Indonesian Journal of Electrical Engineering and Computer Science
Not a member yet
9109 research outputs found
Sort by
Interlined dynamic voltage restorer using time-domain methodologies with Z-source inverter/voltage source inverter
Get PDFElectronic devices and loads are very sensitive to the voltage disturbances like voltage sag and voltage swell. Significant financial losses and safety issues may emerge from voltage sags and interruptions, which can be caused by variables such as system breakdowns and load changes. In order to protect against voltage fluctuations and keep vital loads running, dynamic voltage restorers (DVRs) have become more popular. To mitigate the voltage disturbances, an interlined DVR (IDVR) using a Z-source inverter (ZSI) is developed to protect the sensitive devices and loads. Back-to-back DVR connects the distributed feeders with a common direct current (DC) link. The IDVR compensates for the sag voltage and supplies the energy to control the power flow. In addition, proposed a modified synchronous reference frame (MSRF)/direct quadrature theory, hysteresis controller, and proportional integral (PI) controller, which provides the required amount of control signals for a ZSI and voltage source inverter (VSI). MATLAB/Simulink validated the simulation results. The experimental findings show that the suggested system can be implemented successfully and is effective at reducing voltage dips and interruptions, allowing crucial loads to keep operating consistently and without interruption in residential as well as commercial environments
Stereo object matching for mobile robot path planning using artificial fish algorithms
Get PDFThe popularity of robots is on the rise, not only in industrial settings but increasingly in daily venues such as airports. Recently, some organizations have carried out experiments utilizing robots specifically created to improve airport hygiene, security, and passengers’ overall satisfaction. Furthermore, the utilization of the artificial fish (AFs) algorithm in path planning for mobile robots yielded exceptional outcomes. The robot can replicate the prey behavior of the AFs algorithm, as evidenced by the prevalence of pos one in the simulation. The robot exhibits another behavior, which is the subsequent behavior. The behavior of the AFs algorithm is influenced by the available food sources. Simultaneously, mobile robots are influenced by the stimulation of their neighboring responses. Afterwards, the three primary classifiers are employed to perform stereo-object matching on different objects. The recognition rate achieved by the AdaBoost classifier is promising, with an accuracy rate of 92.4%. This result shows excellent potential for improving the path planning of mobile robots equipped with visual surveillance systems for their surroundings
Modelling and estimating trajectory points from RTK-GNSS based on an integrated modelling approach
Get PDFThe sparse Gaussian process regression (GPR) has been used to model trajectory data from Real time kinematics-global navigation satellite system (RTK-GNSS). However, upon scrutinizing the model residuals; the sparse GPR model poorly fits the data and exhibits presence of correlated noise. This work attempts to address these issues by proposing an integrated modeling approach called GPR-LR-ARIMA where the sparse GPR was integrated with the linear regression with autoregressive integrated moving average errors (LR-ARIMA) to further enhance the description of the trajectory data. In this integrated approach, the predicted trajectory points from the GPR were further described by the LR-ARIMA. Simulation of the GPR-LR-ARIMA on three sets of trajectory data indicated better model fit, revealed in the normally distributed model residuals and symmetrically distributed scatter plots. Correlated noise was also successfully eliminated by the model. The GPR-LR-ARIMA outperformed both the GPR and LRARIMA by its ability to improve mean-absolute-error in 2-dimension positioning by up to 86%. The GPR-LR-ARIMA contributes to enhancement of positioning accuracy of dynamic GNSS measurements in localization and navigation system with good model fit
Big data analysis and its impact on the marketing industry: a systematic review
Get PDFThis systematic review focused on understanding the impact of big data on marketing productivity, following the guidelines of systematic literature reviews and using the PICOC (problem/population, intervention, comparison, results, context) method. 50 high-impact articles were selected in Scopus, prioritizing those in the areas of engineering, computer science and business, and published between 2020 and 2023. These articles, selected for their relevance and contribution to the study objectives, showed that the big data offers notable benefits in the marketing industry. The ability to customize marketing strategies to individual customer needs, improved optimization, and a better understanding of customer behaviors and preferences were key aspects. These findings highlight how big data can boost productivity in marketing, strengthening customer relationships and increasing loyalty by improving understanding and adaptation to the specific demands and preferences of each customer. This deeper, more personalized approach to consumers represents a significant shift in the effectiveness and efficiency of marketing strategies in the current era
One level deep convolutional neural network for facial key points detection
Get PDFFacial landmark detection has a lot of applications in face recognition, face alignment, facial expression recognition, video surveillance and security systems. In the existing literature, there are multiple methods utilizing convolutional neural networks (CNNs) that address this problem in various ways. In many cases, the models use a tree-like structure of CNNs to achieve better results. This paper proposes a combination of three parallel deep convolutional neural networks (DCNNs) to estimate the accurate localization of each keypoint. The first one focuses on the whole face to outperform five points, including the eyes, nose, and mouth corners. The second one focuses on the eyes-nose parts to outperform three points, specifically the eyes and nose. The last one focuses on the nose-mouth parts to outperform three points, namely the nose and mouth corners. Further, we combine all outputs of the three DCNNs and take the average value of each detected key point as the final output. In the first step, we improvthe the parameter efficiency and accuracy of each DCNNs through a set of experiments using the labeled face parts in-the-wild database (LFPW) and the helen facial feature dataset (Helen). Then, we demonstrate that our approach yields more accurate estimations of facial key points than two state-of-the-art methods and commercial software in terms of accuracy
