cover
Contact Name
Triwiyanto
Contact Email
triwiyanto123@gmail.com
Phone
+628155126883
Journal Mail Official
triwiyanto123@gmail.com
Editorial Address
Pucang Jajar Timur No. 10, Surabaya, Indonesia
Location
Kota surabaya,
Jawa timur
INDONESIA
Indonesian Journal of Electronics, Electromedical Engineering, and Medical Informatics
ISSN : -     EISSN : 26568624     DOI : https://doi.org/10.35882/ijeeemi
Indonesian Journal of Electronics, Electromedical Engineering, and Medical Informatics (IJEEEMI) publishes peer-reviewed, original research and review articles in an open-access format. Accepted articles span the full extent of the Electronics, Biomedical, and Medical Informatics. IJEEEMI seeks to be the world’s premier open-access outlet for academic research. As such, unlike traditional journals, IJEEEMI does not limit content due to page budgets or thematic significance. Rather, IJEEEMI evaluates the scientific and research methods of each article for validity and accepts articles solely on the basis of the research. Likewise, by not restricting papers to a narrow discipline, IJEEEMI facilitates the discovery of the connections between papers, whether within or between disciplines. The scope of the IJEEEMI, covers: Electronics: Intelligent Systems, Neural Networks, Machine Learning, Fuzzy Systems, Digital Signal Processing, Image Processing, Electromedical: Biomedical Signal Processing and Control, Artificial intelligence in biomedical imaging, Machine learning and Pattern Recognition in a biomedical signal, Medical Diagnostic Instrumentation, Laboratorium Instrumentation, Medical Calibrator Design. Medical Informatics: Intelligent Biomedical Informatics, Computer-aided medical decision support systems using heuristic, Educational computer-based programs pertaining to medical informatics
Articles 199 Documents
The Impactness of SMOTE as Imbalance Class Handling for Myocardial Infarction Complication Classification using Machine Learning Approach with Data Imputation and Hyperparameter Ahmad Tajali; Saragih, Triando Hamonangan; Mazdadi, Muhammad Itqan; Budiman, Irwan; Farmadi, Andi
Indonesian Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol. 6 No. 4 (2024): November
Publisher : Jurusan Teknik Elektromedik, Politeknik Kesehatan Kemenkes Surabaya, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/ijeeemi.v6i4.13

Abstract

Myocardial Infarction (MI) is a critical medical emergency characterized by the sudden blockage of blood flow to the heart muscle, often resulting from a blood clot in a coronary artery that has been narrowed by atherosclerotic plaque buildup. This condition demands immediate attention, as prolonged disruption of blood supply can cause irreversible damage to the heart muscle. Diagnosing MI typically involves a combination of methods, including a physical examination, electrocardiogram (ECG) analysis, blood tests to measure heart-specific enzymes, and imaging techniques such as coronary angiography. Early prediction of potential MI complications is crucial to prevent severe outcomes and improve patient prognosis. This study focuses on the early prediction of MI complications through the application of machine learning classification methods. We employed algorithms such as Support Vector Machine (SVM), Random Forest, and XGBoost to analyze patient medical records and accurately predict these complications. The selection of Support Vector Machine (SVM), Random Forest, and XGBoost in this study is driven by their proven effectiveness in handling complex classification problems. To manage incomplete datasets and preserve valuable information, data imputation techniques like K-Nearest Neighbors (KNN) Imputation, Iterative Imputation, and MissForest were applied.  KNN, Iterative, and MissForest imputations were chosen to handle missing data due to their effectiveness in preserving data integrity, which is crucial for accurate predictions in myocardial infarction complication studies. Additionally, Bayesian Optimization was utilized to fine-tune the hyperparameters of the models, thereby enhancing their predictive accuracy. The Iterative Imputation method yielded the best performance, particularly in SVM and XGBoost algorithms. SVM achieved 100% accuracy, precision, sensitivity, F1 score, and Area Under the Curve (AUC), while XGBoost attained 99.4% accuracy, 100% precision, 79.6% sensitivity, an F1 score of 88.7%, and an AUC of 0.898. While XGBoost and MissForest proved to be the most successful pairing, the overall effectiveness of the models suggests that Iterative Imputation and Random Forest also have potential under certain conditions.
Control Watering Nutrients for Rice Plants With a Drip Irrigation System Using Arduino and RTC Haryanti, Tri; Fitriyanto, Indra; Maknunah, Jauharotul
Indonesian Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol. 6 No. 4 (2024): November
Publisher : Jurusan Teknik Elektromedik, Politeknik Kesehatan Kemenkes Surabaya, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/ijeeemi.v6i4.14

