Indonesian Journal of Electrical Engineering and Informatics (IJEEI)
Not a member yet
776 research outputs found
Sort by
IoT-based Smart Campus Monitoring Based on an Improved Chimp Optimization-Based Deep Belief Neural Network
Get PDFInternet of Things (IoT) is a fast emerging technology that gained momentum steadily and shaped the future of the smart world. It has been created from the curiosity of human beings to provide comfortable and connected lifestyles with the mitigation of labor and therein promptly reduces the errors. This led to the usage of smart devices in everyday activities and thus enhances the efficacy of all smart applications. Smart applications include smart farming, healthcare, smart grid, smart city, and more. The application of IoT in monitoring the smart campus is an inevitable one to monitor the attendance of students and monitoring other activitieson the campus to protect the students and improve the education standards. Most education institutes use smart classrooms to achieve the aforementioned quality. Smart classrooms include audio-visual aids, multimedia, and smart boards along with these it is ineluctable to monitor the activities such as students’ attendance, analyzing the students-faculty performance, and content deliveries. To record the students’ attendance automatically we propose a Bluetooth-enabled IoT smart system for the positing of students with low energy utilization. The attendance can be recorded in the cloud environment by the Received signal strength indicator (RSSI). To achieve this we propose a novel IoT-based Deep Belief Neural Network (DBN) based Improved Chimp Optimization algorithm (ICO) for monitoring the attendance and positioning of the students’. An experimental study is conducted on Raspberry Pi with the deployment of Python and shows that our proposed approach provides better accuracy even with high interference signals
A Review on Explainable Artificial Intelligence Methods, Applications, and Challenges
Get PDFExplainable Artificial Intelligence (XAI) has emerged as a critical area of research and development in the field of artificial intelligence. This abstract provides an overview of XAI, covering its methods, applications, and challenges. XAI Methods: XAI methods aim to enhance the transparency and interpretability of complex machine learning models. Model-agnostic techniques like LIME and model-specific methods like SHAP have gained prominence in providing explanations for AI predictions. The field also explores interpretable deep learning architectures and approaches to make neural networks more transparent. XAI Applications: XAI finds applications across diverse domains. In healthcare, XAI assists in interpreting medical diagnoses and treatment recommendations. In finance, it aids in risk assessment and regulatory compliance. XAI is crucial in autonomous vehicles to explain decision-making processes, contributing to safety and trust. In customer service, it improves chatbot interactions by providing understandable responses. Moreover, XAI has relevance in agriculture, manufacturing, energy efficiency, education, content recommendation, and more. XAI Challenges: Despite its significance, XAI faces several challenges. Balancing model complexity with interpretability remains a fundamental trade-off. Detecting and mitigating bias in AI systems is crucial, especially in sensitive domains. Ensuring ethical considerations, data privacy, and user consent are paramount. Challenges also include providing explanations for high-stakes decisions, addressing the need for human oversight, and adapting to international and cultural norms. In conclusion, XAI plays a pivotal role in making AI systems more transparent, fair, and accountable. As it continues to evolve, it is poised to shape the future of AI by enabling users to understand and trust AI systems, fostering responsible AI development, and addressing ethical and practical challenges in various applications
A Five Level Modified Cascaded H-Bridge Inverter STATCOM for Power Quality Improvement
Get PDFMultilevel converters have received serious attention on account of their capability of high voltage operation, high efficiency, and low electromagnetic interference. It has many advantages compared to conventional two-level inverters such as high dc-link voltages, reduced harmonic distortion, fewer voltage stresses, and low electromagnetic interferences. The multilevel converters have been used for STATCOM widely as it can improve the power rating of the compensator to make it suitable for medium or high-voltage high power applications. While deploying multilevel STATCOMs, designer’s role is to reduce the number of switching devices since, the total switching losses are proportional to the number of switching devices. The reduction in the count of switching devices also reduces the size and cost. In this paper, a five-level modified cascaded H-bridge inverter STATCOM is proposed for mitigation of harmonics. Modified Five-level CHB configuration is the most suitable as with lesser number of switches, give better performance resulting in a compact system. The PQ theory-based controller is developed for control of STATCOM operation. MATLAB simulation results are presented to demonstrate mitigation of harmonics
Hardware Security Module Cryptosystem Using Petri Net
Get PDFAn embedded system is a combination of hardware and software designed to perform specific functions. It consists of SoCs (system on chip) that it relies on to do its computing work. A key feature of an embedded system is that it consumes less power and components occupy less space on the IC (integrated circuit) thus, the use of SoCs. Embedded system manufacturers get these SoCs from third-party companies to reduce their time to market. That would increase the possibility of the systems to be compromised. In this paper, we present a novel approach to securing such critical systems. For that, we made a Hardware Security Module (HSM), which consists of secure SoC with encrypt/decrypt engine that use Petri net for algorithm modulation to secure data flow. We ensure that the system uses genuine firmware and data is secured since we use encrypt/decrypt algorithms only known to manufacturers
Cloud Computing Adoption in the South African Public Sector
