Dyah Titisari

Bio: Dyah Titisari is an academic researcher. The author has contributed to research in topics: Computer science & Exoskeleton. The author has an hindex of 2, co-authored 15 publications receiving 17 citations.

Embedded Machine Learning Using a Multi-Thread Algorithm on a Raspberry Pi Platform to Improve Prosthetic Hand Performance

Abstract: High accuracy and a real-time system are priorities in the development of a prosthetic hand. This study aimed to develop and evaluate a real-time embedded time-domain feature extraction and machine learning on a system on chip (SoC) Raspberry platform using a multi-thread algorithm to operate a prosthetic hand device. The contribution of this study is that the implementation of the multi-thread in the pattern recognition improves the accuracy and decreases the computation time in the SoC. In this study, ten healthy volunteers were involved. The EMG signal was collected by using two dry electrodes placed on the wrist flexor and wrist extensor muscles. To reduce the complexity, four time-domain features were applied to extract the EMG signal. Furthermore, these features were used as the input of the machine learning. The machine learning evaluated in this study were k-nearest neighbor (k-NN), Naive Bayes (NB), decision tree (DT), and support vector machine (SVM). In the SoC implementation, the data acquisition, feature extraction, machine learning, and motor control process were implemented using a multi-thread algorithm. After the evaluation, the result showed that the pairing of the MAV feature and machine learning DT resulted in higher accuracy among other combinations (98.41%) with a computation time of ~1 ms. The implementation of the multi-thread algorithm in the pattern recognition system resulted in significant impact on the time processing.

The Measuring of Vital Signs Using Internet Of Things Technology (Heart Rate And Respiration)

Abstract: Vital signs are a measurement of the most basic functions of the body which to find out the clinical signs. It is useful for diagnosing disease and determining the appropriate medical treatment plan. The respiratory rate is one of the most critical parameters because the respiratory rate can provide valuable information related to the condition of the heart, nerves, and lungs pulmonary. Patients who are in critical condition are generally monitored by measuring their respiratory rate. Heart rate is an important parameter in the human cardiovascular system. When the heart rate is irregular, it can be a critical sign. The objective of this study is to design the respiration rate and heart rate monitor. So the author designed an apparatus to detect the respiration by using a flex sensor and the heart rate monitor using the SEN11574 module. The results of these sensors are then sent to the Internet via ESP32 microcontroller. The parameters were displayed to the Web using the Internet of Things (IoT) based on ThingSpeak application. After the comparison between design and standard, the results showed that the error is 2.3% and 0.57% for respiration rate and heart rate, respectively.

Incubator Analyzer Using Bluetooth Android Display (Humidity & Air Flow)

Abstract: — Incubator Analyzer is a calibrator used to calibrate incubator temperature, mattress temperature, noise, humidity and airflow so that conditions in the baby incubator environment remain stable and within normal limits. The purpose of this study is to develop a system for sending data to android and data storage. "Incubator Analyzer Using Bluetooth Appear Android" has four parameters for measuring temperature, noise, humidity, and water flow. Using the Atmega328 microcontroller as a data processor, and the output results will be displayed on the LCD display and equipped with data transmission via bluetooth HC-05 displayed to Android with data storage. The moisture parameter detects humidity quite well where the biggest error is obtained at 1.28% DHT-22, the Ultrasound Sensor HC SR-04 can detect Air Flow with an error of 311.66% as measured by a comparison device. Incubator Design This analyzer is made portable to calibrate baby incubator tools.

Effect of Temperature on pH Meter Based on Arduino Uno With Internal Calibration

Abstract: PH Meter is a device used to express the level of acidity or basicity possessed by a substance or solution. Normal pH has a value of 7 while the pH valueg 7 indicates that the substance has alkaline properties while the pH value l7 indicates acidic properties. pH 0 shows a high degree of acidity, and pH 14 shows the highest degree of alkalinity. pH Meter reads the pH and temperature values ​​in a sample. The author uses glass electrodes as a pH sensor, DS18B20 as a temperature sensor and LCD to make pH and temperature values. This module is equipped with an internal calibration that is used to set the module to read the pH value properly and correctly using a pH buffer and equipped with internal storage and this module facilitates battery usage. Based on pH measurements on the module the error value in buffer 4 calibration is 5.39%, in buffer 7 is 1.76%, in buffer 10 is 1.04%. The highest error value in the measurement sample is 3.54% and the lowest error value is 0.03%. The temperature of the sample is very influential on the reading of the pH value because the higher the temperature the pH value also increases even though it is not so significant.

Waterbath Calibrator with Nine Channels Sensor

Abstract: Water bath is a laboratory equipment that contains water or special liquid that can maintain the temperature under certain conditions during the specified time interval. For this reason, calibration is needed so that the temperature in the chamber waterbath is stable or not. calibration is carried out by comparing measuring instruments and measuring materials to be calibrated to traceable standards that are traceable to national and / or International standards. Based on the results of the identification of the problems mentioned above, the author makes a waterbath calibrator entitled "Waterbath Calibrator (9 channel)" which is very practical, and easy to operate. .This calibration tool uses a K type thermocouple sensor and also the output is displayed to the character LCD to make it easier for users to retrieve data, the reason for choosing a thermocouple sensor is because the error rate is +/- 1,1C while the LM35 is +/- 1,4C. The thermocouple temperature sensor can detect the chamber temperature quite well where the biggest error is obtained with a comparator of 2%, and the lowest error is 0%.

