Indonesian Journal of Electrical Engineering and Computer Science
Not a member yet
9109 research outputs found
Sort by
Energy-efficient and reliable data transmission to enhance the performance of wireless sensor networks using artificial intelligence
Get PDFFor many years, the area of wireless sensor networks (WSN) has been popular for its wide range of time-critical and potential applications. However, it has many challenges that require more attention from the research communities to improve the network’s operational efficiency. However, with consistently rising concerns for energy efficiency and optimized data transmission performance, most current research emphasises minimum power consumption and reliable data transmission aspects. The critical analysis and study of related works exhibit the shortcomings in existing data transmission schemes, which fail to cope with the dynamic conditions of WSNs on a larger scale and do not retain considerable energy performance. The study thereby introduces a unique approach to an energy-efficient and reliable data transmission framework that formulates machine learning-driven functional components to ensure effective data gathering, aggregation, and routing and dissemination strategies to properly balance energy and data transmission performance in WSN under dynamic conditions. The proposed framework's performance evaluation considers multiple metrics, such as analysis of network lifetime, Energy Consumption, Throughput, and Latency performance. The experimental outcome shows that the proposed system outperforms the existing baselines for the above performance metrics
Plant leaf disease detection and classification using artificial intelligence techniques: a review
Get PDFAgriculture is a cornerstone of human civilization, providing both food and economic stability. While not necessarily fatal, leaf diseases are a crucial threat to plant health. Accurate detection and classification of diseases in early stages are essential to minimize damage. Manual identification can be challenging, and delays in detection can lead to crop devastation. Fortunately, computer-aided image processing offers a solution. Researchers have explored several techniques for disease detection and classification by usage of affected leaf images, making significant progress over time. However, there's always room for improvement. Machine learning (ML), Deep learning (DL) techniques have shown hopeful results. ML, DL approaches act as black-box; eXplainable AI (XAI) provides clear explanations on decisions made by these black-boxes. This study aims to present a comprehensive review on plant leaf disease detection and classification by means of ML, DL and XAI methods with an overview of the outcomes of existing techniques, summarizes their performance, evaluation metrics, and analyses the challenges in existing systems, and offers the study's inferences
Enhancing malware detection through self-union feature selection using gray wolf optimizer
Get PDFThis research explores the impact of malware on the digital world and presents an innovative system to detect and classify malware instances. The suggested system combines a random forest (RF) classifier and gray wolf optimizer (GWO) to identify and detect malware effectively. Therefore, the suggested system is called RFGWO-Mal. The RFGWO-Mal system employs the GWO for feature selection in binary and multiclass classification scenarios. Then, the RFGWO-Mal system uses a novel self-union feature selection approach, combining features from different subsets of binary and multiclass classification extracted using the GWO optimizer. The RF classifier is then applied for classifying malware and benign data. The comprehensive Obfuscated-MalMem2022 dataset was utilized to evaluate the suggested RFGWO-Mal system, which has been implanted using Python. The suggested RFGWO-Mal system achieves significantly improved results using the novel self-union feature selection approach. Specifically, the RFGWO-Mal system achieves an outstanding accuracy of 99.95% in binary classification and maintains a high accuracy of 86.57% with multiclass classification. The findings underscore the achievement of a self-union feature selection approach in enhancing the performance of malware detection systems, providing a valuable contribution to cybersecurity
Facial emotion recognition based on upper features and transfer learning
Get PDFFacial expression recognition (FER) in the upper face focuses on the analysis and recognition of emotions based on features extracted from the upper region of the face. This region typically affects the eyes, eyebrows, forehead, and sometimes the upper cheeks. Since these areas are often less affected by face masks or other facial coverings, FER algorithms can concentrate on capturing and interpreting the relevant facial cues, such as eye movements, eyebrow positions, and forehead wrinkles, to accurately recognize and classify different emotions. By focusing on the upper face, FER systems can mitigate the impact of occlusions caused by masks and still provide meaningful insights into the emotional states of individuals. In this work, a FER approach focusing on the upper region is proposed. Several experiments have been made using the CK+ dataset in addition to a comparison between the emotion recognition scores using the upper and the entire face in order to determine whether this area can reflect the real expressed emotion. The results of our approach are promising compared to previous studies with an accuracy up to 96%
Exploring parents’ perceptions of sex education pedagogy in Moroccan schools using an association rules mining-based algorithm
Get PDFSex education is vital for promoting healthy relationships and preventing sexual exploitation by teaching boundaries, consent and abuse recognition. Customized strategies are needed for children, balancing age-appropriate content with parental and community perspectives. Our study assessed Moroccan parents’ views on sex education’s adoption in schools. Conducted in Taza city, the survey targeted 1946 parents of students over 7 years old. Using association rule mining (ARM), we analyzed their responses. Therefore, Apriori algorithm was implemented to discover strong association rules within parents’ selected responses. Results showed that 74.53% of parents aged 19-30 support sexual education, citing its absence as a factor in child abuse. Meanwhile, 60.48% of those aged 31-59 with university education believe psychological disorders contribute to assaults. While some fathers (32.48%) and some mothers (67.52%) support sexual education, others don’t, but all agree on restricting children’s internet use until age 16 to avoid harmful content. These findings can inform comparative studies, aid decision-makers and enhance AI-based EdTech systems by offering insights into sex education perceptions
