Indonesian Journal of Electrical Engineering and Informatics (IJEEI)
Not a member yet
776 research outputs found
Sort by
Unlocking Doors: A TinyML-Based Approach for Real-Time Face Mask Detection in Door Lock Systems
Get PDFIn response to the rapid spread of coronaviruses, including COVID-19 and seasonal common cold viruses, this article introduces a proposed system for enhancing door lock systems using TinyML technology for real-time face mask detection. The research project focuses on developing a machine learning model based on the YOLOv5 architecture to classify individuals based on their mask-wearing behavior correctly, incorrectly, or not at all in high-risk spaces prone to the transmission of coronaviruses, such as healthcare facilities, laboratories, and public settings. The study outlines the hardware and software tools utilized, including the Raspberry Pi 4, camera hardware, and the YOLOv5 machine learning model. The model is trained using a dataset containing three different classes and converted to a TFLite format for efficient implementation on the Raspberry Pi. Evaluation results demonstrate a mean Average Precision (mAP) of 0.99 and an inference rate of 10FPS for a 128-frame size input. This proposed system offers practical implications for enhancing door lock systems and promoting public health and safety during outbreaks of coronaviruses, including COVID-19 and other seasonal coronaviruses, providing a valuable approach to decrease the spread of these diseases and mitigate transmission risks in high-risk spaces, thereby contributing to the overall reduction of public health threats
Optimized Reversible Logic Multiplexer Designs for Energy-Efficient Nanoscale Computing
Get PDFNano- and quantum-based low-power applications are where reversible logic really shines. By using digitally equivalent circuits with reversible logic gates, energy savings may be achieved. Reducing garbage output and ancilla inputs is a primary emphasis of this study, which aims to lower power consumption in reversible multiplexers. Multiplexers with switchable 2:1, 4:1, and 8:1 ratios may be built using the SJ gate and other simple reversible logic gates. The number of ancilla inputs has been cut in half from four to zero, and the amount of garbage output has been cut in half as well, from eight to three, making the 2:1 multiplexer an improvement over the prior design. New 4:1 multiplexer has 10' ancilla inputs, up from 2' in the previous designs. The proposed 4:1 multiplexer also cuts waste production in half from the current 5-to-6 bins per day. The 8:1 multiplexer has two ancilla inputs and nine trash outputs, while the current architecture only has one of each. The functionality of the VHDL and Xilinx 14.7-coded designs is validated by ISIM simulations
Predictive-TOPSIS-based MPPT for PEMFC Featuring Switching Frequency Reduction
Get PDFA maximum power point tracking (MPPT) for a proton exchange membrane fuel cell (PEMFC) using a combination of conventional finite control set model predictive control (FCS-MPC) and Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) is proposed in this paper. The key idea is to maximize the power generation from a PEMFC while minimizing the switching frequency of the power converter. The FCS-MPC technique is formulated to track the maximum power of PEMFC highly affected by ever-changing internal parameters. Meanwhile, the TOPSIS algorithm is applied to overcome the potential weaknesses of insulated-gate bipolar transistor (IGBT), which can only withstand a lower switching frequency. In this project, all simulations were run using MATLAB software to display the output power of the PEMFC system. As a result, the proposed predictive-TOPSIS-based MPPT algorithm can track the MPP for various PEMFC parameters within 0.019 s with an excellent accuracy up to 99.11%. The proposed MPPT technique has fast-tracking of the MPP locus, excellent accuracy, and robustness to environmental changes
Design and Performance Analysis of a Fast 4-Way Set Associative Cache Controller using Tree Pseudo Least Recently Used Algorithm
Get PDFIn the realm of modern computing, cache memory serves as an essential intermediary, mitigating the speed disparity between rapid processors and slower main memory. Central to this study is the development of an innovative cache controller for a 4-way set associative cache, meticulously crafted using VHDL and structured as a Finite State Machine. This controller efficiently oversees a cache of 256 bytes, with each block encompassing 128 bits or 16 bytes, organized into four sets containing four lines each. A key feature of this design is the incorporation of the Tree Pseudo Least Recently Used (PLRU) algorithm for cache replacement, a strategic choice aimed at optimizing cache performance. The effectiveness of this controller was rigorously evaluated using ModelSim, which generated a comprehensive timing diagram to validate the design's functionality, especially when integrated with