Abstract

Indramayu Regency is one of the largest rice-producing areas in West Java, but its rice productivity, averaging 6 tonnes per hectare, falls short of the national target of 8 tonnes per hectare. One key problem contributing to this gap is the nutrient imbalance in rice plants, which can lead to pest and disease attacks. To address this, an automated drip irrigation system was developed to optimize nutrient delivery and improve crop yield. The aim of this study was to design a nutrient control system for hydroponic rice using Arduino and an RTC (Real-Time Clock), allowing for precise and scheduled watering of nutrients. The system contributes to better plant health, higher crop productivity, and more efficient use of water and nutrients. The method involved testing eight water pumps, each controlling different nutrient doses, in a hydroponic rice planting system. The system was set to irrigate according to a programmed schedule, with pumps activated at specific times to deliver nutrients to rice plants grown in polybags with fine sand. Data collection was conducted over 30 days by analyzing the condition of rice plant leaves for each nutrient dose. The results showed that the drip irrigation system successfully controlled nutrient delivery, and the analysis identified the optimal nutrient dose for healthy plant growth. In conclusion, the automated drip irrigation system using Arduino and RTC not only improved water and nutrient efficiency but also contributed to higher rice yield quality and quantity. The system shows promise for reducing production costs by lowering water and fertilizer usage while minimizing environmental impact.
Classification of brain tumor based on shape and texture features and machine learning Rizki, M. Alfi; Faisal, Mohammad Reza; Farmadi, Andi; Saragih, Triando Hamonangan; Nugrahadi, Dodon Turianto; Bachtiar, Adam Mukharil; Keswani, Ryan Rhiveldi
Indonesian Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol. 6 No. 4 (2024): November
Publisher : Jurusan Teknik Elektromedik, Politeknik Kesehatan Kemenkes Surabaya, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/27236g49

Abstract

Information from brain tumour visualisation using MRI can be used for brain tumour classification. The information can be extracted using different feature extraction techniques. This study compares shape-based feature extraction such as Zernike Moment (ZM), and Pyramid Histogram of Oriented Gradients (PHOG) with texture-based feature extraction such as Local Binary Patterns (LBP), Gray Level Co-occurrence Matrix (GLCM), Histogram of Oriented Gradients (HOG) in brain tumour classification. This research aims to find out which feature extraction is better for handling brain tumour images through the accuracy and f1-score produced. This research proposes to combine each feature based on its approach, i.e. ZM+PHOG for shape-based feature extraction and LBP+GLCM+HOG for texture-based feature extraction with default parameters from the library and modified parameters configured based on previous research. The dataset used comes from Kaggle and has three classes: meningioma, glioma, and pituitary. The machine learning classification models used are Support Vector Machine (SVM), Random Forest (RF), Naive Bayes (NB) and K-Nearest Neighbours (KNN) with default parameters from the library. The models were evaluated using 10-fold stratified cross-validation. This research resulted in an accuracy and f1-score of 84% for texture-based feature extraction with modified parameters in RF classification. In comparison, shape-based feature extraction resulted in accuracy and f1-score of 70% and 68% with modified parameters in RF classification. From the results, it can be concluded that texture-based feature extraction is better in handling brain tumour images compared to shape-based feature extraction. This study suggests that focusing on texture details in feature extraction can significantly improve classification performance in medical imaging such as brain tumours
Implementation of the Web-Based K-Means Clustering Algorithm on Hypertension Levels in the Elderly at the Bungah District Health Center Hermanto, Hermanto; Hendi, Ade; Zuhriyah, Aminatuz
Indonesian Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol. 6 No. 2 (2024): May
Publisher : Jurusan Teknik Elektromedik, Politeknik Kesehatan Kemenkes Surabaya, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/h6596074

