Search

With the current technology trend of IoT and Smart Device, there is a possibility for the improvement of our infant incubator in responding to the real baby’s condition. This work is trying to see that possibility. First is by analyzing of open baby voice database. From there, a procedure to find out baby cry classification will be explained. The approach was starting with an analysis of sound’s power from that WAV files before going further into the 2D pattern, which will have features for the machine learning. From this work, around 85% accuracy could be achieved. Then together with sensors, it would be useful for infant incubator’s innovation by utilizing this proposed configuration.

This paper proposed a simple but highly accurate feature extraction method for epilepsy detection from electroencephalogram (EEG) signals. Based on the combination of Discrete Wavelet Transform (DWT) and the newly proposed features Local Binary Pattern Transition Histogram (LBPTH) and Local Binary Pattern Mean Absolute Deviation (LBPMAD), our proposed feature extraction method can efficiently extract features from EEG signals for machine learning classification of epilepsy, achieving high classification accuracy with a feature size of only 18 for each signal. Tested on the publicly available University of Bonn Epilepsy EEG Dataset using a signal length of 4097 data points (23.61 seconds), the proposed method achieved larger than 99.6% accuracy results for Support Vector Machine (SVM) and k-Nearest Neighbor (KNN) classification of ictal (set E) against any non-ictal (set A, B, C, or D) or combinations of non-ictal (set $\text{A}+\text{B}$ , set $\text{C}+\text{D}$ , or set $\text{A}+\text{B}+\text{C}+\text{D}$ ) EEG signals, which is among the best of currently published works. Our method can maintain high classification accuracy even with short input signals, achieving more than 99.1% SVM classification accuracy when input signal length is reduced to 512 data points (2.95 seconds). The high accuracy, small feature size, ability to work with short input signals and low computing requirements made the proposed method suitable for mobile, low power, and low-cost wearable medical devices.

The article describes a new way to define the threshold voltage for Machine Learning-based Digital Residual Current Circuit Breaker (RCCB), enabling the right cut-off point. Using the described methods, the authors obtained a gap to common mid voltage being around 0.5 V. The proposed technique is illustrated with three different loads of 3W, 5W, and 9W as the scope of this work. The authors try to apply it in Residual Current Circuit Breaker (RCCB). It could be useful in a hospital with a limited number of technicians to maintain various machines quickly. This work tries to realize a machine that could find out the best condition to cut off the electricity when there is any leakage current but keep the supply if it is still under tolerance. This allows improving the mistake of the midpoint about 16.97% over its wide range. The effectiveness of Python libraries usage realized the Artificial Neural Network (ANN) implementation as one of machine-learning algorithms. The learning process is applied to the measured leakage current data set. It goes with input preprocessing, training, testing, and data analysis. From all of those steps, it is possible to determine the induction voltage threshold at 1.080 from 3.3V as its maximum value with a negligible loss value of 0.0006. By comparing the value with a reference, it can be concluded that this method could be used in a real situation.

This document describes the implementation of IoT-based incubator monitoring system. The proposed module used a microcontroller board along with three groups of components: biosensors, environment monitoring sensors, and communication module. This research replaced Arduino Uno Rev3 and ESP8266 communication module with an Arduino Uno+WiFi, a microcontroller and communication module in a single board, and an additional sensor to measure pulse rate and pulse oximeter. This research also acquired data from the new sensor and used related measuring tools data for comparison purpose. The measurement results show that the average error of pulse rate was less than one per cent, while the SpO2 is slightly above three per cent.

This document describes the design of the hardware module of IoT-based infant incubator monitoring system. The hardware module consists of microcontroller, data acquisition submodule and data communication submodule. In this research, the microcontroller used is Arduino Uno Rev3 along with a body temperature sensor as the representation of biosensors and ambience temperature sensor, humidity sensor, and gas sensor as the representation of environment monitoring sensors. The Arduino board connected with an ESP8266 WiFi as a data communication submodule. This research also compared data acquired from this module with the data from related measuring tools.

This work proposes a tool that can be used for monitoring and detecting electricity leakage current by utilizing common RCD core. Those values could be remotely observed by utilizing Internet of Things (IoT) technology. The leakage current is measured using common RCD's toroid before being inserted into analog input of IoT Board, an ESP8266 based microcontroller. The measured voltage will be sent to Blynk server wirelessly. Finally, users will be able to monitor its changes in values by using common smart phone, through Blynk app. From the test, the induced voltage was 0.032 V and 2.568 V during the normal condition and the leakage current condition respectively. It showed that the leakage current was possible to be detected and monitored using this system.

Many applications could be developed in Android Phone for the improvements of modern car's condition monitoring. That could be a simple user interface for an On-Board Diagnostics (OBD) tools for a car condition monitoring in nowadays manual driving, or up to replacement of its driver for further control in an autonomous driving. However all of them will be so much dependent on its position tracking. In this work, a position tracking system would be designed started from the system's architecture with telecommunication network until its behavior with UML Diagrams. Overall, the system consisted of two parts. They were an android application (app) and the nodeJs web server. The app would deal with the data collection. Then, the web server would show the result using map interface from Open Street Map. From a testing trip, 611 position points were obtained. From those points, it was found also that the shortest processing time between the records was 5 seconds and the longest could be more than 3 minutes.

