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 287 Documents
 22   23   24   25   26 
Advanced Deep Learning for Stroke Classification Using Multi-Slice CT Image Analysis Lezzar, Fouzi; Mili, Seif Eddine
Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol 7 No 3 (2025): July
Publisher : Department of Electromedical Engineering, POLTEKKES KEMENKES SURABAYA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/jeeemi.v7i3.947

Abstract

Brain stroke is a leading cause of mortality and disability globally, necessitating rapid and accurate diagnosis for timely intervention. While Computed Tomography (CT) imaging is the gold standard for stroke detection, manual interpretation is time-consuming, prone to error, and subject to inter-observer variability. Although deep learning models have shown promise in automating stroke detection, many rely on 2D analysis, ignore 3D spatial relationships, or require labour-intensive slice-level annotations, which limits their scalability and clinical applicability. To address these challenges, we propose MedHybridNet, a novel hybrid deep learning architecture that integrates convolutional neural networks (CNNs) for local feature extraction with Transformer-based modules to model global contextual dependencies across volumetric brain scans. Our main contribution is twofold: (1) the SliceAttention mechanism, which dynamically identifies diagnostically relevant slices using only patient-level labels, eliminating the need for costly slice-level annotations while enhancing interpretability through attention maps and Grad-CAM visualizations; and (2) a cGAN-based augmentation strategy that generates high-quality, pathology-informed synthetic CT slices to overcome data scarcity and class imbalance. The framework processes complete 3D brain volumes, leveraging both CNNs and Transformers in a dual-path design, and incorporates hierarchical attention for refined feature selection and classification. Evaluated via patient-wise 5-fold cross-validation on a real-world dataset of 2501 CT scans from 82 patients, MedHybridNet achieves an accuracy of 98.31%, outperforming existing methods under weak supervision. These results demonstrate its robustness, generalization capability, and superior interpretability. By combining architectural innovation with clinically relevant design choices, MedHybridNet advances the integration of Artificial Intelligence (AI) into real-world stroke care, offering a scalable, accurate, and explainable solution that can significantly improve diagnostic efficiency and patient outcomes in routine clinical practice.
Advanced Traffic Flow Optimization Using Hybrid Machine Learning and Deep Learning Techniques El Kaim Billah, Mohammed; Mabrouk, Abdelfettah
Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol 7 No 3 (2025): July
Publisher : Department of Electromedical Engineering, POLTEKKES KEMENKES SURABAYA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/jeeemi.v7i3.948

Abstract

Road traffic congestion remains a persistent and critical challenge in modern urban environments, adversely affecting travel times, fuel consumption, air quality, and overall urban livability. To address this issue, this study proposes a hybrid ensemble learning framework for accurate short-term traffic flow prediction across signalized urban intersections. The model integrates Random Forest, Gradient Boosting, and Multi-Layer Perceptron within a weighted voting ensemble mechanism, wherein model contributions are dynamically scaled based on individual validation performance. Benchmarking is performed against traditional and advanced baselines, including Linear Regression, Support Vector Regression, and Long Short-Term Memory (LSTM) networks. A real-world traffic dataset, comprising 56 consecutive days of readings from six intersections, is utilized to validate the approach. A robust preprocessing pipeline is implemented, encompassing anomaly detection, temporal feature engineering especially time-of-day and day-of-week normalization, and sliding window encoding to preserve temporal dependencies. Experimental evaluations on 4-intersection and 6-intersection scenarios reveal that the ensemble consistently outperforms all baselines, achieving a peak R² of 0.954 and an RMSE of 0.045. Statistical significance testing using Welch’s t-test confirms the reliability of these improvements. Furthermore, SHAP-based interpretability analysis reveals the dominant influence of temporal features during high-variance periods. While computational overhead and data sparsity during rare events remain limitations, the framework demonstrates strong applicability for deployment in smart traffic systems. Its predictive accuracy and model transparency make it a viable candidate for adaptive signal control, congestion mitigation, and urban mobility planning. Future work may explore real-time streaming adaptation, external event integration, and generalization across heterogeneous urban networks.
Improving Accuracy and Efficiency of Medical Image Segmentation Using One-Point-Five U-Net Architecture with Integrated Attention and Multi-Scale Mechanisms Fathur Rohman, Muhammad Anang; Prasetyo, Heri; Yudha, Ery Permana; Hsia, Chih-Hsien
Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol 7 No 3 (2025): July
Publisher : Department of Electromedical Engineering, POLTEKKES KEMENKES SURABAYA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/jeeemi.v7i3.949

