Indonesian Journal of Electrical Engineering and Computer Science
Not a member yet
9109 research outputs found
Sort by
Study of design thinking and software engineering integration in education and training
Get PDFIntegrating design thinking (DT) with software engineering (SE) is widely applied in industry, serving as a reference for SE in education and training. The industry has various integration models, but researchers and educators mainly adapt them for education. A clear understanding of DT-SE integration models is essential to figuring out their implementation. This study examines existing DT-SE integration models, challenges, and integration methods using Kitchenham’s framework in education and training. The paper was collected from ScienceDirect, IEEEXplore, Scopus, ACM, SpringerLink, and Google Scholar, yielding 593 initial publications, with 43 selected for in-depth analysis. Findings indicate that the d.school model is the most widely adopted DT model. Key challenges include team dynamics, process management, complexity, and cultural factors. DT is integrated into requirements engineering (RE) due to its user-centered nature, though only two studies explicitly describe DT-SE integration models, both applied early in SE processes. These findings suggest educational practices align with industry trends in model adoption and integration focus. Educators and practitioners can use these insights to design or adapt integration models suitable for education and training by shaping curricula that emphasize user-centered design, collaboration, and the extension of DT practices beyond RE-strengthening its impact for education and training
Low-resolution image quality enhancement using enhanced super-resolution convolutional network and super-resolution residual network
Get PDFThis research explores the integration of enhanced super-resolution convolutional network (ESPCN) and super-resolution residual network (SRResNet) to enhance image quality captured by low-resolution (LR) cameras and in internet of things (IoT) devices. Focusing on face mask prediction models, the study achieves a substantial improvement, attaining a peak signal-to-noise ratio (PSNR) of 28.5142 dB and an execution time of 0.34704638 seconds. The integration of super-resolution techniques significantly boosts the visual geometry group-16 (VGG16) model’s performance, elevating classification accuracy from 71.30% to 96.30%. These findings highlight the potential of super-resolution in optimizing image quality for low-performance devices and encourage further exploration across diverse applications in image processing and pattern recognition within IoT and beyond
Quick response code generation for e-invoicing in Saudi Arabia
Get PDFIn the digital era, the emergence of quick response (QR) code technology has become a vital tool for enhancing the efficiency of electronic invoice management and promoting security and transparency in financial transactions, while reducing costs and ensuring compliance with regulations. This study focuses on QR code technology and electronic invoice requirements in the Kingdom of Saudi Arabia, by exploring the generation of QR codes for electronic invoices. The study begins by analyzing QR code technology and its role in encoding and decoding information. Subsequently, the electronic invoice requirements in Saudi Arabia are reviewed, with a focus on the applicable systems and regulations. The research also includes details on generating QR codes for electronic invoices, considering factors such as data encoding, security protocols, and compatibility standards using the Python programming language. Various steps of this process are explained. The study aims to provide a comprehensive understanding of the technology and requirements related to electronic invoices in Saudi Arabia and to develop a program for creating QR codes for electronic invoices to improve and develop the financial and technological infrastructure in the Kingdom of Saudi Arabia, thereby contributing to supporting the digital economy and promoting sustainable development
Improving breast cancer prediction through explainable artificial intelligence - A transdisciplinary approach
Get PDFArtificial intelligence (AI) technology has shown tremendous contributions in various applications like speech recognition, expert systems, computer vision, robotics, and gaming. machine learning (ML) and deep learning (DL) algorithms under AI address problems such as prediction, classification, and regression. AI has touched many domains. The results or the predictions generated by these algorithms are not easily accepted by the user. Especially, the Healthcare domain is facing a great challenge in accepting the results or the predictions with the concern, Are AI results reliable, correct, and ethical? Doctors or medical practitioners are not ready to treat patients based on results or suggestions generated by AI algorithms. Hence, a technology that can explain how the results returned by AI algorithms are trustworthy, transparent, and interpretable was strongly needed. This need has given rise to the latest technology-explainable artificial intelligence (XAI). With the use of XAI, all the predictions, classifications made by AI algorithms are explainable, auditable, comprehensive, validating, and socially acceptable. This paper discusses explaining the results of breast cancer prediction as a case study. The results show that such an explanation will build trust in the doctors and hence will increase the acceptance of the AI-based systems
Handling missing values and clustering industrial liquid waste using K-medoids
Get PDFThe textile industry is a significant contributor to environmental pollution due to its wastewater, which contains hazardous substances such as dyes, heavy metals, and chemicals that can severely harm aquatic ecosystems. Effective management of this wastewater is crucial to mitigate its environmental impact. This study focuses on classifying industrial liquid waste data using the K-medoids clustering method, chosen for its robustness to noise and outliers compared to K-means. To address challenges in wastewater data processing, such as missing values and varying data scales, two approaches are compared: replacing missing values with zero and K-nearest neighbors (KNN) imputation, alongside Z-score normalization for data uniformity. The clustering quality is evaluated using the Davies-Bouldin index (DBI) for cluster variations of k=2, 3, 4, and 5. The results show that the best clustering quality is achieved at k=2, with the smallest DBI values obtained using KNN imputation (0.139) and zero replacement (0.149). The superior performance of KNN imputation highlights its effectiveness in handling missing data. These findings provide valuable insights into the characteristics of textile industry wastewater pollution, offering a robust framework for effective wastewater management. The study concludes with practical recommendations for policymakers and industry stakeholders to adopt advanced data-driven approaches for sustainable wastewater treatment strategies