In the industrial era 4.0, domestic baby incubator producers are facing the challenge of free trade of foreign products that will compete in innovation with the application of IoT technology. One of the opportunities that arise consciously or unconsciously at the NICU (Neonatal Intensive Care Unit) unit in Hospitals, in general, is that there are no facilities for parents to monitor the baby’s condition inside the incubator directly. The purpose of this research project is to build a prototype of an internet-based baby incubator monitoring system based on things equipped with various sensors that will send data to the server in real-time and mobile apps for monitoring facilities for parents, including the voice of the baby. This study focused on how to develop baby incubators that can listen to baby’s crying, capture the voice, and interpret it using artificial intelligence. More than 40 (forty) voice datasets were used and successfully classified into five possible terms of the baby’s condition: burping, sleepy, hungry, uncomfortable, and pain by energy signal and spectrum analysis. The benefit of this research is as a driver of innovation for baby incubator products that will support the national medical devices manufacturing company.

[EN] Residual-current devices (RCDs) are used to protect humans from electrical shocks. This study explores the DC limit parameters of RCDs using the capacitor. To find out the possible parameters, a common signal from the RCD in AC waveform is analyzed using a digital oscilloscope for reference. This signal is then transformed into a DC signal using a common circuit of a full-bridge rectifier, capacitor, and a voltage regulator. Finally, the signal is characterized using an oscilloscope and multimeter. The result of this work is I-V characteristic of the DC measurement obtained from the RCD. It shows two possible parameters. First is a voltage gap of 1 V which representing input current with a range from 0.4 to 64.3 mA. Second is an increasing speed of 1.06 V/s on average. These parameters could be used to overcome the nuisance trips of common RCDs., The work and publications are supported by the Faculty of Science and Technology, UniversitasAirlangga with a Young Lecturer's Research Fund Program. This article would not have been completed without the support of all the team members. Many thanks for all of the team members, as well as other colleagues for their suggestions and indirect assistance.

Electric vehicles (EVs) have received massive attention in their adoption as transportation and energy-assisting instruments. This phenomenon has been led mainly by the increased awareness and experience of the user (driver) on EVs regarding their excellent driving convenience, clean environment, and energy efficiency. Besides, several government policies also have driven the new user to shift from conventional vehicles to EVs following several favorable treatments, especially related to taxes. Generally, EVs have large battery capacity which can be controlled in both charging and discharging. Therefore, the idea of Vehicle-Grid Integration (VGI) has emerged recently, following the increased grid stress due to the massive charging of EVs and the opportunities to control and utilize EVs to participate in grid ancillary services. Several possible ancillary services include frequency regulation, load leveling (peak shaving), renewable energy storage, voltage regulation, and congestion mitigation. In this study, a preliminary analysis on the implementation of VGI in Indonesian grid, especially related to load leveling and frequency regulation, is discussed. Indonesian grid currently faces several problems, especially related to its quality and capability to balance and response to the fluctuating supply and demand. The well-coordinated EVs give high opportunity to the grid to utilize them as huge and responsive power storage to balance and maintain the electrical grid quality.

For leakage current safety, Residual Current Device (RCD) has been well known. The purpose of this work is to make the employment of low price components to measure residual current feasible and the Residual Current Device (RCD) must to be taken into account because it is a well known device for leakage current safety. For this purpose, experiments employing the Helmholtz Coil Configuration were performed with the different current flow. Furthermore, the residual current was formulated and simulated through the software Easy Java Simulation (EJS). The results showed that it is possible to move the magnet into different angles using leakage current with linear gradient as low as 0.382 degree/mA. Finally, it was proposed a way to increase the sensitivity and to reduce the hysteresis phenomenon.

Affordable high magnetic permeability material has always been a challenge for those who are working with RCD. This article tried to show the possibility of using the low cost Iron Oxide powder. This is because Fe 2 O 3 is more available nowadays. The first work was trying to analyze Fe 2 O 3 permeability using physics approaches. It was included the simulation using Abninit - a Density Functional Theory software. Then it discussed the test of the simple magnetic core using common household's AC voltage. From the test, 9.52 mV AC could be easily induced from 230 V AC using the magnetic core with only sixteen windings at a low current of 13.21 mA

Leakage current measurement which can follow IEC standard for medical device is one of many challenges to be answered. The IEC 60601-1 has defined that the limit for a leakage current for Medical Device can be as low as 10 µA and as high as 500 µA, depending on which type of contact (applied part) connected to the patient. Most people are using ELCB (Earth-leakage circuit breaker) for safety purpose as this is the most common and available safety device in market. One type of ELCB devices is RCD (Residual Current Device) and this RCD type can measure the leakage current directly. This work will show the possibility on how Helmholtz Coil Configuration can be made to be like the RCD. The possibility is explored by comparing the magnetic field formula from each device, then it proceeds with a simulation using software EJS (Easy Java Simulation). The simulation will make sure the concept of magnetic field current cancellation follows the RCD concept. Finally, the possibility of increasing the measurement's sensitivity is also analyzed. The sensitivity is needed to see the possibility on reaching the minimum leakage current limit defined by IEC, 0.01mA.

The paper describes an adaptive finite element analysis of the transient axisymmetric freezing process. Adaptivity schemes are applied to both space and time tessellations. Error equidistribution adjusts the nodal positions and Taylor series analysis of time truncation error selects the time step. In implicit time integration, the location of the freezing front and the nodal temperatures at the next time is solved by full Newton all at once. The method appears to be accurate; in cases for which closed-form solutions are available, it agrees well with them. It also avoids the problem found in the Modified Isotherm Migration Method where the freezing front tends to retrogress when solid just forms on the outer surface cooled by convection.