Abstract

Medical image segmentation is essential for supporting computer-aided diagnosis (CAD) systems by enabling accurate identification of anatomical and pathological structures across various imaging modalities. However, automated medical image segmentation remains challenging due to low image contrast, significant anatomical variability, and the need for computational efficiency in clinical applications. Furthermore, the scarcity of annotated medical images due to high labelling costs and the requirement of expert knowledge further complicates the development of robust segmentation models. This study aims to address these challenges by proposing One-Point-Five U-Net, a novel deep learning architecture designed to improve segmentation accuracy while maintaining computational efficiency. The main contribution of this work lies in the integration of multiple advanced mechanisms into a compact architecture: ghost modules, Multi-scale Residual Attention (MRA), Enhanced Parallel Attention (EPA) in skip connections, the Convolutional Block Attention Module (CBAM), and Multi-scale Depthwise Convolution (MSDC) in the decoder. The proposed method was trained and evaluated on four public datasets: CVC-ClinicDB, Kvasir-SEG, BUSI, and ISIC2018. One-Point-Five U-Net achieved sensitivity, specificity, accuracy, DSC, and IoU of of 94.89%, 99.63%, 99.23%, 95.41%, and 91.27% on CVC-ClinicDB; 91.11%, 98.60%, 97.33%, 90.93%, and 83.84% on Kvasir-SEG; 85.35%, 98.65%, 96.81%, 87.02%, and 78.18% on BUSI; and 87.67%, 98.11%, 93.68%, 89.27%, and 83.06% on ISIC2018. These results outperform several state-of-the-art segmentation models. In conclusion, One-Point-Five U-Net demonstrates superior segmentation accuracy with only 626,755 parameters and 28.23 GFLOPs, making it a highly efficient and effective model for clinical implementation in medical image analysis.
Combination Of Gamma Correction and Vision Transformer In Lung Infection Classification On CT-Scan Images Kesuma, Lucky Indra; Octavia , Pipin; Sari , Purwita; Batubara, Gracia Mianda Caroline; Karina, Karina
Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol 7 No 3 (2025): July
Publisher : Department of Electromedical Engineering, POLTEKKES KEMENKES SURABAYA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/jeeemi.v7i3.588

Abstract

Lung infection is an inflammatory condition of the lungs with a high mortality rate. Lung infections can be identified using CT-Scan images, where the affected areas are analyzed to determine the infection type. However, manual interpretation of CT-Scan results by medical specialists is often time-consuming, subjective, and requires a high level of accuracy. To address these challenges, this study proposes an automated classification method for lung infections using deep learning techniques. Convolutional Neural Networks (CNNs) are widely used for image classification tasks. However, CNN operates locally with limited receptive fields, making capturing global patterns in complex lung CT images challenging. CNN also struggles to model long-range pixel dependencies, which is crucial for analyzing visually similar regions in lung CT-Scans. This study uses a Vision Transformer (ViT) to overcome CNN limitations. ViT employs self-attention mechanisms to capture global dependencies across the entire image. The main contribution of this study is the implementation of ViT to enhance classification performance in lung CT-Scan images by capturing complex and global image patterns that CNN fails to model. However, ViT requires a large dataset to perform optimally. To overcome these challenges, augmentation techniques such as flipping, rotation, and gamma correction are applied to increase the amount of data without altering the important features. The dataset comprises lung CT-scan images sourced from Kaggle and is divided into Covid and Non-Covid classes. The proposed method demonstrated excellent classification performance, achieving accuracy, sensitivity, specificity, precision, and F1-Score above 90%. Additionally, the Cohen’s kappa coefficient reached 89%. These results show that the proposed method effectively classifies lung infections using CT-Scan images and has strong potential as a clinical decision-support tool, particularly in reducing diagnostic time and improving consistency in medical evaluations.
EEG Performance Signal Analysis for Diagnosing Autism Spectrum Disorder using Butterworth and Empirical Mode Decomposition Fathur Rahman, Imam; Melinda, Melinda; Irhamsyah, Muhammad; Yunidar, Yunidar; Nurdin, Yudha; Wong, W.K.; Zakaria, Lailatul Qadri
Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol 7 No 3 (2025): July
Publisher : Department of Electromedical Engineering, POLTEKKES KEMENKES SURABAYA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/jeeemi.v7i3.788

