Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Jurnal Teknologi Sistem Informasi dan Aplikasi

Rancang Bangun Aplikasi Pemantauan Detak Jantung dan Pelacakan Lokasi bagi Penderita Lemah Jantung Berbasis IoT dan Android Somantri, Somantri; Fergina, Anggun; Maulana, Yosep
Jurnal Teknologi Sistem Informasi dan Aplikasi Vol. 6 No. 3 (2023): Jurnal Teknologi Sistem Informasi dan Aplikasi
Publisher : Program Studi Teknik Informatika Universitas Pamulang

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

Abstract

Weak heart is a medical condition that reduces the heart's ability to heat blood throughout the body with optimal efficiency. People with weak heart need regular monitoring regarding their heart condition. Under normal conditions, they should measure the heart rate regularly otherwise a weak heart can lead to serious complications such as acute heart failure or arrhythmias. By using the application, people with heart failure can monitor early signs and symptoms that might indicate complications. The data collected by the application can assist in detecting early changes that are potentially harmful to the patient's health. In this study, the authors designed and developed an IoT and Android-based heart rate monitoring and location tracking system using the prototype method. The prototype method is used in the process of developing this system because it is capable of producing initial prototypes of tools and applications that can be used for testing and validating concepts before carrying out a full implementation. This system consists of two main components, the first is a component of hardware (hardware) and the second is a component of software (software). The hardware used is a pulse sensor that is connected to an Android device via a wireless connection. This sensor is able to detect the patient's heart rate in real-time and send it to the Android device for further processing. In addition, this system is also equipped with a GPS tracking module that allows traveling to the user's location accurately. Software developed using the App Inventor platform. This Android application has an easy-to-use user interface. This application can display real-time heart rate data in graphical form and provide notifications if a significant change is detected in the patient's heart rate. In addition, this application can also display the patient's location on an interactive map. The test results show that this system is capable of monitoring the patient's heart rate with high accuracy and sending data in real-time to an Android device. In addition, tracking the location of the patient's whereabouts was also successfully carried out with an adequate level of precision. This system provides great benefits in monitoring and treating patients with heart failure, enabling medical staff and the patient's family to take quick and appropriate action if there is a significant change in the patient's heart rate or if the patient is in an emergency situation
Comparative Analysis of Logistic Regression, SVM, Xgboost, and Random Forest Algorithms for Diabetes Classification Hidayat, Rahmat; Mahdiana, Deni; Fergina, Anggun
Jurnal Teknologi Sistem Informasi dan Aplikasi Vol. 7 No. 1 (2024): Jurnal Teknologi Sistem Informasi dan Aplikasi
Publisher : Program Studi Teknik Informatika Universitas Pamulang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32493/jtsi.v7i1.38258

Abstract

Diabetes is a disease that can attack anyone, where this disease occurs because there is excessive sugar content in the human body. Therefore, prevention of diabetes is necessary so that preventive measures can be given as early as possible. In this research, a classification process will be carried out using the Random Forest algorithm, Support Vector Classification and XGBoost. This research will use a dataset which consists of 768 total data with a distribution of non-diabetic data of 500 and a distribution of diabetes data of 268. For the classification results after testing, the results were that classification using random forest obtained a testing accuracy of 79.22%, with using support vector classification gets a testing accuracy of 76.62%, using XGBoost gets a testing accuracy of 79.22% using Logistic Regression gets a testing accuracy of 80.52%. The best classification value is obtained when using the Logistic Regression algorithm, namely with a precision of 79.00%, recall of 77.00% and F1-Score of 78.00%.