Indonesian Journal of Electrical Engineering and Computer Science
Not a member yet
9109 research outputs found
Sort by
Prediction of Parkinson's disease using feature selection and ensemble learning techniques
Get PDFParkinson's disease (PD) is a progressive neurodegenerative disorder that significantly impacts quality of life and healthcare systems. Early detection is crucial for timely interventions that can mitigate disease progression and improve patient outcomes. This study leverages advanced machine learning (ML) techniques to detect PD using speech features as non-invasive biomarkers. A dataset containing 754 features derived from sustained vowel phonations of 252 individuals (188 PD patients, 64 healthy controls) was analyzed. The dataset, originally collected by Istanbul University and publicly hosted via the UCI ML repository, was accessed through Kaggle for preprocessing and analysis. To identify the most predictive features, we employed recursive feature elimination (RFE), random forest importance, lasso regression, and the boruta algorithm—ensuring robust feature selection while reducing dimensionality. The XGBoost model, optimised using synthetic minority oversampling technique (SMOTE) for class balancing, achieved an accuracy of 96.69%, a recall of 96%, and an F1-score of 98%. Model robustness was validated through 5-fold cross-validation, yielding an average accuracy of 89.54%. These findings establish a scalable, costeffective, and non-invasive framework for early PD detection, demonstrating the potential of speech analysis and ML in neurodegenerative disease management
Accurate plate number recognition based on Sobel edge detection and weighted morphological structuring element
Get PDFNumber plate recognition (NPR) became a very important in our daily life because of the unlimited increase of cars and transportation systems which make it impossible to be fully managed and monitored by humans, examples are like traffic monitoring, tracking stolen cars, managing parking toll, red-light traffic violation enforcement, border, and customs checkpoints. Yet it is a very challenging problem, due to the diversity of plate formats, different scales, rotations, and non-uniform illumination conditions during image acquisition. The proposed system is simple but efficient for recognizing plate numbers. The Sobel edge detection and morphological process are used in the proposed framework with weighted structuring element. This approach simplifies the task by using the bounding box method for character segmentation to segment all the characters on the plate number. Template matching is then applied to recognize the numbers and characters. This approach produces accurate results as shown by the experimental process
A hybrid approach to behavioral spam review detection on e-commerce platforms using apriori and CNN
Get PDFSpam reviews significantly undermine the credibility of online review systems on e-commerce websites. This paper presents a hybrid methodology that combines the Apriori algorithm and convolutional neural networks (CNN) to efficiently identify and mitigate spam reviews. By examining user behavior, including activity patterns, reviewer reputation, temporal dynamics, and sentiment consistency, we propose a comprehensive model for understanding user interactions and engagement. To extract important information and build precise spam detection models, we use data mining and machine learning approaches. Furthermore, contextual and domain-specific analyses are conducted to improve detection strategies. The study highlights the significance of hybrid techniques in preserving the integrity of e-commerce platforms through successful industry implementations and presents evaluation metrics, problems, and future research objectives
An embedded system for the classification of sleep disorders using ECG signals
Get PDFSleep apnea (SA) is a well-known sleep disorder. It predominantly appears due to lack of oxygen in humans. Identifying SA at an early stage can help early diagnosis. The primary motto of our research is to identify SA using electrocardiogram (ECG) signals. Here, three classes are considered for classification. One is normal (N), and the other two are SA classes obstructive sleep apnea (OA) and central sleep apnea (CA). ECG signals are accumulated for MIT-BIH polysomnographic dataset. The ECG data divided into ECG segments and labelled using annotation file. The proposed deep long short-term memory (LSTM) model is then trained using ECG segments and further tested. The model is then finetuned and optimized to obtain the best accuracy. An accuracy of 98.51% is obtained. In addition, performance measures like precision, sensitivity, specificity, F-score are also evaluated. The model is then deployed on NVIDIA’s Jetson nano board to build a prototype. Our model is effective, promising and outperformed existing state of art techniques
A multi-tier framework of decentralized computing environment for precision agriculture (DCEPA)
Get PDFAlthough collecting enormous volumes of heterogeneous data from many sensors and guaranteeing real-time decision-making are problems, precision agriculture (PA) has emerged as a promising approach to increase agricultural efficiency. The efficacy of current centralized solutions is limited in large-scale agricultural settings due to resource limitations and data saturation. In order to solve these problems, this paper suggests a decentralized computing environment for precision agriculture (DECPA), which divides resource management and data processing among several layers (end, edge, and cloud). DECPA optimizes task execution and resource allocation in the field by utilizing ensemble machine learning models (deep neural network (DNN), long short-term memory (LSTM), autoencoder (AE), and support vector machine (SVM)) and a multi-tier architecture. The findings demonstrate that DECPA combined with DNN performs better than alternative models, achieving a 20% decrease in energy usage, an 18% speedup in response time, a 5% improvement in accuracy, and a 51% reduction in latency. This illustrates the system’s capacity to manage massive amounts of data effectively while preserving peak performance. To sum up, DECPA uses decentralized resources and cutting-edge machine learning models to provide a scalable and affordable precision agriculture solution. To improve the system’s flexibility and real-time responsiveness, future research will investigate additional optimization and use in various agricultural contexts
Optimization of IoT-based monitoring system for automatic power factor correction using PZEM-004T sensor