Enhancing business analytics predictions with hybrid metaheuristic models: a multi-attribute optimization approach
Get PDFThis approach aims to optimize business analytical predictions through multiattribute optimization using a hybrid metaheuristic model based on the modified particle swarm optimization (MPSO) and gravitational search optimization (GSO) algorithms. This research uses a variety of data, such as revenue, expenses, and customer behavior, to improve predictive modeling and achieve superior results. MPSO, an interparticle collaborative mechanism, efficiently explores the search space, whereas GSO models’ gravitational interactions between particles to solve optimization problems. The integration of these two algorithms can improve the performance of business analytical predictions by increasing model precision and accuracy, as well as speeding up the optimization process. Model validation test results, precision 95.60%, recall 96.35%, accuracy 96.69%, and F1 score 96.11%. This research contributes to the development of more sophisticated and effective business analysis techniques to face the challenges of an increasingly complex business world
A solar PV-fed MF-DVR for compensation of grid-islanding issues and power-quality issues in grid-connected distribution system
Get PDFDifficulties with the quality of power come up as an effect of the inte-conneted renewable energy through grid called as distribution generation (DG) scheme. The voltage harmonics and swell-sag are happened in the utility grid as a result of power quality issues, affecting end-level consumers. Moreover, grid islanding issues is considered the most affected problem in distribution system for affecting the uninterrupted energy-flow to respective load demand. The main aim of this paper provides affective designing of the suitable cost-effective multi-functional dynamic voltage restorer (MF-DVR) has been proposed for resolving the problems. The major objective is mitigation of voltage-interruptions during grid-islanding, voltage-sag, voltage-swell and voltage-harmonics, any voltage quality in the utility grid, by utilizing the solar photovoltaic (PV) integrated MF-DVR as DG scheme through synchronous reference frame (SRF) control theory. Also, it can regulate the voltage and phase of the distribution system during sudden voltage interruptions occurred in grid-islanding. The performance of the proposed SRF controlled MFDVR for power-quality (PQ) improvement and DG integration during grid-islanding has been validated via Matlab/Simulink computing tool; the simulation findings are shown with an appealing comparison analysis
Face recognition based on landmark and support vector machine
Get PDFNowadays, the fast development of face recognition technologies used in fields such as security and video surveillance, gives us many theories and algorithms, a view of these algorithms provides us with an idea of their performance and limitations. In this paper, we will develop a new face recognition approach using the face estimation landmark algorithm to detect faces in real-time videos. Then, we use a pre-trained neural network to extract the 128 facial features of each face detected in the database images and register each vector of 128 values with the corresponding person’s name. Then, we form the linear support vector machine (SVM) classifier to recognize faces. Extensive experiments on real and generated data are presented to demonstrate the quality of the proposed method in terms of accuracy, reliability, and speed
Techniques of image segmentation: a review
Get PDFImage segmentation is a popular topic of research. Image segmentation divides an image into different parts that can be used for further analysis. By doing so, the image becomes simple and more meaningful information can be extracted. The segmentation techniques divide an image into multiple parts based on certain features of the image namely: color, texture, and intensity value of the pixel. Segmentation is considered as one of the toughest tasks for extracting features from an image, detection of objects and lastly classification of the image. The applications of image segmentation in every aspect of life such as satellite image analysis, object detection and recognition, in agricultural field, self-driving vehicles, and medical imaging. Has become indispensable. Till date, though researchers have developed many segmentation techniques, they are unable to design a generalized methodology for the image segmentation problems. A review of image segmentation techniques has been presented in this study. A summary of the advantages and disadvantages of these techniques has been presented. The focus of this manuscript is to provide a summary of the available research work on segmentation which will benefit the enthusiastic researchers in gaining better understanding about segmentation models in various application domains
Electrical system load re-phasing: a case of a university building in the Philippines
Get PDFIn the pursuit of attaining energy efficiency, administrators must delve deeply into the electrical system of a facility, especially if it is an old structure. As years go by, renovations and the addition of new equipment may lead to an imbalance in the electrical system. These imbalances may lead to inefficiencies, contributing to damage to equipment. This study aimed to investigate the electrical system of a university building by determining whether the percent current and voltage unbalance values in the system meet the standards. For non-conforming electrical branches, re-phasing schemes were proposed. Data revealed that the majority of the panelboards in the building have voltage imbalances that are within the allowable limit, while there is a considerable number of panelboards with above-the-minimum current unbalance value. The original configurations of some panelboards were retained to avoid further increase in the percentage of current imbalance associated with re-phasing. Merging certain panelboards, however, resulted in a reduction of current imbalances within the acceptable limit. If the re-phasing and merging of loads are to be implemented, a cost-benefit analysis and a study on the improvements in energy efficiency may be considered for further research