Abstract

This research was carried out at the community health center in Bungah sub - district with the aim that so that patients receive appropriate treatment, a web-based system is needed to group hypertension data into several classes (clusters). The method used in data grouping is the K-Means Clustering method . In this study, 100 hypertension data were grouped into 4 clusters . The hypertension data used consists of two attributes, namely systole and diastole, the working mechanism is to normalize the data first, then the system groups the data into groups that have the same characteristics. The system will display the results of the clustering process which consists of four (4) clusters , namely cluster 1 Isolated Systolic Hypertension, cluster 2 Grade 1 (mild hypertension), cluster 3 Grade 2 (moderate hypertension), and cluster 4 Grade 3 (high hypertension). The data used for clustering is 100 data from blood pressure checks of patients at the Community Health Center using a blood pressure monitor. The results of the last iteration of 100 hypertension data in the system were used as parameters for calculating the level of effectiveness, by comparing the data from the clustering test results to the data from diagnosis a which produced an effectiveness value of 80%.
Diabetes Detection Using Extreme Gradient Boosting (XGBoost) with Hyperparameter Tuning Dinanthi, Devi Aprilya; Ramadanti, Elisa; Aditya, Christian Sri Kusuma; Chandranegara, Didih Rizki
Indonesian Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol. 6 No. 2 (2024): May
Publisher : Jurusan Teknik Elektromedik, Politeknik Kesehatan Kemenkes Surabaya, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/qr3hw926

Abstract

Diabetes is a serious condition that can lead to fatal complications and death due to metabolic disorders caused by a lack of insulin production in the body. This study aims to find the best classification performance on diabetes dataset using Extreme Gradient Boosting (XGBoost) method. The dataset used has 768 rows and 9 columns, with target values of 0 and 1. In this study, resampling is applied to overcome data imbalance using SMOTE, and hyperparameter optimization is performed using GridSearchCV and RandomSearchCV. Model evaluation was performed using confusion matrix as well as metrics such as accuracy, precision, recall, and F1-score. The test results show that the use of GridSearchCV and RandomSearchCV for hyperparameter tuning provides good results. The application of data resampling also managed to improve the overall model performance, especially in the XGBoost method that has been optimized using GridSearchCV, which achieved the highest accuracy of 85%, while XGBoost with RandomSearchCV optimization showed 83% accuracy performance.
Analysis Implementation of Hospital Management Information System (SIMRS) at Place of Inpatient Registration (TPPRI) Using The PIECES Method at The Ajibarang Government Hospital Afgani, Abu Sofyan Al; Indira, Zahrasita Nur; Nadi, Danu Tirta; Marini, Budiana
Indonesian Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol. 6 No. 2 (2024): May
Publisher : Jurusan Teknik Elektromedik, Politeknik Kesehatan Kemenkes Surabaya, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/k1wbwp80