DoS attack detection and hill climbing based optimal forwarder selection
Get PDFWireless networks are becoming a more and more common form of networking and communication, with several uses in many industries. However, the rising popularity has also increased security risks, such as Denial of Service (DoS) attacks. To solve these issues, Denial of Service Attack Detection and Hill Climbing (DDHC) based optimal forwarder selection in Wireless Network. The suggested method seeks to efficiently identify DoS attacks and enhance network performance by preventing the communication hiccups brought on by such attacks. Fuzzy learning method is suggested to analyze trends and find DoS threats. The node bandwidth, connectivity, packet received rate, utilized energy and response time parameters to detect the node abnormality. This abnormality decides the node's future state and detects the DoS attacker. A fuzzy learning algorithm is proposed to detect DoS attacks, which increases attack detection accuracy and lowers false alarm rates. Using the Hill Climbing (HC) procedure, the proposed system transmits data from sender to receiver. Simulation results illustrate the DDHC mechanism increases the DoS attacker detection ratio and minimizes the false positive ratio. Furthermore, it raises the network throughput and reduces the Delay in the networ
Method level static source code analysis on behavioral change impact analysis in software regression testing
Get PDFThough a myriad of changes take place in a software system during maintenance, behavioral changes carry the bulk of the reasons of software modifications. In assessing the impact of the changes made in software, static source code analysis plays a key role. However, static source code analysis can be a little complex depending on the reason for the expedition. Despite the work done so far, little focus has been made on the potential of changed methods analysis during static source code analysis in assessing the impact of the changes made in a software system. We propose and investigate a static source code analysis technique that would generate information on the modified methods in the source code. This study analyzes four aThough a myriad of changes take place in a software system during maintenance, behavioral changes carry the bulk of the reasons for software modifications. In assessing the impact of the changes made in the software, static source code analysis can be a little complex depending on the reason for the expedition. Despite the works done so far, little focus has been directed on the potential of changed methods during static source code analysis, in assessing the impact of the changes made in software. This study investigates a method-level static source code analysis technique that would generate information on the methods affected by changes made in the software. The work analyzed three Java projects. The results indicate an improvement in leveraging on the knowledge of edited methods in change impact assessment during regression testing. The approach enhances code review efforts in light of assessing operational behavior impacted by the changes made.Java projects and shows that an analysis of the changed methods reveals the level of regression testing that ought to be conducted for the changes made
Impedance analysis of squirrel-cage induction motor at high harmonics condition
Get PDFThis study examines different methodologies for representing an asynchronous motor at higher harmonics by utilizing its equivalent circuit. Several approaches were compared based on simulation modeling. An experimental investigation was conducted in a laboratory setting using asynchronous electric motors with power ratings of 1.5 kW and 5.5 kW. The purpose of this investigation was to examine the characteristics of impedance in the presence of high-harmonic conditions. The generation of higher harmonics was achieved through the utilization of a precisely regulated thyristor rectifier in conjunction with a thyristor power controller. The findings indicate that the load on the shaft solely impacts the resistance at the fundamental harmonic, while the resistance at higher harmonics remains unaffected by the operating mode of the asynchronous motor (AM)
Customized convolutional neural networks for Moroccan traffic signs classification
Get PDFRecognition of traffic signs is a challenging task that can enhance road safety. Deep neural networks have demonstrated remarkable results in numerous applications, such as traffic signs recognition. In this paper, we propose an innovative and efficient system for recognizing traffic signs, based on customized convolutional neural network (CNN) developed through hyperparameters optimization. The effectiveness of the proposed system is assessed using a novel dataset, the Moroccan traffic signs dataset. The results show that the proposed design recognizes traffic signs with an accuracy of 0.9898, outperforming several CNN architectures such as VGGNet, DensNet, and ResNet
Optimizing assembly processes with augmented reality: a case study on TurtleBots
Get PDFAugmented reality (AR) technology is revolutionizing traditional assembly processes, offering intuitive and interactive guidance that significantly enhances operational efficiency and accuracy. This study investigates the impact of AR on the assembly of Turtlebots, a complex task representative of industrial applications. Through a comparative analysis involving traditional paper manuals, modified paper manuals, and AR-based manuals, the benefits of AR integration are quantitatively assessed. Participants utilizing AR-based manuals completed the Turtlebot assembly 21.72% faster than those using traditional paper manuals, with a notable reduction in assembly time from an average of 03:00:40 to 02:21:26. Furthermore, the incidence of assembly errors significantly decreased, with AR manual users making an average of 2.25 errors compared to 5 by paper manual users. These findings underscore the potential of AR to expedite complex assembly tasks and enhance the accuracy of these processes. The study highlights the novel application of AR in improving both the speed and quality of assembly in an industrial context, demonstrating AR’s role as a pivotal technology for the future of manufacturing.