Indonesian Journal of Electrical Engineering and Computer Science
Not a member yet
9109 research outputs found
Sort by
Enhanced time series forecasting using hybrid ARIMA and machine learning models
Get PDFAccurate energy demand forecasting is essential for optimizing resource management and planning within the energy sector. Traditional time series models, such as ARIMA and SARIMA, have long been employed for this purpose. However, these methods often face limitations in handling nonstationary data, complexity in model tuning, and susceptibility to overfitting. To address these challenges, this study proposes a hybrid approach that integrates traditional statistical models with advanced computational methods. By combining the strengths of both approaches, the proposed models aim to enhance predictive accuracy, improve computational efficiency, and maintain robustness across varied energy datasets. Experimental results demonstrate that these hybrid models consistently outperform standalone traditional methods, providing more reliable and precise forecasts. These findings underscore the potential of hybrid methodologies in advancing energy demand forecasting and supporting more effective decision-making in energy management
Adaptive deep learning framework for multi-scale plant disease detection
Get PDFPlant disease detection is a critical task in modern agriculture, directly impacting crop yield, food security, and sustainable farming practices. Traditional methods rely on expert visual inspection, which is time-consuming, inconsistent, and inaccessible in remote areas. This study introduces an advanced deep learning (DL) framework, the adaptive multi-scale convolutional network (AMS-ConvNet), optimized for accurate and efficient plant disease identification. hierarchical feature extraction network (HFEN) integrates the multi-domain attention framework (MDAF) and adaptive scale fusion module (ASFM) to enhance feature extraction and address challenges such as complex natural backgrounds, non-uniform leaf structures, and varying environmental conditions. The proposed framework employs pre-trained knowledge adaptation (PTKA) techniques to improve generalization and overcome data scarcity. Comprehensive evaluations on multiple datasets demonstrate the model's better performance, achieving state-of-the-art metrics in precision, recall, F1-score, and accuracy. Furthermore, this approach ensures scalability and adaptability, making it suitable for real-field conditions. The study emphasizes the importance of robust, automated solutions in minimizing crop losses, reducing labor costs, and enhancing agricultural sustainability through precision disease management
Determining social assistance recipients using fuzzy-TOPSIS method in Sumur Bandung district Indonesia
Get PDFThis study aims to improve the selection process for social assistance recipients in the Sumur Bandung District, Indonesia, using the fuzzyTOPSIS method. The research establishes eligibility criteria and evaluates alternatives based on data from April 2024. By combining multi-criteria decision-making with fuzzy logic, the fuzzy-TOPSIS approach enhances the accuracy and fairness of recipient selection. The methodology involves determining criteria weights, fuzzification, and ranking alternatives against ideal solutions. The results demonstrate that fuzzy-TOPSIS significantly improves decision-making, leading to more objective and reliable outcomes than traditional methods. These findings underscore the potential of fuzzyTOPSIS in optimizing social assistance distribution, ensuring that assistance reaches the most deserving recipients efficiently
A sentiment analysis on skewed product reviews: Ben & Jerry's ice cream
Get PDFSentiment analysis of product reviews offers valuable insights into consumer perspectives, which can inform product development and marketing strategies. Given the growing importance of user-generated content like product reviews, this study explored sentiment classification in online reviews of Ben & Jerry's ice cream. We designed and evaluated three machine learning algorithms for sentiment classification: Naïve Bayes (NB), logistic regression (LR), and support vector machine (SVM). The dataset exhibited a significant class imbalance, with substantially more positive than negative reviews. We employed two oversampling techniques: the synthetic minority oversampling technique (SMOTE) and the adaptive synthetic sampling approach (ADASYN). With the original skewed data, NB, LR, and SVM achieved accuracies of 91.90%, 93.77%, and 95.09%, respectively. While SMOTE did not improve performance in some scenarios, ADASYN yielded positive results and generally enhanced model reliability across all algorithms. Post-balancing with ADASYN, the sentiment distribution became less skewed, and accuracies shifted to 92.04% for NB, 94.96% for LR, and 95.23% for SVM. The combination of SVM and ADASYN demonstrated promising results, suggesting this approach may offer robust and efficient performance for binary sentiment classification, especially with imbalanced datasets
Predictive modeling of electric vehicle loads through driving behavior analysis
Get PDFElectric vehicles (EVs) can potentially be integrated into microgrids via vehicle-to-grid (V2G) technology, which enhances the energy system's stability and durability. This paper provides an in-depth examination and evaluation of V2G integration in microgrid systems. It analyses the present state of research as well as possible uses, challenges, and directions for V2G technology in the future. This article addresses the technological, economic, and regulatory aspects of implementing V2G and provides case studies and pilot projects to shed light on potential benefits and barriers associated with its adoption. The research highlights how V2G contributes to more efficient integration of renewable energy sources, grid stabilization, and cost savings for EV owners. It also addresses the latest developments in technology and proposed laws aimed at encouraging growing applications of V2G
Enhancing small-signal stability in high-voltage DC systems: supplementary controls for damping inter-area oscillations