Abstract

Hospital Management Information System (SIMRS) is an information communication technology system that processes and integrates the entire process flow of hospital services in the form of a network of coordination, reporting and administrative procedures to obtain information precisely and accurately, and is part of the Health Information System. The implementation of SIMRS at the Ajibarang Regional General Hospital (RSUD) has been carried out since 2014 in almost all units, one of which is the Inpatient Registration Place (TPPRI). This study aims to improve the shortcomings of the system that has been made at SIMRS RSUD Ajibarang. The method used in this study is qualitative. The data collection method used in this study was using in-depth interviews. The data analysis method uses Performance, Information, Economy, Control, Efficiency, and Service (PIECES) which aims to obtain information related to the implementation of SIMRS at the Ajibarang Regional General Hospital. Based on the results of the SIMRS analysis in the TPPRI section, there are still obstacles in its implementation, both in terms of Performance, Information, Economy, Control, Efficiency, and Service. The results showed that there are still several problems, namely the presence of menus that are not functioning optimally, different TPPRI and TPPRJ SIMRS, inaccurate data, Human error, server down, and no warning if an error occurs. SIMRS has been running according to user needs, but cannot be separated from various problems, so it is necessary to improve and develop SIMRS through researcher recommendations so that SIMRS can maintain and improve the quality of service to patients. Based on the description of the problem, as there is no warning if an error occurs, the user will easily continue to input data on SIMRS so that errors are not detected that result in losses for hospitals and produce inaccurate data.
A Hybrid Approach for Optimal Multi-Class Classification of Neglected Tropical Skin Diseases using Multi-Channel HOG Features Steyve, Nyatte; Steve, Perabi; Kedy, Mepouly; Ndjakomo, Salomé; Pierre, Ele
Indonesian Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol. 6 No. 2 (2024): May
Publisher : Jurusan Teknik Elektromedik, Politeknik Kesehatan Kemenkes Surabaya, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/hx3pcz75

Abstract

Neglected tropical skin diseases (NTDs) pose significant health challenges, especially in resource-limited settings. Early diagnosis is crucial for effective treatment and preventing complications. This study proposes a novel multi-class classification approach using multi-channel HOG features and a hybrid metaheuristic algorithm to improve the accuracy of NTD diagnosis. The method extracts optimal HOG features from images of Buruli Ulcer, Leprosy, and Cutaneous Leishmaniasis through different cell sizes, generating multiple training datasets. A hybrid Whale Optimization Algorithm and Shark Smell Optimization Algorithm (WOA-SSO) optimizes the Error Correcting Output Code (ECOC) framework for SVM, achieving superior multi-class classification performance. Notably, the multi-channel dataset, derived from averaging HOG features of different cell sizes, yields the highest accuracy of 89%. This study demonstrates the potential of the proposed method for developing mobile applications that facilitate early and accurate diagnosis of NTDs through image analysis, potentially improving patient outcomes and disease control. The hybrid metaheuristic algorithm plays a crucial role in optimizing the ECOC framework, enhancing the accuracy and efficiency of the multi-class classification process. This approach holds significant promise for revolutionizing NTD diagnosis and management, particularly in underserved communities.
Development of a Diabetes Mellitus Monitoring Information System in Health Monitoring and Health Decision Making Renata, Agnes Lia; Fatmasari, Diyah; Sukini, Sukini
Indonesian Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol. 6 No. 2 (2024): May
Publisher : Jurusan Teknik Elektromedik, Politeknik Kesehatan Kemenkes Surabaya, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/xqmb8f89

Abstract

Individuals with diabetes mellitus are more likely to experience acute and chronic health complications including oral diseases. However, there are still many of them who do not carry out routine controls and do not record the history of examination results, resulting in a lack of monitoring of their health. Information systems in the health sector can be utilized in managing health information as an effort to monitor risk factors that allow complications of oral and dental disease. In addition, there is no information system that focuses on monitoring dental health in patients with diabetes mellitus. The development of SIP DM-DENT Monitoring is focused on monitoring general health and dental health in patients with diabetes mellitus. This study aims to produce SIP DM-DENT Monitoring for people with diabetes mellitus that is feasible in monitoring health and providing health recommendations based on the results of their health checks, especially in controlling blood sugar and dental health. This research combines descriptive and analytical types of research called R&D to develop a new product output with the stages of information gathering, design making, expert validation, product testing and product results. The data collected is primary data using interview questionnaires and Linkert questionnaires. Sampling using purposive sampling technique obtained a sample of 35 respondents. The data obtained were analyzed using ICC test and descriptive statistics. The average result of the expert validation assessment was 85.76 with a decent category. The ICC test results show a p-value of 0.00 <0.05 which means the system is feasible to use. While in the product test assessment, the average respondent agrees that the system provides information and is easy to use. Based on this research, it shows that SIP DM-DENT Monitoring is feasible and effective in monitoring the health of people with diabetes mellitus and providing health recommendations for them.
Compared RGB Methods Towards Efficient Money Detector for Blind People Fadilah, Maulina; Maulana, Yulian Zetta; Yusro, Muhammad
Indonesian Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol. 6 No. 1 (2024): February
Publisher : Jurusan Teknik Elektromedik, Politeknik Kesehatan Kemenkes Surabaya, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/0521cr88

