Indonesian Journal of Electrical Engineering and Computer Science
Not a member yet
9109 research outputs found
Sort by
A novel boundary adaptive oversampling approach for intrusion detection
Get PDFManaging unbalanced datasets is a significant challenge in intrusion detection, since uncommon assaults are often obscured by the bulk of regular network traffic. In order to mitigate the effects of class imbalance and improve intrusion detection system (IDS) performance, it is necessary to use a variety of imbalanced learning algorithms. Methods of data augmentation such as adaptive synthetic sampling (ADASYN) and synthetic minority oversampling technique (SMOTE) are useful in addressing class imbalance. This paper introduces a novel technique to data resampling where decision tree-generated decision boundaries are used to conduct ADASYN on complicated and unusual samples. When this method’s efficacy was evaluated using the standard NSL-KDD dataset, the accuracy of the unusual class u2r was increased to 42% and, for r2l it was improved to 83%, respectively. The UNSW-NB 15 dataset has been used for further validation of the method, and its statistical significance has been asserted by comparing the suggested method to other oversampling techniques
A case study on the causal of electric two-wheelers traffic accidents in Yangzhou, China
Get PDFIn recent years, electric two-wheelers are a very popular means of transportation in China and are loved by the people. And, because driving electric two-wheelers does not require a driver's license or insurance, electric two-wheelers have become the preferred mode of transportation for the people in China. However, while electric two-wheelers bring convenience to people, they also bring hidden dangers to traffic safety. Nearly 200,000 traffic accidents occur in China every year, of which electric two-wheelers account for 60%. In addition, the trend of traffic accidents is increasing year by year, which is seriously threatening the safety of people's lives and property. It is urgent to prevent the traffic accidents of electric two-wheelers and maintain the personal safety of citizens. Therefore, this study aims to determine which factors contribute to traffic accidents of electric two-wheelers and to explore the importance of their influence on traffic accidents. The sample data for this study will be collected from the people of Yangzhou City, Jiangsu Province, China by distributing questionnaires. The data from the completed questionnaires will also be analyzed using SPSS analysis tool
An efficient frequent itemsets finding in distributed datasets with minimum communication overhead
Get PDFFinding frequent itemsets is an essential researched technique and a challenging task of data mining. Traditional approaches for distributed frequent itemsets require massive communication overhead among different distributed datasets. In this paper, we adopt a new strategy for optimizing the time of communications/synchronizations from large datasets and, we present a novel algorithm for discovering frequent itemsets in different distributed datasets on the slave sites called finding efficient distributed frequent itemsets (FEDFI). The proposed algorithm is capable of generating the important frequent itemsets by applying an efficient technique for pruning the candidate itemsets. The experimental results confirm that our algorithm FEDFI performs better than Apriori and candidate distribution (CD) algorithms in terms of communication and computation costs
EDK-LEACH: improving LEACH protocol-based machine learning in wireless sensor networks
Get PDFIn wireless sensor networks (WSNs), many sensor devices are spread throughout the environment with the goal of collecting data and sending them to a base station (BS) for further studies. The issue of their limited battery power has aroused the interest of researchers, and several protocols were developed to optimize energy use and thus increase the network’s lifetime. The present research enhances the well-known low-energy adaptive clustering hierarchy (LEACH) protocol with a new artificial intelligence (AI) protocol named energy distance K-means LEACH (EDK-LEACH). For this purpose, an innovative clustering strategy built on the machine learning K-means algorithm is used in WSNs to improve the cluster formation process and maximise network stability. By implementing an objective function that considers each node’s residual energy and distance from the cluster centre when selecting the cluster head (CH) of each cluster, EDK-LEACH also eliminates the inherent randomness in LEACH during the CH election process. The proposed protocol has the advantage of ensuring better CH distribution throughout the network surface with a balanced load across all network nodes. In comparison with the known LEACH, the simulation results demonstrate the efficiency of our approach: the lifetime of the network is extended and the energy consumption is reduced
Investigations related to effect of mass density of metal oxide on specific capacitance of asymmetrical supercapacitor
Get PDFVarious types of batteries and fuel cells are widely used electrical energy storage devices in most of the applications. Supercapacitors have also become increasingly popular for energy storage in a few applications. Recently the need to develop better energy storage device has resulted in the development of asymmetrical supercapacitors (ASCs). Modeling of this device can be promising to obtain the desired characteristics to meet the need of continuous power and pulse current. For this, both positive and negative electrodes are important components for ASCs. The effect of mass density of metal oxide in positive electrode of this device is hardly researched. Component-based modeling for positive electrode is presented in the paper. Positive electrode parameters are being analyzed with the three most significant parameters affecting specific capacitance. The parameters viz. loading of materials on the current collector, percentage metal oxide, and mass density of metal oxide of the positive electrode are correlated with specific capacitance by using statistical methods to avoid the use of costly electrochemical methods. The major contribution of the presented research work is the identification of – mass density of metal oxide used in positive electrode plays the most significant role in deciding the value of the specific capacitance of this device
Enhancing patient navigation and referral through tele-referral system with geographical information systems