Abstract

Electroencephalography (EEG) is a technique used to measure electrical activity in the brain by placing electrodes on the scalp. EEG plays an essential role in analyzing a variety of neurological conditions, including autism spectrum disorder (ASD). However, in the recording process, EEG signals are often contaminated by noise, hindering further analysis. Therefore, an effective signal processing method is needed to improve the data quality before feature extraction is performed. This study applied the Butterworth Band-Pass Filter (BPF) as a preprocessing method to reduce noise in EEG signals and then used the Empirical Mode Decomposition (EMD) method to extract relevant features. The performance of this method was evaluated using three main parameters, namely Mean Square Error (MSE), Mean Absolute Error (MAE), and Signal-to-Noise Ratio (SNR). The results showed that EMD was able to retain important information in EEG signals better than signals that only passed through the BPF filtration stage. EMD produces lower MAE and MSE values than Butterworth, suggesting that this method is more accurate in maintaining the original shape of the signal. In subject 3, EMD recorded the lowest MAE of 0.622 compared to Butterworth, which reached 20.0, and the MSE value of 0.655 compared to 771.5 for Butterworth. In addition, EMD also produced a higher SNR, with the highest value of 23,208 in subject 5, compared to Butterworth, which reached only 1,568. These results prove that the combination of BPF as a preprocessing method and EMD as a feature extraction method is more effective in maintaining EEG signal quality and improving analysis accuracy compared to the use of the Butterworth Band-Pass Filter alone.
A Quantum Convolutional Neural Network for Breast Cancer Classification using Boruta and GA-Based Feature Selection with Quantum Feature Maps Pagadala, Veeranjaneyulu; B, Venkatesh; Boinapalli, Sindhu; Dhulipalla, Ramya Krishna; Annapoorna, S
Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol 7 No 3 (2025): July
Publisher : Department of Electromedical Engineering, POLTEKKES KEMENKES SURABAYA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/jeeemi.v7i3.792

Abstract

Accurate and computationally efficient classification systems are essential for the early detection of breast cancer, particularly when dealing with complex and high-dimensional medical datasets. Traditional machine learning models often face limitations in capturing intricate nonlinear relationships inherent in such data, potentially compromising diagnostic performance. In this study, we introduce QBG-QCNN, a Quantum-enhanced framework named Boruta-GA optimized Quantum Convolutional Neural Network, designed for breast cancer classification. The model is trained on the Breast Cancer Wisconsin (Diagnostic) Dataset, which contains 30 numerical features extracted from fine needle aspiration (FNA) images of breast tissue samples. To reduce dimensionality while preserving critical diagnostic information, a hybrid Boruta-GA feature selection strategy is applied to extract key features such as radius_mean, texture_mean, area_mean, and concavity_mean. These selected features are then encoded into a 4-qubit quantum circuit using advanced quantum feature maps ZZFeatureMap, RealAmplitudes, and EfficientSU2, eliminating the need for manual feature engineering. The encoded quantum data is processed through a QCNN that incorporates quantum convolution, pooling, and parameterized ansatz layers, leveraging quantum entanglement and parallelism for more efficient learning. Implemented using PennyLane and IBM Qiskit, and optimized with the COBYLA, the model achieves outstanding performance: 94.3% accuracy, 95.2% precision, 94.6% recall, and a 93.0% F1-score. These results significantly outperform those of classical CNNs, standard QNNs, and other hybrid models. In conclusion, QBG-QCNN demonstrates that quantum machine learning, when integrated with intelligent feature selection, offers a powerful, scalable, and interpretable solution for early-stage breast cancer diagnosis. Future research will extend this framework to multi-modal datasets and real-device deployment on real quantum devices under noise constraints.
SympTextML: Leveraging Natural Language Symptom Descriptions for Accurate Multi-Disease Prediction Dhairya Vyas; Milind Shah; Harsh Kantawala; Brijesh Patel; Patel, Tejas; Enamala, Jalaja
Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol 7 No 3 (2025): July
Publisher : Department of Electromedical Engineering, POLTEKKES KEMENKES SURABAYA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/jeeemi.v7i3.946