Get PDFHigh voltage direct current (HVDC) transmission systems have emerged as a leading technology for efficient and cost-effective long-distance power transmission, offering significant advantages over traditional high voltage alternating current (HVAC) systems. These benefits include seamless integration of asynchronous grids and renewable energy sources (RES), enhancing the reliability of power supply. However, the dynamic behavior of HVDC systems and their ability to maintain stability under small disturbances introduce challenges to overall system stability.To address these challenges, this study focuses on improving small-signal stability in HVDC systems by exploring supplementary control strategies for damping interarea power oscillations.The proposed strategy was tested using the kundur two-area four-machine (K-TAFM) system modeled in power systems computer-aided design (PSCAD), incorporating case study under a three phase-to-ground fault scenario.The active power imbalance and inter-area oscillations observed during fault conditions highlight the critical need for advanced stability enhancement techniques to effectively mitigate small signal disturbances. This approach significantly improved the small-signal stability of the HVDC system, underscoring its potential to enhance the reliability and resilience of modern power grids
A variant of particle swarm optimization in cloud computing environment for scheduling workflow applications
Get PDFCloud computing offers on-demand access to shared resources, with user costs based on resource usage and execution time. To attract users, cloud providers need efficient schedulers that minimize these costs. Achieving cost minimization is challenging due to the need to consider both execution and data transfer costs. Existing scheduling techniques often fail to balance these costs effectively. This study proposes a variant of the particle swarm optimization algorithm (VPSO) for scheduling workflow applications in a cloud computing environment. The approach aims to reduce both execution and communication costs. We compared VPSO with several PSO variants, including Inertia-weighted PSO, gaussian disturbed particle swarm optimization (GDPSO), dynamic-PSO, and dynamic adaptive particle swarm optimization with self-supervised learning (DAPSO-SSL). Results indicate that VPSO generally offers significant cost reductions and efficient workload distribution across resources, although there are specific scenarios where other algorithms perform better. VPSO provides a robust and cost-effective solution for cloud workflow scheduling, enhancing task-resource mapping and reducing costs compared to existing methods. Future research will explore further enhancements and additional PSO variants to optimize cloud resource management
A novel (, ) multi-secret image sharing scheme harnessing RNA cryptography and 1-D group cellular automata
Get PDFIn the modern landscape, securing digital media is crucial, as digital images are increasingly disseminated through unsecured channels. Therefore, image encryption is widely employed, transforming visual data into an unreadable format to enhance image security and prevent unauthorized access. This paper proposes an efficient (, ) multi-secret image sharing (MSIS) scheme that leverages ribonucleic acid (RNA) cryptography and one-dimensional (1-D) group cellular automata (GCA) rules. The (, ) MSIS scheme encrypts images into distinct shares, necessitating all shares for decryption to accurately reconstruct the original images. Initially, a key image is generated using RNA cryptography, harnessing the extensive sequence variability and inherent complexity of RNA. This secret key is then used to encrypt images in the primary phase. In the secondary phase, pixel values are transformed through multiple processes, with randomness achieved by executing a key function derived from GCA, known for its reversible properties, computational efficiency, and robustness against cryptographic attacks. The proposed model, implemented in Python, is validated through experimental results, demonstrating its effectiveness in resisting a broad spectrum of attacks, including statistical, entropy, differential, and pixel parity analyses. These findings affirm the model's durability, security, and resilience, underscoring its superior performance compared to existing models
Assessment of cloud-free normalized difference vegetation index data for land monitoring in Indonesia
Get PDFContinuous land monitoring in Indonesia using optical remote sensing satellites is difficult due to frequent clouds. Therefore, we studied the feasibility of monthly land monitoring during the second half of 2019, using moderate resolution imaging spectroradiometer (MODIS) normalized difference vegetation index (NDVI) data from Terra and Aqua satellites. We divide the Indonesian area into seven regions (Sumatra, Java, Kalimantan, Sulawesi, Nusa Tenggara, Maluku, and Papua) and examine NDVI data for each of the regions. We also calculated the cloud occurrence percentage every hour using Himawari-8 data to compare cloud conditions at different acquisition times. This research shows that Terra satellite provides more cloud-free pixels than Aqua while combining data from both significantly increase the cloud-free NDVI pixels. Monthly monitoring is feasible in most regions because the cloudy areas are less than 10%. However, in Sumatra, the cloudy area was more than 10% in October 2019. We need to include further data processing to improve the feasibility of continuous monitoring in Sumatra. This research concludes that monthly monitoring is still feasible in Indonesia, although some data require further processing. The use of additional data from other satellites in the monitoring can be an option for further research
A GRU-based approach for botnet detection using deep learning technique
Get PDFThe increasing volume of network traffic data exchanged among interconnected devices on the internet of things (IoT) poses a significant challenge for conventional intrusion detection systems (IDS), especially in the face of evolving and unpredictable security threats. It is crucial to develop adaptive and effective IDS for IoT to mitigate false alarms and ensure high detection accuracy, particularly with the surge in botnet attacks. These attacks have the potential to turn seemingly harmless devices into zombies, generating malicious traffic that disrupts network operations. This paper introduces a novel approach to IoT intrusion detection, leveraging machine learning techniques and the extensive UNSW-NB15 dataset. Our primary focus lies in designing, implementing, and evaluating machine learning (ML) models, including K-nearest neighbors (KNN), random forest (RF), long short-term memory (LSTM), and gated recurrent unit (GRU), against prevalent botnet attacks. The successful testing against prominent Bot- net attacks using a dedicated dataset further validates its potential for enhancing intrusion detection accuracy in dynamic and evolving IoT landscapes