Geographic information system-based approaches for evaluating CO2 storage in Kalimantan basins, Indonesia
Get PDFTo achieve the energy transition towards more environmentally friendly energy, various approaches must be taken, one of which is CO2 source-to-sink matching. A basin evaluation study has been carried out through classifying, weighting, and scoring in the geographic information system (GIS) for screening and ranking basins for CO2 storage on the island of Kalimantan, Indonesia. The region covers 13 sedimentary basins that have the potential to serve as CO2 sinks. As many as 21 parameters have been analyzed through classification and weighting using a pairwise comparison matrix method to produce scores and ranks for each basin. The results show that the Kutai, Tarakan, and Barito basins are the top three basins for CO2 storage potential. Singkawang, Nangapinoh, Pangkalanbun Utara, and Embaluh Selatan basins have been found to have the lowest sink potential
Comparison of robust machine learning algorithms on outliers and imbalanced spam data
Get PDFEffective spam detection is essential for data security, user experience, and organizational trust. However, outliers and class imbalance can impact machine learning models for spam classification. Previous studies focused on feature selection and ensemble learning but have not explicitly examined their combined effects. This study evaluates the performance of random forest (RF), gradient boosting (GB), and extreme gradient boosting (XGBoost) under four experimental scenarios: (i) without synthetic minority over-sampling technique (SMOTE) and outliers, (ii) without SMOTE but with outliers, (iii) with SMOTE and without outliers, and (iv) with SMOTE and with outliers. Results show that XGBoost achieves the highest accuracy (96%), an area under the curve-receiver operating characteristic (AUCROC) of 0.9928, and the fastest computation time (0.6184 seconds) under the SMOTE and outlier-free scenario. Additionally, RF attained an AUCROC of 0.9920, while GB achieved 0.9876 but required more processing time. These findings emphasize the need to address class imbalance and outliers in spam detection models. This study contributes to developing more robust spam filtering techniques and provides a benchmark for future improvements. By systematically evaluating these factors, it lays a foundation for designing more effective spam detection frameworks adaptable to real-world imbalanced and noisy data conditions
Voltage stability investigation: enabling large-scale renewable energy integration in Tamil Nadu’s grid
Get PDFThe integration of renewable energy sources (RES) such as wind and solar, characterized by their inherent intermittency and variability, poses notable challenges to the stability and reliability of power systems. This research addresses these challenges by conducting a detailed load flow, voltage sensitivity and stability analysis at a significant extra high voltage (EHV) pooling station under high-RES penetration. Employing advanced simulation methodologies, the study evaluates the effects of RES integration on voltage profiles and the system’s capacity to sustain equilibrium under steady-state operations. The findings highlight that substantial RES integration induces considerable voltage fluctuations and reactive power disparities. To counter these effects, static var compensators (SVCs) were deployed, demonstrating their efficacy in enhancing voltage stability and providing essential reactive power support. The study confirms the pivotal role of SVCs in alleviating voltage sensitivity to RES fluctuations, thereby promoting a more stable and reliable power supply. This research underscores the importance of strategic reactive power management devices in enabling a seamless transition towards a renewable-dominant energy landscape
Hybrid energy storage solutions through battery-supercapacitor integration in photovoltaic installations
Get PDFBatteries integrated into renewable energy storage systems may experience multiple irregular charge and discharge cycles due to the variability of photovoltaic energy production characteristics or load fluctuations. This could negatively impact the battery’s longevity and lead to an increase in project costs. This article presents an approach for the sharing of embedded energy between the battery, which serves as the main energy storage system, and the supercapacitors (SC), which act as an auxiliary energy storage system. By delivering or absorbing peak currents according to the load requirements, supercapacitors increase the lifespan of batteries and reduce their stresses. An maximum power point tracking (MPPT) algorithm regulates the connection of the photovoltaic (PV) cells to the DC bus through a boost converter. A buck-boost converter connects supercapacitors and batteries to the DC bus. A DC-AC converter connects the inductive load to the DC bus. The system regulates static converters connected to batteries and supercapacitors based on current. An energy management block supervises the system components. We implement the entire system in the MATLAB/Simulink environment. We present the simulation results to demonstrate the effectiveness of the proposed control strategy for the entire system
A comparative analysis of hybrid of traditional load flow methods for IEEE distributed power generation networks
Get PDFAnalyzing power flow or load flow is crucial for planning, operating, maintaining, and controlling electrical power systems. Two traditional power flow methods namely the Newton-Raphson (NR) method are known for their accuracy and robustness nevertheless high computational intensity, and the fast decoupled load flow (FD) method, is valued for its computational efficiency and speed, however, generating less accurate data. This research aims to develop a hybrid load flow technique that integrates both strengths, achieving higher accuracy and faster convergence. The validation processes are based on several IEEE standard bus systems, including the 3-bus, 9-bus, 14-bus, and 30-bus systems. These systems, with different bus types and interconnections, represent real-world operations and help generate comprehensive data on iteration count, execution time, and the accuracy of the output data results. A new hybrid method generated from this research work compared to traditional load flow methods, provides a substantially well-balanced number of iteration counts, the fastest execution times, improved by 41.55%, and produces a similar accuracy of the data set. These improvements make the hybrid method highly advantageous in practical real-time applications and large-scale systems where both accuracy and speed are critical