Get PDFPower factor correction (PFC) is crucial for improving energy efficiency and reducing excessive power consumption, especially in inductive loads commonly found in household and industrial environments. Conventional PFC methods often rely on manual capacitor switching, which is inefficient and impractical for real-time applications. This study proposes an IoT-based automatic power factor monitoring and correction system that dynamically adjusts the power factor using real-time data analysis. The system integrates NodeMCU ESP32 and the PZEM-004T sensor to monitor electrical parameters and automatically switch capacitors based on power factor conditions. The research follows the ADDIE approach (analysis, design, development, implementation, evaluation) to ensure a structured development process. Experimental results demonstrate an average power factor improvement of 48.77% and a reduction in current consumption by 39.90%, significantly enhancing energy efficiency. The system's web-based interface allows real-time monitoring with an average data transmission response time of 207.67 ms, ensuring efficient remote management. Compared to existing systems, the proposed approach eliminates manual intervention and optimizes PFC adaptively. Future research should focus on expanding system reliability, testing on larger-scale applications, and integrating artificial intelligence (AI) for predictive power factor adjustments
Performance evaluation of a photovoltaic system with phase change material in Guwahati
Get PDFRecently, there has been a lot of interest in solar photovoltaic (PV) technology as a clean and renewable energy source. The operating temperature of PV modules significantly impacts their performance; as the temperature rises, the modules perform worse. The phase change material (PCM) paraffin wax has been used to cool a PV system passively. The experiment was carried out during summer over three months, viz. April, May, and June when relative humidity was around 80.75% to 86.5% with two identical 20-watt PV panels in Guwahati, India (26.1332° North and 91.6214° East). One panel was coated with PCM, while the other panel functioned as a point of reference. The study reveals an impressive result: the output power produced by the system with PCM was 9.8%, 13.1%, and 10.3% greater than the reference PV, while the surface temperature had been lowered by 21.6%, 26.2%, and 30.6% in the three respective months. High humidity delays the release of latent heat of paraffin wax and hence improves its thermal conductivity. This study adds to the continuing efforts to promote sustainable energy solutions and creates new opportunities to enhance the performance of PV systems
Chaotic crow search enhanced CRNN: a next-gen approach for IoT botnet attack detection
Get PDFInternet of things (IoT) botnet attack detection is crucial for reducing and identifying hostile threats in networks. To create efficient threat detection systems, deep learning (DL) and machine learning (ML) are currently being used in many sectors, mostly in information security. The botnet attack categorization problem is difficult as data dimensionality increases. By combining convolutional and recurrent neural layers, our work effectively addressed the vanishing and expanding gradient difficulties, improving the ability to capture spatial and temporal connections. The problem of weight decaying and class imbalance affects the accuracy rate of the existing DL models. In convolutional neural network (CNN), fully connected layer optimizes the hyperparameters by utilizing its comprehension of the chaotic crow search method. The chaotic mapping maintains equilibrium between the global and local search spaces. The crow's strategy for hiding food is the main source of inspiration for optimizing the learning rate, weight, and bias components involved in the prediction process. When compared to other existing algorithms, the UNSW-NB15 dataset's results for IoT botnet attack detection in the presence of a high degree of class imbalance demonstrated the effectiveness of the proposed convolutional recurrent neural network (CRNN) boosted with chaotic crow searching algorithm, which produced the highest detection rate with the lowest false alarm rate
Sensitivity-based approach for evaluation and enhancement of available transfer capability using FACTS devices
Get PDFAvailable transfer capability (ATC) plays an important role in the reliable and secure power system operation. It measures the transfer capability available in the transmission system for further trading over and above existing commitments without violating the system limits. The increased demand for electric power in recent years due to increasing population, automation in industries, and use of electricity in transportation, and also the deregulation of power systems results in an overload of the transmission network and hence congestion in the system. Therefore, quick and accurate calculation of ATC and its enhancement is needed for secured and reliable operation. It is possible to enhance ATC by placing the flexible alternating current transmission systems (FACTS) devices of appropriate size and at optimal locations in the system. In this paper, a computationally efficient sensitivity-based approach for evaluation and enhancement of available transfer capability in the presence of of FACTS devices is presented. The developed approach is implemented on the IEEE 14 bus system
Optimization of 3D rendering algorithms for carbon reduction in virtual reality technology
Get PDFVirtual reality (VR) systems are widely used across various domains, yet their high computational demands significantly contribute to energy consumption and carbon emissions. Optimizing rendering algorithms is essential to address these environmental challenges, particularly in multiuser VR environments where efficiency is critical. This study aims to evaluate the effectiveness of various rendering techniques in reducing energy consumption and carbon emissions as optimal solutions for multiuser VR applications. The research methodology followed the PRISMA framework, with a literature search conducted using the Scopus database and keywords such as “virtual reality” and “energy efficiency.” The search yielded 1,374 articles published after 2019, which were screened and narrowed down to 24 critical articles. Results demonstrate that Occlusion Culling achieves up to 85% energy savings per frame, translating to a carbon emission reduction of 76.5 g CO₂/hour, while LOD provides a 50% energy efficiency improvement, reducing carbon emissions by 45 g CO₂/hour. These findings highlight the critical role of these techniques in enhancing the sustainability of VR systems, particularly in multi-user environments, and underscore their potential as key strategies in reducing the environmental footprint of VR technology