Abstract

Limitations of profound visual impairment distinguishing each nominal number of banknotes are often used by people with bad intentions to take advantage of that basis, like money fraud. Due to this reason, the blind people need to be helped to recognize their surroundings by developing assistive technology that is advanced for them. This study aims to build an efficient design of a money detector by comparing three RGB methods: range breakdown, If-Then Rules, and decision tree to recognize the nominal of money. By comparing the RGB methods, this research contributes to investigate the most accurate and efficient method for further development of money detector for blind people. The sample used in this experiment is rupiah banknotes for the 2016 and 2022 issuances. The device is built with a TCS3200 colour sensor and designed in a real-time platform. It has been found that the highest average percentage accuracy was achieved by the breakdown range method with 100% (2016 sample) and 90% (2022 sample). This device also successfully produced a notification sound from a speaker that mentions the detected nominal value. This research could be used as a reference to improve assistive technology for blind people.
Monitoring Baby Incubator Central through Internet of Things (IoT) based on Raspberry Pi Zero W with Personal Computer View Puspitasari, Dila Anggraeni; Irianto, Bambang Guruh; Lamidi, Lamidi; Triwiyanto, Triwiyanto
Indonesian Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol. 6 No. 1 (2024): February
Publisher : Jurusan Teknik Elektromedik, Politeknik Kesehatan Kemenkes Surabaya, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/dk550458

Abstract

Kids born before 37 weeks of pregnancy or weighing less than 2500 grams are considered premature, whereas kids born between 38 and 40 weeks of pregnancy and between 2500 to 4000 grams are considered full-term. Given that their organ systems are still developing within the womb, premature infants find it difficult to adjust to life outside the womb. As a result, special consideration must be made. They include modifying the environment's temperature, humidity, and oxygen needs to reflect those of the mother's womb. These conditions might be replaced with a baby incubator. This tool's creation is intended to make it easier for midwives and other healthcare professionals to keep an eye on many baby incubators. The Internet of Things (IoT) system is used by this instrument to transfer data. Using three ESP32 modules that have been put together to create modules that can collect data and have that data analyzed by a server (central monitoring) Raspberry Pi Zero W. Data will be sent via Internet of Things (IoT) technology, and the website will display the data. Two tests were conducted at 32 degrees Celsius, one at 34 degrees Celsius, and one at 36 degrees Celsius for a total of five tests. This technique was developed using a form of pre-experimental, after-only study. In this configuration, researchers may only see the module reading results; incubator analyzer data are not shown. Error value 3 in monitoring at 32 degrees Celsius has a maximum error of -0.04 percent. The largest error value occurs when the temperature is set to 34 degrees Celsius, when the monitoring error value is -0.016%. Monitoring inaccuracy is at its highest, 0.01%, when the temperature is 36 degrees Celsius. The monitoring 3 error value is most at 32 degrees Celsius (-0.025 percent), followed by 34 degrees Celsius (0.031 percent), and finally 36 degrees Celsius (0.049 percent), as shown by data on noise measurements. The findings demonstrate that each measurement performed by the module still contains mistakes. Medical staff should find it easier to concurrently monitor many infant incubators thanks to this discovery.

Page 2 of 20 | Total Record : 199