorithms for Patient Severity Condition Classification Edi Ismanto; Abdul Fadlil; Anton Yudhana; Kitagawa, Kodai
Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol 6 No 3 (2024): July
Publisher : Department of Electromedical Engineering, POLTEKKES KEMENKES SURABAYA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/jeeemi.v6i3.452

Abstract

The evolution of Electronic Health Records (EHR) has facilitated comprehensive patient record-keeping, enhancing healthcare delivery and decision-making processes. Despite these advancements, analyzing EHR data using ensemble machine learning methods poses unique challenges. These challenges include data dimensionality, imbalanced class distributions, and the need for effective hyperparameter tuning to optimize model performance. The study conducted a thorough comparative analysis of various ensemble machine learning (EML) models using Electronic Health Record (EHR) datasets. After addressing data imbalance and reducing dimensionality, the accuracy of the EML models showed significant improvement. Notably, the Gradient Boosting Machine (GBM) and CatBoost models exhibited superior performance with an accuracy of 73%, achieved through experiments involving dimensionality reduction and handling of imbalanced data. Furthermore, optimization techniques such as Grid Search and Random Search were employed to enhance the EML models. The results of model optimization revealed that the GBM + Random Search model performed the best, achieving an accuracy of 74%, followed by the XGBoost + Grid Search model with an accuracy of 73%. The GBM model also excelled in distinguishing between positive and negative classes, boasting the highest Area under Curve (AUC) value of 0.78, indicative of its superior classification capabilities compared to other models. This study emphasizes the significance of incorporating cutting-edge EML techniques into clinical workflows and emphasizes the revolutionary potential of GBM in classification modeling for patient severity conditions. Future research should focus on deep learning (DL) applications and the integration of these models.
Analysis of Important Features in Software Defect Prediction Using Synthetic Minority Oversampling Techniques (SMOTE), Recursive Feature Elimination (RFE) and Random Forest Ghinaya, Helma; Herteno, Rudy; Faisal, Mohammad Reza; Farmadi, Andi; Indriani, Fatma
Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol 6 No 3 (2024): July
Publisher : Department of Electromedical Engineering, POLTEKKES KEMENKES SURABAYA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/jeeemi.v6i3.453

Abstract

Software Defect Prediction (SDP) is essential for improving software quality during testing. As software systems grow more complex, accurately predicting defects becomes increasingly challenging. One of the challenges faced is dealing with imbalanced class distributions, where the number of defective instances is significantly lower than non-defective ones. To tackle the imbalanced class issue, use the SMOTE technique. Random Forest as a classification algorithm is due to its ability to handle non-linear data, its resistance to overfitting, and its ability to provide information about the importance of features in classification. This research aims to evaluate important features and measure accuracy in SDP using the SMOTE+RFE+Random Forest technique. The dataset used in this study is NASA MDP D", which included 12 data sets. The method used combines SMOTE, RFE, and random forest techniques. This study is conducted in two stages of approach. The first stage uses the RFE+Random Forest technique; the second stage involves adding the SMOTE technique before RFE and Random Forest to measure the accurate data from NASA MDP. The result of this study is that the use of the SMOTE technique enhances accuracy across most datasets, with the best performance achieved on the MC1 dataset with an accuracy of 0.9998. Feature importance analysis identifies "maintenance severity" and "cyclomatic density" as the most crucial features in data modeling for SDP. Therefore, the SMOTE+RFE+RF technique effectively improves prediction accuracy across various datasets and successfully addresses class imbalance issues.
A Comparative Analysis of Polynomial-fit-SMOTE Variations with Tree-Based Classifiers on Software Defect Prediction Nur Hidayatullah, Wildan; Herteno, Rudy; Reza Faisal, Mohammad; Adi Nugroho, Radityo; Wahyu Saputro, Setyo; Akhtar, Zarif Bin
Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol 6 No 3 (2024): July
Publisher : Department of Electromedical Engineering, POLTEKKES KEMENKES SURABAYA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/jeeemi.v6i3.455

Abstract

Software defects present a significant challenge to the reliability of software systems, often resulting in substantial economic losses. This study examines the efficacy of polynomial-fit SMOTE (pf-SMOTE) variants in combination with tree-based classifiers for software defect prediction, utilising the NASA Metrics Data Program (MDP) dataset. The research methodology involves partitioning the dataset into training and test subsets, applying pf-SMOTE oversampling, and evaluating classification performance using Decision Trees, Random Forests, and Extra Trees. Findings indicate that the combination of pf-SMOTE-star oversampling with Extra Tree classification achieves the highest average accuracy (90.91%) and AUC (95.67%) across 12 NASA MDP datasets. This demonstrates the potential of pf-SMOTE variants to enhance classification effectiveness. However, it is important to note that caution is warranted regarding potential biases introduced by synthetic data. These findings represent a significant advancement over previous research endeavors, underscoring the critical role of meticulous algorithm selection and dataset characteristics in optimizing classification outcomes. Noteworthy implications include advancements in software reliability and decision support for software project management. Future research may delve into synergies between pf-SMOTE variants and alternative classification methods, as well as explore the integration of hyperparameter tuning to further refine classification performance.
A Classification of Appendicitis Disease in Children Using SVM with KNN Imputation and SMOTE Approach Difa Fitria; Triando Hamonangan Saragih; Muliadi; Dwi Kartini; Fatma Indriani
Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol 6 No 3 (2024): July
Publisher : Department of Electromedical Engineering, POLTEKKES KEMENKES SURABAYA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/jeeemi.v6i3.470

Abstract

This study evaluates the effect of SMOTE and KNN imputation techniques on the performance of SVM classification models on a nearly balanced dataset. The results show that using SMOTE increases model precision but decreases recall. This shows the importance of careful consideration when choosing data processing strategies to achieve optimal classification model performance. This study evaluates the effect of the Synthetic Minority Over-sampling Technique (SMOTE) and K-Nearest Neighbors (KNN) imputation on the performance of Support Vector Machine (SVM) classification models on nearly balanced datasets. The results of this study noted that the use of SMOTE techniques in balancing the dataset led to a decrease in classification model accuracy from 87.26% to 85.99%. However, there was a slight increase in AUC-ROC, from 85.96% to 88.04%. The results of this study noted that the use of the SMOTE technique in balancing the dataset caused a decrease in the accuracy of the classification model from 87.26% to 85.99%. However, there was an improvement in the AUC-ROC, from 85.96% to 88.04%.

Page 1 of 1 | Total Record : 9

 1 

Filter by Year

2024 2024


Reset
Filter By Issues
All Issue Vol 8 No 1 (2026): January Vol 7 No 4 (2025): October Vol 7 No 3 (2025): July Vol 7 No 2 (2025): April Vol 7 No 1 (2025): January Vol 6 No 4 (2024): October Vol 6 No 3 (2024): July Vol 6 No 2 (2024): April Vol 6 No 1 (2024): January Vol 5 No 4 (2023): October Vol 5 No 3 (2023): July Vol 5 No 2 (2023): April Vol 5 No 1 (2023): January Vol 4 No 4 (2022): October Vol 4 No 3 (2022): July Vol 4 No 2 (2022): April Vol 4 No 1 (2022): January Vol 3 No 3 (2021): October Vol 3 No 2 (2021): July Vol 3 No 1 (2021): January Vol 2 No 3 (2020): October Vol 2 No 2 (2020): July Vol 2 No 1 (2020): January Vol 1 No 2 (2019): October Vol 1 No 1 (2019): July More Issue