Get PDFA tele-referral system with a geographic information system (GIS) integrates telehealth services with spatial data to enhance healthcare delivery. Resource constraints can significantly impact the effectiveness of a tele-referral system with GIS. Addressing delayed or missed referrals is critical to ensuring timely patient care and improving health outcomes. Implementing a tele-referral system with GIS can significantly enhance healthcare delivery by leveraging spatial data and telehealth technologies to improve access, efficiency, and outcomes. One major issue is the lack of access to specialists, particularly in underprivileged communities. Patients face accessing specialized care due to a cumbersome referral process or long wait times, as well as the lack of patient engagement. The results showed that the GIS-enabled tele-referral system significantly reduced patient waiting times and improved the coordination of care. By incorporating these functionalities and strategies, the tele-referral system with GIS can effectively address issues related to delayed or missed referrals, ensuring timely patient care and improving overall health outcomes. By incorporating these strategies and functionalities, the tele-referral system with GIS can effectively address limited access to specialists, ensuring timely patient care and optimal use of available resources
Enhancing attack detection in IoT through integration of weighted emphasis formula with XGBoost
Get PDFThis research addresses the challenge of detecting attacks in the internet of things (IoT) environment, where minority classes often go unnoticed due to the dominance of majority classes. The primary objective is to introduce and integrate the imbalance ratio formula (IRF) into the XGBoost algorithm, aiming to provide greater emphasis on minority classes and ensure the model's focus on attack detection, particularly in binary and multiclass scenarios. Experimental validation using the IoTID20 dataset demonstrates the significant enhancement in attack detection accuracy achieved by integrating IRF into XGBoost. This enhancement contributes to the consistent improvement in distinguishing attacks from normal traffic, thereby resulting in a more reliable attack detection system in complex IoT environments. Moreover, the implementation of IRF enhances the robustness of the XGBoost model, enabling effective handling of imbalanced datasets commonly encountered in IoT security applications. This approach advances intrusion detection systems by addressing the challenge of class imbalance, leading to more accurate and efficient detection of malicious activities in IoT networks. The practical implications of these findings include the enhancement of cybersecurity measures in IoT deployments, potentially mitigating the risks associated with cyber threats in interconnected smart environments
Sustainable supply chain modeling: a review based on the application of the system dynamics approach
Get PDFSustainable supply chains, evolving with supply chain 5.0 revolution, are crucial for achieving sustainable development goals (SDGs) by balancing economic growth, environmental protection, and social responsibility. They help reduce environmental impacts, promote ethical labor practices, and ensure financial viability. Sustainable supply chains involve complex interactions and external influences. The system dynamics approach effectively captures these intricate interactions through feedback loops and non-linear relationships. This review seeks to identify issues in modeling sustainable supply chains using system dynamics and offer insights for developing sustainable, flexible, responsive, and resilient models. This paper reviews literature from 2020 to 2023 using thematic analysis. It examines dynamics, behaviors, management, sustainability strategies, decision-making, and future directions for sustainable supply chain modeling. The findings suggest that a comprehensive framework can enhance management practices, support policymaking, and promote sustainability. Integrated risk management is essential for resilient, adaptable supply chains, while financial viability and scalability are essential for the widespread adoption of sustainability practices. Understanding the roles of various actors and integrating supply chain components can improve support systems, and exploring green energy, technology adoption, and consumer behavior can advance sustainability goals. Future research should also better integrate sustainability aspects and explore a broader range of literature for deeper insights
Optimization machine learning models for selecting transmit antennas in 5G/6G systems
Get PDFTransmit antenna selection (TAS) plays a crucial role in improving the performance and spectral efficiency of 5G/6G systems. This study proposes to use the GridSearchCV method for hyperparameter optimization in two supervised learning models, support vector machine (SVM) and K-nearest neighbors (KNN), to optimally select antenna peers based on channel gain. These models were applied to Alamouti’s space-time block coding to improve performance, resulting in increased signal-to-noise ratio (SNR) and reduced bit error rate (BER). The results show that optimizing the hyperparameters led to a significant improvement in the performance of the SVM and KNN models. The SVM and KNN models were evaluated using a variety of metrics, with the SVM demonstrating superior predictive performance in terms of accuracy, average macro recall, average macro precision, average macro F1 score, and cross-validation score. Even before optimization, the SVM outperforms the KNN in terms of performance metrics. After optimization, this gap widens further, demonstrating the robustness of SVM for classification tasks. Although KNN is faster to train
Visual treatment with AR for children with dysphasia
Get PDFThe language disorder known as dysphasia significantly affects the ability to communicate effectively, presenting challenges in both comprehension and expression of language. To address this issue, the development of a visual treatment using augmented reality (AR) specifically designed for children with dysphasia has been proposed. The methodology selected for this project is analysis, design, development, implementation, and evaluation (ADDIE), an innovative methodology that encompasses analysis, design, development, implementation and evaluation. This methodology is perfectly adapted to the needs of the project, allowing a systematic and complete approach at all stages of the process of creating the visual treatment. The results obtained show that the visual treatment with AR has been positively evaluated by development experts and dysphasia specialists. Its innovative capacity to assist children with this disorder in health and educational settings is highlighted. This approach provides an effective tool to improve the communication and language development of children affected by dysphasia, offering new opportunities for their learning and growth. Its implementation in healthcare and educational settings could have a significant impact on the quality of life and development of these children