Abstract

This research presents an AI-driven framework for multi-disease classification using natural language symptom descriptions, optimized through large language model (LLM) oriented preprocessing techniques. The proposed system integrates essential NLP steps text normalization, lemmatization, and n-gram vectorization to convert unstructured clinical symptom data into machine-readable form. A publicly available dataset comprising 8,498 samples across ten common diseases, including pneumonia, heart attack, diabetes, stroke, asthma, and depression, was used for training and evaluation. Data balancing and cleaning ensured uniform class representation with 1,200 samples per disease category. The processed dataset was subjected to supervised machine learning models, including SVM, KNN, Decision Tree, Random Forest, and Extra Trees, to identify the most effective classifier. Experimental results, conducted in Google Colab, showed that ensemble models (Random Forest and Extra Trees) significantly outperformed the others, achieving 99% accuracy, precision, recall, and F1-scores, while SVM and Decision Tree followed closely with 98% performance across metrics. Notably, the models consistently predicted pneumonia with high confidence for relevant input queries , validating the framework's robustness. This work demonstrates the efficacy of integrating LLM-compatible preprocessing with traditional ML classifiers for accurate disease detection based on symptom narratives. The proposed approach serves as a foundational step toward developing scalable, intelligent healthcare support systems capable of real-time disease prediction and decision-making assistance.
Machine Learning-Based Approach for Uterine Cancer Detection and Classifier Evaluation Samarasam, Brindha; Justin, Judith
Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol 7 No 3 (2025): July
Publisher : Department of Electromedical Engineering, POLTEKKES KEMENKES SURABAYA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/jeeemi.v7i3.632

Abstract

The necessity of early diagnosis of abnormal cell growth is critical to support patient monitoring and earlier clinical analysis. Uterine cancer is the most common gynecological malignancy among women, with endometrial cancer being the predominant type occurring in the endometrial layer. Endometrial cancer is a commonly identified type of uterine cancer that majorly occurs in the endometrial layer. This research applies machine learning (ML) algorithms to detect uterine cancer using texture-based features extracted from medical images. Specifically, a hybrid combination of Grey Level Co-occurrence Matrix (GLCM) and Grey Level Run Length Matrix (GLRLM) properties is proposed to derive 34 features, including entropy, long-run emphasis, short-run low grey level emphasis, and high grey level run emphasis. To ensure data quality, a comprehensive dataset was collected and preprocessed, followed by the implementation of an improved approach for feature normalization and ranking. The top-ranked features were then used to train and validate multiple ML algorithms, including Adaptive Neuro-Fuzzy Inference System (ANFIS), K-Nearest Neighbor (K-NN), Linear Discriminant Analysis (LDA), Radial Basis Function (RBF), Support Vector Machine (SVM), Naïve Bayes (NB), and Artificial Neural Network (ANN). Results show that the best-performing algorithm achieves an accuracy of 97.3%, sensitivity of 96.3%, and specificity of 99.2%. The algorithm's performance was further validated using Receiver Operating Characteristics (ROC) analysis and F1 scores, both of which demonstrated superior predictive capability. Additionally, Explainable AI (XAI) techniques were integrated to elucidate the features and patterns recognized by the algorithm as indicative of endometrial carcinoma. Layer-wise relevance propagation (LRP) was employed to backtrack the neural network’s output decisions to the input features, highlighting the most influential factors in the algorithm's predictions. This research demonstrates the potential of applying ML algorithms to improve early detection of uterine cancer, offering a non-invasive, accurate, and cost-effective alternative to traditional imaging methods.
Improving Kidney Stone Detection with YOLOV10 and Channel Attention Mechanisms in Medical Imaging Bala, Saroj; Arora, Kumud; V, Satheeswaran; S, Mohan; J, Deepika; K, Sangamithrai; Doss, Amala Nirmal
Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol 7 No 3 (2025): July
Publisher : Department of Electromedical Engineering, POLTEKKES KEMENKES SURABAYA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/jeeemi.v7i3.868