Get PDFScholars have touted a variety of benefits for adopting cloud computing solutions in the public sector. However, the adoption of cloud computing has been low in the South African (SA) government context. This study investigates the factors influencing cloud computing adoption within the SA public sector. The study adopted a case study approach. The research was informed by the Technological Organisational Environmental (TOE) and the Diffusion of Innovation (DOI) theoretical frameworks to understand the trajectory of cloud computing adoption. Primary data was collected using a questionnaire and semi-structured interviews with respondents from government departments. Additionally, secondary data from government Information Technology (IT) policies and strategic documents was analysed. The results highlighted that the enablers that are critical for cloud adoption include cloud computing policy, skills, IT infrastructure and financial support. The barriers that are hindering cloud adoption are related to security risks, network connection, cloud computing policy, costs and budget availability, among others. The identified benefits that may be realised through cloud adoption include enhanced service improvement, cost savings, high system availability, green IT, centralised and shared services and accessibility. The study proposes several guiding principles for cloud computing adoption in the public sector
Detecting Urban Road Changes using Segmentation and Vector Analysis
Get PDFThe rapid growth of urbanization is driving increased road infrastructure development. Detecting and monitoring changes in urban road areas is challenging for city planners. This research proposes using semantic segmentation and vector analysis on high-resolution images to identify road network changes. The U-Net model performs semantic segmentation, pre-trained on a Massachusetts road dataset, predicting labels for a specific area with temporal data and co-registration to reduce distortions. Predicted labels are converted to shapefiles for vector analysis. Satellite images from Google Earth archives demonstrate the change detection process. The outcome of this predictive phase was the transformation of projected labels into shapefiles, thereby facilitating vector analysis to pinpoint and characterize alterations
Simplified Kinetic Model of Heart Pressure for Human Dynamical Blood Flow
Get PDFThe blood flow that carries various particles results in disturbed physical flow in the heart organ caused by speed, density, and pressure. This phenomenon is complicated resulting in a wide variety of medical problems. This research provides a mathematical technique and numerical experiment for a straightforward solution to cardiac blood flow to arteries. Finite element analysis (FEA) is used to study and construct mathematical models for human blood flow through arterial branches. Furthermore, FEA is used to simulate the steady two-dimensional flow of viscous fluids across various geometries. The results showed that the blood flow in the carotid artery branching is simulated after the velocity profiles obtained are plotted against the experimental design. The computational method's validity is evaluated by comparing the numerical experiment with the analytical results of various functions
Master-Slave Synchronization of Robotic Arm using PID Controller
Get PDFThis paper analyzes the position control of a master-slave synchronization robotic arm driven by a D.C. motor using a PID (Proportional, Integral, and Derivative) controller with software and hardware design. This controller works to achieve the exact desired position simultaneously for the master and slave robot arm with minimal defects. The transfer function of the D.C. motor for the robotic arms used in this research is calculated with black box modelling. MATLAB Simulink block is used to test the software result. The MATLAB built-in auto-tuning method obtains Kp, Ki and Kd gain. These gains are adjusted with manual tuning to get precise angular positions for two robotic arms. This research uses Arduino Uno to act as a controller in the experiment. First, the position control of one robotic arm is tested with the same PID gain in MATLAB Simulink at different input degrees. Then, the hardware experiment of position control in one robotic arm is operated with only one PID gain at various reference degrees. Finally, the I2C communication protocol connects the master and slave robot arms. The main work that the PID controller hardware experiment with controls different level angular positions of two robotic arms
Stability Enhancement of DFIG Wind Farm Using SSSC With FOPID Controller
Get PDFThe wind power generation has become more important nowadays to meet the increase in power demand. DFIG based wind power generation is the recent and used in many countries due to its better power controllability. The controllers like Proportional Integral (PI) are used for the stabilization of the waveforms of the supply system. The change in controllers produces better oscillation damping in recent days. The effect of varying the wind input to generate power using the wind turbine resulting in instability in the power system because of the control is done on a grid supply. This paper aims to proposes an optimum FOPID controller for damping power system instability using a Static Synchronous Series Compensator (SSSC) system that takes into account the dynamics of wind energy conversion systems (WECS) connected to a infinite grid. The WECS model, which includes variations in wind supply to the wind turbine, has been developed to test the durability of the optimized controller that was developed to damping power system oscillations. The controller used to take the power system dynamics into account. A new controller is being designed to include a corrective measure for the damping the oscillations to adjust the instability caused by wind supply variations. The controller helps to tune the controller settings that lead to the achievement of the power oscillation damping objectives. These results are compared with conventional PMSM based wind turbine system
An Improved Energy Saving Technique for Wireless Power Transfer in Near Field Communication Systems
Get PDFIn this work, an improved communication algorithm was developed to reduce energy wastage in a Near Field Communication (NFC) system using dynamic field Strength scaling technique. With a variable resistor in the reader coil, the field strength of the system was scaled in real-time by adjusting the value of the resistor in relation to distance. This system was tested with the advanced design system's Application Extension Language (AEL) and simulated on Advanced Digital Technology. The results showed a responsive change in the magnetic field when the two scenarios (with and without optimization) were simulated. There was a 66% change in energy transfer within the time frame referenced. Results further indicated that the adoption of the proposed algorithm could help engineers to design a more effective NFC system