a segmented main memory of four 1KB banks. The results from this evaluation were promising, showcasing precise logic outputs within the timing diagram. Operational efficiency was evidenced by the controller's swift processing speeds: read hits were completed in a mere three cycles, read misses in five and a half cycles, and both write hits and misses in three and a half cycles. These findings highlight the controller's capability to enhance cache memory efficiency, striking a balance between the complexities of set-associative mapping and the need for optimized performance in contemporary computing systems. This study not only demonstrates the potential of the proposed cache controller design in bridging the processor-memory speed gap but also contributes significantly to the field of cache memory management by offering a viable solution to the challenges posed by traditional cache configurations
Impact of Trust on The Willingness to Use E-Government Services
No full textThe primary objective of this study was to gain insight into individual perceptions of using online public services offered by local governments. The research aimed to determine how performance expectancy, effort expectancy, trust in government, facilitating conditions, and social influence impact individuals' intentions and behaviors in using online government services. Data were collected using an online questionnaire, and analysis was conducted using structural equation modeling with SmartPLS. The key findings include the positive influences of trust in government and facilitating conditions on users' intentions and behaviors related to e-government services. However, the study did not identify a significant relationship between performance expectancy, effort expectancy, and social influence concerning user intentions and behaviors in using e-government services
On the Audio-Visual Emotion Recognition using Convolutional Neural Networks and Extreme Learning Machine
Get PDFThe advances in artificial intelligence and machine learning concerning emotion recognition have been enormous and in previously inconceivable ways. Inspired by the promising evolution in human-computer interaction, this paper is based on developing a multimodal emotion recognition system. This research encompasses two modalities as input, namely speech and video. In the proposed model, the input video samples are subjected to image pre-processing and image frames are obtained. The signal is pre-processed and transformed into the frequency domain for the audio input. The aim is to obtain Mel-spectrogram, which is processed further as images. Convolutional neural networks are used for training and feature extraction for both audio and video with different configurations. The fusion of outputs from two CNNs is done using two extreme learning machines. For classification, the proposed system incorporates a support vector machine. The model is evaluated using three databases, namely eNTERFACE, RML, and SAVEE. For the eNTERFACE dataset, the accuracy obtained without and with augmentation was 87.2% and 94.91%, respectively. The RML dataset yielded an accuracy of 98.5%, and for the SAVEE dataset, the accuracy reached 97.77%. Results achieved from this research are an illustration of the fruitful exploration and effectiveness of the proposed system
Optimized Weight Point ADF using SOS Algorithm
Get PDFActive dc filter (ADF) has become the most viable alternatives for the compensation of the harmonics in the power system analysis. These filters are capable enough to minimize the total harmonic distortion (THD) and provide compensation towards the power quality issues appearing in the transmission system. A simulated model of a HVDC system is designed in MATLAB and the disturbance is injected in the form of load change and the controller efficacy is checked. This paper basically deals with the operational characteristics of the active filter for specific voltage rating irrespective of load and used to reduce harmonics present in the output voltage of the HVDC converter when cascaded with the inverter. The gains of the ADF are optimized with Symbiotic Organism Search Optimization (SOS) with THD as a constraint
A Novel Framework To Investigate The Impact Of Social Media Advertising Features On Customer Purchase Intention Using Bwo-Dann
Get PDFSocial Media (SM) has turned out to be a platform for marketing as well as advertising activities. In relation to SM Advertising (SMA), the cultural influence on consumers’ behavior as well as attitude is more vital. Organizations have used up loads of money, time, and also resources on SMA. Nevertheless, it is always a challenge for the organizations to model SM advertisement in a means to effectively attract and also motivate customers into purchasing their brands. This paper proposed a novel framework to scrutinize the SMA features’ impact on Customer Purchase Intention (CPI) by means of the BWO-DANN. Initially, the questionnaires are given to the various customer and their answers are collected. Then, answers will be uploaded and are converted into numerical format into the system. Next, the CSGA-KM is utilizedfor clustering the questionnaires on the base of personal information. Then the BWO-DANN is utilized to train the converted questionnaire set. After that, the system is tested by utilizing KFCV. Finally, through the mean model, CPI is founded out. The extensive experimentation’s outcomes illustrated that the system trounced the other methodologies, and also it is best to examine the CPI