Abstract

Accurate and timely detection of kidney stones is crucial for effective medical intervention and treatment planning. However, existing detection methods often struggle with challenges related to sensitivity, precision, and the ability to process complex and variable medical images. In this study, an advanced kidney stone detection system is developed using the latest object detection algorithm, You Only Look Once version 10 (YOLOv10), integrated with channel attention mechanisms to enhance model performance. This combination aims to improve detection accuracy by enabling the network to focus more precisely on critical regions in medical images, particularly in Computed Tomography (CT) scans, where kidney stones may appear in varying shapes, sizes, and intensities. The proposed system begins with data augmentation techniques, such as rotation, scaling, and contrast adjustments, to enhance the model’s generalization ability across different image conditions and patient profiles. YOLOv10 was selected due to its lightweight architecture, high detection speed, and enhanced performance in small object detection tasks. To further improve feature extraction, channel attention mechanisms such as Squeeze-and-Excitation (SE) blocks or Efficient Channel Attention (ECA) modules are incorporated. These modules enable the network to selectively focus on the most informative feature channels associated with kidney stone regions, while suppressing irrelevant background information, thereby improving the distinction between stones and surrounding tissues. The model is trained and fine-tuned using a diverse CT scan dataset containing various types and sizes of kidney stones. Evaluation results demonstrate that the proposed model achieves a high detection accuracy of 93.7% with a very low loss of 0.18. It exhibits stability without issues like overfitting, underfitting, or local minima entrapment, making it a highly reliable tool for clinical applications.
Heart Disease Classification Using Random Forest and Fox Algorithm as Hyperparameter Tuning Masbakhah, Afidatul; Sa'adah, Umu; Muslikh, Mohamad
Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol 7 No 4 (2025): October
Publisher : Department of Electromedical Engineering, POLTEKKES KEMENKES SURABAYA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/jeeemi.v7i4.932

Abstract

Heart disease remains the leading cause of death worldwide, making early and accurate diagnosis crucial for reducing mortality and improving patient outcomes. Traditional diagnostic approaches often suffer from subjectivity, delay, and high costs. Therefore, an effective and automated classification system is necessary to assist medical professionals in making more accurate and timely decisions. This study aims to develop a heart disease classification model using Random Forest, optimized through the FOX algorithm for hyperparameter tuning, to improve predictive performance and reliability. The main contribution of this research lies in the integration of the FOX metaheuristic optimization algorithm with the RF classifier. FOX, inspired by fox hunting behavior, balances exploration and exploitation in searching for the optimal hyperparameters. The proposed RF-FOX model is evaluated on the UCI Heart Disease dataset consisting of 303 instances and 13 features. Several preprocessing steps were conducted, including label encoding, outlier removal, missing value imputation, normalization, and class balancing using SMOTE-NC. FOX was used to optimize six RF hyperparameters across a defined search space. The experimental results demonstrate that the RF-FOX model achieved superior performance compared to standard RF and other hybrid optimization methods. With a training accuracy of 100% and testing accuracy of 97.83%, the model also attained precision (97.83%), recall (97.88%), and F1-score (97.89%). It significantly outperformed RF-GS, RF-RS, RF-PSO, RF-BA, and RF-FA models in all evaluation metrics. In conclusion, the RF-FOX model proves highly effective for heart disease classification, providing enhanced accuracy, reduced misclassification, and clinical applicability. This approach not only optimizes classifier performance but also supports medical decision-making with interpretable and reliable outcomes. Future work may involve validating the model on more diverse datasets to further ensure its generalizability and robustness.

Page 24 of 29 | Total Record : 287

 22   23   24   25   26 

Filter by Year

2019 2026


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