@pcr.ac.id
Electronic Engineering
Politeknik Caltex Riau
Biomedical Engineering
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Putri Madona, Jepri Simatupang, and Ahmad Yani H
Akademia Baru Publishing
The availability of health monitoring devices that can be used independently, conveniently, and portably is increasing in line with busy lifestyles and the difficulty of scheduling medical tests. Measuring vital body signals with various devices makes measurements longer, less effective, and relatively more expensive. The proposed research can monitor vital body signals, such as heart rate, body temperature, respiratory rate, oxygen saturation, GSR, blood pressure, and snoring, which are integrated into a Raspberry Pi 4B-based device, with results displayed on an LCD screen. Data acquisition results show reasonably good accuracy in almost all parameters but require improvement in respiratory rate measurements. In the subsequent work, these seven-acquisition data will be used to predict several possible diseases.
Juni Nurma Sari, Putri Madona, Hari Kusryanto, Muhammad Mahrus Zain, and May Valzon
Institute of Advanced Engineering and Science
<span>Coronary heart is the highest cause of death in Indonesia reaching 26%. Therefore, to prevent the high mortality rate of coronary heart disease (CHD), early detection of CHD can be carried out. One way is to examine the electrocardiogram/electrocardiograph (ECG) recording. ECG hardware has been made in previous studies to record ECG signals. ECG research is an important study because it can detect cardiovascular disease. Cardiovascular diseases can be classified as arrhythmic diseases. Arrhythmia is a disorder that occurs in the heart rhythm. The method used to recognize and classify ECG signal patterns is the R-R interval (RRI) method. In this study, the ECG signal is classified as normal and abnormal. Abnormal means that a person has a heart rhythm disorder. The classification method used is random forest. The advantage of the random forest classifier is that it can handle noise and missing values and can handle large amounts of data. The accuracy of the ECG signal classification using the Random forest method is 96%. The contribution of this research is that early detection of heart rhythm disorders using an ECG can be monitored through the smart healthcare web.</span>
Putri Madona, Yogi Zafitrah, Juni Nurma Sari, Muhammad Mahrus Zain, and May Valzon
IEEE
Based on the data from Basic Health Research (Riskesdas), the incidence of heart and blood vessel disease is increasing from year to year. At least 15 out of 1000 people in Indonesia suffer from heart disease. The lack of early detection of heart disease makes sufferers of this disease increase. Also, general practitioners as the first health facility visited by patients do not have the ability like a cardiologist does in examining the heart. Therefore, an application of an android-based heart rhythm abnormality classification is made for general practitioners in an effort to overcome this problem as early detection of heart abnormalities. This application utilizes a portable ECG recording device (Electrocardiogram) to record the patient's ECG signal. The recorded ECG signal is then extracted by taking the values of PT interval, Bpm, RR interval, and local RR to be classified using machine learning with the Naïve bayes algorithm. The accuracy obtained by using naive bayes is about 75%. The results of this application can assist general practitioners in early detection of heart abnormalities and as a reference in the development of research on early detection of ECG signal abnormalities.
Putri Madona, Rahmat Ilias Basti, and Muhammad Mahrus Zain
Elsevier BV
Arjon Turnip, Dwi Esti Kusumandari, Siti Aminah Sobana, Arifah Nur Istiqomah, Teddy Hidayat, Shelly Iskandar, Yumna Nabila, Ririn Amrina, and Putri Madona
Springer Singapore
Putri Madona, Husna Khairun Nisa, Yusmar Palapa Wijaya, and Amnur Akhyan
IOP Publishing
Abstract In this study, an electric wheelchair that combines two controls: joystick analog and voice control is designed. IC MCP3008 is used to navigate wheelchairs by using Josytick, where joystick analog data will be converted into digital data. The movements resulted from the joystick analog on the xAxis axis (horizontally) are the right turn and left turn, and on the yAxis axis (vertically) are forward and backward. The movements on the yAxis and xAxis axes set by the user affects the speed of the wheelchair. Meanwhile, the AMR-Voice application on Android is used to navigate wheelchairs by using sound. There are five commands in this voice control: “Forward”, “backward”, “left”, “right”, “stop”. The order will be sent to Raspberry Pi 3 via the HC-06 module to then be recognized for the command. If the voice commands are received accordingly, Raspberry Pi 3 will provide an activation signal to the motor driver to move the wheelchair in the direction corresponding to the command given by the user. Voice control testing on wheelchairs is tested in quiet rooms and noisy rooms. The results of the wheelchair control testing with sound indicate that the accuracy and speed of the wheelchair response rely heavily on Internet connection and room conditions. The average response when the condition of the room is quiet is 0.16 s and when the condition of the room is noisy is 5.18 s. Wheelchairs with joystick control and the voice made can be used for the disabled, whether for those who can move their fingers or not, at a low cost so that they can be an alternative in developing countries.
Putri Madona, Renndy Raldy Mujiono, and Yusmar Palapa Wijaya
IEEE
This study discusses the processing of EEG and EOG signals for the classification of wheelchairs movement. Brain signals are obtained with NeuroSky mind wave sensor; this sensor emits attention, meditation, and RAW data values. Attention value will be used for forward movement, meditation is used for backward movement, while RAW data will be used for left, right, and stop movements. The test results of forward orders have a success rate of 92%, turn right 96%, turn left 100%, stop 96%, and backward 76%.