Prediction of Digital Eye Strain Due to Online Learning Based on the Number of Blinks
Get PDFEye strain is a big concern, especially when it comes to continuous and prolonged online learning. If this is allowed to continue, it will result in Computer Vision Syndrome, also known as Digital Eye Strain (DES), which includes headaches, blurred vision, dry eyes, and even neck and shoulder pain. This condition can be observed either directly based on excessive eye blinking or indirectly based on observations of the electrical activity of eye movements or electrooculography (EOG). The observed blink signal from the EOG, as a representation of eye strain, is the focus of this study. Data acquisition was obtained using the EOG sensor and was carried out on the condition that the participants were conducting online learning activities. There are four different modes of observation taken in succession: when the eye is in a viewing state but without blinking, when the eye blinks intentionally, when the eye is closed, and finally when the eye sees naturally. Observation time is 10s, 20s and 30s, where each interval is performed three times for every mode. The obtained signal is processed by the proposed method. The resulting signal is then labeled as a Blinking signal. Determination of the number of blinks or CNT_PEAK is the result of training this signal by tuning its threshold and width. If the number of blinks is less than or more than 17 then the system will provide a prediction of eye status which is stated in two categories, the first is normal eye while the last is eye strain or fatigue
The Problems of Renewable Power Plant Construction Affecting the Energy Security of Thailand
Get PDFThe objectives of this research were to study the process of submitting an application for every license that affects the success of renewable power plant construction and the energy security of Thailand in accordance with the Energy Industry Act 2007, the engineering factors used in the selection of all types of renewable power plant construction, and the Key Performance Indicators of all types of renewable power plant construction. The data analysis was divided into two sections. For the first section, the quantitative data was collected from the questionnaire conducted by the purposive sampling that included those related to renewable power plant projects, which asked the questions about the rules and regulations and power purchase agreement under the Energy Industry Act 2007. As for the factors influencing the project success, the private sector, combined in the sample group, included the design engineers, consulting and control engineers, and contractors. The 400 engineers were randomly selected from the registration of the Council of Engineers, including senior professional engineers, professional engineers, associate engineers, and adjunct engineers. In the second section, the qualitative data came from the in-depth interviews with five specialists and experts in the renewable power plant industry and in legal knowledge about the rules and regulations and power purchase agreements according to the Energy Industry Act 2007, who work in the Metropolitan Electricity Authority, a renewable power plant construction company, a renewable energy consulting company, in the field of renewable power plant investment, and as a renewable power plant specialist (Office of the Energy Regulatory Commission). The data was analyzed by using the following statistics: percentage, frequency, mean, standard deviation, and the Enter method of multiple regression. According to the results, the overall success of using the engineering factors in selecting a renewable power plant establishment has the mean at a high level. With regard to the types of power plants, the solar power plant is ranked at the top, followed by the second, the biomass power plant; then, the waste-to-energy power plant, the biogas power plant, and the wind power plant, respectively. The type of power plant with a moderately high mean is the hydroelectric power plant. The findings show the engineering factors related to the success of all types of renewable power plants. Moreover, regarding the problem of energy policy, deciding which type of energy to use is highly complicated because there are many dimensional reasons and no form of energy is the best or the worst option. However, it is not too difficult for specialists to make a decision