Jurnal Rekayasa Elektrika
Not a member yet
345 research outputs found
Sort by
Authentication of an Indonesian ID Card with Simultaneous NFC and Face Recognition
Full text linkoai:jurnal.usk.ac.id:article/41142Identity (ID) card forgery remains a significant issue in Indonesia, often leading to crimes such as identity theft and fraud. To address this challenge, this study proposes the development of an identity authentication system that integrates near field communication (NFC) and facial recognition based on K-nearest neighbors (KNN) algorithm. The primary objective of this system is to enhance the security of ID card (KTP) data and to ensure efficient and accurate access to services requiring identity verification. The system stores facial data and ID card information securely in Firebase, which serves both as a user authentication platform and a secure cloud-based storage solution. The application, developed using Flutter, incorporates facial recognition for biometric verification, while NFC is employed as an additional authentication layer to provide dual-factor verification and reinforce identity security. Experimental results demonstrate that the facial recognition based on KKN achieved an accuracy rate of 100% with a false acceptance rate (FAR) of 0%, indicating a highly reliable performance. These findings confirm that the integration of facial recognition and NFC technologies offers a robust and effective solution to combat ID card forgery, thereby improving the overall reliability and security of the population data authentication system in Indonesia
LoRa-Based IoT Recommendations for Surabaya City Drainage Channel Using Multi-Node Multi-Hop Communication
Full text linkThis paper focuses on the development of a multi-hop LoRa (Long-Range) communication network for real-time monitoring of urban drainage Internet of Things (IoT), specifically simulating the flood-prone area along the drainage channel of Jalan Jawa, Surabaya City. The novelty of this research lies in the selection of the optimal communication environment through path loss and shadowing analysis prior to implementing a multi-node, multi-hop, sensor medium access control (S-MAC) method. The selected environment at the first location demonstrated a lower path loss exponent of 1.55, typical of "in-building line-of-sight," compared to the second location with a loss exponent of 2.82, which resembled "urban area cellular radio." Applying the multi-hop technique successfully extended the data transmission range up to 750 meters with nodes placed at 250-meter intervals while maintaining a high data transfer rate. The experiments showed that increasing distance significantly reduced the received signal strength indicator (RSSI), with values dropping from -52.75 dBm at 150 meters to -98.25 dBm at 750 meters. This paper demonstrates the feasibility of using multi-hop communication rather than the conventional multi-node technique to ensure reliable data transmission and wider range, offering a solid foundation for building a robust communication network in urban drainage monitoring systems
A Single Phase Active Front-End Converter for Unity Power Factor
Full text linkA rectifier is an electronic circuit that converts Alternating Current (AC) into Direct Current (DC). This circuit is very important in many electronic applications, especially in power supplies, battery chargers, and other equipment requiring a DC power supply. Conventional rectifiers use diodes or thyristors as rectifying components. Although a rectifier that uses a diode is generally effective and easy to apply in converting AC to DC, the diode or thyristor component has several drawbacks when used as a rectifier, namely the low power factor on the supply side. To overcome these deficiencies, this paper presents the topic of front-end converter which uses Insulated Gate Bipolar Transistor (IGBT) components as a substitute for diode and thyristor components. IGBT is an active component so a SPWM signal is needed to regulate this IGBT so that it can work. In this front-end converter, to achieve unity power factor results on the supply side, SPWM is used so that it can adjust the current waveform on the supply side to be in phase with the voltage waveform on the source side. The front-end converter presented in this paper has also added the load on the AC side to prove the work of the Front-End Converter
Hybrid Deep Learning Models Using LSTM with Random Forest for Radio Frequency-Based Human Activity Recognition in Line-of-Sight and Non-Line-of-Sight Environments