Advances of ECG sensors from hardware, software and format interoperability perspectives

Abstract: It is well-known that cardiovascular disease is one of the major causes of death worldwide nowadays. Electrocardiogram (ECG) sensor is one of the tools commonly used by cardiologists to diagnose and detect signs of heart disease with their patients. Since fast, prompt and accurate interpretation and decision is important in saving the life of patients from sudden heart attack or cardiac arrest, many innovations have been made to ECG sensors. However, the use of traditional ECG sensors is still prevalent in the clinical settings of many medical institutions. This article provides a comprehensive survey on ECG sensors from hardware, software and data format interoperability perspectives. The hardware perspective outlines a general hardware architecture of an ECG sensor along with the description of its hardware components. The software perspective describes various techniques (denoising, machine learning, deep learning, and privacy preservation) and other computer paradigms used in the software development and deployment for ECG sensors. Finally, the format interoperability perspective offers a detailed taxonomy of current ECG formats and the relationship among these formats. The intention is to help researchers towards the development of modern ECG sensors that are suitable and approved for adoption in real clinical settings.

Developing Conductive Fabric Threads for Human Respiratory Rate Monitoring

Abstract: Real-time monitoring of the respiration rate in everyday life enables the early detection of various diseases and disorders that can cause a life-threatening incident. In this article, a passive sensor for real-time monitoring of the human respiration rate is proposed. The sensor is deployed on a chest strap to accurately acquire the respiration rate data and display it on a smartphone through Bluetooth communication. The sensor consists of a stretchable fabric substrate impregnated with silver Nano-particles through drop-casting at ambient conditions. The proposed passive sensor provides a change in electrical resistance against applied strain due to shrinkage of the conducting threads and resets to the initial resistance value when released. The resistance modulation phenomenon is exploited for the respiration sensing application. The demonstrated sensor is $4\times 20$ mm2, however, the dimensions can be changed according to the application and requirements. At rest position, resistance is $180\Omega $ and at 16% stretching, the resistance goes down to $70\Omega $ . The proposed device is characterized by mechanical, electrical, and surface morphology. The proposed sensor can be a good candidate for the respiration sensing application in wearable electronics.

Embedded Machine Learning Using a Multi-Thread Algorithm on a Raspberry Pi Platform to Improve Prosthetic Hand Performance

Abstract: High accuracy and a real-time system are priorities in the development of a prosthetic hand. This study aimed to develop and evaluate a real-time embedded time-domain feature extraction and machine learning on a system on chip (SoC) Raspberry platform using a multi-thread algorithm to operate a prosthetic hand device. The contribution of this study is that the implementation of the multi-thread in the pattern recognition improves the accuracy and decreases the computation time in the SoC. In this study, ten healthy volunteers were involved. The EMG signal was collected by using two dry electrodes placed on the wrist flexor and wrist extensor muscles. To reduce the complexity, four time-domain features were applied to extract the EMG signal. Furthermore, these features were used as the input of the machine learning. The machine learning evaluated in this study were k-nearest neighbor (k-NN), Naive Bayes (NB), decision tree (DT), and support vector machine (SVM). In the SoC implementation, the data acquisition, feature extraction, machine learning, and motor control process were implemented using a multi-thread algorithm. After the evaluation, the result showed that the pairing of the MAV feature and machine learning DT resulted in higher accuracy among other combinations (98.41%) with a computation time of ~1 ms. The implementation of the multi-thread algorithm in the pattern recognition system resulted in significant impact on the time processing.

Internet of things–based vital sign monitoring system

Abstract: Wireless network technology-based internet of things (IoT) has increased significantly and exciting to study, especially vital sign monitoring (body temperature, heart rate, and blood pressure). Vital sign monitoring is crucial to carry out to strengthen medical diagnoses and the continuity of patient health. Vital sign monitoring conducted by medical personnel to diagnose the patient's health condition is still manual. Medical staff must visit patients in each room, and the equipment used is still cable-based. Vital sign examination like this is certainly not practical because it requires a long time in the process of diagnosis. The proposed vital sign monitoring system design aims to assist medical personnel in diagnosing the patient's illness. Vital sign monitoring system uses HRM-2511E sensor for heart detection, DS18b20 sensor for body temperature detection, and MPX5050DP sensor for blood pressure detection. Vital sign data processing uses a raspberry pi as a data delivery media-based internet of things (IoT). Based on the results of the vital sign data retrieval shows that the tool designed functioning correctly. The accuracy of the proposed device for body temperature is 99.51%, heart rate is 97.90%, and blood pressure is 97.69%.

Waterbath Calibrator with Nine Channels Sensor

Abstract: Water bath is a laboratory equipment that contains water or special liquid that can maintain the temperature under certain conditions during the specified time interval. For this reason, calibration is needed so that the temperature in the chamber waterbath is stable or not. calibration is carried out by comparing measuring instruments and measuring materials to be calibrated to traceable standards that are traceable to national and / or International standards. Based on the results of the identification of the problems mentioned above, the author makes a waterbath calibrator entitled "Waterbath Calibrator (9 channel)" which is very practical, and easy to operate. .This calibration tool uses a K type thermocouple sensor and also the output is displayed to the character LCD to make it easier for users to retrieve data, the reason for choosing a thermocouple sensor is because the error rate is +/- 1,1C while the LM35 is +/- 1,4C. The thermocouple temperature sensor can detect the chamber temperature quite well where the biggest error is obtained with a comparator of 2%, and the lowest error is 0%.