Full text linkHuman Activity Recognition (HAR) has become an important field of study because of its wide range of applications in healthcare, security, and smart living systems. Radio Frequency (RF)-based HAR offers a non-invasive and privacy-preserving alternative to traditional vision-based systems. This study proposes a hybrid deep learning model combining Long Short-Term Memory (LSTM) networks with Random Forest classifiers for RF-based HAR, aiming to improve recognition accuracy across diverse environments. The model was evaluated using Channel State Information (CSI) and Received Signal Strength Indicator (RSSI) features under Line-of-Sight (LOS) and Non-Line-of-Sight (NLOS) conditions. Synthetic Minority Over-sampling Technique (SMOTE) was integrated to balance the dataset, and K-fold Cross-Validation was employed to assess robustness. The dataset included data from 8 subjects performing 10 different activities. The model achieved high classification accuracy, with 99.40% in Environment 1 (LOS), 97.58% in Environment 2 (LOS), and 98.30% in Environment 3 (NLOS), demonstrating the models adaptability and effectiveness. The results highlight the potential of the hybrid LSTM with Random Forest approach for scalable and reliable RF-based HAR systems that can be integrated into real-world Internet of Things (IoT) applications
Automating Mining Surface Monitoring using SpatioTemporal Asset Catalog(STAC): A Spectral Index Approach with Sentinel-2 Satellite Imagery
Full text linkMining activities significantly impact the environment, necessitating effective, continuous monitoring. Traditional surface monitoring methods are often costly and labor-intensive. This study proposes an automated workflow using the SpatioTemporal Asset Catalog (STAC) and Sentinel-2 satellite imagery to monitor mining surface changes. By calculating the Normalized Difference Vegetation Index (NDVI), Normalized Difference Water Index (NDWI), and Modified Bare Soil Index (MBI), the workflow identifies land cover changes within mining concessions. The system was Implemented in Python environment using libraries such as PySTAC, PySTAC Client, Xarray, Rioxarray, Geopandas, Dask, and Numpy. The mining surface change was analyzed using the regression line gradient of each spectral index. Results show active mining sites exhibit an NDVI slope lower than -1, indicating rapid conversion of vegetation to non-vegetative land due to land clearing activities. Conversely, the positive NDWI trend indicates increased water coverage from land excavation, while the MBI trend is the weakest, suggesting limited sensitivity to surface changes in mining areas. To evaluate the accuracy of the results, manual verification was conducted. The analysis revealed that 3 out of 25 mining concessions were incorrectly classified, resulting in an overall accuracy of 88%
Featuring Software Defined Radio in Airports for Finding Automatic Descendants Surveillance
Full text linkAs air traffic becomes more complicated, more effective monitoring systems are required to assure aviation safety and security. Automatic Dependent Surveillance-Broadcast (ADS-B) technology has become the international standard for real-time airplane tracking, however typical ADS-B receivers used in airports are expensive and frequently unavailable. This study seeks to assess the dependability and efficiency of Software Defined Radio (RTL-SDR) as a low-cost option for receiving ADS-B signals. The study focuses on the development of a 1090 MHz PCB antenna coupled to an RTL-SDR device, with data processed using RTL1090 software and visualized using Virtual Radar Server. Testing took place at two airports: Yogyakarta International Airport (YIA) and Wirasaba Airport. The results show that the system can identify aircraft within a range of up to 400 km at YIA and 250 km at Wirasaba, with the received data providing precise information on aircraft position, altitude, and speed. The system spotted four airplanes in Wirasaba and nine at YIA, indicating that the latter location has broader coverage. These findings show that RTL-SDR is a dependable and cost-effective option for ADS-B signal reception, with the potential to replace more expensive conventional receivers used in airports
Optimizing Light Detection with Photodiode Sensor Arrays using Linear Regression
Full text linkPhotodiode sensors are widely used in various applications such as light intensity measurement, optoelectronic devices, and automation. In improving the quality of measurement and automation systems, more sophisticated technology is needed such as photodiode sensor arrays, which allow more accurate data collection from multiple sensors simultaneously. This research aims to design a photodiode sensor array with high sensitivity. The system design consists of six photodiode sensors combined with a summing amplifier circuit and a non-inverting amplifier as a signal conditioner which is then processed by a microcontroller. After that, the linear regression function is determined through the calibration process and experiments carried out. Two linear regression functions are obtained and implemented in two operating modes: normal mode and sensitive mode. Experimental results yield two linear regression functions applied to a photodiode sensor array in normal and sensitive modes. Normal mode shows 69.71% accuracy with a 32.81% Coefficient of Variation, while sensitive mode boasts 93.87% accuracy and 44.45% Coefficient of Variation. Both modes cater to different light conditions, with sensitive mode excelling in detecting light intensity. Linear regression implementation proves precise and accurate for light detection
Multi-Sensor Internet of Things System for Monitoring Wastewater in Healthcare Facility
Full text linkWastewater produced by healthcare facilities must meet the parameter criteria set by the Ministry of Environment. These criteria ensure that the discharged wastewater does not harm the environment. The numerous healthcare facilities in an area and irregular monitoring can lead to inaccuracies in recording wastewater content. Technology that can be used for periodic monitoring of wastewater content in healthcare facilities is multi-sensor technology and the Internet of Things (IoT). This paper aims to develop the devices utilizing multi-sensor technology and IoT for monitoring wastewater parameter criteria in healthcare facilities. The developed device measures pH, turbidity, Oxidation Reduction Potential (ORP), and temperature parameters in the wastewater. The sensor data test results showed an accuracy of 98,77% with a precision of 10,030,13 for the pH parameter. The ORP parameter showed an average accuracy of 97,56% with a precision range of 241,205,65. The turbidity parameter showed an average accuracy of 96,20% with a precision range of 101,673,11. The temperature parameter showed an average accuracy of 97,80% with a precision range of 39,230.73. Data transmission to the platform had an average delay of 88.02ms with an average jitter 0,23ms. Based on the performance measurement data for sensor and data transmission categories, the proposed device met the research aim in monitoring wastewater conditions in healthcare facilities. The device has also been used to monitor three healthcare facilities in Central Java. The monitoring results using the device showed that the three healthcare facilities met the criteria required by the Ministry of Environment
Positioning Control System on the Movement of Wheeled Humanoid Robot Using Swerve Drive Model Based on Fuzzy Logic Controller
Full text linkTechnology in robotics has developed rapidly in the last few decades, as evidenced by the increasing number of robots created, such as humanoid robots and mobile robots. In this study, a wheeled humanoid robot is designed to move from one place to another using a swerve drive model, a holonomic type of drive wheel. This model uses a combination of DC motors and gears to ensure smooth movement of the humanoid robot. The swerve drive allows the robot to move freely in all directions. Therefore, the humanoid robot requires a control system to manage and automatically regulate the state of the system. The fuzzy logic control system can perform mathematical calculations based on human knowledge, serving as a controller without requiring a mathematical model of the controlled process. The results obtained from this study demonstrate the robots ability to move stably and accurately, based on the response to the rules provided by the fuzzy logic control system. The more membership functions used, the more stable and accurate the results will be, while using fewer membership functions will result in faster response times to reach the setpoint
Water Quality Monitoring and Control System in Koi Fish Cultivation Based on Internet-of-Things (IoT)
Full text linkThis research develops an Internet-of-Things (IoT)-based system for real-time monitoring and automatic control of water quality in koi fish farming, addressing the lack of knowledge regarding optimal water conditions. The system integrates sensors for pH, ammonia, temperature, total dissolved solids (TDS), and turbidity, along with controllers such as filters, coolers, and heaters, all managed through a mobile application called AquaKoi. System testing is divided into IoT device testing and mobile application testing. IoT device testing ensures proper sensor and controller functionality, with sensor data verified against water quality standards. Application testing includes black box testing, quality-of-service (QoS) measurement, user acceptance test (UAT), and notification warning testing, showing a user satisfaction rate of 92%. The test results indicate that the system functions well and meets specifications, despite challenges like overheating of the ESP32 microcontroller, which was mitigated with a temporary fan solution. Overall, the AquaKoi system demonstrates significant potential in enhancing the efficiency of koi fish farming. However, further development is recommended to address technical constraints, improve the user interface, and expand the systems capabilities to meet more diverse user needs